Unlock instant, AI-driven research and patent intelligence for your innovation.

Compact arithmetic accelerator for data processing devices, systems and methods

An accelerator and data technology, applied in the direction of electrical digital data processing, special data processing applications, digital data processing components, etc., can solve problems affecting system battery life, cost and efficiency, etc.

Active Publication Date: 2021-03-09
ATLAZO INC
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although not limited to IoT, the small form factor, ultra-low power consumption, and low cost requirements make the power consumption and physical footprint of associated circuitry critical in IoT applications as they directly affect the battery life, cost, and cost of such systems. efficiency

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Compact arithmetic accelerator for data processing devices, systems and methods
  • Compact arithmetic accelerator for data processing devices, systems and methods
  • Compact arithmetic accelerator for data processing devices, systems and methods

Examples

Experimental program
Comparison scheme
Effect test

example A2

[0147] Example A2 includes the method of example A1 , wherein writing the vector data into the internal memory, computing the vector operation, and writing the output into the system memory is implemented in a pipelined scheme.

[0148] Example A3 includes the method of example A2, wherein the pipelining scheme for processing the vector operation by the accelerator device utilizes fewer clocks than if the vector operation is processed by the data processing unit cycle.

[0149] Example A4 includes the method of example A2, wherein the pipelining of writing the vector data into the internal memory, computing the vector operation, and writing the output into the system memory is performed simultaneously of.

[0150] Example A5 includes the method of Example A1 , wherein the vector operations include one or more of: (i) a signal processing function that includes a Fast Fourier Transform (FFT) and a Finite Impulse Response (FIR ) one or both of the filters; (ii) a linear algebra...

example A6

[0151] Example A6 includes the method of example A1, further comprising, prior to computing, receiving a run command at the accelerator to perform the vector operation.

[0152] Example A7 includes the method of example A1, wherein the command received includes two or more vector operations, and wherein computing each of the two or more vector operations is computed in serial.

[0153] In some embodiments (Example A8) in accordance with the present technology, a data processing accelerator for processing vector operations includes a configuration register for receiving and storing data for a vector from a data processing unit of an electronic system Operation commands and associated information, the associated information includes the read address in the system memory where the vector data is located, the data length of the vector data, and the address in the system memory used to write the output of the vector operation a write address; an address generator configured to gene...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

Disclosed are methods, devices and systems for all-in-one signal processing, linear and non-linear vector arithmetic accelerator. The accelerator, which in some implementations can operate as a companion co-processor and accelerator to a main system, can be configured to perform various linear and non-linear arithmetic operations, and is customized to provide shorter execution times and fewer taskoperations for corresponding arithmetic vector operation, thereby providing an overall energy saving. The compact accelerator can be implemented in devices in which energy consumption and footprint of the electronic circuits are important, such as in Internet of Things (IoT) devices, in sensors and as part of artificial intelligence systems.

Description

[0001] Cross References to Related Applications [0002] This application claims the title "COMPACT SIGNAL PROCESSING, LINEAR AND NON-LINEAR VECTOR ARITHMETIC ACCELERATOR FOR DATA PROCESSING DEVICES, SYSTEMS ANDMETHODS)" and U.S. Provisional Patent Application No. 62 / 614,914, filed January 8, 2018, entitled "COMPACT ARITHMETIC ACCELERATOR FOR DATA PROCESSING DEVICES, SYSTEMS AND METHODS)" U.S. Provisional Patent Application No. 62 / 614,919. The entire content of the above provisional application is incorporated by reference as part of the disclosure of this patent document. technical field [0003] This patent document relates to compact data processing devices, systems and methods. Background technique [0004] The Internet of Things (IoT) is a network of physical devices that may include appliances, vehicles, and other devices with embedded electronics, software, and network connectivity to enable these physical devices to connect and exchange data. Each physical device...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F15/80G06F7/57G06F9/38
CPCG06F17/142G06F7/5443G06F9/3877G06F9/30036G06F15/8061G06F9/3001G06F12/1081G06F7/49947
Inventor S·埃玛拉J·加法里R·阿尔哈基姆
Owner ATLAZO INC