Fast data manipulation and finite state machines for machine learning

By using lookup tables and finite state machine technology in data processing, detecting and bypassing frequently used data values, the problem of low data processing efficiency in the prior art is solved, and efficient utilization and rapid operation of resources are achieved.

CN108694081BActive Publication Date: 2024-11-08INTEL CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN201810310957.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2017-04-09
Filing Date
2018-04-09
Publication Date
2024-11-08
Estimated Expiration
2038-04-09

AI Technical Summary

Technical Problem

The existing technology is difficult to achieve rapid processing in data processing, resulting in waste of resources and increased waiting time, especially in low efficiency in data value processing that is frequently used in machine learning operations.

Method used

Using lookup tables and reduction mathematical techniques, a finite state machine is introduced, which accelerates processing by detecting frequently used data values ​​and bypassing operations, and merges multiplication and addition operations to improve computational efficiency.

Benefits of technology

It significantly reduces resource consumption and waiting time and improves data processing efficiency, especially in deep learning and machine learning processing capabilities for frequent use of data values.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN108694081B_ABST
    Figure CN108694081B_ABST
Patent Text Reader

Abstract

A mechanism for facilitating fast data operations for machine learning in autonomous machines is described. As described herein, a method of an embodiment includes detecting input data to be used in a computing task by a computing component of a computing pipeline of a processor including a graphics processor. The method may further include determining one or more frequently used data values ​​(FDVs) from the data, and pushing the one or more frequent data values ​​to bypass the computing task.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] Embodiments described herein relate generally to data processing, and more particularly to tools for facilitating rapid data manipulation for use in machine learning in autonomous machines. Background Art

[0002] Current parallel graphics data processing includes systems and methods developed to perform specific operations on graphics data, such as, for example, linear interpolation, tessellation, rasterization, texture mapping, depth testing, etc. Traditionally, graphics processors have used fixed-function compute units to process graphics data; however, recently, portions of graphics processors have become programmable, enabling such processors to support a wider variety of operations for processing vertex and fragment data.

[0003] To further improve performance, graphics processors typically implement processing techniques (such as pipelining) that attempt to process as much graphics data in parallel as possible throughout different parts of the graphics pipeline. Parallel graphics processors with a single instruction multiple thread (SIMT) architecture are designed to maximize the amount of parallel processing in the graphics pipeline. In a SIMT architecture, multiple groups of parallel threads attempt to execute program instructions together synchronously as often as possible to improve processing efficiency. A general overview of software and hardware for a SIMT architecture can be found in Shane Cook's CUDA Programming, Chapter 3, pages 37-51 (2013) and / or Nicholas Wilt's CUDA Handbook, A Comprehensive Guide to GPU Programming, Sections 2.6.2 to 3.1.2 (June 2013).

[0004] Machine learning has been successful in solving many kinds of tasks. The computations that occur when training and using machine learning algorithms (e.g., neural networks) are naturally amenable to efficient parallel implementation. Accordingly, parallel processors such as general-purpose graphics processing units (GPGPUs) have played an important role in the practical implementation of deep neural networks. Parallel graphics processors with a single instruction multiple thread (SIMT) architecture are designed to maximize the amount of parallel processing in the graphics pipeline. In the SIMT architecture, multiple groups of parallel threads attempt to execute program instructions together synchronously as often as possible to improve processing efficiency. The efficiency provided by parallel machine learning algorithm implementations allows the use of high-capacity networks and enables those networks to be trained on larger data sets.

[0005] Conventional techniques are limited to techniques like table lookups and the like and do not provide fast processing of data, and therefore, such conventional techniques are inefficient and wasteful in terms of system resources, resulting in increased latency and energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] Embodiments are illustrated by way of example and not by way of limitation in the various figures of the accompanying drawings in which like reference numerals refer to similar elements. In order that the above-described features may be understood in detail, a more specific description briefly summarized above may be made by reference to embodiments, some of which are illustrated in the accompanying drawings. However, it should be noted that the accompanying drawings illustrate only typical embodiments and therefore should not be considered as limiting the scope thereof, as the drawings may illustrate other equally effective embodiments.

[0007] Figure 1 is a block diagram illustrating a computer system configured to implement one or more aspects of the embodiments described herein.

[0008] Figures 2A to 2D A parallel processor component according to an embodiment is illustrated.

[0009] Figures 3A to 3B is a block diagram of a graphics multiprocessor according to an embodiment.

[0010] Figures 4A to 4F An exemplary architecture is illustrated in which multiple graphics processing units are communicatively coupled to multiple multi-core processors.

[0011] Figure 5 is a conceptual diagram of a graphics processing pipeline according to an embodiment.

[0012] Figure 6 A computing device hosting a finite state machine and a fast computing mechanism according to one embodiment is illustrated.

[0013] Figure 7 A finite state machine and a fast computation mechanism according to one embodiment are illustrated.

[0014] Fig. 8A An architectural arrangement for bypassing frequently used data values ​​according to one embodiment is illustrated.

[0015] Figure 8B An architecture for employing and using a finite state machine 861 according to one embodiment is illustrated.

[0016] Fig. 9 A method for facilitating fast computing operations according to one embodiment is illustrated.

[0017] Fig.10 Illustrated is a machine learning software stack according to an embodiment.

[0018] Fig.11 A highly parallel general purpose graphics processing unit is illustrated in accordance with an embodiment.

[0019] Fig.12 A multi-GPU computing system is illustrated according to an embodiment.

[0020] Figures 13A to 13B The layers of an exemplary deep neural network are illustrated.

[0021] Fig.14 Illustration of the training and deployment of a deep neural network.

[0022] Fig.15 Illustration of the training and deployment of a deep neural network.

[0023] Fig.16 is a block diagram illustrating distributed learning.

[0024] Fig.17 An exemplary inference system-on-chip (SOC) suitable for performing inference using a trained model is illustrated.

[0025] Fig.18 is a block diagram of an embodiment of a computer system with a processor having one or more processor cores and a graphics processor.

[0026] Fig.19 is a block diagram of one embodiment of a processor having one or more processor cores, an integrated memory controller, and an integrated graphics processor.

[0027] Fig. 20 is a block diagram of one embodiment of a graphics processor, which may be a discrete graphics processing unit or may be a graphics processor integrated with multiple processing cores.

[0028] Fig.21 is a block diagram of an embodiment of a graphics processing engine for a graphics processor.

[0029] Fig. 22 is a block diagram of another embodiment of a graphics processor.

[0030] Fig.23 is a block diagram of thread execution logic including an array of processing elements.

[0031] Fig.24 A graphics processor execution unit instruction format is illustrated according to an embodiment.

[0032] Fig.25 is a block diagram of another embodiment of a graphics processor including a graphics pipeline, a media pipeline, a display engine, thread execution logic, and a render output pipeline.

[0033] Fig.26Ais a block diagram illustrating a graphics processor command format according to an embodiment.

[0034] Fig.26B is a block diagram illustrating a graphics processor command sequence according to an embodiment.

[0035] Fig. 27 An exemplary graphics software architecture for a data processing system according to an embodiment is illustrated.

[0036] Fig.28 is a block diagram illustrating an IP core development system that may be used to fabricate an integrated circuit for performing operations according to an embodiment.

[0037] Fig.29 is a block diagram illustrating an exemplary system-on-chip integrated circuit that can be fabricated using one or more IP cores according to an embodiment.

[0038] Fig.30 is a block diagram illustrating an exemplary graphics processor of a system-on-chip integrated circuit.

[0039] Fig.31 is a block diagram illustrating an additional exemplary graphics processor of a system-on-chip integrated circuit. DETAILED DESCRIPTION

[0040] Embodiments provide a novel technique for facilitating detection of frequently used data values ​​and subsequently speeding up operations by using one or more techniques such as lookup tables, reduced math, etc. Embodiments further provide a novel technique for introducing a finite state machine, wherein in one embodiment, this finite state machine provides a pointer to a sequence of base addresses to A, B and output is C+.

[0041] It should be noted that terms or acronyms like “convolutional neural network”, “CNN”, “neural network”, “NN”, “deep neural network”, “DNN”, “recurrent neural network”, “RNN”, etc. may be referred to interchangeably throughout this document. Furthermore, terms like “autonomous machine” or just “machine”, “autonomous vehicle” or just “vehicle”, “autonomous agent” or just “agent”, “autonomous device” or “computing device”, “robot”, etc. may be referred to interchangeably throughout this document.

[0042] In some embodiments, a graphics processing unit (GPU) is communicatively coupled to a host / processor core to accelerate graphics operations, machine learning operations, pattern analysis operations, and various general-purpose GPU (GPGPU) functions. The GPU can be communicatively coupled to the host processor / core via a bus or another interconnect (e.g., a high-speed interconnect such as PCIe or NVLink). In other embodiments, the GPU can be integrated with the core on the same package or chip and communicatively coupled to the core via an internal processor bus / interconnect (i.e., inside the package or chip). Regardless of the manner in which the GPU is connected, the processor core can assign work to the GPU in the form of a sequence of commands / instructions contained in a work descriptor. The GPU then uses dedicated circuits / logic to efficiently process these commands / instructions.

[0043] In the following description, many specific details are set forth. However, without these specific details, the embodiments described herein can also be practiced. In other instances, well-known circuits, structures, and techniques are not shown in detail in order not to obscure the understanding of the description.

[0044] System Overview I

[0045] Figure 1 1 is a block diagram illustrating a computing system 100 configured to implement one or more aspects of the embodiments described herein. The computing system 100 includes a processing subsystem 101 having one or more processors 102 and a system memory 104, the one or more processors and the system memory communicating via an interconnect path, which may include a memory hub 105. The memory hub 105 may be a separate component within a chipset component, or may be integrated within the one or more processors 102. The memory hub 105 is coupled to an I / O subsystem 111 via a communication link 106. The I / O subsystem 111 includes an I / O hub 107, which may enable the computing system 100 to receive input from one or more input devices 108. In addition, the I / O hub 107 may enable a display controller (which may be included in the one or more processors 102) to provide output to one or more display devices 110A. In one embodiment, the one or more display devices 110A coupled to the I / O hub 107 may include a local display device, an internal display device, or an embedded display device.

[0046] In one embodiment, the processing subsystem 101 includes one or more parallel processors 112, which are coupled to the memory hub 105 via a bus or other communication link 113. The communication link 113 can be one of any number of standard-based communication link technologies or protocols (such as but not limited to PCI Express), or can be a vendor-specific communication interface or communication structure. In one embodiment, the one or more parallel processors 112 form a computing-centric parallel or vector processing system that includes a large number of processing cores and / or processing clusters, such as an integrated many-core (MIC) processor. In one embodiment, the one or more parallel processors 112 form a graphics processing subsystem that can output pixels to one of one or more display devices 110A coupled via the I / O hub 107. The one or more parallel processors 112 may also include a display controller and display interface (not shown) to enable direct connection to one or more display devices 110B.

[0047] Within the I / O subsystem 111, a system storage unit 114 may be connected to the I / O hub 107 to provide a storage mechanism for the computing system 100. An I / O switch 116 may be used to provide an interface mechanism to enable connection between the I / O hub 107 and other components that may be integrated into the platform, such as a network adapter 118 and / or a wireless network adapter 119, as well as various other devices that may be added via one or more plug-in devices 120. The network adapter 118 may be an Ethernet adapter or another wired network adapter. The wireless network adapter 119 may include one or more of Wi-Fi, Bluetooth, near field communication (NFC), or other network devices including one or more radio devices.

[0048] Computing system 100 may include other components not explicitly shown, including USB or other port connections, optical storage drives, video capture devices, etc., which may also be connected to I / O hub 107. Figure 1 The communication paths interconnecting the various components may be implemented using any suitable protocol, such as a PCI (Peripheral Component Interconnect) based protocol (e.g., PCI-Express) or any other bus or point-to-point communication interface(s) and / or protocol (such as the NV-Link high-speed interconnect or an interconnect protocol known in the art).

[0049] In one embodiment, one or more parallel processors 112 incorporate circuits optimized for graphics and video processing, including, for example, video output circuits, and the circuits constitute a graphics processing unit (GPU). In another embodiment, one or more parallel processors 112 incorporate circuits optimized for general-purpose processing while retaining the basic computing architecture described in more detail herein. In yet another embodiment, the components of the computing system 100 may be integrated with one or more other system elements on a single integrated circuit. For example, one or more parallel processors 112, a memory hub 105, (one or more) processors 102, and an I / O hub 107 may be integrated into a system-on-chip (SoC) integrated circuit. Alternatively, the components of the computing system 100 may be integrated into a single package to form a system-in-package (SIP) configuration. In one embodiment, at least a portion of the components of the computing system 100 may be integrated into a multi-chip module (MCM), which may be interconnected with other multi-chip modules to form a modular computing system.

[0050] It should be understood that the computing system 100 shown herein is illustrative and variations and modifications are possible. The connection topology, including the number and arrangement of bridges, the number of (one or more) processors 102, and the number of (one or more) parallel processors 112, can be modified as needed. For example, in some embodiments, the system memory 104 is directly connected to the (one or more) processors 102 rather than through a bridge, and other devices communicate with the system memory 104 via the memory hub 105 and the (one or more) processors 102. In other alternative topologies, the (one or more) parallel processors 112 are connected to the I / O hub 107 or directly to one of the one or more processors 102, rather than to the memory hub 105. In other embodiments, the I / O hub 107 and the memory hub 105 can be integrated into a single chip. Some embodiments may include two or more groups of (one or more) processors 102 attached via multiple sockets, which can be coupled to two or more instances of (one or more) parallel processors 112.

[0051] Some specific components shown herein are optional and may not be included in all implementations of computing system 100. For example, any number of plug-in cards or peripherals may be supported, or some components may be omitted. In addition, some architectures may use different terminology to describe components related to the computing system 100. Figure 1 For example, in some architectures, memory hub 105 may be referred to as a north bridge, while I / O hub 107 may be referred to as a south bridge.

[0052] Figure 2AThe parallel processor 200 according to an embodiment is illustrated. The various components of the parallel processor 200 may be implemented using one or more integrated circuit devices such as a programmable processor, an application specific integrated circuit (ASIC), or a field programmable gate array (FPGA). According to an embodiment, the illustrated parallel processor 200 is Figure 1 A variation of one or more parallel processors 112 is shown.

[0053] In one embodiment, parallel processor 200 includes parallel processing unit 202. The parallel processing unit includes an I / O unit 204 that enables communication with other devices including other instances of parallel processing unit 202. I / O unit 204 can be directly connected to other devices. In one embodiment, I / O unit 204 is connected to other devices via the use of a hub or switch interface such as memory hub 105. The connection between memory hub 105 and I / O unit 204 forms communication link 113. Within parallel processing unit 202, I / O unit 204 is connected to host interface 206 and memory cross switch 216, wherein host interface 206 receives commands related to performing processing operations and memory cross switch 216 receives commands related to performing memory operations.

[0054] When host interface 206 receives command buffers via I / O unit 204, host interface 206 may direct work operations for executing those commands to front end 208. In one embodiment, front end 208 is coupled to scheduler 210, which is configured to distribute commands or other work items to processing cluster array 212. In one embodiment, scheduler 210 ensures that processing cluster array 212 is properly configured and in a valid state before distributing tasks to processing clusters of processing cluster array 212.

[0055] Processing cluster array 212 may include up to "N" processing clusters (e.g., cluster 214A, cluster 214B, all the way to cluster 214N). Each cluster 214A to 214N of processing cluster array 212 may execute a large number of concurrent threads. Scheduler 210 may use various scheduling and / or work distribution algorithms to allocate work to clusters 214A to 214N of processing cluster array 212, which may vary depending on the workload caused by each type of program or calculation. Scheduling may be handled dynamically by scheduler 210, or may be partially assisted by compiler logic in the process of compiling program logic configured to be executed by processing cluster array 212.

[0056] In one embodiment, different clusters 214A through 214N of processing cluster array 212 may be assigned to process different types of programs or to perform different types of calculations.

[0057] Processing cluster array 212 may be configured to perform various types of parallel processing operations. In one embodiment, processing cluster array 212 is configured to perform general-purpose parallel computing operations. For example, processing cluster array 212 may include logic for performing processing tasks including: filtering of video and / or audio data; performing modeling operations, including physics operations; and performing data transformations.

[0058] In one embodiment, processing cluster array 212 is configured to perform parallel graphics processing operations. In embodiments where parallel processor 200 is configured to perform graphics processing operations, processing cluster array 212 may include additional logic for supporting the execution of such graphics processing operations, including but not limited to texture sampling logic for performing texture operations and tessellation logic and other vertex processing logic. In addition, processing cluster array 212 may be configured to execute shader programs associated with graphics processing, such as but not limited to vertex shaders, tessellation shaders, geometry shaders, and pixel shaders. Parallel processing unit 202 may transfer data from system memory via I / O unit 204 for processing. During processing, the transferred data may be stored in on-chip memory (e.g., parallel processor memory 222) during processing and then written back to system memory.

[0059] In one embodiment, when parallel processing unit 202 is used to perform graphics processing, scheduler 210 can be configured to divide the processing workload into tasks of approximately equal size to better enable the distribution of graphics processing operations to multiple clusters 214A to 214N of processing cluster array 212. In some embodiments, portions of processing cluster array 212 can be configured to perform different types of processing. For example, a first portion can be configured to perform vertex shading and topology generation, a second portion can be configured to perform tessellation and geometry shading, and a third portion can be configured to perform pixel shading or other screen space operations to produce a rendered image for display. Intermediate data generated by one or more of clusters 214A to 214N can be stored in a buffer to allow the intermediate data to be transferred between clusters 214A to 214N for further processing.

[0060] During operation, the processing cluster array 212 may receive processing tasks to be executed via the scheduler 210, which receives commands defining the processing tasks from the front end 208. For graphics processing operations, a processing task may include an index of data to be processed (e.g., surface (patch) data, primitive data, vertex data, and / or pixel data, and state parameters and commands (e.g., which program to execute) that define how the data is to be processed). The scheduler 210 may be configured to obtain an index corresponding to a task or may receive an index from the front end 208. The front end 208 may be configured to ensure that the processing cluster array 212 is configured to a valid state before a workload specified by an incoming command buffer (e.g., a batch buffer, a push buffer, etc.) is initiated.

[0061] Each of the one or more instances of the parallel processing unit 202 may be coupled to a parallel processor memory 222. The parallel processor memory 222 may be accessed via a memory crossbar 216, which may receive memory requests from the processing cluster array 212 and the I / O unit 204. The memory crossbar 216 may access the parallel processor memory 222 via a memory interface 218. The memory interface 218 may include a plurality of partition units (e.g., partition unit 220A, partition unit 220B, up to partition unit 220N), which may each be coupled to a portion (e.g., memory unit) of the parallel processor memory 222. In one implementation, the number of partition units 220A to 220N is configured to be equal to the number of memory units, such that the first partition unit 220A has a corresponding first memory unit 224A, the second partition unit 220B has a corresponding memory unit 224B, and the Nth partition unit 220N has a corresponding Nth memory unit 224N. In other embodiments, the number of partition units 220A to 220N may not be equal to the number of memory devices.

[0062] In various embodiments, the memory units 224A to 224N may include various types of memory devices, including dynamic random access memory (DRAM) or graphics random access memory, such as synchronous graphics random access memory (SGRAM), including graphics double data rate (GDDR) memory. In one embodiment, the memory units 224A to 224N may also include 3D stacked memory, including but not limited to high bandwidth memory (HBM). Those skilled in the art will appreciate that the specific implementation of the memory units 224A to 224N may vary and may be selected from one of a variety of conventional designs. Rendering targets such as frame buffers or texture maps may be stored on the memory units 224A to 224N, allowing the partition units 220A to 220N to write to portions of each rendering target in parallel to efficiently use the available bandwidth of the parallel processor memory 222. In some embodiments, in order to support a unified memory design that utilizes system memory together with local cache memory, the local instance of the parallel processor memory 222 may be excluded.

[0063] In one embodiment, any of the clusters 214A to 214N of the processing cluster array 212 can process data to be written to any of the memory units 224A to 224N within the parallel processor memory 222. The memory crossbar 216 can be configured to transmit the output of each cluster 214A to 214N to any partition unit 220A to 220N or another cluster 214A to 214N, which can perform additional processing operations on the output. Each cluster 214A to 214N can communicate with the memory interface 218 through the memory crossbar 216 to perform read or write operations on various external memory devices. In one embodiment, the memory crossbar 216 can be connected to the memory interface 218 to communicate with the I / O unit 204, and can be connected to the local instance of the parallel processor memory 222, so that the processing units within different processing clusters 214A to 214N can communicate with the system memory or other memory that is not local to the parallel processing unit 202. In one embodiment, the memory crossbar switch 216 may use virtual channels to separate traffic flows between the clusters 214A to 214N and the partition units 220A to 220N.

[0064] Although a single instance of parallel processing unit 202 is illustrated as being within parallel processor 200, any number of instances of parallel processing unit 202 may also be included. For example, multiple instances of parallel processing unit 202 may be provided on a single plug-in card, or multiple plug-in cards may be interconnected. Different instances of parallel processing unit 202 may also be configured to interoperate even if different instances have different numbers of processing cores, different local parallel processor storage amounts, and / or other configuration differences. For example, and in one embodiment, some instances of parallel processing unit 202 may include higher precision floating point units relative to other instances. Systems incorporating one or more instances of parallel processing unit 202 or parallel processor 200 may be implemented in various configurations and form factors, including but not limited to desktop computers, laptop computers or handheld personal computers, servers, workstations, game consoles, and / or embedded systems.

[0065] Figure 2B is a block diagram of a partition unit 220 according to an embodiment. In one embodiment, the partition unit 220 is Figure 2A 220N. As shown, partition unit 220 includes L2 cache 221, frame buffer interface 225, and ROP 226 (raster operation unit). L2 cache 221 is a read / write cache that is configured to perform load and store operations received from memory crossbar switch 216 and ROP 226. Read misses and urgent write-back requests are output by L2 cache 221 to frame buffer interface 225 for processing. Dirty updates can also be sent to the frame buffer via frame buffer interface 225 for opportunistic processing. In one embodiment, frame buffer interface 225 communicates with memory units (such as, Figure 2A The memory cells 224A to 224N (eg, within the parallel processor memory 222)) are interfaced to one of the memory cells 224A to 224N.

[0066] In graphics applications, ROP 226 is a processing unit that performs raster operations such as stenciling, z-testing, blending, etc. ROP 226 then outputs processed graphics data, which is stored in graphics memory. In some embodiments, ROP 226 includes compression logic that compresses z or color data written to memory and decompresses z or color data read from memory. In some embodiments, ROP 226 is included in each processing cluster (e.g., Figure 2A 214A to 214N) rather than being included in the partition unit 220. In such an embodiment, read and write requests for pixel data are transmitted through the memory crossbar 216 rather than pixel fragment data.

[0067] The processed graphic data may be displayed on a display device (such as Figure 1 ), routed by the processor(s) 102 for further processing, or by Figure 2A One of the processing entities within parallel processor 200 is routed for further processing.

[0068] Figure 2C is a block diagram of a processing cluster 214 within a parallel processing unit according to an embodiment. In one embodiment, a processing cluster is Figure 2A An instance of one of the processing clusters 214A to 214N. The processing cluster 214 can be configured to execute many threads in parallel, where the term "thread" refers to an instance of a specific program executed on a specific input data set. In some embodiments, a single instruction multiple data (SIMD) instruction issuance technology is used to support the parallel execution of a large number of threads without providing multiple independent instruction units. In other embodiments, a single instruction multiple thread (SIMT) technology is used to support the parallel execution of a large number of roughly synchronized threads using a common instruction unit configured to issue instructions to a group of processing engines within each of the processing clusters. Unlike the SIMD execution mechanism in which all processing engines generally execute the same instructions, SIMT execution allows different threads to more easily follow divergent execution paths through a given thread program. Those skilled in the art will understand that the SIMD processing mechanism represents a functional subset of the SIMT processing mechanism.

[0069] The operation of the processing cluster 214 can be controlled via a pipeline manager 232 that distributes processing tasks to SIMT parallel processors. The pipeline manager 232 Figure 2A The scheduler 210 receives instructions and manages the execution of those instructions via the graphics multiprocessor 234 and / or the texture unit 236. The illustrated graphics multiprocessor 234 is an exemplary instance of a SIMT parallel processor. However, various types of SIMT parallel processors of different architectures may be included in the processing cluster 214. One or more instances of the graphics multiprocessor 234 may be included in the processing cluster 214. The graphics multiprocessor 234 may process data, and the data crossbar 240 may be used to distribute the processed data to one of a plurality of possible destinations including other shader units. The pipeline manager 232 may facilitate the distribution of processed data by specifying a destination for the processed data to be distributed via the data crossbar 240.

[0070] Each graphics multiprocessor 234 within a processing cluster 214 may include the same set of functional execution logic (e.g., arithmetic logic units, load store units, etc.). The functional execution logic may be configured in a pipelined manner, where a new instruction may be issued before a previous instruction is completed. Functional execution logic may be provided. The functional logic supports a variety of operations, including integer and floating point arithmetic comparison operations, Boolean bit shift operations, and calculation of various algebraic functions. In one embodiment, the same functional unit hardware may be utilized to perform different operations, and any combination of functional units may be present.

[0071] The instructions transmitted to the processing cluster 214 constitute threads. A group of threads executed on a group of parallel processing engines is a thread group. The thread group executes the same program on different input data. Each thread in the thread group can be assigned to a different processing engine in the graphics multiprocessor 234. The thread group can include fewer threads than the number of processing engines in the graphics multiprocessor 234. When the thread group includes fewer threads than the number of processing engines, one or more of the processing engines may be idle during the cycle of processing the thread group. The thread group can also include more threads than the number of processing engines in the graphics multiprocessor 234. When the thread group includes more threads than the number of processing engines in the graphics multiprocessor 234, processing can be performed on consecutive clock cycles. In one embodiment, multiple thread groups can be executed simultaneously on the graphics multiprocessor 234.

[0072] In one embodiment, the graphics multiprocessor 234 includes internal cache memory for performing load and store operations. In one embodiment, the graphics multiprocessor 234 may forgo the internal cache and use cache memory (e.g., L1 cache 308) within the processing cluster 214. Each graphics multiprocessor 234 may also access a partition unit (e.g., L1 cache 308) that is shared among all processing clusters 214. Figure 2A 308 and may be used to transfer data between threads. Graphics multiprocessor 234 may also access off-chip global memory, which may include one or more of local parallel processor memory and / or system memory. Any memory external to parallel processing unit 202 may be used as global memory. Embodiments in which processing cluster 214 includes multiple instances of graphics multiprocessor 234 may share common instructions and data that may be stored in L1 cache 308.

[0073] Each processing cluster 214 may include an MMU 245 (memory management unit) configured to map virtual addresses to physical addresses. In other embodiments, one or more instances of MMU 245 may reside in Figure 2A218. The MMU 245 includes a set of page table entries (PTEs) for mapping virtual addresses to physical addresses of tiles (more referred to as tiles) and optionally cache line indexes. The MMU 245 may include an address translation lookaside buffer (TLB) or cache that may reside within the graphics multiprocessor 234 or L1 cache or processing cluster 214. Physical addresses are processed to distribute surface data access locality to achieve efficient request interleaving between partition units. The cache line index may be used to determine whether a request for a cache line is a hit or a miss.

[0074] In graphics and compute applications, the processing clusters 214 can be configured such that each graphics multiprocessor 234 is coupled to a texture unit 236 to perform texture mapping operations, such as determining texture sample locations, reading texture data, and filtering texture data. Texture data is read from an internal texture L1 cache (not shown) or, in some embodiments, from an L1 cache within the graphics multiprocessor 234 and is retrieved from an L2 cache, local parallel processor memory, or system memory as needed. Each graphics multiprocessor 234 outputs processed tasks to a data crossbar 240 to provide the processed tasks to another processing cluster 214 for further processing or to store the processed tasks in an L2 cache, local parallel processor memory, or system memory via a memory crossbar 216. A preROP 242 (pre-raster operations unit) is configured to receive data from the graphics multiprocessor 234, direct the data to ROP units, which may be used with partition units (e.g., as described herein) as described herein. Figure 2A The preROP 242 unit can optimize color mixing, organize pixel color data, and perform address translation.

[0075] It should be understood that the core architecture described herein is illustrative and variations and modifications are possible. Any number of processing units, such as graphics multiprocessor 234, texture unit 236, preROP 242, etc., may be included in processing cluster 214. In addition, although only one processing cluster 214 is shown, the parallel processing unit described herein may include any number of instances of processing cluster 214. In one embodiment, each processing cluster 214 may be configured to operate independently of other processing clusters 214 using separate and distinct processing units, L1 caches, etc.

[0076] Figure 2DA graphics multiprocessor 234 is shown according to one embodiment. In such an embodiment, the graphics multiprocessor 234 is coupled to the pipeline manager 232 of the processing cluster 214. The graphics multiprocessor 234 has an execution pipeline that includes, but is not limited to, an instruction cache 252, an instruction unit 254, an address mapping unit 256, a register file 258, one or more general purpose graphics processing unit (GPGPU) cores 262, and one or more load / store units 266. The GPGPU cores 262 and the load / store units 266 are coupled to a cache memory 272 and a shared memory 270 via a memory and cache interconnect 268.

[0077] In one embodiment, the instruction cache 252 receives a stream of instructions to be executed from the pipeline manager 232. These instructions are cached in the instruction cache 252 and dispatched for execution by the instruction unit 254. The instruction unit 254 can dispatch instructions as thread groups (e.g., warps), where each thread of the thread group is assigned to a different execution unit within the GPGPU core 262. Instructions can access any of the local, shared, or global address spaces by specifying an address within the unified address space. The address mapping unit 256 can be used to convert addresses in the unified address space into different memory addresses that can be accessed by the load / store unit 266.

[0078] The register file 258 provides a set of registers for the functional units of the graphics multiprocessor 324. The register file 258 provides temporary storage for operands for the data paths of the functional units (e.g., GPGPU core 262, load / store unit 266) connected to the graphics multiprocessor 324. In one embodiment, the register file 258 is divided between each of the functional units so that each functional unit is assigned a dedicated portion of the register file 258. In one embodiment, the register file 258 is divided between the different warps being executed by the graphics multiprocessor 324.

[0079] The GPGPU cores 262 may each include a floating point unit (FPU) and / or an integer arithmetic logic unit (ALU) for executing instructions of the graphics multiprocessor 324. Depending on the embodiment, the architecture of the GPGPU cores 262 may be similar, or may be different. For example, and in one embodiment, the first portion of the GPGPU core 262 includes a single-precision FPU and an integer ALU, while the second portion of the GPGPU core includes a double-precision FPU. In one embodiment, the FPU may implement the IEEE 754-2008 floating-point arithmetic standard or enable variable-precision floating-point arithmetic. In addition, the graphics multiprocessor 324 may also include one or more fixed-function or special-function units for performing specific functions such as copying rectangles or pixel blending operations. In one embodiment, one or more of the GPGPU cores may also include fixed or special-function logic.

[0080] The memory and cache interconnect 268 is an interconnect network that connects each of the functional units of the graphics multiprocessor 324 to the register file 258 and the shared memory 270. In one embodiment, the memory and cache interconnect 268 is a crossbar interconnect that allows the load / store unit 266 to implement load and store operations between the shared memory 270 and the register file 258. The register file 258 can operate at the same frequency as the GPGPU core 262, so data transfer between the GPGPU core 262 and the register file 258 has very low latency. The shared memory 270 can be used to implement communication between threads executed on the functional units within the graphics multiprocessor 234. For example, the cache memory 272 can be used as a data cache to cache texture data communicated between the functional units and the texture unit 236. The shared memory 270 can also be used as a cached managed program. In addition to the automatically cached data stored in the cache memory 272, threads executing on the GPGPU core 262 can also programmatically store data in the shared memory.

[0081] FIG. 3A to FIG. 3B Additional graphics multiprocessors are illustrated according to an embodiment. The illustrated graphics multiprocessors 325, 350 are Figure 2C The illustrated graphics multiprocessors 325, 350 may be configured as streaming multiprocessors (SMs) capable of executing a large number of execution threads simultaneously.

[0082] Figure 3A A graphics multiprocessor 325 is shown according to an additional embodiment. The graphics multiprocessor 325 includes Figure 2DThe graphics multiprocessor 325 may include multiple additional instances of the execution resource unit of the graphics multiprocessor 234. For example, the graphics multiprocessor 325 may include multiple instances of instruction units 332A to 332B, register files 334A to 334B, and (one or more) texture units 344A to 344B. The graphics multiprocessor 325 also includes multiple groups of graphics or compute execution units (e.g., GPGPU cores 336A to 336B, GPGPU cores 337A to 337B, GPGPU cores 338A to 338B) and multiple groups of load / store units 340A to 340B. In one embodiment, the execution resource unit has a common instruction cache 330, texture and / or data cache memory 342, and shared memory 346. The various components can communicate via the interconnect structure 327. In one embodiment, the interconnect structure 327 includes one or more crossbar switches to enable communication between the various components of the graphics multiprocessor 325.

[0083] Figure 3B A graphics multiprocessor 350 is shown according to an additional embodiment. Figure 2D and Figure 3A As shown, the graphics processor includes multiple groups of execution resources 356A to 356D, each of which includes multiple instruction units, register files, GPGPU cores, and load storage units. The execution resources 356A to 356D can work with (one or more) texture units 360A to 360D to perform texture operations while sharing the instruction cache 354 and shared memory 362. In one embodiment, the execution resources 356A to 356D can share multiple instances of the instruction cache 354 and shared memory 362 and texture and / or data cache memory 358A to 358B. The various components can be connected via Figure 3A The interconnect structure 327 communicates with a similar interconnect structure 352 .

[0084] Those skilled in the art will understand that Figure 1 , FIG. 2A to FIG. 2D and FIG. 3A to FIG. 3B The architecture described in is illustrative and does not limit the scope of the embodiments of the present invention. Therefore, the techniques described herein can be implemented on any appropriately configured processing unit, including but not limited to: one or more mobile application processors; one or more desktop or server central processing units (CPUs), including multi-core CPUs; one or more parallel processing units, such as Figure 2A and one or more graphics processors or special purpose processing units without departing from the scope of the embodiments described herein.

[0085] In some embodiments, a parallel processor or GPGPU as described herein is communicatively coupled to a host / processor core to accelerate graphics operations, machine learning operations, pattern analysis operations, and various general-purpose GPU (GPGPU) functions. The GPU can be communicatively coupled to the host processor / core via a bus or other interconnect (e.g., a high-speed interconnect such as PCIe or NVLink). In other embodiments, the GPU can be integrated on the same package or chip as the core and communicatively coupled to the core via an internal processor bus / interconnect (i.e., inside the package or chip). Regardless of the manner in which the GPU is connected, the processor core can assign work to the GPU in the form of a sequence of commands / instructions contained in a work descriptor. The GPU then uses dedicated circuits / logic to efficiently process these commands / instructions.

[0086] Technologies for GPU to host processor interconnect

[0087] Figure 4A An exemplary architecture is illustrated in which multiple GPUs 410 to 413 are communicatively coupled to multiple multi-core processors 405 to 406 via high-speed links 440 to 443 (e.g., buses, point-to-point interconnects, etc.). In one embodiment, the high-speed links 440 to 443 support 4 GB / s, 30 GB / s, 80 GB / s, or higher communication throughput, depending on the implementation. Various interconnect protocols may be used, including but not limited to PCIe 4.0 or 5.0 and NVLink 2.0. However, the underlying principles of the invention are not limited to any particular communication protocol or throughput.

[0088] Furthermore, in one embodiment, two or more of the GPUs 410 to 413 are interconnected via high-speed links 444 to 445, which may be implemented using the same or different protocols / links as used for high-speed links 440 to 443. Similarly, two or more of the multi-core processors 405 to 406 may be connected via high-speed link 433, which may be a symmetric multiprocessor (SMP) bus operating at 20 GB / s, 30 GB / s, 120 GB / s, or higher. Alternatively, Figure 4A All communications between the various system components shown in can be accomplished using the same protocol / links (eg, through a common interconnect structure). However, as mentioned, the underlying principles of the invention are not limited to any particular type of interconnect technology.

[0089] In one embodiment, each multi-core processor 405-406 is communicatively coupled to a processor memory 401-402 via a memory interconnect 430-431, respectively, and each GPU 410-413 is communicatively coupled to a GPU memory 420-423 via a GPU memory interconnect 450-453, respectively. The memory interconnects 430-431 and 450-453 may utilize the same or different memory access technologies. As an example and not by way of limitation, the processor memory 401-402 and the GPU memory 420-423 may be a volatile memory such as a dynamic random access memory (DRAM) (including stacked DRAM), a graphics DDR SDRAM (GDDR) (e.g., GDDR5, GDDR6), or a high bandwidth memory (HBM), and / or may be a non-volatile memory such as 3D XPoint or Nano-Ram. In one embodiment, a portion of the memory may be a volatile memory and another portion may be a non-volatile memory (e.g., using a two-level memory (2LM) hierarchy).

[0090] As described below, although the various processors 405-406 and GPUs 410-413 may each be physically coupled to a specific memory 401-402, 420-423, respectively, a unified memory architecture may be implemented in which the same virtual system address space (also referred to as an "effective address" space) is distributed among all the various physical memories. For example, the processor memories 401-402 may each include 64GB of system memory address space, and the GPU memories 420-423 may each include 32GB of system memory address space (resulting in a total of 256GB of addressable storage space in this example).

[0091] Figure 4B Additional details of the interconnection between the multi-core processor 407 and the graphics acceleration module 446 according to one embodiment are illustrated. The graphics acceleration module 446 may include one or more GPU chips integrated on a line card coupled to the processor 407 via the high-speed link 440. Alternatively, the graphics acceleration module 446 may be integrated on the same package or chip as the processor 407.

[0092] The illustrated processor 407 includes a plurality of cores 460A to 460D, each of which has a translation lookaside buffer 461A to 461D and one or more caches 462A to 462D. These cores may include various other components (e.g., instruction fetch units, branch prediction units, decoders, execution units, reorder buffers, etc.) for executing instructions and processing data not shown to avoid obscuring the basic principles of the present invention. Caches 462A to 462D may include level 1 (L1) and level 2 (L2) caches. In addition, one or more shared caches 426 may be included in the cache hierarchy and shared by each group of cores 460A to 460D. For example, one embodiment of the processor 407 includes 24 cores, each of which has its own L1 cache, 12 shared L2 caches, and 12 shared L3 caches. In this embodiment, one of the L2 cache and the L3 cache is shared by two adjacent cores. The processor 407 and the graphics accelerator integrated module 446 are connected to the system memory 441 , which may include the processor memories 401 to 402 .

[0093] Coherence is maintained for data and instructions stored in the various caches 462A-462D, 456, and the system memory 441 via inter-core communications over the coherence bus 464. For example, each cache may have cache coherence logic / circuitry associated therewith to communicate over the coherence bus 464 in response to a detected read or write to a particular cache line. In one implementation, a cache snooping protocol is implemented over the coherence bus 464 to snoop on cache accesses. Cache snooping / coherence techniques are well understood by those skilled in the art and will not be described in detail herein to avoid obscuring the underlying principles of the present invention.

[0094] In one embodiment, the proxy circuit 425 communicatively couples the graphics acceleration module 446 to the coherence bus 464, thereby allowing the graphics acceleration module 446 to participate in the cache coherence protocol as a peer of the core. Specifically, the interface 435 provides connectivity to the proxy circuit 425 via a high-speed link 440 (e.g., a PCIe bus, NVLink, etc.), and the interface 437 connects the graphics acceleration module 446 to the link 440.

[0095] In one implementation, the accelerator integrated circuit 436 provides cache management, memory access, context management, and interrupt management services on behalf of the multiple graphics processing engines 431, 432, 43N of the graphics acceleration module 446. The graphics processing engines 431, 432, 43N may each include a separate graphics processing unit (GPU). Alternatively, the graphics processing engines 431, 432, 43N may include different types of graphics processing engines within the GPU, such as a graphics execution unit, a media processing engine (e.g., a video encoder / decoder), a sampler, and a block image transfer engine. In other words, the graphics acceleration module may be a GPU having multiple graphics processing engines 431 to 432, 43N, or the graphics processing engines 431 to 432, 43N may be separate GPUs integrated on a common package, line card, or chip.

[0096] In one embodiment, the accelerator integrated circuit 436 includes a memory management unit (MMU) 439 for performing various memory management functions such as virtual to physical memory translation (also known as effective to real memory translation) and a memory access protocol for accessing the system memory 441. The MMU 439 may also include a translation lookaside buffer (TLB) (not shown) for caching virtual / effective to physical / real address translations. In one implementation, the cache 438 stores commands and data for efficient access by the graphics processing engines 431 to 432, 43N. In one embodiment, the data stored in the cache 438 and the graphics memory 433 to 434, 43N is kept consistent with the core caches 462A to 462D, 456 and the system memory 411. As mentioned, this may be accomplished via proxy circuitry 425, which participates in cache coherence mechanisms on behalf of cache 438 and memories 433 to 434, 43N (e.g., sending updates to cache 438 related to modifications / accesses of cache lines on processor caches 462A to 462D, 456 and receiving updates from cache 438).

[0097] A set of registers 445 stores context data for threads executed by the graphics processing engines 431 to 432, 43N, and a context management circuit 448 manages thread contexts. For example, the context management circuit 448 may perform save and restore operations to save and restore contexts of various threads during context switching (e.g., where a first thread is saved and a second thread is stored so that the second thread can be executed by the graphics processing engine). For example, upon context switching, the context management circuit 448 may store current register values ​​to a designated area in memory (e.g., identified by a context pointer). The context management circuit may then restore the register values ​​upon returning to context. In one embodiment, the interrupt management circuit 447 receives and processes interrupts received from system devices.

[0098] In one implementation, the virtual / effective address from the graphics processing engine 431 is converted to a real / physical address in the system memory 411 by the MMU 439. One embodiment of the accelerator integrated circuit 436 supports multiple (e.g., 4, 8, 16) graphics accelerator modules 446 and / or other accelerator devices. The graphics accelerator module 446 can be dedicated to a single application executed on the processor 407, or can be shared between multiple applications. In one embodiment, a virtualized graphics execution environment is presented in which the resources of the graphics processing engines 431 to 432, 43N are shared with multiple applications or virtual machines (VMs). Resources can be subdivided into "slices" that are allocated to different VMs and / or applications based on the processing requirements and priorities associated with the VMs and / or applications.

[0099] Thus, the accelerator integrated circuit acts as a bridge to the system of graphics acceleration modules 446 and provides address translation and system memory cache services. In addition, the accelerator integrated circuit 436 can provide virtualization facilities for the host processor to manage virtualization of the graphics processing engine, interrupts, and memory management.

[0100] Because the hardware resources of the graphics processing engines 431-432, 43N are explicitly mapped to the real address space seen by the host processor 407, any host processor can directly address these resources using effective address values. In one embodiment, one function of the accelerator integrated circuit 436 is the physical separation of the graphics processing engines 431-432, 43N so that they appear on the system as independent units.

[0101] As mentioned, in the illustrated embodiment, one or more graphics memories 433 to 434, 43M are coupled to each of the graphics processing engines 431 to 432, 43N, respectively. The graphics memories 433 to 434, 43M store instructions and data being processed by each of the graphics processing engines 431 to 432, 43N. The graphics memories 433 to 434, 43M may be volatile memories such as DRAM (including stacked DRAM), GDDR memories (e.g., GDDR5, GDDR6), or HBM, and / or may be non-volatile memories such as 3D XPoint or Nano-Ram.

[0102] In one embodiment, in order to reduce data traffic on link 440, biasing techniques are used to ensure that the data stored in graphics memory 433 to 434, 43M is the data most frequently used by graphics processing engines 431 to 432, 43N and preferably not used (at least not frequently) by cores 460A to 460D. Similarly, the biasing mechanism attempts to keep data needed by the core (and preferably not the graphics processing engines 431 to 432, 43N) within the caches 462A to 462D, 456 of the core and system memory 411.

[0103] Figure 4C Another embodiment is shown in which an accelerator integrated circuit 436 is integrated within the processor 407. In this embodiment, the graphics processing engines 431 to 432, 43N communicate directly with the accelerator integrated circuit 436 via the interface 437 and the interface 435 through the high-speed link 440 (which may also utilize any form of bus or interface protocol). The accelerator integrated circuit 436 can perform operations related to Figure 4B The operations are the same as those described, but given their close proximity to the coherency bus 462 and caches 462A to 462D, 426, the operations may be performed at a higher throughput.

[0104] One embodiment supports different programming models, including a dedicated process programming model (without graphics acceleration module virtualization) and a shared programming model (with virtualization). The shared programming model may include a programming model controlled by accelerator integrated circuit 436 and a programming model controlled by graphics acceleration module 446.

[0105] In one embodiment of a dedicated process model, graphics processing engines 431 to 432, 43N are dedicated to a single application or process under a single operating system. A single application can funnel other application requests to graphics engines 431 to 432, 43N, thereby providing virtualization within a VM / partition.

[0106] In a dedicated process programming model, graphics processing engines 431 to 432, 43N can be shared by multiple VM / application partitions. The shared model requires a hypervisor to virtualize graphics processing engines 431 to 432, 43N to allow access by each operating system. For a single partition system without a hypervisor, graphics processing engines 431 to 432, 43N are owned by the operating system. In both cases, the operating system can virtualize graphics processing engines 431 to 432, 43N to provide access to each process or application.

[0107] For the shared programming model, the graphics acceleration module 446 or the individual graphics processing engines 431 to 432, 43N use a process handle to select a processing element. In one embodiment, the processing elements are stored in the system memory 411 and can be addressed using the effective address to real address conversion techniques described herein. The process handle can be an implementation-specific value provided to the host process when registering its context with the graphics processing engine 431 to 432, 43N (i.e., calling the system software to add a processing element to the processing element link table). The lower 16 bits of the process handle can be the offset of the processing element within the processing element link table.

[0108] Figure 4D An exemplary accelerator integrated slice 490 is illustrated. As used herein, a "slice" includes a specified portion of the processing resources of an accelerator integrated circuit 436. An application effective address space 482 within system memory 411 stores processing elements 483. In one embodiment, processing elements 483 are stored in response to GPU calls 481 from applications 480 executed on processor 407. Processing element 483 contains the processing state of the corresponding application 480. A work descriptor (WD) 484 contained in processing element 483 may be a single job requested by an application, or may contain a pointer to a job queue. In the latter case, WD 484 is a pointer to a job request queue in the application address space 482.

[0109] Graphics acceleration module 446 and / or individual graphics processing engines 431-432, 43N may be shared by all processes or a subset of processes in the system. Embodiments of the present invention include an infrastructure for establishing a processing state and sending a WD 484 to the graphics acceleration module 446 to start a job in a virtualized environment.

[0110] In one implementation, the dedicated process programming model is implementation specific. In this model, a single process owns the graphics acceleration module 446 or a separate graphics processing engine 431. Since the graphics acceleration module 446 is owned by a single process, the hypervisor initializes the accelerator integrated circuit 436 to obtain the belonging partition, and the operating system initializes the accelerator integrated circuit 436 to obtain the belonging process when the graphics acceleration module 446 is assigned.

[0111] In operation, the WD acquisition unit 491 in the accelerator integrated slice 490 acquires the next WD 484, which includes an indication of the work to be performed by one of the graphics processing engines of the graphics acceleration module 446. As shown, the data from the WD484 can be stored in the register 445 and used by the MMU 439, the interrupt management circuit 447 and / or the context management circuit 446. For example, one embodiment of the MMU 439 includes a segment / page walk circuit for accessing the segment / page table 486 within the OS virtual address space 485. The interrupt management circuit 447 can process the interrupt event 492 received from the graphics acceleration module 446. When performing graphics operations, the effective address 493 generated by the graphics processing engines 431 to 432, 43N is converted into a real address by the MMU 439.

[0112] In one embodiment, the same set of registers 445 is replicated for each graphics processing engine 431 to 432, 43N and / or graphics acceleration module 446, and this set of registers can be initialized by a hypervisor or an operating system. Each of these replicated registers can be included in an accelerator integrated slice 490. Table 1 shows exemplary registers that can be initialized by a hypervisor.

[0113] Table 1 - Hypervisor Initialization Registers

[0114] 1 Slice Control Register 2 Real address (RA) dispatch process area pointer 3 Authorization Mask Override Register 4 Interrupt vector table entry offset 5 Interrupt vector table entry limit 6 Status Register 7 Logical Partition ID 8 Real Address (RA) Hypervisor Accelerator Utilizing Record Pointers 9 Storage Description Register

[0115] Example registers that may be initialized by the operating system are shown in Table 2.

[0116] Table 2 - Operating System Initialization Registers

[0117] 1 Process and thread identities 2 Effective Address (EA) context save / restore pointer 3 Virtual Address (VA) Accelerator Utilizes Record Pointers 4 Virtual Address (VA) Segment Table Pointer 5 Authorization Mask 6 Job Descriptor

[0118] In one embodiment, each WD 484 is specific to a particular graphics acceleration module 446 and / or graphics processing engine 431 to 432, 43N. The WD contains all the information needed by the graphics processing engine 431 to 432, 43N to complete its work, or the WD can be a pointer to a memory location where the application has established a command queue for work to be completed.

[0119] Figure 4E Additional details of one embodiment of a sharing model are illustrated. The embodiment includes a hypervisor real address space 498 in which a process element list 499 is stored. The hypervisor real address space 498 is accessible via a hypervisor 496 that virtualizes a graphics acceleration module engine of an operating system 495.

[0120] The shared programming model allows all processes or a subset of processes from all partitions or a subset of partitions in the system to use the graphics acceleration module 446. There are two programming models where the graphics acceleration module 446 is shared by multiple processes and partitions: time-slice sharing and graphics direct sharing.

[0121] In this model, the hypervisor 496 owns the graphics acceleration module 446 and makes its functionality available to all operating systems 495. In order for the graphics acceleration module 446 to support virtualization of the hypervisor 496, the graphics acceleration module 446 may comply with the following requirements: 1) Application job requests must be autonomous (i.e., no state needs to be maintained between jobs), or the graphics acceleration module 446 must provide a context save and restore mechanism. 2) The graphics acceleration module 446 guarantees that application job requests are completed within a specified amount of time, including any conversion errors, or the graphics acceleration module 446 provides the ability to preempt job processing. 3) When operating in a direct sharing programming model, fairness between processes must be guaranteed for the graphics acceleration module 446.

[0122] In one embodiment, for the shared model, the application 480 is required to make an operating system 495 system call using a graphics acceleration module 446 type, a work descriptor (WD), an authorization mask register (AMR) value, and a context save / restore region pointer (CSRP). The graphics acceleration module 446 type describes the target acceleration function of the system call. The graphics acceleration module 446 type can be a system-specific value. The WD is formatted specifically for the graphics acceleration module 446 and can be in the following form: a graphics acceleration module 446 command; an effective address pointer to a user-defined structure; an effective address pointer to a command queue; or any other data structure used to describe the work to be performed by the graphics acceleration module 446. In one embodiment, the AMR value is the AMR state for the current process. The value passed to the operating system is similar to the application that sets the AMR. If the implementation of the accelerator integrated circuit 436 and the graphics acceleration module 446 does not support the user authorization mask override register (UAMOR), the operating system can apply the current UAMOR value to the AMR value before passing the AMR in the hypervisor call. The hypervisor 496 may optionally apply the current authorization mask override register (AMOR) value before placing the AMR on the processing element 483. In one embodiment, the CSRP is one of the registers 445 that contains the effective address of an area in the application address space 482 for the graphics acceleration module 446 to save and restore context state. This pointer is optional if state is not required to be saved between jobs or when a job is preempted. The context save / restore area may be a plugged in system memory.

[0123] Upon receiving the system call, the operating system 495 can verify that the application 480 is registered and authorized to use the graphics acceleration module 446. The operating system 495 then calls the hypervisor 496 with the information shown in Table 3.

[0124] Table 3 - Parameters of the operating system's call to the hypervisor

[0125] 1 Job Descriptor (WD) 2 Authorization Mask Register (AMR) value (may be masked) 3 Effective Address (EA) Context Save / Restore Region Pointer (CSRP) 4 Process ID (PID) and optional thread ID (TID) 5 Virtual Address (VA) Accelerator Utilization Record Pointer (AURP) 6 Virtual address of the storage segment table pointer (SSTP) 7 Logical Interrupt Service Number (LISN)

[0126] Upon receiving the hypervisor call, hypervisor 496 verifies that operating system 495 has registered and is authorized to use graphics acceleration module 446. Hypervisor 496 then places processing element 483 into a processing element link table for the corresponding graphics acceleration module 446 type. A processing element may include the information shown in Table 4.

[0127] Table 4 - Processing Component Information

[0128] 1 Job Descriptor (WD) 2 Authorization Mask Register (AMR) value (may be masked) 3 Effective Address (EA) Context Save / Restore Region Pointer (CSRP) 4 Process ID (PID) and optional thread ID (TID) 5 Virtual Address (VA) Accelerator Utilization Record Pointer (AURP) 6 Virtual address of the storage segment table pointer (SSTP) 7 Logical Interrupt Service Number (LISN) 8 Interrupt vector table, derived from the hypervisor call parameters 9 Status Register (SR) Value 10 Logical Partition ID (LPID) 11 Real Address (RA) Hypervisor Accelerator Utilizing Record Pointers 12 Storage Descriptor Register (SDR)

[0129] In one embodiment, the hypervisor initializes the plurality of accelerator integrated slices 490 of registers 445 .

[0130] like Figure 4F As shown, one embodiment of the present invention employs a unified memory addressable via a common virtual memory address space for accessing physical processor memories 401 to 402 and GPU memories 420 to 423. In this implementation, operations executed on GPUs 410 to 413 utilize the same virtual / effective memory address space to access processor memories 401 to 402, and vice versa, thereby simplifying programmability. In one embodiment, a first portion of the virtual / effective address space is allocated to processor memory 401, a second portion is allocated to second processor memory 402, a third portion is allocated to GPU memory 420, and so on. The entire virtual / effective memory space (sometimes referred to as the effective address space) is thus distributed across each of processor memories 401 to 402 and GPU memories 420 to 423, thereby allowing any processor or GPU to access any physical memory having a virtual address mapped to that memory.

[0131] In one embodiment, bias / coherency management circuits 494A-494E within one or more of MMUs 439A-439E ensure cache coherency between caches of a host processor (e.g., 405) and GPUs 410-413 and implement biasing techniques that indicate physical memory where certain types of data should be stored. Figure 4F 4. Multiple instances of bias / consistency management circuits 494A to 494E are illustrated in FIG. 4, but bias / consistency circuits may also be implemented within an MMU of one or more host processors 405 and / or within an accelerator integrated circuit 436.

[0132] One embodiment allows the GPU-attached memory 420 to 423 to be mapped as part of the system memory and accessed using shared virtual memory (SVM) technology, but without suffering from the typical performance drawbacks associated with full system cache coherence. The ability to access the GPU-attached memory 420 to 423 as system memory does not incur heavy cache coherence overhead, which provides a favorable operating environment for GPU offloading. This arrangement allows the host processor 405 software to set operands and access calculation results without the overhead of traditional I / O DMA data copies. These traditional copies involve driver calls, interrupts, and memory mapped I / O (MMIO) accesses, which are all inefficient relative to simple memory accesses. At the same time, the ability to access the GPU-attached memory 420 to 423 without cache coherence overhead may be critical to the execution time of the offloaded calculation. For example, in the case of a large number of streaming write memory transactions, the cache coherence overhead can significantly reduce the effective write bandwidth seen by the GPU 410 to 413. The efficiency of operand setup, the efficiency of result access, and the efficiency of GPU calculation all play an important role in determining the effectiveness of GPU offloading.

[0133] In one implementation, the selection between GPU bias and host processor bias is driven by a bias tracker data structure. For example, a bias table may be used, which may be a page granular structure including 1 or 2 bits per GPU attached memory page (i.e., controlled at the granularity of a memory page). The bias table may be implemented in the stolen memory range of one or more GPU attached memories 420 to 423, with or without a bias cache in GPUs 410 to 413 (e.g., to cache frequently / recently used bias table entries). Alternatively, the entire bias table may be maintained within the GPU.

[0134] In one implementation, the bias table entry associated with each access to the GPU attached memory 420 to 423 is accessed before the GPU memory is actually accessed, resulting in the following operations. First, local requests from GPUs 410 to 413 whose pages are found in the GPU bias are forwarded directly to the corresponding GPU memory 420 to 423. Local requests from the GPU whose pages are found in the host bias are forwarded to the processor 405 (e.g., over a high-speed link as discussed above). In one embodiment, the request from the processor 405 to find the requested page in the host processor bias completes the request like a normal memory read. Alternatively, the request for the GPU bias page can be forwarded to the GPU 410 to 413. Then, if the GPU is not currently using the page, the GPU can transfer the page to the host processor bias.

[0135] The bias state of a page may be changed by a software-based mechanism, a hardware-assisted software-based mechanism, or, for a limited set of cases, a hardware-only based mechanism.

[0136] One mechanism for changing the bias state employs an API call (e.g., OpenCL) which in turn calls a GPU device driver which in turn sends a message (or queues a command descriptor) to the GPU, thereby directing the GPU to change the bias state and, for certain transitions, perform a cache flush operation in the host. The cache flush operation is required for a transition from host processor 405 bias to GPU bias, but not for the reverse transition.

[0137] In one embodiment, cache coherency is maintained by temporarily rendering GPU bias pages uncacheable to host processor 405. To access these pages, processor 405 may request access from GPU 410, which may or may not grant access immediately, depending on the implementation. Therefore, to reduce communication between processor 405 and GPU 410, it is advantageous to ensure that GPU bias pages are pages that are needed by the GPU but not by the host processor 405, and vice versa.

[0138] Graphics processing pipeline

[0139] Figure 5 A graphics processing pipeline 500 is illustrated according to an embodiment. In one embodiment, a graphics processor may implement the illustrated graphics processing pipeline 500. The graphics processor may be included in a parallel processing subsystem as described herein, such as a Figure 2A In one embodiment, the parallel processor 200 is Figure 1 As described herein, various parallel processing systems may be implemented via parallel processing units (e.g., Figure 2A The graphics processing pipeline 500 may be implemented using one or more instances of a parallel processing unit 202 of the graphics processing unit. For example, a shader unit (e.g., Figure 2D The graphics multiprocessor 234 of the embodiment of the present invention may be configured to perform the functions of one or more of the vertex processing unit 504, the tessellation control processing unit 508, the tessellation evaluation processing unit 512, the geometry processing unit 516, and the fragment / pixel processing unit 524. The functions of the data assembler 502, the primitive assemblers 506, 514, 518, the tessellation unit 510, the rasterizer 522, and the raster operation unit 526 may also be performed by a processing cluster (e.g., Figure 3A Other processing engines and corresponding partition units (e.g., Figure 2C The graphics processing pipeline 500 may also be implemented using one or more dedicated processing units. In one embodiment, one or more portions of the graphics processing pipeline 500 may be executed by parallel processing logic within a general purpose processor (e.g., a CPU). In one embodiment, one or more portions of the graphics processing pipeline 500 may access on-chip memory (e.g., such as a CPU) via a memory interface 528. Figure 2A ), the memory interface may be Figure 2A An example of a memory interface 218 .

[0140] In one embodiment, data assembler 502 is a processing unit that collects vertex data for surfaces and primitives. Data assembler 502 then outputs vertex data including vertex attributes to vertex processing unit 504. Vertex processing unit 504 is a programmable execution unit that executes vertex shader programs to illuminate and transform vertex data as specified by the vertex shader programs. Vertex processing unit 504 reads data stored in cache, local or system memory for processing vertex data, and can be programmed to transform vertex data from an object-based coordinate representation to a world space coordinate space or a normalized device coordinate space.

[0141] A first instance of primitive assembler 506 receives vertex attributes from vertex processing unit 504. Primitive assembler 506 reads the stored vertex attributes and constructs graphics primitives as needed for processing by tessellation control processing unit 508. Graphics primitives include triangles, line segments, points, patches, etc. as supported by various graphics processing application programming interfaces (APIs).

[0142] The tessellation control processing unit 508 treats the input vertices as control points of a geometric patch. These control points are transformed from an input representation from the patch (e.g., a basis for the patch) to a representation suitable for surface evaluation by the tessellation evaluation processing unit 512. The tessellation control processing unit 508 may also calculate tessellation factors for the edges of the geometric patch. The tessellation factors apply to individual edges and quantify the viewpoint-dependent level of detail associated with the edge. The tessellation unit 510 is configured to receive the tessellation factors for the edges of the patch and tessellate the patch into a plurality of geometric primitives, such as lines, triangles, or quadrilateral primitives, which are transmitted to the tessellation evaluation processing unit 512. The tessellation evaluation processing unit 512 operates on the parameterized coordinates of the tessellated patch to generate a surface representation and vertex attributes for each vertex associated with the geometric primitive.

[0143] A second instance of primitive assembler 514 receives vertex attributes from tessellation evaluation processing unit 512, reads stored vertex attributes as needed, and constructs graphics primitives for processing by geometry processing unit 516. Geometry processing unit 516 is a programmable execution unit that executes geometry shader programs to transform graphics primitives received from primitive assembler 514 as specified by the geometry shader programs. In one embodiment, geometry processing unit 516 is programmed to tessellate the graphics primitives into one or more new graphics primitives and to compute parameters for rasterizing the new graphics primitives.

[0144] In some embodiments, the geometry processing unit 516 can add or delete elements in the geometry stream. The geometry processing unit 516 outputs parameters and vertices specifying new graphics primitives to the primitive assembler 518. The primitive assembler 518 receives the parameters and vertices from the geometry processing unit 516 and constructs graphics primitives for processing by the viewport scaling, picking, and clipping unit 520. The geometry processing unit 516 reads data stored in the parallel processor memory or the system memory for processing geometry data. The viewport scaling, picking, and clipping unit 520 performs clipping, picking, and viewport scaling, and outputs the processed graphics primitives to the rasterizer 522.

[0145] Rasterizer 522 may perform depth culling and other depth-based optimizations. Rasterizer 522 also performs scan conversion on new graphics primitives to generate fragments and outputs these fragments and associated coverage data to fragment / pixel processing unit 524.

[0146] The fragment / pixel processing unit 524 is a programmable execution unit configured to execute a fragment shader program or a pixel shader program. The fragment / pixel processing unit 524 transforms the fragments or pixels received from the rasterizer 522 as specified by the fragment or pixel shader program. For example, the fragment / pixel processing unit 524 can be programmed to perform operations including but not limited to texture mapping, shading, blending, texture correction, and perspective correction to produce shaded fragments or pixels output to the raster operation unit 526. The fragment / pixel processing unit 524 can read data stored in a parallel processor memory or system memory for use in processing fragment data. The fragment or pixel shader program can be configured to shade at a sample, pixel, tile, or other granularity according to the sampling rate configured for the processing unit.

[0147] Raster operations unit 526 is a processing unit that performs raster operations including, but not limited to, stenciling, z-testing, blending, etc., and outputs pixel data as processed graphics data for storage in graphics memory (e.g., as Figure 2A The parallel processor memory 222 and / or Figure 1104) for display on one or more display devices 110 or further processing by one of the one or more processors 102 or parallel processor(s) 112. In some embodiments, raster operations unit 526 is configured to compress z or color data written to memory and decompress z or color data read from memory.

[0148] Figure 6 A computing device 600 is illustrated that hosts a finite state machine and a fast computing mechanism ("computing mechanism") 610 according to one embodiment. The computing device 600 represents a communication and data processing device, which includes (but is not limited to) a smart wearable device, a smart phone, a virtual reality (VR) device, a head mounted display (HMD), a mobile computer, an Internet of Things (IoT) device, a laptop computer, a desktop computer, a server computer, etc., and is compatible with Figure 1 The computing system 100 is similar or identical to the computing system 100 of FIG. 1 ; accordingly, for the sake of brevity, clarity and ease of understanding, the above reference Figures 1 to 5 Many of the details described are not further discussed or repeated below.

[0149] The computing device 600 may further include (but not limited to) autonomous machines or artificial intelligence agents, such as mechanical agents or machines, electronic agents or machines, virtual agents or machines, electromechanical agents or machines, etc. Examples of autonomous machines or artificial intelligence agents may include (but not limited to) robots, autonomous vehicles (e.g., self-driving cars, self-flying aircraft, self-navigating ships, etc.), autonomous equipment (self-operating construction vehicles, self-operating medical equipment, etc.), etc. Throughout this document, a "computing device" may be interchangeably referred to as an "autonomous machine" or an "artificial intelligence agent" or just a "robot".

[0150] It is contemplated that, although reference is made throughout this document to "autonomous vehicles" and "autonomous driving," embodiments are not so limited. For example, an "autonomous vehicle" is not limited to an automobile, but may include any number and type of autonomous machines, such as robots, autonomous equipment, domestic autonomous devices, and the like, and any one or more tasks or operations associated with such autonomous machines may be interchangeably referenced with respect to autonomous driving.

[0151] The computing device 600 may further include, but is not limited to, a large computing system (such as a server computer, a desktop computer, etc.), and may further include a set-top box (such as an Internet-based cable TV set-top box, etc.), a device based on a global positioning system (GPS), etc. The computing device 600 may include a mobile computing device that acts as a communication device, such as a cellular phone including a smart phone, a personal digital assistant (PDA), a tablet computer, a laptop computer, an e-reader, a smart TV, a TV platform, a wearable device (such as glasses, watches, bracelets, smart cards, jewelry, clothing items, etc.), a media player, etc. For example, in one embodiment, the computing device 600 may include a mobile computing device that employs a computer platform that hosts an integrated circuit (“IC”) such as a system on a chip (“SoC” or “SOC”), which integrates various hardware and / or software components of the computing device 600 on a single chip.

[0152] As illustrated, in one embodiment, computing device 600 may include any number and types of hardware and / or software components such as, but not limited to, a graphics processing unit (“GPU” or just “graphics processor”) 614, a graphics driver (also referred to as a “GPU driver”, “graphics driver logic”, “driver logic”, a user mode driver (UMD), UMD, a user mode driver framework (UMDF), UMDF or just “driver”) 616, a central processing unit (“CPU” or just “application processor”) 612, memory 608, network devices, drivers, etc., and input / output (I / O) sources 604 such as a touch screen, touch panel, touchpad, virtual or regular keyboard, virtual or regular mouse, ports, connectors, etc. The computing device 600 may include an operating system (OS) 606 that acts as an interface between the hardware and / or physical resources of the computing device 600 and a user. It is contemplated that the graphics processor 614 and the application processor 612 may be Figure 1 One or more of the processor(s) 102.

[0153] It should be understood that for some implementations, systems with fewer or more equipment than the above examples may be preferred. Thus, the configuration of computing device 600 may vary from implementation to implementation depending on many factors, such as price constraints, performance requirements, technology improvements, or other circumstances.

[0154] Embodiments may be implemented as any one or a combination of the following: one or more microchips or integrated circuits interconnected using a motherboard, hardwired logic, software stored by a memory device and executed by a microprocessor, firmware, an application specific integrated circuit (ASIC), and / or a field programmable gate array (FPGA). As an example, the terms "logic", "module", "component", "engine", and "mechanism" may include software or hardware and / or a combination of software and hardware.

[0155] In one embodiment, the computing mechanism 610 may be hosted or facilitated by an operating system 606 of the computing device 600. In another embodiment, the computing mechanism 610 may be hosted or facilitated by a graphics processing unit (“GPU” or just “graphics processor”) 614 or firmware of the graphics processor 614. For example, the computing mechanism 610 may be embedded in or implemented as part of the processing hardware of the graphics processor 614. Similarly, in yet another embodiment, the computing mechanism 610 may be hosted or facilitated by a central processing unit (“CPU” or just “application processor”) 612. For example, the computing mechanism 610 may be embedded in or implemented as part of the processing hardware of the application processor 614. In yet another embodiment, the computer mechanism 610 may be hosted by or be part of any number and type of components of the computing device 600, such as a portion of the computer mechanism 610 may be hosted by or be part of the operating system 606, another portion may be hosted by or be part of the graphics processor 614, another portion may be hosted by or be part of the application processor 612, and one or more portions of the computer mechanism 610 may be hosted by or be part of the operating system 606 and / or any number and type of devices of the computing device 600. It is contemplated that one or more portions or components of the computer mechanism 610 may be implemented as hardware, software, and / or firmware.

[0156] It is contemplated that embodiments are not limited to any particular implementation or hosting of computer mechanism 610, and that computer mechanism 610, and one or more of its components, may be implemented as hardware, software, firmware, or any combination thereof.

[0157] The computing device 600 may host (one or more) host network interfaces to provide access to a network, such as a LAN, a wide area network (WAN), a metropolitan area network (MAN), a personal area network (PAN), Bluetooth, a cloud network, a mobile network (e.g., 3rd generation (3G), 4th generation (4G), etc.), an intranet, the Internet, etc. The (one or more) network interfaces may include, for example, a wireless network interface having an antenna, which may represent one or more antennas. The (one or more) network interfaces may also include, for example, a wired network interface for communicating with a remote device via a network cable, which may be, for example, an Ethernet cable, a coaxial cable, a fiber optic cable, a serial cable, or a parallel cable.

[0158] Embodiments may be provided, for example, as a computer program product, which may include one or more machine-readable media having machine-executable instructions stored thereon, which when executed by one or more machines such as a computer, a computer network, or other electronic device, may cause the one or more machines to perform operations according to the embodiments described herein. The machine-readable medium may include, but is not limited to, a floppy disk, an optical disk, a CD-ROM (compact disk read-only memory) and a magneto-optical disk, a ROM, a RAM, an EPROM (erasable programmable read-only memory), an EEPROM (electrically erasable programmable read-only memory), a magnetic or optical card, a flash memory, or other types of media / machine-readable media suitable for storing machine-executable instructions.

[0159] In addition, embodiments may be downloaded as a computer program product, wherein the program may be transmitted from a remote computer (e.g., a server) to a requesting computer (e.g., a client) via a communication link (e.g., a modem and / or a network connection) by means of one or more data signals embodied in and / or modulated by a carrier wave or other propagation medium.

[0160] Throughout this document, the term "user" may be referred to interchangeably as a "viewer," "observer," "person," "individual," "end-user," and / or the like. It should be noted that throughout this document, terms like "graphics domain" may be referred to interchangeably with "graphics processing unit," "graphics processor," or just "GPU," and similarly, "CPU domain" or "host domain" may be referred to interchangeably with "computer processing unit," "application processor," or just "CPU."

[0161] It is noted that throughout this document, terms like "node", "computing node", "server", "server device", "cloud computer", "cloud server", "cloud server computer", "machine", "host", "device", "computing device", "computer", "computing system", etc. may be used interchangeably. It should be further noted that throughout this document, terms like "application", "software application", "program", "software program", "package", "software software package", etc. may be used interchangeably. Likewise, throughout this document, terms like "job", "input", "request", "message", etc. may be used interchangeably.

[0162] Figure 7 The diagram shows a method according to an embodiment Figure 6 For the sake of brevity, the following does not repeat or discuss the calculation mechanism 610. Figures 1 to 6 In one embodiment, the computing mechanism 610 may include any number and type of components, such as (but not limited to): detection / observation logic 701; bypass / detour logic 703; calculation / customization logic 705; and communication / compatibility logic 707.

[0163] Conventional techniques such as those involving general purpose computational logic are unable to use frequently used data values, and therefore, conventional techniques are known to repeat computational operations even when processing the same values, resulting in energy consumption and high latency.

[0164] Embodiments provide novel techniques for detecting frequently used data values ​​and then speeding up operations by employing techniques like lookup tables, reduced math, etc. when facilitated by the computing mechanism 610. For example, in one embodiment, a frequently used data list may contain numbers like 0, 1, 0.5, etc., while machine learning operations use sparse matrix linear algebra.

[0165] It is envisioned that using this novel technology, computations dedicated to deep learning, machine learning acceleration, etc. can greatly benefit from being customized for frequently used data values ​​and operations. By avoiding routine repetition of operations using the same known values, resource consumption and waiting time can be significantly reduced.

[0166] In one embodiment, the detection / observation logic 701 may be used to act as a frequently used data value (FDV) detection engine, which is used to continuously, periodically, or when needed to detect operands for which the computational logic pipeline may be bypassed when facilitated by the bypass / detour logic 703; in turn, in one embodiment, this process can simply run through a shorter and faster computational pipeline without having to undergo conventional calculations when facilitated by the bypass / detour logic 703.

[0167] In one embodiment, the FDV blocks may be made configurable at runtime or in areas that allow for greater customization, where this may be associated with configurable FDVs bypassing configurable compute blocks to compute simplified mathematical operations, and / or the like.

[0168] As reference Fig. 8A As illustrated, in one embodiment, detection / observation logic 701 is used to detect operands or values, and this information is then forwarded to bypass / detour logic 703. In one embodiment, bypass / detour logic 703 analyzes the information or data to determine whether some of the values ​​are frequently used values. For example, if the detected values ​​are not frequently used values, bypass / detour logic 703 may allow the values ​​to pass through the calculation blocks, where the values ​​are calculated and the corresponding results are output.

[0169] However, if upon analyzing the values, the bypass / detour logic 703 determines that the values ​​are frequently used data values ​​or FDVs, such values ​​are placed on detour routes (which do not pass through the computational blocks), and these values ​​are instead routed through the bypass routes. In this case, no computation or additional operations are performed with respect to these FDVs, which in turn saves latency and other system resources, such as power, bandwidth, etc.

[0170] In one embodiment, this novel technique, when facilitated by the computation mechanism 610, also provides for the use of the computation / customization logic 705 for customization of processes and / or components by allowing configuration of one or more of the FDVs, bypass blocks, computation blocks, etc., to further simplify mathematical operations of whether the FDV passes through a bypass block or a computation block. For example, certain mathematical operations may be dropped entirely or altered or replaced to further simplify computation operations.

[0171] For example, using detection / observation logic 701, based on detection of one or more patterns of FDV used in one or more operations (such as in the case of media access control (MAC) operations), the entire multiplication operation can be discarded by bypass / detour logic 703 on frequent values ​​like 0 / 1 / 0.5.

[0172] Embodiments provide novel techniques for hosting finite state machines (FSMs), such as those for C+ as facilitated by compute / customization logic 705. A typical finite state machine represents a mathematical model of computation, being an abstract machine that can be in exactly one of a finite number of states at any given time.

[0173] In one embodiment, this novel FSM, when facilitated by the compute / customization logic 705, acts as a common primitive for convolution and fully connected computations to facilitate memory read accesses as well as combinations of multiplications and additions, essentially acting as a super MAC. For example, when facilitated by the compute / customization logic 705, the FSM can be facilitated to merge addition and multiplication operations at the partial product level because there are N ordered addends.

[0174] As previously mentioned, acting as a common primitive for convolution and fully connected computations, in one embodiment, the FSM can combine memory read accesses with multiplication and addition, while combining memory accesses with a direct memory access (DMA) module when facilitated by the compute / customization logic 705. Addition and multiplication can be merged at the partial product level because there are N ordered addends.

[0175] The primitives can be defined as follows: sequential_MAC(A_base, B_base, N, step, C_immediate) or sequential_MAC(A_base, B_base, N, step, C_base); sequential_MAC(A_base, B_base, N, step, C_immediate) = ;and sequential_MAC(A_base,B_base,N,step,C_base)= As reference Figure 8B As shown, base[n] can be considered as the nth item in the address base, where the special case includes process=1. In one embodiment, the FSM module is input with A_base and B_base, N, step or process and start signal, and outputs each Ai and Bi address. As shown in FIG. Figure 8B As shown, the Ai and Bi addresses are used in the memory read module to access the A and B memories to obtain the Ai and Bi data. Further, the A and B memories can be combined and separated, while the start signal also controls the multiplexer used to initialize AC with C-immediate, while the ACC cumulatively adds the product of itself and the Ai / Bi data. When the FSM passes through all address ranges, it can signal the end and the ACC returns to the result SUM.

[0176] Furthermore, communication / compatibility logic 707 may be used to facilitate desired communications and compatibility between any number of devices of computing device 600 and various components of computing mechanism 610 .

[0177] The communication / compatibility logic 707 can be used to facilitate dynamic communication and compatibility between the computing device 600 and the following while ensuring compatibility with changing technologies, parameters, protocols, standards, etc.: any number and type of other computing devices (such as mobile computing devices, desktop computers, server computing devices, etc.); processing devices or components (such as CPUs, GPUs, etc.); capture / sensing / detection devices (such as capture / sensing components, including cameras, depth sensing cameras, camera sensors, red-green-blue ("RGB" or "rgb") sensors, microphones, etc.); display devices (such as output components, including display screens, display areas, display projectors, etc.); user / context awareness components and / or identification / authentication sensors / devices (such as biometric sensors / detectors, scanners, etc.); (one or more ) database 730, such as a memory or storage device, a database and / or a data source (such as a data storage device, a hard drive, a solid-state drive, a hard disk, a memory card or device, a memory circuit, etc.); (one or more) communication media 725, such as one or more communication channels or networks (e.g., a cloud network, the Internet, an intranet, a cellular network, a proximity network, such as Bluetooth, Bluetooth Low Energy (BLE), Bluetooth Smart, Wi-Fi Proximity, Radio Frequency Identification (RFID), Near Field Communication (NFC), Body Area Network (BAN), etc.); wireless or wired communications and related protocols (e.g., Wi-Fi®, WiMAX, Ethernet, etc.); connectivity and location management technologies; software applications / websites (e.g., social and / or business networking websites, business applications, games and other entertainment applications, etc.); and programming languages, etc.

[0178] In addition, any use of specific brands, words, terms, phrases, names and / or acronyms such as "detection", "observation", "decision", "normal path", "detour", "computation box", "bypass", "frequently used data value", "FDV", "finite state machine", "training set", "agent", "machine", "vehicle", "robot", "drive", "CNN", "DNN", "NN", "execution unit", "EU", "shared local memory", "SLM", "graphics stream", "cache", "graphics cache", "GPU", "graphics processor", "GPU domain", "GPGPU", "CPU", "application processor", "CPU domain", "graphics driver", "workload", "application", "graphics pipeline", "pipeline process", "API", "3D API", "OpenGL®", "DirectX®", "hardware", "software", "agent", "graphics driver", "kernel mode graphics driver", "user mode driver", "user mode driver framework", "buffer", "graphics buffer", "task", "process", "operation", "software application", "game", etc. should not be construed to limit the embodiments to software or devices carrying such labels in documents or products outside of this document.

[0179] It is contemplated that any number and type of components may be added to and / or removed from the computer mechanism 610 to facilitate various embodiments including adding, removing, and / or enhancing certain features. For brevity, clarity, and ease of understanding of the computer mechanism 610, many standard and / or known components, such as those of a computing device, are not shown or discussed herein. It is contemplated that, as described herein, the embodiments are not limited to any particular technology, topology, system, architecture, and / or standard, and are sufficiently dynamic to adopt and adapt to any future changes.

[0180] Fig. 8A An architectural arrangement 800 for bypassing FDVs according to one embodiment is illustrated. Figure 1-7 Many details of the discussion may not be discussed or repeated below. Figure 6 When facilitated by the computer mechanism 610 of the embodiment of the present invention, any process related to the arrangement 800 may be performed by processing logic, which may include hardware (e.g., circuits, dedicated logic, programmable logic, etc.), software (such as instructions running on a processing device), or a combination thereof. For simplicity and clarity in presentation, the processes associated with the arrangement 800 may be shown or described in a linear sequence; however, it is contemplated that any number of them can be performed in parallel, asynchronously, or in a different order. In addition, the embodiments are not limited to any specific architectural placement, framework, arrangement, or structure of components and / or processes, such as the arrangement 800.

[0181] As shown here and referenced Figure 7 As described, Figure 7 When facilitated by the detection / observation logic 701 of FIG. 802 , data 811 is received at the FDV detection block 801. At the FDV detection block 801, the data 811 is not only detected or observed, but also analyzed when facilitated by the bypass / detour logic 703 to determine whether the data contains any FDVs that can be bypassed (such as by FDV bypass block 805) without going through the normal computation path (such as by computation block 803).

[0182] For example, if the data 801 does not contain any FDV, the data 801 is then classified as processing data and is placed on a normal path to pass through the calculation block 803 for a normal set of calculations, thereby outputting a result 815. However, if it is determined that the data 801 has an FDV, some or all of the data 801 with the FDV is then classified as bypass data and is placed on a detour through FDV bypass block 805 to pass through it without passing through any normal set of calculations in the calculation block 805, thereby reducing time, waiting time, consumption of system resources, etc., and is output as the result 815.

[0183] Additionally, in one embodiment, the FDV detection block 801 and the FDV bypass block 805 are shown as receiving the FDV configuration, as shown in FIG. Figure 7 As described, this allows customization of the FDV and its processing. In one embodiment, this customization of the FDV configuration 813 is provided with additional efficiency and speed, such as by simplifying and / or eliminating certain mathematical operations (e.g., multiplication, addition, etc.) that may be unnecessary depending on the nature of the data 801 and whether it passes through the calculation block 803 or the FDV bypass block 805.

[0184] In one embodiment, the FDV may be configured at runtime or on a field allowing for greater customization using FDV configuration 813, which may then be associated with a configurable FDV bypass block 805 to bypass calculations or pass through a configurable calculation block 803 for calculations using simplified mathematical operations.

[0185] Figure 8B The diagram shows an architecture 850 for employing and using a finite state machine 861 according to one embodiment. Figure 1-7 Many details of the discussion may not be discussed or repeated below. Figure 6When facilitated by the computer mechanism 610 of the architecture 800, any process related to the architecture 800 may be performed by processing logic, which may include hardware (e.g., circuits, dedicated logic, programmable logic, etc.), software (such as instructions running on a processing device), or a combination thereof. For simplicity and clarity in presentation, the processes associated with the architecture 800 may be shown or described in a linear sequence; however, it is contemplated that any number of them can be executed in parallel, asynchronously, or in a different order. In addition, embodiments are not limited to any specific architectural placement, framework, arrangement, or structure of components and / or processes, such as the model 900.

[0186] As discussed previously, common primitives are provided for convolution and fully connected computations. For example, FSM 861 may be able to combine memory read accesses and multiplications with additions, like a super MAC. This memory access may also be combined with a DMA module, where additions and multiplications may be merged at a partial production level, since there are N ordered addends.

[0187] For example, input 851 is received in FSM 861, where primitives are defined as follows: sequential_MAC(A_base, B_base, N, step, C_immediate) or sequential_MAC(A_base, B_base, N, step, C_base); sequential_MAC(A_base, B_base, N, step, C_immediate) = ;and sequential_MAC(A_base,B_base,N,step,C_base)= .

[0188] As shown, base[n] can be thought of as the nth entry in the address base as referenced by Figure 8BAs shown, base[n] may be considered as the nth entry in the address base, with the special case containing process=1. In one embodiment, the FSM 861 is input with A_base and B_base, N, the step or process and the start signal of the input 851, and outputs each Ai address 863 and Bi address 875. As further shown, the Ai and Bi addresses are used in the memory read module 865 to access the A memory 871 and the B memory 873 to obtain the Ai data 881 and the Bi data 883. Further, the A and B memories 871, 873 may be combined and separated, while the start signal also controls the multiplexer 867 that receives the input 853 and initializes the AC with C-immediate, while the ACC cumulatively adds the product of itself and the Ai / Bi data 881, 883. When the FSM has passed through all address ranges, it may signal the end 855 and the ACC 869 returns to the result SUM 855.

[0189] Fig. 9 A method 900 for facilitating fast computing operations according to one embodiment is illustrated. Figures 1 to 8B Any process associated with method 900 may be performed by a processing logic that may include hardware (e.g., circuitry, dedicated logic, programmable logic, etc.), software (such as instructions running on a processing device), or a combination thereof. Figure 6 As facilitated by the computer mechanism 610 of . For simplicity and clarity in presentation, the processes associated with the method 900 may be illustrated or recorded in a linear sequence; however, it is contemplated that any number of them may be performed in parallel, asynchronously, or in a different order.

[0190] Method 900 begins at block 901 where operands / values / data being communicated for potential computations involving tasks associated with one or more processors of a computing device are detected. At block 903, all data values ​​are analyzed and, in some embodiments, configurations may be applied to the process and components involved in the process for customization of the computation and / or bypass.

[0191] In one embodiment, at block 905, a determination is made as to whether the value is considered a frequently used value. If so, the data is set on the normal path of calculation, where a partially customized calculation is performed on the value at the calculation block. If not, the data is set on a detour, such that any traditional calculation is skipped and the value is bypassed to the result.

[0192] Machine Learning Overview

[0193] A machine learning algorithm is an algorithm that can learn based on a set of data. Embodiments of machine learning algorithms can be designed to model high-level abstractions within a data set. For example, an image recognition algorithm can be used to determine which of several categories a given input belongs to; a regression algorithm can output a numerical value given an input; and a pattern recognition algorithm can be used to generate translated text or perform text-to-speech and / or speech recognition.

[0194] One exemplary type of machine learning algorithm is a neural network. There are many types of neural networks; a simple type of neural network is a feedforward network. A feedforward network can be implemented as an acyclic graph in which nodes are arranged in layers. Typically, a feedforward network topology includes an input layer and an output layer separated by at least one hidden layer. The hidden layer transforms the input received by the input layer into a representation useful for generating output in the output layer. The network nodes are fully connected to the nodes in the adjacent layers via edges, but there are no edges between the nodes within each layer. Data received at the nodes of the input layer of the feedforward network is propagated (i.e., "fed forward") to the nodes of the output layer via an activation function, which calculates the state of the nodes of each successive layer in the network based on coefficients ("weights"), which are respectively associated with each of the edges connecting these layers. Depending on the specific model represented by the algorithm being executed, the output from the neural network algorithm can take a variety of forms.

[0195] Before a machine learning algorithm can be used to model a specific problem, the algorithm is trained using a training data set. Training a neural network involves: selecting a network topology; using a set of training data representing the problem being modeled by the network; and adjusting weights until the network model behaves with minimal error for all instances of the training data set. For example, during a supervised learning training process for a neural network, the output generated by the network in response to an input representing an instance in the training data set is compared to the "correct" labeled output for the instance; an error signal representing the difference between the output and the labeled output is calculated; and when the error signal is propagated back through the layers of the network, the weights associated with the connections are adjusted to minimize the error. The network is considered "trained" when the error for each output generated from an instance of the training data set is minimized.

[0196] The accuracy of a machine learning algorithm can be greatly affected by the quality of the data set used to train the algorithm. The training process can be computationally intensive and can take a significant amount of time on a conventional general purpose processor. Therefore, many types of machine learning algorithms are trained using parallel processing hardware. This is particularly useful for optimizing the training of neural networks, as the calculations performed when adjusting the coefficients in a neural network are naturally suited to parallel implementations. In particular, many machine learning algorithms and software applications have been adapted to use parallel processing hardware within general purpose graphics processing devices.

[0197] Fig.10 is a generalized diagram of a machine learning software stack 1000. Machine learning applications 1002 may be configured to train a neural network using a training data set or to use a trained deep neural network to implement machine intelligence. Machine learning applications 1002 may include training and inference capabilities for neural networks and / or specialized software that may be used to train neural networks prior to deployment. Machine learning applications 1002 may implement any type of machine intelligence, including but not limited to: image recognition, mapping and localization, autonomous navigation, speech synthesis, medical imaging, or language translation.

[0198] Hardware acceleration for machine learning applications 1002 can be implemented via a machine learning framework 1004. The machine learning framework 1004 can provide a library of machine learning primitives. Machine learning primitives are basic operations that machine learning algorithms typically perform. Without the machine learning framework 1004, developers of machine learning algorithms would be required to create and optimize the main computational logic associated with the machine learning algorithm, and then re-optimize the computational logic when a new parallel processor is developed. Instead, machine learning applications can be configured to use primitives provided by the machine learning framework 1004 to perform necessary calculations. Exemplary primitives include tensor convolutions, activation functions, and pooling, which are computational operations performed when training a convolutional neural network (CNN). The machine learning framework 1004 can also provide primitives for implementing basic linear algebra subroutines, such as matrix and vector operations, performed by many machine learning algorithms.

[0199] The machine learning framework 1004 can process the input data received from the machine learning application 1002 and generate appropriate inputs to the computing framework 1006. The computing framework 1006 can abstract the underlying instructions provided to the GPGPU driver 1008 so that the machine learning framework 1004 can take advantage of hardware acceleration via the GPGPU hardware 1010 without requiring the machine learning framework 1004 to be very familiar with the architecture of the GPGPU hardware 1010. In addition, the computing framework 1006 can implement hardware acceleration for the machine learning framework 1004 across multiple types and generations of GPGPU hardware 1010.

[0200] GPGPU machine learning acceleration

[0201] Fig.11 A highly parallel general purpose graphics processing unit 1100 is illustrated in accordance with an embodiment. In one embodiment, a general purpose processing unit (GPGPU) 1100 may be configured to be particularly efficient in processing the type of computational workload associated with training deep neural networks. Additionally, a GPGPU 1100 may be directly linked to other instances of a GPGPU for creating a multi-GPU cluster, thereby improving the training speed of particularly deep neural networks.

[0202] GPGPU 1100 includes a host interface 1102 for enabling connection to a host processor. In one embodiment, host interface 1102 is a PCI Express interface. However, the host interface may also be a vendor-specific communication interface or communication structure. GPGPU 1100 receives commands from the host processor and uses a global scheduler 1104 to distribute execution threads associated with those commands to a set of computing clusters 1106A to H. Computing clusters 1106A to H share a cache memory 1108. Cache memory 1108 may act as a higher-level cache in the cache memory within computing clusters 1106A to H.

[0203] GPGPU 1100 includes memory 1114A-B, which is coupled to computing clusters 1106A-H via a set of memory controllers 1112A-B. In various embodiments, memory 1114A-B may include various types of memory devices, including dynamic random access memory (DRAM) or graphics random access memory (such as synchronous graphics random access memory (SGRAM), including graphics double data rate (GDDR) memory). In one embodiment, memory units 224A-224N may also include 3D stacked memory, including but not limited to high bandwidth memory (HBM).

[0204] In one embodiment, each computing cluster GPLAB06A-H includes a set of graphics multiprocessors such as Figure 4A The graphics multiprocessor 400 of the computing cluster includes multiple types of integer and floating point logic units that can perform computational operations at a range of precisions, including precisions suitable for machine learning computations. For example and in one embodiment, at least a subset of the floating point units in each of the computing clusters 1106A to H can be configured to perform 16-bit or 32-bit floating point operations, while a different subset of the floating point units can be configured to perform 64-bit floating point operations.

[0205] Multiple instances of GPGPU 1100 can be configured to operate as a computing cluster. The communication mechanism used by the computing cluster for synchronization and data exchange varies across embodiments. In one embodiment, multiple instances of GPGPU 1100 communicate through a host interface 1102. In one embodiment, GPGPU 1100 includes an I / O hub 1108 that couples GPGPU 1100 with a GPU link 1110, which implements direct connection to other instances of GPGPU. In one embodiment, GPU link 1110 is coupled to a dedicated GPU-GPU bridge, which implements communication and synchronization between multiple instances of GPGPU 1100. In one embodiment, GPU link 1110 is coupled to a high-speed interconnect for transmitting and receiving data to other GPGPUs or parallel processors. In one embodiment, multiple instances of GPGPU 1100 are located in a separate data processing system and communicate via a network device, which can be accessed via host interface 1102. In one embodiment, in addition to or as an alternative to host interface 1102 , GPU link 1110 may be configured to enable connection to a host processor.

[0206] Although the illustrated configuration of the GPGPU 1100 can be configured to train a neural network, one embodiment provides an alternative configuration of the GPGPU 1100 that can be configured for deployment within a high-performance or low-power inference platform. In the inference configuration, the GPGPU 1100 includes fewer computing clusters 1106A to H relative to the training configuration. In addition, the memory technology associated with the memory 1114A to B can be different between the inference and training configurations. In one embodiment, the inference configuration of the GPGPU 1100 can support inference-specific instructions. For example, the inference configuration can provide support for one or more 8-bit integer dot product instructions, which are typically used during inference operations for deployed neural networks.

[0207] Fig.12 A multi-GPU computing system 1200 is illustrated according to an embodiment. The multi-GPU computing system 1200 may include a processor 1202 coupled to a plurality of GPGPUs 1206A to D via a host interface switch 1204. In one embodiment, the host interface switch 1204 is a PCI Express switch device that couples the processor 1202 to a PCI Express bus, through which the processor 1202 may communicate with the set of GPGPUs 1206A to D. Each of the plurality of GPGPUs 1206A to 1206D may be Fig.111100. GPGPUs 1206A to D may be interconnected via a set of high-speed point-to-point GPU-GPU links 1216. High-speed GPU-GPU links may be connected via dedicated GPU links (such as Fig.11 1206D. The P2P GPU link 1216 enables each of the GPGPUs 1206A to 1206D to communicate directly with each other without having to communicate through a host interface bus (to which the processor 1202 is connected). In the case where GPU-GPU traffic is directed to the P2P GPU link, the host interface bus can still be used for system memory access or communication with other instances of the multi-GPU computing system 1200 (e.g., via one or more network devices). Although in the illustrated embodiment, the GPGPUs 1206A to D are connected to the processor 1202 via the host interface switch 1204, in one embodiment, the processor 1202 includes direct support for the P2P GPU link 1216 and can be directly connected to the GPGPUs 1206A to D.

[0208] Machine Learning Neural Network Implementation

[0209] The computing architecture provided by the embodiments described herein can be configured to perform these types of parallel processing that are particularly suitable for training and deploying neural networks for machine learning. A neural network can be generalized as a network of functions with a graph relationship. As is well known in the art, there are many types of neural network implementations used in machine learning. One exemplary type of neural network is a feedforward network as previously described.

[0210] The second exemplary type of neural network is a convolutional neural network (CNN). CNN is a specialized feedforward neural network for processing data (such as image data) with a known, grid-like topology. Therefore, CNNs are commonly used for computational vision and image recognition applications, but they can also be used for other types of pattern recognition, such as speech and language processing. The nodes in the input layer of a CNN are organized as a set of "filters" (feature detectors inspired by the receptive fields found in the retina), and the output of each set of filters is propagated to the nodes in the successive layers of the network. The calculations for CNNs include applying a convolution mathematical operation to each filter to produce the output of the filter. Convolution is a specialized mathematical operation performed by two functions to produce a third function, which is a modified version of one of the two original functions. In convolutional network terminology, the first function about the convolution can be called the input, and the second function can be called the convolution kernel. The output can be called a feature map. For example, the input to the convolution layer can be a multidimensional data array that defines the various color components of the input image. The convolution kernel can be a multidimensional parameter array, where the parameters are adapted by a training process for the neural network.

[0211] A recurrent neural network (RNN) is a class of feedforward neural networks that include feedback connections between layers. RNNs enable modeling of sequence data by sharing parameter data across different parts of the neural network. The architecture of an RNN includes loops. These loops represent the effect of the current value of a variable on its own value at future times, as at least a portion of the output data from the RNN is used as feedback for processing subsequent inputs in the sequence. This feature makes RNNs particularly useful for language processing due to the mutable nature of the language data that can be composed.

[0212] The figures described below present exemplary feedforward, CNN, and RNN networks, and describe the general process for training and deploying each of those types of networks, respectively. It will be understood that these descriptions are exemplary and non-limiting with respect to any specific embodiment described herein, and that the illustrated concepts can generally be applied to deep neural networks and machine learning techniques in general.

[0213] The exemplary neural network described above can be used to perform deep learning. Deep learning is machine learning performed using deep neural networks. In contrast to shallow neural networks that include only a single hidden layer, the deep neural networks used in deep learning are artificial neural networks composed of multiple hidden layers. Deeper neural networks are generally more computationally intensive to train. However, the additional hidden layers of the network enable multi-step pattern recognition, which results in reduced output errors relative to shallow machine learning techniques.

[0214] The deep neural networks used in deep learning typically include a front-end network for performing feature recognition coupled to a back-end network representing a mathematical model that can perform operations (e.g., object classification, speech recognition, etc.) based on the feature representations provided to the model. Deep learning enables machine learning to be performed without having to perform manual feature engineering for the model. Instead, deep neural networks can learn features based on statistical structures or correlations within the input data. The learned features can be provided to a mathematical model that can map the detected features to an output. The mathematical model used by the network is typically dedicated to the specific task to be performed, and different models will be used to perform different tasks.

[0215] Once a neural network is structured, a learning model can be applied to the network to train the network to perform a specific task. The learning model describes how to adjust the weights within the model to reduce the output error of the network. Backpropagation of errors is a common method for training neural networks. An input vector is presented to the network for processing. The output of the network is compared to the desired output using a loss function, and an error value is calculated for each neuron in the output layer. These error values ​​are then propagated backward until each neuron has an associated error value that roughly represents its contribution to the original output. The network can then learn from those errors using an algorithm (such as a stochastic gradient descent algorithm) to update the weights of the neural network.

[0216] Figures 13A to 13B An exemplary convolutional neural network is illustrated. Fig.13A The diagram shows the various layers within a CNN. Fig.13A As shown in , an exemplary CNN for modeling image processing can receive an input 1302 that describes the red, green, and blue (RGB) components of an input image. The input 1302 can be processed by multiple convolutional layers (e.g., convolutional layer 1304, convolutional layer 1306). Optionally, the outputs from the multiple convolutional layers can be processed by a set of fully connected layers 1308. The neurons in the fully connected layer have full connections to all activations in the previous layer, as previously described for the feedforward network. The output from the fully connected layer 1308 can be used to generate output results from the network. Matrix multiplication can be used instead of convolution to calculate the activations within the fully connected layer 1308. Not all CNN implementations use the fully connected layer 1308. For example, in some implementations, the convolutional layer 1306 can generate the output of the CNN.

[0217] The convolutional layers are sparsely connected, which is different from the traditional neural network configuration found in the fully connected layer 1308. Traditional neural network layers are fully connected so that each output unit interacts with each input unit. However, the convolutional layers are sparsely connected because the output of the convolution of the receptive field (rather than the corresponding state value of each node in the receptive field) is input to the nodes of the subsequent layer, as shown. The kernel associated with the convolutional layer performs a convolution operation, the output of which is sent to the next layer. The dimensionality reduction performed within the convolutional layer is one aspect that enables CNNs to scale to process large images.

[0218] Fig. 13B Illustrated are exemplary computational stages within a convolutional layer of a CNN. An input 1312 to a convolutional layer of a CNN may be processed in three stages of a convolutional layer 1314. The three stages may include a convolution stage 1316, a detector stage 1318, and a pooling stage 1320. The convolutional layer 1314 may then output data to a successive convolutional layer. The last convolutional layer of the network may generate output feature map data or provide input to a fully connected layer, for example to generate a classification value for input to the CNN.

[0219] Several convolutions are performed in parallel in the convolution stage 1316 to produce a set of linear activations. The convolution stage 1316 may include an affine transformation, which is any transformation that can be specified as a linear transformation plus a translation. Affine transformations include rotations, translations, scaling, and combinations of these transformations. The convolution stage calculates the output of a function (e.g., a neuron) connected to a specific region in the input, which can be determined as a local region associated with the neuron. The neuron calculates the dot product between the weight of the neuron and the region in the local input (to which the neuron is connected). The output from the convolution stage 1316 defines a set of linear activations processed by successive stages of the convolution layer 1314.

[0220] The linear activations may be processed by the detector stage 1318. In the detector stage 1318, each linear activation is processed by a non-linear activation function. The non-linear activation function increases the non-linear nature of the overall network without affecting the receptive field of the convolutional layer. Several types of non-linear activation functions may be used. One specific type is the rectified linear unit (ReLU), which uses an activation function defined as f(x)=max(0,x) so that the activation is thresholded at zero.

[0221] The pooling stage 1320 uses a pooling function that replaces the output of the convolutional layer 1306 with a summary statistic of nearby outputs. The pooling function can be used to introduce translation invariance into the neural network so that a slight translation to the input does not change the pooled output. The invariance of local translation can be useful in scenarios where the presence of features in the input data is more important than the precise location of the features. Various types of pooling functions can be used during the pooling stage 1320, including maximum pooling, average pooling, and L2 norm pooling. In addition, some CNN implementations do not include a pooling stage. Instead, such an implementation substitutes an additional convolution stage, which has an increased stride relative to the previous convolution stage.

[0222] The output from the convolutional layer 1314 may then be processed by the next layer 1322. The next layer 1322 may be an additional convolutional layer or one of the fully connected layers 1308. For example, Fig.13A The first convolutional layer 1304 can output to the second convolutional layer 1306, and the second convolutional layer can output to the first layer in the fully connected layer 1308.

[0223] Fig.14 An exemplary recurrent neural network 1400 is illustrated. In a recurrent neural network (RNN), the previous state of the network affects the output of the current state of the network. RNNs can be constructed in a variety of ways using a variety of functions. The use of RNNs generally revolves around the use of mathematical models to predict the future based on previous input sequences. For example, RNNs can be used to perform statistical language modeling to predict upcoming words given a previous word sequence. The illustrated RNN 1400 can be described as having the following: an input layer 1402, which receives an input vector; a hidden layer 1404, for implementing a recursive function; a feedback mechanism 1405, for implementing a 'memory' of previous states; and an output layer 1406, for outputting a result. RNN 1400 operates based on time steps. The state of the RNN at a given time step is affected based on the previous time step via the feedback mechanism 1405. For a given time step, the state of the hidden layer 1404 is defined by the previous state and the input at the current time step. The initial input (x1) at the first time step can be processed by the hidden layer 1404. The second input (x2) can be processed by the hidden layer 1404 using the state information determined during the processing of the initial input (x1). The given state can be calculated as s t =f(Ux t + Ws t-1), where U and W are parameter matrices. Function f is typically nonlinear, such as a variant of the hyperbolic tangent function (Tanh) or a modified function f(x)=max(0,x). However, the specific mathematical function used in hidden layer 1404 may vary depending on the specific implementation details of RNN 1400.

[0224] In addition to the basic CNN and RNN networks described, variations of those networks can also be implemented. An example RNN variant is the Long Short Term Memory (LSTM) RNN. LSTM RNNs are able to learn long-term dependencies that may be necessary for processing longer language sequences. A variant of CNN is a convolutional deep belief network, which has a structure similar to a CNN and is trained in a manner similar to a deep belief network. A deep belief network (DBN) is a generative neural network consisting of multiple layers of stochastic (random) variables. A DBN can be trained layer by layer using greedy unsupervised learning. The learned weights of the DBN can then be used to provide a pre-trained neural network by determining a set of optimal initial weights for the neural network.

[0225] Fig.15 The training and deployment of a deep neural network is illustrated. Once a given network has been structured for a task, the neural network is trained using a training data set 1502. Various training frameworks 1504 have been developed to enable hardware acceleration of the training process. For example, Fig.10 The machine learning framework 1004 can be configured as a training framework 1504. The training framework 1504 can be hooked up to the untrained neural network 1506 and enable the untrained neural network to be trained to generate a trained neural network 1508 using the parallel processing resources described herein.

[0226] To start the training process, initial weights can be chosen randomly or by pre-training with a deep belief network. The training cycle can then be performed in a supervised or unsupervised manner.

[0227] Supervised learning is a learning method in which training is performed as an arbitration operation, such as when the training data set 1502 includes inputs (which are paired with the expected outputs of the inputs), or when the training data set includes inputs with known outputs and the outputs of the neural network are manually graded. The network processes the inputs and compares the resulting outputs with a set of expected or desired outputs. Then, the error is back-propagated through the system. The training framework 1504 can be adjusted to adjust the weights of the untrained neural network 1506. The training framework 1504 can provide tools for monitoring the extent to which the untrained neural network 1506 converges to a model suitable for generating the correct answer based on the known input data. The training process occurs repeatedly when the weights of the network are adjusted to improve the output generated by the neural network. The training process can continue until the neural network reaches a statistically expected accuracy associated with the trained neural network 1508. Then, the trained neural network 1508 can be deployed to implement any number of machine learning operations.

[0228] Unsupervised learning is a learning method in which a network attempts to train itself using unlabeled data. Thus, for unsupervised learning, the training data set 1502 will include input data without any associated output data. The untrained neural network 1506 can learn groupings within the unlabeled inputs and can determine how individual inputs relate to the overall data set. Unsupervised training can be used to generate a self-organizing map, which is a type of trained neural network 1507 that can perform operations useful in data dimensionality reduction. Unsupervised training can also be used to perform anomaly detection, which allows identification of data points in the input data set that deviate from the normal pattern of the data.

[0229] Variations of supervised and unsupervised training may also be employed. Semi-supervised learning is a technique in which the training data set 1502 includes a mixture of labeled and unlabeled data of the same distribution. Incremental learning is a variation of supervised learning in which input data is continually used for further training the model. Incremental learning enables a trained neural network 1508 to adapt to new data 1512 without forgetting the knowledge embedded within the network during initial training.

[0230] Whether supervised or unsupervised, the training process for particularly deep neural networks may be too computationally intensive for a single computing node. The training process can be accelerated using a distributed network of computing nodes rather than a single computing node.

[0231] Fig.16is a block diagram illustrating distributed learning. Distributed learning is a training model that uses multiple distributed computing nodes to perform supervised or unsupervised training of a neural network. The distributed computing nodes may each include one or more host processors and one or more general processing nodes, such as Fig.11 A highly parallel general purpose graphics processing unit 1100 in FIG. As illustrated, distributed learning can perform model parallelism 1602 , data parallelism 1604 , or a combination of model and data parallelism 1604 .

[0232] In model parallelization 1602, different computing nodes in a distributed system can perform training calculations for different parts of a single network. For example, each layer of a neural network can be trained by a different processing node of the distributed system. The benefits of model parallelism include the ability to scale to particularly large models. Splitting the calculations associated with different layers of a neural network enables training of very large neural networks, where the weights of all layers will not fit into the memory of a single computing node. In some instances, model parallelism can be particularly useful in performing unsupervised training of large neural networks.

[0233] In data parallelization 1604, different nodes of the distributed network have complete instances of the model, and each node receives a different portion of the data. Then, the results from different nodes are combined. Although different methods for data parallelization are possible, data parallel training methods all require a technique for combining results and synchronizing model parameters between each node. Exemplary methods for combining data include parameter averaging and update-based data parallelization. Parameter averaging trains each node on a subset of the training data and sets global parameters (e.g., weights, biases) to the average value of the parameters from each node. Parameter averaging uses a central parameter server that maintains parameter data. Update-based data parallelism is similar to parameter averaging, except that updates to the model are passed instead of passing parameters from the node to the parameter server. In addition, update-based data parallelism can be performed in a decentralized manner, where updates are compressed and passed between nodes.

[0234] For example, the combined model and data parallelism 1606 can be implemented in a distributed system where each computing node includes multiple GPUs. Each node can have a complete instance of the model, with separate GPUs within each node used to train different parts of the model.

[0235] Distributed training has increased overhead relative to training on a single machine. However, the parallel processors and GPGPUs described herein can each implement various techniques for reducing the overhead of distributed training, including techniques for implementing high-bandwidth GPU-GPU data transfer and accelerated remote data synchronization.

[0236] Example Machine Learning Applications

[0237] Machine learning can be applied to solve a variety of technical problems, including but not limited to computer vision, autonomous driving and navigation, speech recognition, and language processing. Computer vision has traditionally been one of the most active research areas for machine learning applications. Applications of computer vision range from reproducing human visual capabilities (such as recognizing faces) to creating new categories of visual capabilities. For example, a computer vision application can be configured to recognize sound waves from vibrations induced in objects visible in a video. Parallel processor-accelerated machine learning enables the use of significantly larger training data sets than previously feasible training data sets to train computer vision applications, and enables the use of low-power parallel processors to deploy inference systems.

[0238] Parallel processor-accelerated machine learning has autonomous driving applications, including lane and road sign recognition, obstacle avoidance, navigation, and driving control. Accelerated machine learning techniques can be used to train driving models based on data sets that define appropriate responses to specific training inputs. The parallel processors described herein can enable rapid training of increasingly complex neural networks for autonomous driving solutions and enable the deployment of low-power inference processors in mobile platforms suitable for integration into autonomous vehicles.

[0239] Deep neural networks accelerated by parallel processors have enabled machine learning methods for automatic speech recognition (ASR). ASR involves creating a function that computes the most likely speech sequence given a sequence of input sounds. Accelerated machine learning using deep neural networks has been implemented to replace the hidden Markov models (HMMs) and Gaussian mixture models (GMMs) previously used for ASR.

[0240] Parallel processor accelerated machine learning can also be used to accelerate natural language processing. Automatic learning programs can use statistical inference algorithms to produce models that are robust to erroneous or unfamiliar inputs. Exemplary natural language processor applications include automatic machine translation between human languages.

[0241] Parallel processing platforms for machine learning can be divided into training platforms and deployment platforms. Training platforms are typically highly parallel and include optimizations for accelerating multi-GPU single-node training and multi-node multi-GPU training. Exemplary parallel processors suitable for training include Fig.11The highly parallel general purpose graphics processing unit 1100 and Fig.12 The multi-GPU computing system 1200 of FIG. In contrast, deployed machine learning platforms typically include lower-power parallel processors suitable for use in products such as cameras, autonomous robots, and autonomous vehicles.

[0242] Fig.17 An exemplary inference system-on-chip (SOC) 1700 suitable for performing inference using a training model is illustrated. The SOC 1700 may integrate processing components, including a media processor 1702, a vision processor 1704, a GPGPU 1706, and a multi-core processor 1708. The SOC 1700 may additionally include an on-chip memory 1705, which may implement a shared on-chip data pool accessible by each of the processing components. The processing components may be optimized for low-power operation to enable deployment to a variety of machine learning platforms, including autonomous vehicles and autonomous robots. For example, an implementation of the SOC 1700 may be used as part of a master control system for an autonomous vehicle. In the case where the SOC 1700 is configured for use in an autonomous vehicle, the SOC is designed and configured to comply with relevant functional safety standards of the deployment jurisdiction.

[0243] During operation, the media processor 1702 and the visual processor 1704 can work in concert to accelerate computer vision operations. The media processor 1702 can enable low latency decoding of multiple high-resolution (e.g., 4K, 8K) video streams. The decoded video streams can be written to a buffer in the on-chip memory 1705. The visual processor 1704 can then parse the decoded video and perform preliminary processing operations on the frames of the decoded video in preparation for processing the frames using a trained image recognition model. For example, the visual processor 1704 can accelerate convolution operations for CNNs (for performing image recognition on high-resolution video data), while the back-end model calculations are performed by the GPGPU 1706.

[0244] The multi-core processor 1708 may include control logic for facilitating the sequencing and synchronization of data transfers and shared memory operations performed by the media processor 1702 and the visual processor 2504. The multi-core processor 1708 may also act as an application processor for executing software applications that may use the inference computing capabilities of the GPGPU 1706. For example, at least a portion of the navigation and driving logic may be implemented in software executed on the multi-core processor 1708. Such software may directly issue computational workloads to the GPGPU 1706, or may issue computational workloads to the multi-core processor 1708, which may offload at least a portion of those operations to the GPGPU 1706.

[0245] GPGPU 1706 may include a computing cluster, such as a low-power configuration of computing clusters 1106A to 1106H within a highly parallel general-purpose graphics processing unit 1100. The computing cluster within GPGPU 1706 may support instructions that are specifically optimized for performing inference calculations on trained neural networks. For example, GPGPU 1706 may support instructions for performing low-precision calculations (such as 8-bit and 4-bit integer vector operations).

[0246] System Overview II

[0247] Fig.18 1800 is a block diagram of a processing system 1800 according to an embodiment. In various embodiments, the system 1800 includes one or more processors 1802 and one or more graphics processors 1808, and may be a single-processor desktop system, a multi-processor workstation system, or a server system with a large number of processors 1802 or processor cores 1807. In one embodiment, the system 1800 is a processing platform incorporated into a system-on-chip (SoC) integrated circuit for use in a mobile device, a handheld device, or an embedded device.

[0248] Embodiments of the system 1800 may include or be incorporated into the following: a server-based gaming platform; a gaming console, including a gaming and media console, a mobile gaming console, a handheld gaming console, or an online gaming console. In some embodiments, the system 1800 is a mobile phone, a smart phone, a tablet computing device, or a mobile Internet device. The data processing system 1800 may also include a wearable device (such as a smart watch wearable device, a smart glasses device, an augmented reality device, or a virtual reality device), coupled to the wearable device, or integrated into the wearable device. In some embodiments, the data processing system 1800 is a television or set-top box device having one or more processors 1802 and a graphical interface generated by one or more graphics processors 1808.

[0249] In some embodiments, one or more processors 1802 each include one or more processor cores 1807 for processing instructions, which when executed perform operations of the system and user software. In some embodiments, each processor core in the one or more processor cores 1807 is configured to process a specific instruction set 1809. In some embodiments, the instruction set 1809 can facilitate complex instruction set computing (CISC), reduced instruction set computing (RISC), or computing via very long instruction words (VLIW). Multiple processor cores 1807 can each process different instruction sets 1809, which may include instructions for facilitating emulation of other instruction sets. The processor core 1807 may also include other processing devices, such as a digital signal processor (DSP).

[0250] In some embodiments, the processor 1802 includes a cache memory 1804. Depending on the architecture, the processor 1802 may have a single internal cache or multiple levels of internal cache. In some embodiments, the cache memory is shared among various components of the processor 1802. In some embodiments, the processor 1802 also uses an external cache (e.g., a level 3 (L3) cache or a last level cache (LLC)) (not shown), which may be shared among the processor cores 1807 using known cache coherence techniques. In addition, a register file 1806 is included in the processor 1802, which may include different types of registers (e.g., integer registers, floating point registers, status registers, and instruction pointer registers) for storing different types of data. Some registers may be general purpose registers, while other registers may be specific to the design of the processor 1802.

[0251] In some embodiments, the processor 1802 is coupled to a processor bus 1810, which is used to transmit communication signals, such as address, data, or control signals, between the processor 1802 and other components in the system 1800. In one embodiment, the system 1800 uses an exemplary 'hub' system architecture, including a memory controller hub 1816 and an input-output (I / O) controller hub 1830. The memory controller hub 1816 facilitates communication between memory devices and other components of the system 1800, while the I / O controller hub (ICH) 1830 provides connections to I / O devices via a local I / O bus. In one embodiment, the logic of the memory controller hub 1816 is integrated within the processor.

[0252] The memory device 1820 may be a dynamic random access memory (DRAM) device, a static random access memory (SRAM) device, a flash memory device, a phase change memory device, or some other memory device having suitable properties to function as processing memory. In one embodiment, the memory device 1820 may operate as system memory for the system 1800 to store data 1822 and instructions 1821 for use when one or more processors 1802 execute applications or processes. The memory controller hub 1816 is also coupled to an optional external graphics processor 1812, which may communicate with one or more graphics processors 1808 in the processor 1802 to perform graphics and media operations.

[0253] In some embodiments, the ICH 1830 enables peripherals to be connected to the memory device 1820 and the processor 1802 via a high-speed I / O bus. The I / O peripherals include, but are not limited to, an audio controller 1846, a firmware interface 1828, a wireless transceiver 1826 (e.g., Wi-Fi, Bluetooth), a data storage device 1824 (e.g., a hard drive, flash memory, etc.), and a traditional I / O controller 1840 for coupling traditional (e.g., Personal System 2 (PS / 2)) devices to the system. One or more Universal Serial Bus (USB) controllers 1842 connect input devices, such as a keyboard and mouse 1844 combination. A network controller 1834 may also be coupled to the ICH 1830. In some embodiments, a high-performance network controller (not shown) is coupled to the processor bus 1810. It should be understood that the system 1800 shown is exemplary and not limiting, as other types of data processing systems configured in different ways may also be used. For example, I / O controller hub 1830 may be integrated within one or more processors 1802 , or memory controller hub 1816 and I / O controller hub 1830 may be integrated into a discrete external graphics processor, such as external graphics processor 1812 .

[0254] Fig.19 is a block diagram of an embodiment of a processor 1900 having one or more processor cores 1902A- 1902N, an integrated memory controller 1914 , and an integrated graphics processor 1908 . Fig.19Those elements having the same reference numerals (or names) as elements of any other figure herein may operate or function in any manner similar to, but not limited to, those described elsewhere herein. Processor 1900 may include additional cores up to and including additional core 1902N represented by a dashed box. Each of processor cores 1902A to 1902N includes one or more internal cache units 1904A to 1904N. In some embodiments, each processor core may also access one or more shared cache units 1906.

[0255] Internal cache units 1904A to 1904N and shared cache unit 1906 represent a cache memory hierarchy within processor 1900. The cache memory hierarchy may include at least one level of instruction and data cache within each processor core and one or more levels of shared mid-level cache, such as level 2 (L2), level 3 (L3), level 4 (L4), or other levels of cache, where the highest level of cache before external memory is classified as LLC. In some embodiments, cache coherence logic maintains coherence between the various cache units 1906 and 1904A to 1904N.

[0256] In some embodiments, the processor 1900 may also include a set of one or more bus controller units 1916 and a system agent core 1910. The one or more bus controller units 1916 manage a set of peripheral buses, such as one or more peripheral component interconnect buses (e.g., PCI, PCI Express). The system agent core 1910 provides management functions for various processor components. In some embodiments, the system agent core 1910 includes one or more integrated memory controllers 1914 to manage access to various external memory devices (not shown).

[0257] In some embodiments, one or more of the processor cores 1902A to 1902N include support for simultaneous multithreading. In such embodiments, the system agent core 1910 includes components for coordinating and operating the cores 1902A to 1902N during multithreaded processing. In addition, the system agent core 1910 may also include a power control unit (PCU) that includes logic and components for regulating the power state of the processor cores 1902A to 1902N and the graphics processor 1908.

[0258] In some embodiments, in addition, the processor 1900 further includes a graphics processor 1908 for performing graphics processing operations. In some embodiments, the graphics processor 1908 is coupled to a set of shared cache units 1906 and a system agent core 1910, which includes one or more integrated memory controllers 1914. In some embodiments, a display controller 1911 is coupled to the graphics processor 1908 to drive the graphics processor output to one or more coupled displays. In some embodiments, the display controller 1911 can be a separate module coupled to the graphics processor via at least one interconnect, or can be integrated within the graphics processor 1908 or the system agent core 1910.

[0259] In some embodiments, a ring-based interconnect unit 1912 is used to couple the internal components of the processor 1900. However, alternative interconnect units may be used, such as point-to-point interconnects, switched interconnects, or other technologies, including those well known in the art. In some embodiments, the graphics processor 1908 is coupled to the ring interconnect 1912 via an I / O link 1913.

[0260] Exemplary I / O links 1913 represent at least one of a plurality of varieties of I / O interconnects, including package I / O interconnects that facilitate communication between various processor components and high-performance embedded memory modules 1918, such as eDRAM modules. In some embodiments, each of processor cores 1902A through 1902N and graphics processor 1908 use embedded memory modules 1918 as a shared last-level cache.

[0261] In some embodiments, processor cores 1902A to 1902N are homogeneous cores that execute the same instruction set architecture. In another embodiment, processor cores 1902A to 1902N are heterogeneous in terms of instruction set architecture (ISA), wherein one or more of processor cores 1902A to N execute a first instruction set, while at least one of the other cores executes a subset of the first instruction set or a different instruction set. In one embodiment, processor cores 1902A to 1902N are heterogeneous in terms of microarchitecture, wherein one or more cores with relatively high power consumption are coupled with one or more power cores with lower power consumption. In addition, processor 1900 may be implemented on one or more chips or as a SoC integrated circuit having the illustrated components in addition to other components.

[0262] Fig. 202000 is a block diagram of a graphics processor 2000, which may be a discrete graphics processing unit or may be a graphics processor integrated with multiple processing cores. In some embodiments, the graphics processor communicates via a memory mapped I / O interface to registers on the graphics processor and using commands placed in the processor memory. In some embodiments, the graphics processor 2000 includes a memory interface 2014 for accessing memory. The memory interface 2014 may be an interface to local memory, one or more internal caches, one or more shared external caches, and / or to system memory.

[0263] In some embodiments, the graphics processor 2000 also includes a display controller 2002 for driving display output data to a display device 2020. The display controller 2002 includes hardware for one or more overlapping planes of the display and a composition of multiple layers of video or user interface elements. In some embodiments, the graphics processor 2000 includes a video codec engine 2006 for encoding media to one or more media encoding formats, decoding media from one or more media encoding formats, or transcoding media between one or more media encoding formats, including but not limited to: Moving Picture Experts Group (MPEG) formats (such as MPEG-2), Advanced Video Coding (AVC) formats (such as H.264 / MPEG-4 AVC), and Society of Motion Picture and Television Engineers (SMPTE) 421M / VC-1, and Joint Photographic Experts Group (JPEG) formats (such as JPEG), and Motion JPEG (MJPEG) formats.

[0264] In some embodiments, graphics processor 2000 includes a block image transfer (BLIT) engine 2004 for performing two-dimensional (2D) rasterizer operations, including, for example, bit boundary block transfers. However, in one embodiment, 2D graphics operations are performed using one or more components of a graphics processing engine (GPE) 2010. In some embodiments, graphics processing engine 2010 is a compute engine for performing graphics operations, including three-dimensional (3D) graphics operations and media operations.

[0265] In some embodiments, GPE 2010 includes a 3D pipeline 2012 for performing 3D operations, such as rendering three-dimensional images and scenes using processing functions that act on 3D primitive shapes (e.g., rectangles, triangles, etc.). 3D pipeline 2012 includes programmable and fixed functional elements that perform various tasks within the element and / or generate execution threads to 3D / media subsystem 2015. Although 3D pipeline 2012 can be used to perform media operations, embodiments of GPE 2010 also include a media pipeline 2016 that is specifically used to perform media operations, such as video post-processing and image enhancement.

[0266] In some embodiments, the media pipeline 2016 includes fixed-function or programmable logic units to perform one or more specialized media operations, such as video decoding acceleration, video deinterlacing, and video encoding acceleration, instead of or on behalf of the video codec engine 2006. In some embodiments, in addition, the media pipeline 2016 also includes a thread generation unit to generate threads for execution on the 3D / media subsystem 2015. The generated threads perform calculations for media operations on one or more graphics execution units included in the 3D / media subsystem 2015.

[0267] In some embodiments, the 3D / media subsystem 2015 includes logic for executing threads generated by the 3D pipeline 2012 and the media pipeline 2016. In one embodiment, the pipeline sends a thread execution request to the 3D / media subsystem 2015, which includes thread dispatching logic for arbitrating various requests and dispatching various requests to available thread execution resources. The execution resources include an array of graphics execution units for processing 3D and media threads. In some embodiments, the 3D / media subsystem 2015 includes one or more internal caches for thread instructions and data. In some embodiments, the subsystem also includes shared memory (including registers and addressable memory) to share data between threads and store output data.

[0268] 3D / Media Processing

[0269] Fig.21 is a block diagram of a graphics processing engine 2110 of a graphics processor according to some embodiments. In one embodiment, the graphics processing engine (GPE) 2110 is Fig. 20 The version of GPE 2010 shown in the figure. Fig.21 Elements having the same reference numeral (or name) as elements of any other figure herein may operate or function in any manner similar to that described elsewhere herein, but are not limited to these. Fig. 202012 and media pipeline 2016. The media pipeline 2016 is optional in some embodiments of the GPE 2110 and may not be explicitly included in the GPE 2110. For example and in at least one embodiment, separate media and / or image processors are coupled to the GPE 2110.

[0270] In some embodiments, the GPE 2110 is coupled to or includes a command stream transmitter 2103, which provides a command stream to the 3D pipeline 2012 and / or the media pipeline 2016. In some embodiments, the command stream transmitter 2103 is coupled to a memory, which may be a system memory, or one or more cache memories of an internal cache memory and a shared cache memory. In some embodiments, the command stream transmitter 2103 receives commands from the memory and sends these commands to the 3D pipeline 2012 and / or the media pipeline 2016. The commands are instructions obtained from a ring buffer storing commands for the 3D pipeline 2012 and the media pipeline 2016. In one embodiment, in addition, the ring buffer may also include a batch command buffer storing multiple batches of multiple commands. Commands for the 3D pipeline 2012 may also include references to data stored in memory, such as, but not limited to, vertex and geometry data for the 3D pipeline 2012 and / or image data and memory objects for the media pipeline 2016. The 3D pipeline 2012 and the media pipeline 2016 process the commands and data by performing operations via logic within the respective pipelines or by dispatching one or more execution threads to the graphics core array 2114.

[0271] In various embodiments, the 3D pipeline 2012 can execute one or more shader programs, such as vertex shaders, geometry shaders, pixel shaders, fragment shaders, compute shaders, or other shader programs, by processing instructions and dispatching execution threads to the graphics core array 2114. The graphics core array 2114 provides a unified execution resource block. The multi-purpose execution logic (e.g., execution unit) within the graphics core array 2114 includes support for various 3D API shader languages ​​and can execute multiple simultaneous execution threads associated with multiple shaders.

[0272] In some embodiments, graphics core array 2114 also includes execution logic for performing media functions such as video and / or image processing. In one embodiment, the execution unit also includes general logic that can be programmed to perform parallel general computing operations in addition to graphics processing operations. The general logic can be connected to Fig.18 (one or more) processor cores 1807 or such Fig.19The general logic within cores 1902A to 1902N performs processing operations in parallel or in combination.

[0273] Output data generated by threads executing on the graphics core array 2114 can output data to memory in a unified return buffer (URB) 2118. URB 2118 can store data for multiple threads. In some embodiments, URB 2118 can be used to send data between different threads executing on the graphics core array 2114. In some embodiments, URB 2118 can also be used for synchronization between threads on the graphics core array and fixed function logic within the shared function logic 2120.

[0274] In some embodiments, graphics core array 2114 is scalable such that the array includes a variable number of graphics cores each having a variable number of execution units based on the target power and performance level of GPE 2110. In one embodiment, execution resources are dynamically scalable such that execution resources can be enabled or disabled as needed.

[0275] The graphics core array 2114 is coupled to a shared function logic 2120, which includes a plurality of resources shared between the graphics cores in the graphics core array. The shared functions within the shared function logic 2120 are hardware logic units that provide dedicated supplementary functions to the graphics core array 2114. In various embodiments, the shared function logic 2120 includes, but is not limited to, a sampler 2121, math 2122, and inter-thread communication (ITC) 2123 logic. In addition, some embodiments implement one or more caches 2125 within the shared function logic 2120. The shared functions are implemented in the case where the demand for a given dedicated function is insufficient to be included within the graphics core array 2114. Instead, a single instantiation of the dedicated function is implemented as an independent entity in the shared function logic 2120 and shared between execution resources within the graphics core array 2114. The exact set of functions shared between the graphics core array 2114 and included within the graphics core array 2114 varies between embodiments.

[0276] Fig. 22 is a block diagram of another embodiment of a graphics processor 2200 . Fig. 22 Elements having the same reference number (or name) as elements of any other figure herein may operate or function in any manner similar to that described elsewhere herein, but are not limited to these.

[0277] In some embodiments, graphics processor 2200 includes ring interconnect 2202, pipeline front end 2204, media engine 2237, and graphics cores 2280A to 2280N. In some embodiments, ring interconnect 2202 couples the graphics processor to other processing units, including other graphics processors or one or more general-purpose processor cores. In some embodiments, the graphics processor is one of many processors integrated into a multi-core processing system.

[0278] In some embodiments, the graphics processor 2200 receives batches of commands via a ring interconnect 2202. Incoming commands are interpreted by a command streamer 2203 in a pipeline front end 2204. In some embodiments, the graphics processor 2200 includes scalable execution logic for performing 3D geometry processing and media processing via (one or more) graphics cores 2280A to 2280N. For 3D geometry processing commands, the command streamer 2203 supplies the commands to a geometry pipeline 2236. For at least some media processing commands, the command streamer 2203 supplies the commands to a video front end 2234, which is coupled to a media engine 2237. In some embodiments, the media engine 2237 includes a video quality engine (VQE) 2230 for video and image post-processing and a multi-format encoding / decoding (MFX) 2233 engine for providing hardware accelerated media data encoding and decoding. In some embodiments, the geometry pipeline 2236 and the media engine 2237 each generate an execution thread, which is used for thread execution resources provided by at least one graphics core 2280A.

[0279] In some embodiments, the graphics processor 2200 includes scalable thread execution resource characterization modular cores 2280A to 2280N (sometimes referred to as core slices), each of which has multiple sub-cores 2250A to 2250N, 2260A to 2260N (sometimes referred to as core sub-slices). In some embodiments, the graphics processor 2200 can have any number of graphics cores 2280A to 2280N. In some embodiments, the graphics processor 2200 includes a graphics core 2280A, and the graphics core 2280A has at least a first sub-core 2250A and a second sub-core 2260A. In other embodiments, the graphics processor is a low-power processor with a single sub-core (e.g., 2250A). In some embodiments, the graphics processor 2200 includes multiple graphics cores 2280A to 2280N, each of which includes a group of first sub-cores 2250A to 2250N and a group of second sub-cores 2260A to 2260N. Each of the group of first sub-cores 2250A to 2250N includes at least a first group of execution units 2252A to 2252N and media / texture samplers 2254A to 2254N. Each of the group of second sub-cores 2260A to 2260N includes at least a second group of execution units 2262A to 2262N and samplers 2264A to 2264N. In some embodiments, each sub-core 2250A to 2250N, 2260A to 2260N shares a group of shared resources 2270A to 2270N. In some embodiments, the shared resources include shared cache memory and pixel operation logic. Other shared resources may also be included in various embodiments of the graphics processor.

[0280] Execution Logic

[0281] Fig.23 Illustrated is thread execution logic 2300 that includes an array of processing elements employed in some embodiments of a GPE. Fig.23 Elements having the same reference number (or name) as elements of any other figure herein may operate or function in any manner similar to that described elsewhere herein, but are not limited to these.

[0282] In some embodiments, the thread execution logic 2300 includes a pixel shader 2302, a thread dispatcher 2304, an instruction cache 2306, a scalable execution unit array including a plurality of execution units 2308A to 2308N, a sampler 2310, a data cache 2312, and a data port 2314. In one embodiment, the included components are interconnected via an interconnect structure that links to each of the components. In some embodiments, the thread execution logic 2300 includes one or more connections to a memory (such as a system memory or a cache memory) through the instruction cache 2306, the data port 2314, the sampler 2310, and one or more of the execution unit arrays 2308A to 2308N. In some embodiments, each execution unit (e.g., 2308A) is a separate vector processor capable of executing multiple simultaneous threads and processing multiple data elements in parallel for each thread. In some embodiments, the execution unit arrays 2308A to 2308N include any number of separate execution units.

[0283] In some embodiments, execution unit arrays 2308A to 2308N are primarily used to execute "shader" programs. In some embodiments, the execution units in arrays 2308A to 2308N execute instruction sets (the instruction set includes native support for many standard 3D graphics shader instructions) so that shader programs from graphics libraries (e.g., Direct 3D and OpenGL) are executed with minimal conversion. These execution units support vertex and geometry processing (e.g., vertex programs, geometry programs, vertex shaders), pixel processing (e.g., pixel shaders, fragment shaders), and general processing (e.g., compute and media shaders).

[0284] Each execution unit in the execution unit array 2308A to 2308N operates on an array of data elements. The number of data elements is the "execution size", or number of lanes of the instruction. An execution lane is a logical unit for the execution of data element access, masking, and flow control within an instruction. The number of lanes may be independent of the number of physical arithmetic logic units (ALUs) or floating point units (FPUs) for a particular graphics processor. In some embodiments, execution units 2308A to 2308N support integer and floating point data types.

[0285] The execution unit instruction set includes single instruction multiple data (SIMD) or single instruction multiple thread (SIMT) instructions. Various data elements can be stored in registers as compressed data types, and the execution unit will process various elements based on the data size of the element. For example, when operating on a 256-bit wide vector, 256 bits of the vector are stored in registers, and the execution unit operates on the vector as four separated 64-bit compressed data elements (quadruple word (QW) size data elements), eight separated 32-bit compressed data elements (double word (DW) size data elements), sixteen separated 16-bit compressed data elements (word (W) size data elements), or thirty-two separated 8-bit data elements (byte (B) size data elements). However, different vector widths and register sizes are possible.

[0286] One or more internal instruction caches (e.g., 2306) are included in the thread execution logic 2300 to cache thread instructions for the execution unit. In some embodiments, one or more data caches (e.g., 2312) are included to cache thread data during thread execution. In some embodiments, a sampler 2310 is included to provide texture sampling for 3D operations and media sampling for media operations. In some embodiments, the sampler 2310 includes a specialized texture or media sampling function to process texture or media data during the sampling process before providing the sampled data to the execution unit.

[0287] During execution, the graphics and media pipelines send thread initiation requests to the thread execution logic 2300 via the thread generation and dispatch logic. In some embodiments, the thread execution logic 2300 includes a local thread dispatcher 2304 that arbitrates thread initiation requests from the graphics and media pipelines and instantiates the requested threads on one or more execution units 2308A to 2308N. For example, the geometry pipeline (e.g., Fig. 22 2236) dispatches vertex processing, tessellation or geometry processing threads to thread execution logic 2300 ( Fig.23 ). In some embodiments, thread dispatcher 2304 may also process runtime thread generation requests from executing shader programs.

[0288] Once a set of geometric objects have been processed and rasterized into pixel data, the pixel shader 2302 is called to further calculate output information and cause the results to be written to an output surface (e.g., a color buffer, a depth buffer, a stencil buffer, etc.). In some embodiments, the pixel shader 2302 calculates the values ​​of various vertex attributes that are to be interpolated across rasterized objects. In some embodiments, the pixel shader 2302 then executes a pixel shader program supplied by an application programming interface (API). To execute the pixel shader program, the pixel shader 2302 dispatches threads to execution units (e.g., 2308A) via a thread dispatcher 2304. In some embodiments, the pixel shader 2302 uses texture sampling logic in a sampler 2310 to access texture data in a texture map stored in memory. Arithmetic operations on texture data and input geometric data calculate pixel color data for each geometric fragment, or discard one or more pixels without further processing.

[0289] In some embodiments, data port 2314 provides a memory access mechanism for thread execution logic 2300 to output processed data to memory for processing on the graphics processor output pipeline. In some embodiments, data port 2314 includes or is coupled to one or more cache memories (e.g., data cache 2312) to cache data via the data port for memory access.

[0290] Fig.24 2400 is a block diagram illustrating a graphics processor instruction format 2400 according to some embodiments. In one or more embodiments, a graphics processor execution unit supports an instruction set having instructions in a variety of formats. Solid line boxes illustrate components that are typically included in execution unit instructions, while dashed lines include optional components or components that are only included in a subset of instructions. In some embodiments, the described and illustrated instruction format 2400 are macroinstructions because they are instructions supplied to the execution unit, in contrast to micro-operations that are generated by instruction decoding once the instruction is processed.

[0291] In some embodiments, the graphics processor execution unit natively supports instructions in 128-bit instruction format 2410. 64-bit compact instruction format 2430 can be used for some instructions based on the selected instruction, instruction options and number of operands. Native 128-bit instruction format 2410 provides access to all instruction options, while some options and operations are restricted to 64-bit instruction format 2430. The native instructions available in 64-bit instruction format 2430 vary according to the embodiment. In some embodiments, instructions are compressed using, in part, a set of index values ​​in index field 2413. The execution unit hardware references a set of compression tables based on the index values ​​and uses the compression table output to reconstruct native instructions in 128-bit instruction format 2410.

[0292] For each format, the instruction opcode 2412 defines the operation to be performed by the execution unit. The execution unit executes each instruction in parallel across multiple data elements of each operand. For example, in response to an add instruction, the execution unit performs a simultaneous add operation across each color channel, the color channel representing a texture element or a picture element. By default, the execution unit executes each instruction across all data channels of the operand. In some embodiments, the instruction control field 2414 enables control of certain execution options such as channel selection (e.g., prediction) and data channel order (e.g., swizzling). For 128-bit instructions 2410, the execution size field 2416 limits the number of data channels that will be executed in parallel. In some embodiments, the execution size field 2416 is not available for use in a 64-bit compact instruction format 2430.

[0293] Some execution unit instructions have up to three operands, including two source operands (src0 2420, src1 2422) and a destination 2418. In some embodiments, the execution unit supports dual destination instructions, where one of the destinations is implicit. Data manipulation instructions may have a third source operand (e.g., SRC2 2424), where the instruction opcode 2412 determines the number of source operands. The last source operand of an instruction may be an immediate (e.g., hard-coded) value passed with the instruction.

[0294] In some embodiments, the 128-bit instruction format 2410 includes access / addressing mode information 2426, which specifies, for example, whether direct register addressing mode or indirect register addressing mode is used. When direct register addressing mode is used, the register address of one or more operands is provided directly by bits in the instruction 2410.

[0295] In some embodiments, the 128-bit instruction format 2410 includes an access / addressing mode field 2426, which specifies an addressing mode and / or access mode for the instruction. In one embodiment, the access mode defines the data access alignment for the instruction. Some embodiments support access modes, including 16-byte aligned access modes and 1-byte aligned access modes, wherein the byte alignment of the access mode determines the access alignment of the instruction operands. For example, when in a first mode, the instruction 2410 can use byte aligned addressing for source operands and destination operands, and when in a second mode, the instruction 2410 can use 16-byte aligned addressing for all source operands and destination operands.

[0296] In one embodiment, the addressing mode portion of the access / addressing mode field 2426 determines whether the instruction is to use direct addressing or indirect addressing. When direct register addressing mode is used, the bits in the instruction 2410 directly provide the register address of one or more operands. When indirect register addressing mode is used, the register address of one or more operands can be calculated based on the address register value and the address immediate field in the instruction.

[0297] In some embodiments, instructions are grouped based on the opcode 2412 bit field to simplify opcode decoding 2440. For 8-bit opcodes, bits 4, 5, and 6 allow the execution unit to determine the type of opcode. The precise opcode grouping shown is only an example. In some embodiments, the move and logic opcode group 2442 includes data movement and logic instructions (e.g., move (mov), compare (cmp)). In some embodiments, the move and logic group 2442 shares five most significant bits (MSBs), where the move (mov) instruction takes the form of 0000xxxxb, and the logic instruction takes the form of 0001xxxxb. The flow control instruction group 2444 (e.g., call (call), jump (jmp)) includes instructions in the form of 0010xxxxb (e.g., 0x20). The miscellaneous instruction group 2446 includes a mixture of instructions, including synchronization instructions (e.g., wait, send) in the form of 0011xxxxb (e.g., 0x30). The parallel math instruction group 2448 includes component-wise arithmetic instructions (e.g., add, multiply (mul)) in the form of 0100xxxxb (e.g., 0x40). The parallel math group 2448 performs arithmetic operations in parallel across data lanes. The vector math group 2450 includes arithmetic instructions (e.g., dp4) in the form of 0101xxxxb (e.g., 0x50). The vector math group performs arithmetic operations on vector operands, such as dot product operations.

[0298] Graphics Pipeline

[0299] Fig.25 is a block diagram of another embodiment of a graphics processor 2500 . Fig.25 Elements having the same reference number (or name) as elements of any other figure herein may operate or function in any manner similar to that described elsewhere herein, but are not limited to these.

[0300] In some embodiments, the graphics processor 2500 includes a graphics pipeline 2520, a media pipeline 2530, a display engine 2540, a thread execution logic 2550, and a rendering output pipeline 2570. In some embodiments, the graphics processor 2500 is a graphics processor within a multi-core processing system that includes one or more general-purpose processing cores. The graphics processor is controlled by register writes to one or more control registers (not shown) or via commands issued to the graphics processor 2500 through the ring interconnect 2502. In some embodiments, the ring interconnect 2502 couples the graphics processor 2500 to other processing components, such as other graphics processors or general-purpose processors. Commands from the ring interconnect 2502 are interpreted by a command stream transmitter 2503, which supplies instructions to separate components of the graphics pipeline 2520 or the media pipeline 2530.

[0301] In some embodiments, the command stream conveyor 2503 directs the operation of the vertex fetcher 2505, which reads vertex data from the memory and executes the vertex processing commands provided by the command stream conveyor 2503. In some embodiments, the vertex fetcher 2505 provides the vertex data to the vertex shader 2507, which performs coordinate space transformation and lighting operations on each vertex. In some embodiments, the vertex fetcher 2505 and the vertex shader 2507 execute the vertex processing instructions by dispatching execution threads to the execution units 2552A, 2552B via the thread dispatcher 2531.

[0302] In some embodiments, execution units 2552A, 2552B are vector processor arrays with instruction sets for performing graphics and media operations. In some embodiments, execution units 2552A, 2552B have an attached L1 cache 2551 that is dedicated to each array or shared between arrays. The cache can be configured as a data cache, an instruction cache, or a single cache that is partitioned to contain data and instructions in different partitions.

[0303] In some embodiments, the graphics pipeline 2520 includes a tessellation component for performing hardware accelerated tessellation of 3D objects. In some embodiments, a programmable hull shader 2511 configures the tessellation operation. A programmable domain shader 2517 provides back-end evaluation of the tessellation output. The tessellation 2513 operates at the direction of the hull shader 2511 and contains dedicated logic for generating a set of detailed geometric objects based on a coarse geometric model that is provided as input to the graphics pipeline 2520. In some embodiments, the tessellation components 2511, 2513, 2517 can be bypassed if tessellation is not used.

[0304] In some embodiments, the complete geometric object may be processed by the geometry shader 2519 via one or more threads dispatched to the execution units 2552A, 2552B, or may proceed directly to the clipper 2529. In some embodiments, the geometry shader operates on entire geometric objects (rather than vertices or vertex patches as in previous stages of the graphics pipeline). If tessellation is disabled, the geometry shader 2519 receives input from the vertex shader 2507. In some embodiments, the geometry shader 2519 may be programmed by a geometry shader program to perform geometry tessellation when the tessellation unit is disabled.

[0305] Before rasterization, the clipper 2529 processes the vertex data. The clipper 2529 can be a fixed function clipper or a programmable clipper with clipping and geometry shader functions. In some embodiments, the rasterizer and depth test component 2573 in the render output pipeline 2570 dispatches a pixel shader to convert the geometric object into its per-pixel representation. In some embodiments, the pixel shader logic is included in the thread execution logic 2550. In some embodiments, the application can bypass rasterization and access the unrasterized vertex data via the outflow unit 2523.

[0306] The graphics processor 2500 has an interconnect bus, interconnect structure, or some other interconnect mechanism that allows data and messages to be passed between the main components of the processor. In some embodiments, the execution units 2552A, 2552B and the associated caches 2551, texture and media samplers 2554, and texture / sampler caches 2558 are interconnected via data ports 2556 to perform memory accesses and communicate with the rendering output pipeline components of the processor. In some embodiments, the samplers 2554, caches 2551, 2558, and execution units 2552A, 2552B each have separate memory access paths.

[0307] In some embodiments, the rendering output pipeline 2570 includes a rasterizer and a depth test component 2573, which converts vertex-based objects into associated pixel-based representations. In some embodiments, the rendering output pipeline 2570 includes a windower / masker unit for performing fixed-function triangle and line rasterization. An associated rendering cache 2578 and a depth cache 2579 are also available in some embodiments. The pixel operation component 2577 performs pixel-based operations on data, but in some instances, pixel operations associated with 2D operations (e.g., using mixed bit block image transfer) are performed by the 2D engine 2541, or replaced by the display controller 2543 using overlapping display planes at display time. In some embodiments, a shared L3 cache 2575 can be used for all graphics components, thereby allowing data to be shared without using the main system memory.

[0308] In some embodiments, the graphics processor media pipeline 2530 includes a media engine 2537 and a video front end 2534. In some embodiments, the video front end 2534 receives pipeline commands from the command stream transmitter 2503. In some embodiments, the media pipeline 2530 includes a separate command stream transmitter. In some embodiments, the video front end 2534 processes the media commands before sending the commands to the media engine 2537. In some embodiments, the media engine 2537 includes a thread generation function for generating threads for dispatching to the thread execution logic 2550 via the thread dispatcher 2531.

[0309] In some embodiments, the graphics processor 2500 includes a display engine 2540. In some embodiments, the display engine 2540 is external to the processor 2500 and is coupled to the graphics processor via a ring interconnect 2502, or some other interconnect bus or structure. In some embodiments, the display engine 2540 includes a 2D engine 2541 and a display controller 2543. In some embodiments, the display engine 2540 contains dedicated logic that can operate independently of the 3D pipeline. In some embodiments, the display controller 2543 is coupled to a display device (not shown), which can be a system integrated display device (such as in a laptop computer), or an external display device attached via a display device connector.

[0310] In some embodiments, the graphics pipeline 2520 and the media pipeline 2530 can be configured to perform operations based on multiple graphics and media programming interfaces and are not dedicated to any one application programming interface (API). In some embodiments, the driver software of the graphics processor converts API calls dedicated to a specific graphics or media library into commands that can be processed by the graphics processor. In some embodiments, support is provided for the Open Graphics Library (OpenGL) and Open Computing Language (OpenCL) from the Khronos Group, the Direct3D library from Microsoft, or support can be provided for both OpenGL and D3D. Support can also be provided for the open source computer vision library (OpenCV). If a mapping can be made from the pipeline of a future API to the pipeline of a graphics processor, a future API with a compatible 3D pipeline will also be supported.

[0311] Graphics pipeline programming

[0312] Fig.26A is a block diagram illustrating a graphics processor command format 2600 according to some embodiments. Fig.26B is a block diagram illustrating a graphics processor command sequence 2610 according to an embodiment. Fig.26A Solid line boxes in illustrate components that are typically included in a graphics command, while dashed lines include components that are optional or included only in a subset of the graphics commands. Fig.26A The exemplary graphics processor command format 2600 includes a data field for identifying the target client 2602 of the command, a command operation code (opcode) 2604, and associated data 2606 for the command. Some commands also include a sub-opcode 2605 and a command size 2608.

[0313] In some embodiments, client 2602 specifies the client unit of the graphics device that processes the command data. In some embodiments, the graphics processor command parser checks the client field of each command to adjust the further processing of the command and routes the command data to the appropriate client unit. In some embodiments, the graphics processor client unit includes a memory interface unit, a rendering unit, a 2D unit, a 3D unit, and a media unit. Each client unit has a corresponding processing pipeline for processing the command. Once the command is received by the client unit, the client unit reads the opcode 2604 and the sub-opcode 2605 (if present) to determine the operation to be performed. The client unit uses the information in the data field 2606 to execute the command. For some commands, an explicit command size 2608 is expected to specify the size of the command. In some embodiments, the command parser automatically determines the size of at least some of the commands in the command based on the command opcode. In some embodiments, the commands are aligned via multiples of double words.

[0314] Fig.26B An exemplary graphics processor command sequence 2610 is shown in the flowchart in FIG. In some embodiments, software or firmware of a data processing system featuring an embodiment of a graphics processor uses the version of the command sequence shown to set up, execute, and terminate a set of graphics operations. The sample command sequence is shown and described for exemplary purposes only, as the embodiments are not limited to these particular commands or to the command sequence. Moreover, the commands may be issued as a batch of commands in a command sequence so that the graphics processor will process the command sequence in an at least partially simultaneous manner.

[0315] In some embodiments, the graphics processor command sequence 2610 may begin with a pipeline flush command 2612 to cause any active graphics pipeline to complete currently pending commands for that pipeline. In some embodiments, the 3D pipeline 2622 and the media pipeline 2624 are not operating simultaneously. The pipeline flush is performed to cause the active graphics pipeline to complete any pending commands. In response to the pipeline flush, the command parser for the graphics processor will suspend command processing until the active drawing engine completes pending operations and invalidates the associated read cache. Optionally, any data marked as 'dirty' in the render cache may be flushed to memory. In some embodiments, the pipeline flush command 2612 may be used for pipeline synchronization or before placing the graphics processor in a low power state.

[0316] In some embodiments, pipeline select command 2613 is used when a command sequence requires the graphics processor to explicitly switch between pipelines. In some embodiments, pipeline select command 2613 is required only once within an execution context before issuing pipeline commands unless the context is to issue commands for both pipelines. In some embodiments, pipeline flush command 2612 is required immediately prior to a pipeline switch via pipeline select command 2613.

[0317] In some embodiments, pipeline control commands 2614 configure the graphics pipeline for operation and are used to program 3D pipeline 2622 and media pipeline 2624. In some embodiments, pipeline control commands 2614 configure the pipeline state of the active pipeline. In one embodiment, pipeline control commands 2614 are used for pipeline synchronization and for clearing data from one or more cache memories within the active pipeline before processing a batch of commands.

[0318] In some embodiments, commands for return buffer state 2616 are used to configure a set of return buffers for corresponding pipelines to write data. Some pipeline operations require allocating, selecting or configuring one or more return buffers into which the operation writes intermediate data during processing. In some embodiments, the graphics processor also uses one or more return buffers to store output data and perform cross-thread communication. In some embodiments, configuring return buffer state 2616 includes selecting the size and number of return buffers to use for the set of pipeline operations.

[0319] The remaining commands in the command sequence differ based on the active pipeline for operation. Based on pipeline determination 2620 , the command sequence is tailored to either the 3D pipeline 2622 starting at 3D pipeline state 2630 or the media pipeline 2624 starting at media pipeline state 2640 .

[0320] The commands for 3D pipeline state 2630 include 3D state setting commands for vertex buffer state, vertex element state, constant color state, depth buffer state, and other state variables to be configured before processing 3D primitive commands. The values ​​of these commands are determined at least in part based on the specific 3D API in use. In some embodiments, the 3D pipeline state 2630 commands can also selectively disable or bypass specific pipeline elements (if those elements will not be used).

[0321] In some embodiments, 3D primitive 2632 commands are used to submit 3D primitives to be processed by the 3D pipeline. The commands and associated parameters passed to the graphics processor via the 3D primitive 2632 commands are forwarded to the vertex acquisition function in the graphics pipeline. The vertex acquisition function uses the 3D primitive 2632 command data to generate a vertex data structure. The vertex data structure is stored in one or more return buffers. In some embodiments, 3D primitive 2632 commands are used to perform vertex operations on 3D primitives via vertex shaders. In order to process vertex shaders, the 3D pipeline 2622 dispatches the shader execution thread to the graphics processor execution unit.

[0322] In some embodiments, the 3D pipeline 2622 is triggered via an execute 2634 command or event. In some embodiments, a register write triggers the command execution. In some embodiments, the execution is triggered via a 'go' or 'kick' command in the command sequence. In one embodiment, the command execution is triggered using a pipeline synchronization command to dump the command sequence through the graphics pipeline. The 3D pipeline will perform geometry processing for the 3D primitives. Once the operation is completed, the resulting geometric objects are rasterized and the pixel engine shades the resulting pixels. For those operations, additional commands for controlling pixel shading and pixel backend operations may also be included.

[0323] In some embodiments, when performing media operations, the graphics processor command sequence 2610 follows the media pipeline 2624 path. Generally, the specific purpose and manner of programming the media pipeline 2624 depends on the media or computing operation to be performed. During media decoding, specific media decoding operations can be offloaded to the media pipeline. In some embodiments, the media pipeline can also be bypassed, and media decoding can be performed in whole or in part using resources provided by one or more general processing cores. In one embodiment, the media pipeline also includes elements for general purpose graphics processor unit (GPGPU) operations, wherein the graphics processor is used to perform SIMD vector operations using compute shader programs that are not explicitly related to rendering graphics primitives.

[0324] In some embodiments, the media pipeline 2624 is configured in a similar manner to the 3D pipeline 2622. A set of commands for configuring the media pipeline state 2640 is dispatched or placed in the command queue before the media object commands 2642. In some embodiments, the commands for the media pipeline state 2640 include data for configuring the media pipeline elements that will be used to process the media objects. This includes data for configuring the video decoding and video encoding logic within the media pipeline, such as encoding or decoding formats. In some embodiments, the commands for the media pipeline state 2640 also support the use of one or more pointers to "indirect" state elements that contain a batch of state settings.

[0325] In some embodiments, media object commands 2642 supply pointers to media objects for media pipeline processing. The media object includes a memory buffer that contains video data to be processed. In some embodiments, all media pipeline states must be valid before issuing media object commands 2642. Once the pipeline state is configured and the media object commands 2642 are queued, the media pipeline 2624 is triggered via an execution command 2644 or an equivalent execution event (e.g., a register write). The output from the media pipeline 2624 can then be post-processed by operations provided by the 3D pipeline 2622 or the media pipeline 2624. In some embodiments, GPGPU operations are configured and executed in a manner similar to media operations.

[0326] Graphics software architecture

[0327] Fig. 27 An exemplary graphics software architecture of a data processing system 2700 according to some embodiments is illustrated. In some embodiments, the software architecture includes a 3D graphics application 2710, an operating system 2720, and at least one processor 2730. In some embodiments, the processor 2730 includes a graphics processor 2732 and one or more general purpose processor cores 2734. The graphics application 2710 and the operating system 2720 are each executed in a system memory 2750 of the data processing system.

[0328] In some embodiments, the 3D graphics application 2710 includes one or more shader programs that include shader instructions 2712. The shader language instructions may be in a high-level shader language, such as High Level Shader Language (HLSL) or OpenGL Shader Language (GLSL). The application also includes executable instructions 2714 in a machine language suitable for execution by (one or more) general purpose processor cores 2734. The application also includes graphics objects 2716 defined by vertex data.

[0329] In some embodiments, the operating system 2720 is a Microsoft® Windows® operating system from Microsoft Corporation, a proprietary UNIX-style operating system, or an open source UNIX-style operating system using a Linux kernel variant. The operating system 2720 can support a graphics API 2722, such as a Direct3D API or an OpenGL API. When the Direct3D API is in use, the operating system 2720 uses a front-end shader compiler 2724 to compile any shader instructions 2712 using HLSL into a lower-level shader language. The compilation can be a just-in-time (JIT) compilation, or the application can perform shader precompilation. In some embodiments, during the compilation of the 3D graphics application 2710, a high-level shader is compiled into a low-level shader.

[0330] In some embodiments, the user mode graphics driver 2726 includes a backend shader compiler 2727 that converts shader instructions 2712 into hardware-specific representations. When the OpenGL API is in use, shader instructions 2712 in the GLSL high-level language are passed to the user mode graphics driver 2726 for compilation. In some embodiments, the user mode graphics driver 2726 uses the operating system kernel mode function 2728 to communicate with the kernel mode graphics driver 2729. In some embodiments, the kernel mode graphics driver 2729 communicates with the graphics processor 2732 to dispatch commands and instructions.

[0331] IP Core Implementation

[0332] One or more aspects of at least one embodiment may be implemented by representative code stored on a machine-readable medium that represents and / or defines logic within an integrated circuit such as a processor. For example, a machine-readable medium may include instructions representing various logic within a processor. When read by a machine, the instructions may cause the machine to manufacture logic for performing the techniques described herein. This representation (referred to as an "IP core") is a reusable unit of logic for an integrated circuit that may be stored on a tangible machine-readable medium as a hardware model that describes the structure of the integrated circuit. The hardware model may be supplied to various customers or manufacturing facilities that load the hardware model on a manufacturing machine that manufactures the integrated circuit. The integrated circuit may be manufactured so that the circuit performs the operations described in association with any of the embodiments described herein.

[0333] Fig.2828 is a block diagram illustrating an IP core development system 2800 that can be used to manufacture an integrated circuit for performing operations according to an embodiment. The IP core development system 2800 can be used to generate modular, reusable designs that can be incorporated into a larger design or used to construct an entire integrated circuit (e.g., a SOC integrated circuit). The design facility 2830 can generate a software simulation 2810 for the IP core design in a high-level programming language (e.g., C / C++). The software simulation 2810 can be used to design, test, and verify the behavior of the IP core using a simulation model 2812. The simulation model 2812 can include functional, behavioral, and / or timing simulations. A register transfer level (RTL) design 2815 can then be created or synthesized based on the simulation model 2812. The RTL design 2815 is an abstraction of the behavior of an integrated circuit (including associated logic executed using the modeled digital signals) that models the flow of digital signals between hardware registers. In addition to the RTL design 2815, a lower-level design at the logic level or transistor level can also be created, designed, or synthesized. Therefore, the specific details of the initial design and simulation can vary.

[0334] The RTL design 2815 or equivalent may be further synthesized by the design facility into a hardware model 2820, which may be in a hardware description language (HDL) or some other representation of physical design data. The HDL may be further simulated or tested to verify the IP core design. The IP core design may be stored using a non-volatile memory 2840 (e.g., a hard disk, flash memory, or any non-volatile storage medium) for delivery to a third-party manufacturing facility 2865. Alternatively, the IP core design may be transmitted (e.g., via the Internet) via a wired connection 2850 or a wireless connection 2860. The manufacturing facility 2865 may then manufacture an integrated circuit based at least in part on the IP core design. The manufactured integrated circuit may be configured to perform operations according to at least one embodiment described herein.

[0335] Exemplary System-on-Chip Integrated Circuit

[0336] Figure 29 to Figure 31 An exemplary integrated circuit and associated graphics processor that can be manufactured using one or more IP cores according to various embodiments described herein are illustrated. In addition to what is illustrated, other logic and circuits may also be included, including additional graphics processors / cores, peripheral interface controllers, or general purpose processor cores.

[0337] Fig.292900, which may be manufactured using one or more IP cores in accordance with an embodiment. The exemplary integrated circuit 2900 includes one or more application processors 2905 (e.g., CPUs), at least one graphics processor 2910, and may additionally include an image processor 2915 and / or a video processor 2920, any of which may be modular IP cores from the same or multiple different design facilities. The integrated circuit 2900 includes peripheral or bus logic, including a USB controller 2925, a UART controller 2930, an SPI / SDIO controller 2935, and an I 2 S / I 2 The integrated circuit may also include a display device 2945 coupled to one or more of a high-definition multimedia interface (HDMI) controller 2950 and a mobile industry processor interface (MIPI) display interface 2955. Storage may be provided by a flash memory subsystem 2960 (including flash memory and a flash memory controller). A memory interface may be provided via a memory controller 2965 to access SDRAM or SRAM memory devices. In addition, some integrated circuits also include an embedded security engine 2970.

[0338] Fig.30 is a block diagram illustrating an exemplary graphics processor 3010 of a system-on-chip integrated circuit that may be fabricated using one or more IP cores according to an embodiment. The graphics processor 3010 may be Fig.29 A variation of the graphics processor 2910 of FIG. The graphics processor 3010 includes a vertex processor 3005 and one or more fragment processors 3015A to 3015N (e.g., 3015A, 3015B, 3015C, 3015D, all the way to 3015N-1 and 3015N). The graphics processor 3010 can execute different shader programs via separate logic, so that the vertex processor 3005 is optimized to perform operations of the vertex shader program, while one or more fragment processors 3015A to 3015N perform fragment (e.g., pixel) shading operations for fragment or pixel shader programs. The vertex processor 3005 performs the vertex processing stage of the 3D graphics pipeline and generates primitives and vertex data. (One or more) fragment processors 3015A to 3015N use the primitives and vertex data generated by the vertex processor 3005 to generate a frame buffer displayed on a display device. In one embodiment, the fragment processor(s) 3015A- 3015N are optimized to execute fragment shader programs provided in the OpenGL API, which can be used to perform similar operations as pixel shader programs provided in the Direct 3D API.

[0339] In addition, the graphics processor 3010 also includes one or more memory management units (MMUs) 3020A-3020B, cache(s) 3025A-3025B, and circuit interconnect(s) 3030A-3030B. The one or more MMUs 3020A-3020B provide virtual to physical address mappings for the graphics processor 3010, including for the vertex processor 3005 and / or the fragment processor(s) 3015A-3015N, which may reference vertex or image / texture data stored in memory in addition to vertex or image / texture data stored in the one or more caches 3025A-3025B. In one embodiment, the one or more MMUs 3020A-3020B may communicate with other MMUs within the system, including with Fig.29 The graphics processor 3010 may be synchronized with one or more MMUs associated with one or more application processors 2905, image processor 2915, and / or video processor 2920 so that each processor 2905 to 2920 may participate in a shared or unified virtual memory system. According to an embodiment, one or more circuit interconnects 3030A to 3030B may enable the graphics processor 3010 to interact with other IP cores within the SoC via an internal bus of the SoC or via a direct connection.

[0340] Fig.31 is a block diagram illustrating an additional exemplary graphics processor 3110 of a system-on-chip integrated circuit that may be fabricated using one or more IP cores in accordance with an embodiment. The graphics processor 3110 may be Fig.29 A variant of the graphics processor 2910. The graphics processor 3110 includes Fig.30 One or more MMUs 3020A-3020B, cache(s) 3025A-3025B, and circuit interconnect(s) 3030A-3030B of the integrated circuit 3000.

[0341] The graphics processor 3110 includes one or more shader cores 3115A to 3115N (e.g., 3115A, 3115B, 3115C, 3115D, 3115E, 3115F, all the way to 3015N-1 and 3015N), which provide a unified shader core architecture in which a single core or type or core can execute all types of programmable shader code, including shader program code to implement vertex shaders, fragment shaders, and / or compute shaders. The exact number of shader cores present may vary between embodiments and implementations. In addition, the graphics processor 3110 also includes an inter-core task manager 3105, which acts as a thread dispatcher for dispatching execution threads to one or more shader cores 3115A to 3115N. The graphics processor 3110 further includes a tiling unit 3118 for accelerating tiling operations for tile-based rendering, in which the rendering operations of a scene are subdivided in image space. Tile based rendering can be used to exploit local spatial coherence within a scene or to optimize the use of internal caches.

[0342] This disclosure / application provides the following technical solutions:

[0343] 1. A device comprising:

[0344] detection / observation logic, when implemented by or at least partially in a processor, for detecting input data to be used in a computational task by a computational component of a computational pipeline of said processor including a graphics processor; and

[0345] A bypass / detour logic, when implemented by or at least partially in the processor, is used to determine one or more frequently used data values ​​(FDVs) from the data, wherein the bypass / detour logic is used to push the one or more frequent data values ​​to bypass the computing task.

[0346] 2. The device as described in technical solution 1, wherein the bypass / detour logic is further used to determine one or more non-FDVs from the data, wherein the bypass / detour logic further sets the non-FDVs on a computing path to pass through the computing component.

[0347] 3. An apparatus as described in technical solution 1, wherein the one or more FDVs include frequently occurring values ​​whose calculated values ​​and results are known or predictable.

[0348] 4. The device as described in technical solution 1 further includes a calculation / customization logic, which, when implemented by or at least partially in the processor, is used to generate one or more configuration sets to be assigned to the input data to reduce mathematical operations associated with the one or more FDVs and the one or more non-FDVs.

[0349] 5. A device as described in technical solution 4, wherein the mathematical operation includes one or more of addition, subtraction, multiplication, and division.

[0350] 6. A device as described in technical solution 4, wherein the calculation / customization logic is further used to host a finite state machine (FSM) to provide common primitives for convolution and fully connected calculations, wherein the FSM is used to combine memory read accesses and merge one or more of the mathematical operations with another one or more of the mathematical operations.

[0351] 7. A device as described in Technical Solution 1, wherein the graphics processor and the application processor are co-located on a common semiconductor package.

[0352] 8. A method comprising:

[0353] detecting input data to be used in a computational task by a computational component of a computational pipeline of a processor including a graphics processor; and

[0354] determining one or more frequently used data values ​​(FDVs) from the data;

[0355] and pushing the one or more frequent data values ​​to bypass the computing task.

[0356] 9. The method as described in technical solution 8 further comprises:

[0357] determining one or more non-FDVs from the data; and

[0358] The non-FDV is disposed on a computation path to pass through the computation component.

[0359] 10. A method as described in technical solution 8, wherein the one or more FDVs include frequently occurring values ​​whose calculated values ​​and results are known or predictable.

[0360] 11. The method of technical solution 8 further comprises generating one or more configuration sets to be assigned to the input data to reduce mathematical operations associated with the one or more FDVs and the one or more non-FDVs.

[0361] 12. A method as described in technical solution 11, wherein the mathematical operation includes one or more of addition, subtraction, multiplication, and division.

[0362] 13. The method as described in technical solution 11 further includes a master finite state machine (FSM) to provide common primitives for convolution and fully connected calculations, wherein the FSM is used to combine memory read accesses and merge one or more of the mathematical operations with another one or more of the mathematical operations.

[0363] 14. A method as described in Technical Solution 8, wherein the graphics processor and the application processor are co-placed on a common semiconductor package.

[0364] 15. At least one machine-readable medium comprising instructions that, when executed by a computing device, cause the computing device to perform operations comprising:

[0365] detecting input data to be used in a computing task by a computing component of a computing pipeline of a processor including a graphics processor; and

[0366] determining one or more frequently used data values ​​(FDVs) from the data; and

[0367] The one or more frequent data values ​​are pushed to bypass the computation task.

[0368] 16. The machine-readable medium of claim 15, further comprising determining one or more non-FDVs from the data; and placing the non-FDVs on a computational path to pass through the computational component.

[0369] 17. A machine-readable medium as described in technical solution 15, wherein the one or more FDVs include frequently occurring values ​​whose calculated values ​​and results are known or predictable.

[0370] 18. The machine-readable medium of technical solution 15, wherein the processor is further configured to generate one or more configuration sets to be assigned to the input data to reduce mathematical operations associated with the one or more FDVs and the one or more non-FDVs.

[0371] 19. A machine-readable medium as described in technical solution 18, wherein the mathematical operation includes one or more of addition, subtraction, multiplication, and division.

[0372] 20. A machine-readable medium as described in technical solution 18, wherein the processor is further used to host a finite state machine (FSM) to provide common primitives for convolution and fully connected calculations, wherein the FSM is used to combine memory read accesses and merge one or more of the mathematical operations with another one or more of the mathematical operations, wherein the graphics processor and the application processor are co-located on a common semiconductor package.

[0373] References to "one embodiment," "an embodiment," "example embodiment," "various embodiments," etc. indicate that the embodiment(s) so described may include a particular feature, structure, or characteristic, but not every embodiment necessarily includes the particular feature, structure, or characteristic. Furthermore, some embodiments may have some, all, or none of the features described for other embodiments.

[0374] In the foregoing specification, the embodiments have been described with reference to specific exemplary embodiments thereof. However, it will be apparent that various modifications and changes may be made thereto without departing from the broader spirit and scope of the embodiments as set forth in the appended claims. The description and drawings are accordingly to be regarded in an illustrative rather than a restrictive sense.

[0375] In the following description and claims, the term "coupled," along with its derivatives, may be used. "Coupled" is used to indicate that two or more elements co-operate or interact with each other, but they may or may not have intervening physical or electrical components between them.

[0376] As used in the claims, unless otherwise specified, use of ordinal adjectives "first," "second," "third," etc. to describe common elements merely indicates that different instances of similar elements are mentioned and is not intended to mean that the elements so described must be in a given sequence temporally, spatially, in rank, or in any other manner.

[0377] The following clauses and / or examples relate to additional embodiments or examples. Details in the examples may be used anywhere in one or more embodiments. Various features of different embodiments or examples may be combined in various ways with some features included and other features excluded to suit a variety of different applications. Examples may include subject matter such as methods, components for performing actions of the methods, at least one machine-readable medium including instructions that, when executed by a machine, cause the machine to perform the actions of the methods, or an apparatus or system for facilitating hybrid communications according to the embodiments and examples described herein.

[0378] Some embodiments relate to Example 1, which includes an apparatus for facilitating fast data operations for machine learning, the apparatus comprising: detection / observation logic, when implemented by or at least partially in a processor, for detecting input data to be used in a computing task by a computing component of a computing pipeline of a processor including a graphics processor; and bypass / detour logic, when implemented by or at least partially in the processor, for determining one or more frequently used data values ​​(FDVs) from the data, wherein the bypass / detour logic is used to push the one or more frequent data values ​​to bypass the computing task.

[0379] Example 2 includes the subject matter of Example 1, wherein the bypass / detour logic is further to determine one or more non-FDVs from the data, wherein the bypass / detour logic further places the non-FDVs on a computation path to pass through the computation component.

[0380] Example 3 includes the subject matter of Examples 1-2, wherein the one or more FDVs include frequently occurring values ​​whose calculations and results are known or predictable.

[0381] Example 4 includes the subject matter of Examples 1-3, further comprising calculation / customization logic, when implemented by or at least partially in a processor, for generating one or more configuration sets to be assigned to the input data to reduce mathematical operations associated with the one or more FDVs and the one or more non-FDVs.

[0382] Example 5 includes the subject matter of Examples 1-4, wherein the mathematical operation comprises one or more of addition, subtraction, multiplication, and division.

[0383] Example 6 includes the subject matter of Examples 1-5, wherein the computation / customization logic is further used to host a finite state machine (FSM) to provide common primitives for convolution and fully connected computations, wherein the FSM is used to combine memory read accesses and merge one or more of the mathematical operations with another one or more of the mathematical operations.

[0384] Example 7 includes the subject matter of Examples 1-6, wherein the graphics processor is co-located with the application processor on a common semiconductor package.

[0385] Some embodiments relate to Example 8, which includes a method for facilitating sharing of data and compression and expansion of models, the method comprising: detecting input data to be used in a computing task by a computing component of a computing pipeline of a processor including a graphics processor; determining one or more frequently used data values ​​(FDVs) from the data; and pushing the one or more frequent data values ​​to bypass the computing task.

[0386] Example 9 includes the subject matter of Example 8, further comprising determining one or more non-FDVs from the data; and placing the non-FDVs on a computation path to pass through the computation component.

[0387] Example 10 includes the subject matter of Examples 8-9, wherein the one or more FDVs include frequently occurring values ​​whose calculations and results are known or predictable.

[0388] Example 11 includes the subject matter of Examples 8-10, further comprising generating one or more sets of configurations to be assigned to the input data to reduce mathematical operations associated with the one or more FDVs and the one or more non-FDVs.

[0389] Example 12 includes the subject matter of Examples 8-11, wherein the mathematical operation comprises one or more of addition, subtraction, multiplication, and division.

[0390] Example 13 includes the subject matter of Examples 8-12, further comprising a master finite state machine (FSM) to provide common primitives for convolution and fully connected computations, wherein the FSM is used to combine memory read accesses and merge one or more of the mathematical operations with another one or more of the mathematical operations.

[0391] Example 14 includes the subject matter of Examples 8-13, wherein the graphics processor is co-located with the application processor on a common semiconductor package.

[0392] Some embodiments relate to Example 15, which includes a graphics processing system, the graphics processing system comprising a computing device having a memory, the memory coupled to a processor, the processor for: detecting input data to be used in a computing task by a computing component of a computing pipeline of a processor including a graphics processor; determining one or more frequently used data values ​​(FDV) from the data; and pushing the one or more frequent data values ​​to bypass the computing task.

[0393] Example 16 includes the subject matter of Example 15, determining one or more non-FDVs from the data; and placing the non-FDVs on a computation path to pass through the computation component.

[0394] Example 17 includes the subject matter of Examples 15-16, wherein the one or more FDVs include frequently occurring values ​​whose calculations and results are known or predictable.

[0395] Example 18 includes the subject matter of Examples 15-17, wherein the processor is further configured to generate one or more sets of configurations to be assigned to the input data to reduce mathematical operations associated with the one or more FDVs and the one or more non-FDVs.

[0396] Example 19 includes the subject matter of Examples 15-18, wherein the mathematical operation comprises one or more of addition, subtraction, multiplication, and division.

[0397] Example 20 includes the subject matter of Examples 15-19, wherein the processor is further configured to host a finite state machine (FSM) to provide common primitives for convolution and fully connected computations, wherein the FSM is configured to combine memory read accesses and merge one or more of the mathematical operations with another one or more of the mathematical operations.

[0398] Example 21 includes the subject matter of Examples 15-20, wherein the graphics processor is co-located with the application processor on a common semiconductor package.

[0399] Example 22 includes at least one non-transitory or tangible machine-readable medium comprising a plurality of instructions that, when executed on a computing device, are used to implement or perform a method as claimed in any of the claims or Examples 8-14.

[0400] Example 23 includes at least one machine-readable medium comprising a plurality of instructions, which when executed on a computing device, are used to implement or perform a method as claimed in any of the claims or examples 8-14.

[0401] Example 24 includes a system comprising mechanisms for implementing or performing a method as claimed in any of the claims or Examples 8-14.

[0402] Example 25 includes an apparatus comprising components for performing a method as claimed in any of the claims or Examples 8-14.

[0403] Example 26 includes a computing device arranged to implement or perform a method as claimed in any of the claims or examples 8-14.

[0404] Example 27 comprises a communication device arranged to implement or perform a method as claimed in any one of the claims or examples 8-14.

[0405] Example 28 includes at least one machine-readable medium comprising a plurality of instructions, which, when executed on a computing device, are used to implement or perform a method as claimed in any of the above claims, or to implement an apparatus as claimed in any of the above claims.

[0406] Example 29 includes at least one non-transitory or tangible machine-readable medium comprising a plurality of instructions that, when executed on a computing device, are used to implement or perform a method as claimed in any of the above claims, or to implement an apparatus as claimed in any of the above claims.

[0407] Example 30 includes a system comprising means for implementing or executing a method as claimed in any of the above claims or implementing an apparatus as claimed in any of the above claims.

[0408] Example 31 comprises an apparatus comprising components for performing a method as claimed in any of the above claims.

[0409] Example 32 includes a computing device arranged to implement or perform a method as claimed in any of the above claims or to implement an apparatus as claimed in any of the above claims.

[0410] Example 33 comprises a communication device arranged to implement or perform a method as claimed in any of the above claims or to implement an apparatus as claimed in any of the above claims.

[0411] The accompanying drawings and the foregoing description give examples of embodiments. It will be appreciated by those skilled in the art that one or more of the elements described may be well combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, the order of the processes described herein may be changed and are not limited to the manner described herein. In addition, the actions of any flowchart do not need to be implemented in the order shown; nor do all actions necessarily need to be performed. Moreover, those actions that are independent of other actions may be performed in parallel with the other actions. The scope of the embodiments is by no means limited by these specific examples. Many variations (whether or not explicitly given in the specification, such as differences in structure, size, and material use) are possible. The scope of the embodiments is at least as wide as given in the appended claims.

Claims

1. A device for facilitating rapid data manipulation for machine learning, the device include: detection / observation logic for detecting input data to be used in a computational task by a computational component of a computational pipeline of a processor including a graphics processor; bypass / detour logic for determining one or more frequently used data values ​​FDV from the data, wherein the bypass / detour logic is used to push the one or more frequent data values ​​to bypass the computing task; as well as calculation / customization logic for generating one or more sets of configurations to be assigned to the input data to reduce mathematical operations associated with the one or more FDVs and the one or more non-FDVs, The computation / customization logic is further used to host a finite state machine FSM to provide common primitives for convolution and fully connected computations, wherein the FSM is used to combine memory read accesses and merge one or more of the mathematical operations with another one or more of the mathematical operations.

2. The apparatus of claim 1, wherein the bypass / detour logic is further to determine one or more non-FDVs from the data, wherein the bypass / detour logic further places the non-FDVs on a computation path to pass through the computation component.

3. The apparatus of claim 1, wherein the one or more FDVs include frequently occurring values ​​whose calculated values ​​and results are known or predictable.

4. The apparatus of claim 1, wherein the mathematical operation comprises one or more of addition, subtraction, multiplication, and division.

5. The apparatus of claim 1, wherein the graphics processor is co-located with an application processor on a common semiconductor package.

6. A method for facilitating rapid data manipulation for machine learning, the method include: detecting input data to be used in a computational task by a computational component of a computational pipeline of a processor including a graphics processor; as well as determining one or more frequently used data values ​​FDV from the data; Pushing the one or more frequent data values ​​to bypass the computing task; generating one or more sets of configurations to be assigned to the input data to reduce mathematical operations associated with the one or more FDVs and the one or more non-FDVs; as well as A finite state machine (FSM) is hosted to provide common primitives for convolution and fully connected computations, wherein the FSM is used to combine memory read accesses and merge one or more of the mathematical operations with another one or more of the mathematical operations.

7. The method of claim 6, further comprising: include: determining one or more non-FDVs from the data; as well as The non-FDV is disposed on a computation path to pass through the computation component.

8. The method of claim 6, wherein the one or more FDVs include frequently occurring values ​​whose calculated values ​​and results are known or predictable.

9. The method of claim 6, wherein the mathematical operation comprises one or more of addition, subtraction, multiplication, and division.

10. The method of claim 6, wherein the graphics processor is co-located with an application processor on a common semiconductor package.

11. At least one machine-readable medium comprising a plurality of instructions for implementing or performing a method as claimed in any one of claims 6 to 10 when executed on a computing device.

12. A system comprising means for implementing or performing a method as claimed in any one of the claims or examples 6-10.

13. An apparatus comprising components for performing a method as claimed in any of the claims or examples 6-10.

14. A computing device arranged to implement or perform a method as claimed in any of the claims or examples 6-10.

15. A communication device arranged to implement or perform a method as claimed in any of the claims or examples 6-10.

16. A device for facilitating rapid data manipulation for machine learning, the device include: a component for detecting input data to be used in a computing task by a computing component of a computing pipeline of a processor including a graphics processor; as well as a component for determining one or more frequently used data values ​​FDV from said data; as well as a component for pushing the one or more frequent data values ​​to bypass the computing task; components for generating one or more sets of configurations to be assigned to the input data to reduce mathematical operations associated with the one or more FDVs and the one or more non-FDVs; as well as A component for hosting a finite state machine (FSM) to provide common primitives for convolution and fully connected computations, wherein the FSM is used to combine memory read accesses and merge one or more of the mathematical operations with another one or more of the mathematical operations.

17. The device of claim 16, further comprising: include: a component for determining one or more non-FDVs from the data; as well as A component for placing the non-FDV on a computation path through the computation component.

18. The apparatus of claim 16, wherein the one or more FDVs include frequently occurring values ​​whose calculated values ​​and results are known or predictable.

19. The apparatus of claim 16, wherein the mathematical operation comprises one or more of addition, subtraction, multiplication, and division.

20. The apparatus of claim 16, wherein the graphics processor is co-located with an application processor on a common semiconductor package.