Heterogeneous computing

Samsung Unveils Industry-First Memory Module Incorporating New CXL Interconnect Standard

Retrieved on: 
Tuesday, May 11, 2021
Hardware, Consumer electronics, Technology, Telecommunications, Software, Human–computer interaction, Distributed computing architecture, Compute Express Link, Peripheral Component Interconnect, CXL, Heterogeneous computing, Wearable technology, Bus, Computing

b'Samsung Electronics Co., Ltd., the world leader in advanced memory technology, today unveiled the industry\xe2\x80\x99s first memory module supporting the new Compute Express Link (CXL) interconnect standard.

Key Points: 
  • b'Samsung Electronics Co., Ltd., the world leader in advanced memory technology, today unveiled the industry\xe2\x80\x99s first memory module supporting the new Compute Express Link (CXL) interconnect standard.
  • View the full release here: https://www.businesswire.com/news/home/20210511005518/en/\nSamsung Unveils Industry-First Memory Module Incorporating New CXL Interconnect Standard (Photo: Business Wire)\nThe rise of AI and big data has been fueling the trend toward heterogeneous computing, where multiple processors work in parallel to process massive volumes of data.
  • The company is redefining the worlds of TVs, smartphones, wearable devices, tablets, digital appliances, network systems, and memory, system LSI, foundry and LED solutions.
  • For the latest news, please visit the Samsung Newsroom at http://news.samsung.com .\nView source version on businesswire.com: https://www.businesswire.com/news/home/20210511005518/en/\n'

MulticoreWare Inc. Joins Analog Devices, Inc.’s (ADI) Alliances Partner Program

Retrieved on: 
Tuesday, March 16, 2021
Semiconductor, Hardware, Electronic design automation, Technology, Software, Computing, MulticoreWare, Technology, Computer engineering, Computer architecture, Microprocessors, Digital signal processors, Multi-core processor, Blackfin, Heterogeneous computing

MulticoreWare has been providing optimized solutions for various processing platforms with our expertise in Heterogeneous Computing, Micro-Architecture aware optimizations combined with Deep Neural networks expertise.

Key Points: 
  • MulticoreWare has been providing optimized solutions for various processing platforms with our expertise in Heterogeneous Computing, Micro-Architecture aware optimizations combined with Deep Neural networks expertise.
  • Blackfin processors leverage the optimizations implemented by MulticoreWare will provide solutions for a variety of applications: video surveillance, robotics, and real-time security.
  • The collaboration between ADI and MulticoreWare, will open doors to target new opportunities for applications involving Human Behaviour Detection and Recognition, Face Detection.
  • ADIs Alliances partner program offers designers worldwide access to a broad spectrum of ADI technologies and industry expertise.

AMD EPYC™ Processors and New AMD Instinct™ MI100 Accelerator Redefine Performance for HPC and Scientific Research

Retrieved on: 
Monday, November 16, 2020
Computer architecture, GPGPU, Heterogeneous computing, Computing, Epyc, Advanced Micro Devices, Graphics processing unit, AMD Accelerated Processing Unit, Zen

It launched the new AMD Instinct MI100 accelerator with ROCm 4.0 open ecosystem support and showcased a growing list of AMD EPYC CPU and AMD Instinct accelerator based deployments, and highlighted its collaboration with Microsoft Azure for HPC in the cloud.

Key Points: 
  • It launched the new AMD Instinct MI100 accelerator with ROCm 4.0 open ecosystem support and showcased a growing list of AMD EPYC CPU and AMD Instinct accelerator based deployments, and highlighted its collaboration with Microsoft Azure for HPC in the cloud.
  • Built on the new AMD CDNA architecture , the AMD Instinct MI100 GPU enables a new class of accelerated systems for HPC and AI when paired with 2nd Gen AMD EPYC processors.
  • Combining AMD EPYC processors and Instinct accelerators with critical application software and development tools enables AMD to deliver leadership performance for HPC workloads.
  • Designed to complement the 2nd Gen AMD EPYC processors, and built on the AMD Infinity Architecture, the AMD Instinct MI100 delivers true heterogeneous compute capabilities from AMD for HPC and AI.

ArcherMind Unveils New EX 4.0 Automotive Cockpit Solution Powered by Qualcomm Snapdragon Automotive Cockpit Platforms at CES 2020

Retrieved on: 
Wednesday, January 8, 2020
Qualcomm, Fabless semiconductor companies, Electronics, Computer architecture, ARM architecture, Gesture recognition, Qualcomm Snapdragon, System on a chip, Technology, Heterogeneous computing, Consumer Electronics Show, Adreno

LAS VEGAS, Jan. 7, 2020 /PRNewswire/ --ArcherMind, a leading software technology provider, unveiled the company's new EX4.0 Automotive Cockpit Solution today.

Key Points: 
  • LAS VEGAS, Jan. 7, 2020 /PRNewswire/ --ArcherMind, a leading software technology provider, unveiled the company's new EX4.0 Automotive Cockpit Solution today.
  • The 3rd generation Snapdragon Automotive Cockpit Platforms feature integrated heterogeneous computing, high-performance artificial intelligence (AI) capabilities, and scalability with a unified software framework.
  • ArcherMind also provides professional technical support as a scaling partner for automakers and Tier 1 suppliers to work on the latest Snapdragon Automotive Cockpit Platforms.
  • Qualcomm Snapdragon is a product of Qualcomm Technologies, Inc.
    View original content to download multimedia: http://www.prnewswire.com/news-releases/archermind-unveils-new-ex-4-0-au...
    SOURCE ArcherMind Technology (Nanjing) Co., Ltd.

Centaur Demonstrates Industry’s First High-Performance x86 SoC with Server-Class CPUs and Integrated AI Coprocessor Technology

Retrieved on: 
Monday, November 18, 2019
Networks, Semiconductor, Hardware, Data management, Technology, Computer architecture, Digital technology, Computing, Application-specific integrated circuits, Instruction set architectures, Central processing unit, Coprocessor, Heterogeneous computing, AI accelerator, x86, Microprocessor, System on a chip

Centaurs system-on-a-chip (SoC) technology allows users to save substantial cost and power over systems that require both an x86 host processor and external AI accelerators.

Key Points: 
  • Centaurs system-on-a-chip (SoC) technology allows users to save substantial cost and power over systems that require both an x86 host processor and external AI accelerators.
  • Linley Gwennap, Editor-in-Chief, Microprocessor Report, confirms Centaurs achievement, Centaur Technology is the first to announce an x86 processor design that integrates a specialized coprocessor to accelerate deep learning.
  • This coprocessor delivers greater AI performance than any CPU and frees the x86 cores to focus on general-purpose tasks that continue to require x86 compatibility.
  • Glenn Henry, an industry luminary from IBM and Dell before founding Centaur Technology almost 25 years ago, is the chief architect of Centaurs AI coprocessor.

AI Hardware Asia Summit: Chinese and US AI Heavyweights to Meet at AI in Beijing, 4-5 June 2019

Retrieved on: 
Friday, April 26, 2019
Technology, Data management, Hardware, Software, Telecommunications, Professional services, Finance, Computer architecture, Computing, Digital technology, OpenCL compute devices, Peripheral Component Interconnect, Central processing unit, Coprocessor, Heterogeneous computing, Field-programmable gate array, PCI Express

Flex Logix , an established FPGA company that are targeting inference workloads in edge environments, announced their new inference coprocessor: the InferX X1.

Key Points: 
  • Flex Logix , an established FPGA company that are targeting inference workloads in edge environments, announced their new inference coprocessor: the InferX X1.
  • It combines the eFPGA tech with inference-optimized nnMAX clusters in the new combination chip.
  • InferX X1 will be available as chips for edge devices and on half-height, half-length PCIe cards for edge servers and gateways.
  • White Paper on AI Chip Technologies: Tsing Hua University & Beijing Innovation Center for Future Chips, December 2018.

ADLINK to Showcase Plug-and-Play AI and Edge Computing Solutions at 2019 GPU Technology Conference

Retrieved on: 
Thursday, March 14, 2019
Computer architecture, Technology, Computing, GPGPU, ADLINK, Graphics hardware, Coprocessors, Video cards, Application-specific integrated circuits, Nvidia, Heterogeneous computing, Edge computing

SAN JOSE, Calif., March 14, 2019 ADLINK Technology, Inc., a global provider of advanced edge computing products, will showcase a series of plug-and-play AI and heterogeneous computing platforms at the GPU Technology Conference (GTC), March 18-21, 2019, at the San Jose McEnery Convention Center in Booth #317 and Booth #1749 in the Jetson Pavilion.

Key Points: 
  • SAN JOSE, Calif., March 14, 2019 ADLINK Technology, Inc., a global provider of advanced edge computing products, will showcase a series of plug-and-play AI and heterogeneous computing platforms at the GPU Technology Conference (GTC), March 18-21, 2019, at the San Jose McEnery Convention Center in Booth #317 and Booth #1749 in the Jetson Pavilion.
  • With intelligence moving to the edge, ADLINK's heterogeneous computing platforms with plug-and-play AI can perform real-time streaming of data between edge devices and systems, enabling faster and better decision-making.
  • ADLINK will showcase its plug-and-play AI and heterogeneous computing platforms for edge applications at GTC Booth #317, including:
    A portfolio of heterogeneous computing platforms and configurable industrial PCs with NVIDIA Quadro embedded solutions optimized for AI at the edge.
  • ADLINK Technology is a global leader of Edge Computing with a mission to reduce the complexity of building IIoT systems.

CEVA Announces CEVA-BX, a New All-Purpose Hybrid DSP / Controller Architecture for Digital Signal Processing and Digital Signal Control in IoT devices

Retrieved on: 
Friday, January 4, 2019
Computer architecture, Digital signal processors, Central processing unit, Coprocessor, Heterogeneous computing, Digital signal processing, CEVA, Inc.

CEVA-BX offers a new breed of DSP architecture, combining the inherent low power requirements of DSP kernels with the high-level programming and compact code size requirements of a large control code base.

Key Points: 
  • CEVA-BX offers a new breed of DSP architecture, combining the inherent low power requirements of DSP kernels with the high-level programming and compact code size requirements of a large control code base.
  • Processing these heavy-duty signal-processing workloads in edge devices requires an efficient combination of control and DSP capabilities.
  • The CEVA-BX eliminates the need for separate CPUs and DSP coprocessors, employing a hybrid architecture that delivers excellent all-round performance for smart devices."
  • CEVA is the leading licensor of signal processing platforms and artificial intelligence processors for a smarter, connected world.

HSA Foundation China Regional Committee & China Standard Group of Heterogeneous System Technical Symposium to Be Held in Hunan

Retrieved on: 
Tuesday, May 22, 2018
Computer architecture, Heterogeneous System Architecture, Heterogeneous computing, HSA, GPGPU, Fabless semiconductor companies, Parallel computing, HSA Foundation

2018 Working Objectives and Execution Plan for the CRC - Dr. Xiaodong Zhang, Chair of the CRC (30 minutes)

Key Points: 
  • 2018 Working Objectives and Execution Plan for the CRC - Dr. Xiaodong Zhang, Chair of the CRC (30 minutes)
    Recommendations for Implementation of Variable-Length Vector Parallel Computing in Heterogeneous Computing Standards - Dr. Lei Wang, Huaxia (Beijing) General Processor Technologies (30 minute)
    Recommendations for Heterogeneous Computing Instruction Architecture for Convolutional Neural Network Parallel Computing - Dr. Jun Han, State Key Laboratory of ASIC, Fudan University (30 minutes)
    Recommendations for Software-Defined Radio Instruction Architecture based on Heterogeneous Computing Standards - Dr. Chaoyang Tian, Jiangsu Research Center of Software Digital Radio(30 minutes)
    Several Enhancements to Security and Protection Strategies for Heterogeneous Computing Systems - Shaowei Chen, Senior Expert, Nationz Technologies (30 minutes)
    Recommendations for New Heterogeneous Computing Network Interconnection Specification Compatible with International Mainstream Standards - Dr. Zhiyi Yu, Sun Yat-sen University (30 minutes)
    The HSA (Heterogeneous System Architecture) Foundation is a non-profit consortium of SoC IP vendors, OEMs, Academia, SoC vendors, OSVs and ISVs, whose goal is making programming for parallel computing easy and pervasive.
  • HSA members are building a heterogeneous computing ecosystem, rooted in industry standards, which combines scalar processing on the CPU with parallel processing on the GPU, while enabling high bandwidth access to memory and high application performance with low power consumption.
  • HSA defines interfaces for parallel computation using CPU, GPU and other programmable and fixed function devices, while supporting a diverse set of high-level programming languages, and creating the foundation for next-generation, general-purpose computing.
  • View original content with multimedia: http://www.prnewswire.com/news-releases/hsa-foundation-china-regional-co...