Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

109 results about "Jazelle" patented technology

Jazelle DBX (Direct Bytecode eXecution) is an extension that allows some ARM processors to execute Java bytecode in hardware as a third execution state alongside the existing ARM and Thumb modes. Jazelle functionality was specified in the ARMv5TEJ architecture and the first processor with Jazelle technology was the ARM926EJ-S. Jazelle is denoted by a "J" appended to the CPU name, except for post-v5 cores where it is required (albeit only in trivial form) for architecture conformance.

End side model reasoning method and device based on RWKV architecture, electronic equipment and storage medium

The invention provides an end side model reasoning method and device based on an RWKV architecture, electronic equipment and a storage medium, and the method comprises the steps: obtaining a target input request of a target object, and converting the target input request into target model input data; loading a historical reasoning state corresponding to the target input request in a preset state storage space; determining a corresponding RWKV core operator according to the hardware platform type of the terminal equipment; based on the RWKV core operator, performing reasoning calculation on the target model input data and the historical reasoning state to obtain an output token sequence; wherein in the reasoning calculation process, the real-time reasoning state of the large language model is stored in a preset state accelerator memory for multiplexing; converting the output token sequence into a text format and outputting the output token sequence; and updating the historical reasoning state according to the real-time reasoning state after reasoning calculation. According to the method, calculation optimization and hardware acceleration can be carried out on the large language model of the RWKV architecture, so that the reasoning performance of the RWKV architecture model is improved on the end side.
Owner:SHENZHEN YUANSHI INTELLIGENT CO LTD

Deployment method of efficient Transform model reasoning accelerator based on Versa ACAP

The invention discloses an efficient Transform model reasoning accelerator deployment method based on Versaal ACAP, and belongs to the field of software and hardware collaborative acceleration numerical calculation. Firstly, load analysis is carried out on the model, and meanwhile, according to hardware performance, the types and scales of operators needing to be borne by hardware of all parts are determined; then, hardware is equipped with a data transmitter, a data receiver, a nonlinear operator and other modules; then, the modules are reasonably deployed and connected in hardware, pipeline parallelization is completed, and calculation of a multi-head attention stage and a feedforward neural network stage is achieved; and finally, integrating the two stages to realize accelerated calculation of the whole encoder / decoder layer so as to accelerate the reasoning speed of the upper layer model. Experiments prove that the throughout of the model is effectively improved, the reasoning delay is reduced, meanwhile, the accelerator has huge advantages in the aspect of batch reasoning, and the accelerator has wide application prospects in the aspects of reducing the model reasoning cost and improving the model reasoning speed.
Owner:BEIJING UNIV OF TECH

Hardware-Software Co-Design to Accelerate Garbled Circuits

A novel garbled circuit (GC) accelerator and compiler, named HAAC, mitigates performance overheads and makes privacy-preserving computation more practical. HAAC is a hardware-software co-design. GCs are exemplars of co-design as programs are completely known at compile time because all dependence, memory accesses, and control flow are fixed. The compiler can leverage its program understanding to realize hardware's performance potential by generating effective instruction schedules, data layouts, and managing off-chip events. Arbitrary GC programs may be expressed as streams, which simplifies hardware, and the development of an adaptive, on-chip scratchpad that tracks program execution to capture data reuse despite the lack of a regular access pattern or requiring tagging.
Owner:NEW YORK UNIV

Cross-platform program translation method and device

The invention provides a cross-platform program translation method and device, and the method comprises the steps: obtaining a source program used for running on a source platform, converting a parallel built-in variable in the source program into a serial program based on a loop instruction through a large language model, and carrying out the deep learning of the hardware performance of an accelerator according to a target platform, cyclically segmenting the serial program and binding the serial program to a target platform through a built-in parallel variable of the target platform to obtain an input code; checking the storage use condition of the input code, and decorating the storage of the input code according to a preset storage level to obtain an input program; tensor operation existing in the input program is restored into scalar calculation, a tensor operation instruction of the target platform is used for expressing the scalar calculation again, a target program used for running on the target platform is obtained, the deep learning accelerator of the target platform runs the target program, and a running result is obtained.
Owner:INST OF COMPUTING TECH CHINESE ACAD OF SCI

Self-optimizing and self-programming computing systems: a combined compiler, complex networks, and machine learning approach

A self-optimizing and self-programming computing system (SOSPCS) design framework that achieves both programmability and flexibility and exploits computing heterogeneity [e.g., CPUs, GPUs, and hardware accelerators (HWAs)] is provided. First, at compile time, a task pool consisting of hybrid tasks with different processing element (PE) affinities according to target applications is formed. Tasks preferred to be executed on GPUs or accelerators are detected from target applications by neural networks. Tasks suitable to run on CPUs are formed by community detection to minimize data movement overhead. Next, a distributed reinforcement learning-based approach is used at runtime to allow agents to map the tasks onto the network-on-chip-based heterogeneous PEs by learning an optimal policy based on Q values in the environment.
Owner:UNIV OF SOUTHERN CALIFORNIA

Method and system for executing virtual instruction set

The invention discloses a method for executing a virtual instruction set so as to construct an operator library to realize a deep learning accelerator and solve the problem of cross-generation compatibility. The method provides a virtual instruction set execution unit, namely a virtual instruction set, then compiles the virtual instruction set into a vector instruction and / or a dedicated instruction by a compiler, and finally executes the vector instruction and / or the dedicated instruction by the virtual instruction set execution unit. Wherein the virtual instruction set execution unit is used for executing a virtual instruction set and comprises a general vector calculation unit and a special instruction set calculation unit, the general vector calculation unit is used for executing a vector instruction set, and the special instruction set calculation unit is used for executing a special instruction set. The virtual instruction set comprises a first C + + template and a second C + + template, the first C + + template defines a first C + + function, the first C + + function can be compiled by the compiler into vector instructions in the vector instruction set, the second C + + template defines a second C + + function, and the second C + + function can be compiled by the compiler into dedicated instructions in the dedicated instruction set.
Owner:奕行智能科技(广州)有限公司

Acceleration method for accelerating multiplication and addition operation in large language model and hardware accelerator

The invention relates to the technical field of acceleration operation, in particular to an acceleration method for accelerating multiplication and addition operation in a large language model and a hardware accelerator, and the method comprises the following steps: dividing data in the form of m floating-point numbers into a floating-point number block, m being a preset positive integer; performing block floating point coding on the floating-point number block to obtain a shared index and a mantissa of the floating-point number block, and expanding bit widths of the shared index and the mantissa; performing multiplication and addition calculation based on the expanded sharing index and mantissa; the multiply-add calculation result is decoded and restored into a floating-point number form, and a decoding result is obtained; according to the acceleration method for accelerating the multiplication and addition operation in the large language model and the hardware accelerator, relatively high calculation precision can be kept.
Owner:GUANGDONG UNIV OF TECH

Integrated hardware architecture and distribution strategy optimization for deep learning models

A training optimization system implements algorithmic solutions to solve the conjoined problem of accelerator architecture search and model partitioning for distributed training. The system makes the multi-dimensional optimization space of architecture search and device placement tractable by reducing the number of accelerator architectures explored through area-based heuristics and employing a novel integer linear program (ILP), the size of which is dependent only on the number of operators. The ILP scheduling optimization also explores the partitioning of operators across cores, known as intra-operator parallelism. Despite the vast space, the ILP described herein requires significantly less time to perform the optimizations across all explored accelerator configurations. Based on the optimal backward and forward pass latencies, the system leverages a novel dynamic programming (DP) approach to determine the device placement and model partitioning scheme.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Application programming interface to indicate accelerator error handlers

Apparatuses, systems, and techniques to execute one or more application programming interfaces (APIs) to perform one or more operations for one or more accelerators within a heterogeneous processor. In at least one embodiment, one or more processors are to perform one or more instructions in response to one or more APIs to indicate one or more functions to be performed in response to one or more errors from one or more accelerators within a heterogeneous processor.
Owner:NVIDIA CORP

Centralized Acceleration Abstraction Layer for RAN Virtualization

The present application discloses a method for aligning allocation of radio processing operations associated with multiple vRAN nodes (38) to a shared computational resource. In one embodiment, the method includes the steps of invoking, by the vRAN node (38), a virtual operation to request the operation to be accelerated, receiving, by a centralized acceleration abstraction layer, or AAL, broker (36) implemented on top of a shared accelerated computing infrastructure (20), the operation request from the vRAN node (38), selecting, by the AAL broker (36) using a predefined or configurable scheduling policy (37), a physical hardware accelerator (12) for accelerated execution of the requested operation, and forwarding, by the AAL broker (36), the operation request to a processing queue (18) of the selected hardware accelerator (12).
Owner:NEC LAB EURO GMBH

Instruction-level simulation and performance modeling system for parallel computing architecture

The invention provides an instruction-level simulation and performance modeling system for a parallel computing architecture, and belongs to the technical field of computer architecture and simulation verification, and the system comprises an instruction modeling layer which is used for analyzing and executing an intermediate instruction set defined by the architecture; the scheduling execution layer is used for simulating a multi-thread and multi-core parallel execution process; the storage access layer is used for constructing a hierarchical storage access and bandwidth and delay model; and the performance analysis layer is used for collecting and counting key indexes such as an execution period, an instruction utilization rate and memory access delay, and realizing accurate performance modeling of the parallel architecture. According to the method, the performance bottleneck of the design scheme can be rapidly evaluated in the early stage of architecture design, the simulation speed is high, the module configurability is high, the modeling precision is adjustable, and the method is suitable for functional verification, micro-architecture exploration and compiler performance analysis of parallel computing architectures, accelerator chips, heterogeneous multi-core processors and the like.
Owner:YUANQIXIN (SHANDONG) SEMICONDUCTOR TECHNOLOGY CO LTD

Compilation optimization device and method supporting Page Attention and medium

The invention discloses a compiling optimization device and method supporting Page Attention and a medium, and belongs to the field of compiling optimization devices.The device comprises a multi-core AI accelerator, and each calculation core comprises a tensor component, a vector component, a DMA component and an IMM component; the compiling optimization device is optimized through the following modules: (a) a KV Cache management module, which is used for storing page table items corresponding to different KV Cache blocks according to a batch sequence and generating standardized page table items; (b) a DMA control module which supports a linear reading and remapping mode, carries discrete KV Cache blocks from an external memory to an on-chip weight buffer area in a segmented manner according to an index table, and hides data loading delay by adopting a double-buffer technology; and (c) a multi-batch reasoning scheduling module which dynamically allocates computing resources according to the data scale in a code stage. According to the invention, through deep cooperation of a hardware architecture and functional logic, the problems of low KV Cache management efficiency, complex multi-batch dynamic scheduling and insufficient computing resource utilization rate on an ASIC platform are solved.
Owner:BEIJING YIXIN YIYU MICROELECTRONICS TECH CO LTD

Softmax function hardware accelerator based on dynamic pruning and compression lookup table

The invention provides a softmax function hardware accelerator based on dynamic pruning and compression of a lookup table, which retains an input value of an interval near a maximum value through a dynamic pruning method, reduces a to-be-processed data volume and compresses the size of the lookup table, then calculates an e index by using the compressed lookup table, and calculates a reciprocal of summation by using a dynamic Newton iteration method, so as to obtain the softmax function hardware accelerator. And the division method is replaced by multiplication and shift calculation. According to the method, high precision of the softmax function is guaranteed, meanwhile, the calculation amount is remarkably reduced, the hardware overhead is reduced, and the calculation speed of the softmax function is increased.
Owner:SOUTHEAST UNIV

Elliptic curve digital signature verification accelerator based on ARM and FPGA integrated heterogeneous platform

The invention relates to the technical field of integrated circuits, in particular to an elliptic curve digital signature verification accelerator based on an ARM and FPGA integrated heterogeneous platform, which comprises an ARM processor used for executing a software program and connected with the elliptic curve digital signature verification accelerator on the FPGA through an AXI 4 bus interface; wherein the signature verification accelerator comprises a Hash calculation module, a large number reduction module, a public key decoding module and a double scalar multiplication module; the hash calculation module and the large number reduction module calculate and simplify a source operand; the public key decoding module converts operands into coordinates on an elliptic curve; and the double-scalar multiplication module verifies the reliability of the signature and returns a calculation result to the ARM processor, so that a verification task of one-time digital signature is realized. According to the system, the calculation speed of digital signature verification can be accelerated through hardware under limited hardware resource consumption, and the calculation burden of the ARM processor is relieved.
Owner:FUDAN UNIVERSITY

Heterogeneous accelerator uniform interface firmware system and working method thereof

The invention provides a heterogeneous accelerator unified interface firmware system and a working method thereof, and relates to the technical field of computers, the system comprises four modules: a unified interface module which provides a standardized programming interface, shields underlying hardware differences such as a GPU and an NPU, and supports programming models such as OpenCL; the fine-grained task scheduling module is used for decomposing tasks and reasonably distributing the tasks according to task requirements, hardware loads and complexity so as to realize load balancing; the resource management module virtualizes resources of the computing core and the like, and dynamically optimizes multi-task resource allocation; and the expansion support module is used for assisting the integration and drive maintenance of the novel accelerator through a plug-in interface. According to the method, the problems of complex programming, unreasonable task scheduling, low resource utilization efficiency and the like of the heterogeneous accelerator are solved, and the overall performance and development convenience of a heterogeneous computing system are improved.
Owner:HEFEI SUMICROELECTRONICS TECH CO LTD

Compiler for machine learning programs

In variants, a program optimization method can include: receiving a program; determining a set of proxy inputs for the program; generating a set of intermediate traces for the program; and generating a set of execution traces for the program, wherein the set of execution traces can include executor fusions associated with device kernels for hardware accelerators. During runtime, program results can be computed by executing an execution trace instead of executing the program.
Owner:GRID AI INC

Large Language Model-Based Inference Acceleration Method, Medium, And Device

A large language model (LLM)-based inference acceleration method, a medium, and a device are disclosed. The method includes: determining LLMs deployed on a plurality of first hardware accelerators, multiple submodels obtained through segmenting the LLMs and respectively deployed on a plurality of second hardware accelerators, and input data of a to-be-executed task; performing first processing on the input data through the plurality of LLMs to obtain a first processing result; performing second processing on the first processing result through the multiple submodels to obtain a second processing result; and determining an execution result of the to-be-executed task in response to the second processing result meeting a stop inference condition.
Owner:XG TECHNOLOGIES PTE LTD

Multimodal large language model-oriented compiling method and system for generating hardware accelerator executable codes, terminal and storage medium

The invention relates to the technical field of data processing, and discloses a compiling method and system for generating hardware accelerator executable codes facing a multi-mode large language model, a terminal and a storage medium. The method comprises the following steps: constructing a computational graph according to the structure of a to-be-deployed large language model and operators supported by a hardware platform; traversing the computational graph to deduce output tensor type information of each operator, and verifying the type consistency between adjacent operators; based on the verified type information, executing static memory allocation to determine a static storage address of the weight data, and executing dynamic memory allocation to determine a dynamic storage address of the state data; then combining the verified type information and the static and dynamic storage addresses to generate an intermediate representation instruction sequence for configuring a hardware acceleration platform register; and finally, converting the intermediate representation instruction sequence into a target code file which can be directly loaded and executed by a hardware acceleration platform. The compiling efficiency, the deployment reliability and the resource utilization rate are improved.
Owner:SHENZHEN MAITEXIN TECH CO LTD

Heterogenous accelerators for efficient generative LLM inference using phase splitting

A system and method for splitting a prompt and token generation phase in a generative large language model (LLM) inference onto separate virtual machines (VMs) is provided. Two separate pools of VMs for prompt and token processing are maintained. The VMs in each of the pools are pre-loaded with a model of choice. A scheduler allocates an inference to a prompt VM from a pool of prompt VMs and a token VM from a pool of token VMs. Context generated from layers of the generative LLM during the prompt computation is saved in a key-value (KV) cache that is transferred from the prompt VM to token VM as it is used for all the future token generation iterations.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Integrated hardware architecture and distribution strategy optimization for deep learning models

A training optimization system implements algorithmic solutions to solve the conjoined problem of accelerator architecture search and model partitioning for distributed training. The system makes the multi-dimensional optimization space of architecture search and device placement tractable by reducing the number of accelerator architectures explored through area-based heuristics and employing a novel integer linear program (ILP), the size of which is dependent only on the number of operators. The ILP scheduling optimization also explores the partitioning of operators across cores, known as intra-operator parallelism. Despite the vast space, the ILP described herein requires significantly less time to perform the optimizations across all explored accelerator configurations. Based on the optimal backward and forward pass latencies, the system leverages a novel dynamic programming (DP) approach to determine the device placement and model partitioning scheme.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

A dynamic hardware acceleration method and accelerator for a multi-core heterogeneous processor

The application discloses a kind of dynamics hardware acceleration method and accelerator of multi-core heterogeneous processor, it is related to satellite control simulation technical field, this method concentrates multi-body coupling dynamics calculation in programmable logic side of multi-core heterogeneous processor: dynamics processing unit organization input and preloading two-dimensional gravity residual table;Programmable logic side constructs each integration stage state according to Gill type four-order Runge-Kutta integration relationship, sequentially multiplexes geometry and strut force path, gravity path and state differential path in four integration stages, gravity path is analyzed and calculated center gravity and second-order harmonic term on line, and the rest spherical harmonic term residual is obtained by look-up table interpolation and radial compensation;Merging four groups of stage slope obtains the state of next time and calculates relative motion feedback, and complete result is written back and used as the input of next dynamics step.The application reduces hardware complexity and data interaction overhead, improves calculation real-time performance and step-in timing consistency.
Owner:HANGZHOU DIANZI UNIV

Method and system for executing virtual instruction set

The present invention discloses a method for executing a virtual instruction set to build an operator library to realize a deep learning accelerator and solve the problem of cross-generation compatibility. The method provides a virtual instruction set execution unit, that is, a virtual instruction set, and then the compiler compiles the virtual instruction set into vector instructions and / or special instructions, and finally the virtual instruction set execution unit executes the vector instructions and / or special instructions. The virtual instruction set execution unit is used to execute the virtual instruction set, which includes a general vector calculation unit and a special instruction set calculation unit. The general vector calculation unit is used to execute the vector instruction set, and the special instruction set calculation unit is used to execute the special instruction set. The virtual instruction set includes a first C++ template and a second C++ template. The first C++ template defines a first C++ function. The first C++ function can be compiled by the compiler into a vector instruction in the vector instruction set. The second C++ template defines a second C++ function. The second C++ function can be compiled by the compiler into a special instruction in the special instruction set.
Owner:奕行智能科技(广州)有限公司

Application programming interface to indicate accelerator error handlers

Apparatuses, systems, and techniques to execute one or more application programming interfaces (APIs) to perform one or more operations for one or more accelerators within a heterogeneous processor. In at least one embodiment, one or more processors are to perform one or more instructions in response to one or more APIs to indicate one or more functions to be performed in response to one or more errors from one or more accelerators within a heterogeneous processor.
Owner:NVIDIA CORP

A Reinforcement Learning Parallel Processing Accelerator, an Acceleration Method and an Electronic Device

The present invention discloses a reinforcement learning parallel processing accelerator, an acceleration method and an electronic device, which relate to the technical field of accelerators. The controller writes the current view features, at least two groups of batch historical view features and instruction sequences into corresponding memories respectively. The instruction loading and distribution component reads and decodes the instruction sequences and distributes parameters and start calculation instructions to the calculation components. The data loading control component selects the required feature data from the memory according to the parameters of each calculation layer and loads it into the corresponding feature cache. After receiving the start calculation instruction, the calculation components read multiple view feature data simultaneously and perform parallel processing in combination with the parameters, which can greatly improve the data processing efficiency. Through the mutual cooperation of the above components, the characteristics of the reinforcement learning model can be deeply analyzed, and according to different reinforcement learning tasks and data characteristics, the parameters and processing flow can be flexibly adjusted, so as to improve the processing efficiency of the reinforcement learning model, reduce the resource utilization rate of the accelerator at the same time, and have a fast response speed.
Owner:LANGCHAO ELECTRONIC INFORMATION IND CO LTD

VTA acceleration core software and hardware cooperative tuning method and system

The invention discloses a VTA acceleration core software and hardware collaborative tuning method and system, and the method comprises the steps: initializing a hardware design parameter of a multifunctional tensor accelerator to be a default minimum value, and reading a resource utilization rate of an EDA comprehensive report; hardware parameters are dynamically adjusted under the condition that hardware design constraint conditions are met, and the FPGA resource utilization rate is maximized; a tensor shape of a neural network operator is converted according to hardware parameters, and a VTA calculation unit is adapted; analyzing software parameters, and calculating buffer area requirements; verifying the legality of the software parameter according to the buffer area requirement, and judging the software parameter as an illegal software parameter when the buffer area requirement does not meet a set condition; illegal software parameters are triggered to be regenerated, and optimization interruption caused by resource out-of-limit is avoided; a multifunctional tensor accelerator drive program is recompiled for legal hardware parameters; and iteratively executing until the collaborative optimization of the software and hardware parameters reaches the standard. Through a double closed-loop mechanism of hardware parameter dynamic adjustment and software parameter legality verification, the method is suitable for deployment optimization of the compute-intensive model in the power edge equipment.
Owner:CHINA ELECTRIC POWER RESEARCH INSTITUTE CO LTD +2

A large language model quantization method based on orthogonal characteristics and accelerator architecture

The application belongs to the technical field of large language model quantization, and particularly relates to a large language model quantization method based on orthogonal characteristics and an accelerator architecture. The quantization method divides the activation tensor of the large language model into multiple column blocks, and allocates an FP4 quantization format to the entire activation tensor with the column block as the granularity. The concept of the column block is defined as follows: the matrix of the activation tensor is divided into multiple segments with the same number of elements, wherein each element in the segment is arranged continuously in the same row in the first dimension of the matrix, and arranged in multiple continuous columns in the second dimension; the column block includes multiple columns in the second dimension, and the number of columns in each column block is consistent with the number of elements in the segment. The application overcomes the defects existing in the existing large language model grouping quantization technology, and solves the contradiction between the precision of the large language model and the hardware efficiency.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Fluid pulsation accelerator architecture for reinforcement learning of large language model

The invention discloses a fluid pulsation accelerator architecture for reinforcement learning of a large language model, and belongs to the technical field of artificial intelligence hardware acceleration. The system aims at solving the problems that when a current universal processor executes an RLHF working load, an instruction driving normal form is not matched with data flow calculation, fixed parallel granularity cannot adapt to a dynamic load, and the efficiency is low due to the fact that a framework does not sense data statistical characteristics. The core of the system is a liquid systolic array calculation fabric capable of being dynamically reconstructed, execution is triggered through data flow, and kernel boundaries and instruction overhead are eliminated. According to the system, a global lookup table subsystem is fused, and nonlinear calculation is optimized through merging query and parallel lookup by using data distribution prior; and a dynamic scheduling unit is configured, and elastic parallelism is realized by adopting a resource allocation algorithm supporting work stealing. According to the method, the throughput and the energy efficiency of RLHF training and a large language model reasoning stage can be remarkably improved, and a new design normal form is provided for a next-generation AI special computing architecture.
Owner:BEIJING UNIV OF CHEM TECH

Compiler for machine learning programs

In variants, a program optimization method can include: receiving a program; determining a set of proxy inputs for the program; generating a set of intermediate traces for the program; and generating a set of execution traces for the program, wherein the set of execution traces can include executor fusions associated with device kernels for hardware accelerators. During runtime, program results can be computed by executing an execution trace instead of executing the program.
Owner:GRID AI INC

Machine learning model updates to ML accelerators

Examples herein describe a peripheral I / O device having a hybrid gateway that allows the device to have an I / O domain and a coherence domain. Thus, computing resources in the coherence domain of the peripheral I / O device may communicate with the host in a manner similar to CPU-to-CPU communications in the host. Dual domains in a peripheral I / O device may be used for machine learning (ML) applications. Although I / O devices may be used as ML accelerators, these accelerators previously use only I / O domains. In embodiments herein, computing resources may be partitioned between an I / O domain and a coherence domain, with an ML engine in the I / O domain and an ML model in the coherence domain. An advantage doing so is that the ML model can be coherently updated using a reference ML model stored in the host.
Owner:XILINX INC

Accelerating a fully homomorphic encryption (FHE) operation with an on-chip systolic array

Provided are techniques for accelerating a Fully Homomorphic Encryption (FHE) operation with an on-chip systolic array. A computer processing chip comprises an Artificial Intelligence (AI) accelerator comprising a direct memory access and a systolic array, a Level 3 (L3) cache connected to the AI accelerator, and a core connected to the AI accelerator and the L3 cache. The AI accelerator receives AI accelerator code from the core, where the AI accelerator code comprises new instructions, where the systolic array executes the new instructions using first data by executing a BMUL instruction to perform multiplication and generate first results, a BSUB instruction to perform subtraction using the first results to generate second results, and a BADDSUB instruction to perform modular correction on the second results to generate final results, and where the direct memory access prefetches second data for the systolic array.
Owner:INTERNATIONAL BUSINESS MACHINE CORPORATION