Coprocessors

NEC SX-Aurora TSUBASA vector supercomputer sets record in processing performance in STAC-A2 Benchmarks

Retrieved on: 
Friday, July 16, 2021
Concurrent computing, Parallel computing, Computing, Coprocessors, NEC SX, NEC, Vector processor, SX, Supercomputer, STAC, NEC SX-ACE

TOKYO, July 16, 2021 - (JCN Newswire) - NEC Corporation (TSE: 6701) today announced that the NEC SX-Aurora TSUBASA vector supercomputer set a record in the STAC-A2 Benchmark tests, which measure the computational performance of Monte Carlo-based risk simulations common in financial markets.

Key Points: 
  • TOKYO, July 16, 2021 - (JCN Newswire) - NEC Corporation (TSE: 6701) today announced that the NEC SX-Aurora TSUBASA vector supercomputer set a record in the STAC-A2 Benchmark tests, which measure the computational performance of Monte Carlo-based risk simulations common in financial markets.
  • *
    In recent years, as the digitization of financial transactions has progressed, the amount of data being processed has increased exponentially.
  • Based on the results of the STAC-A2, NEC aims to use SX-Aurora TSUBASA to help improve the fairness and reliability of financial markets.
  • Moreover, the system is specialized for high-speed processing of large-scale data using NEC's unique vector processors, making it ideal for contributing to financial markets.

Data Center Accelerator Market worth $65.3 billion by 2026 - Exclusive Report by MarketsandMarkets™

Retrieved on: 
Thursday, July 15, 2021
Computing, Concurrent computing, Technology, Coprocessors, Data management, Technology forecasting, Nvidia, Artificial intelligence, Big data, AI accelerator

The key factors contributing to the growth of the data center accelerator market include growth of cloud-based services, focus on parallel computing in AI data center and deep learning usage in big data analytics, However, The burgeoning application of AI in various sectors has enhanced consumer perception and expectations from AI technologies.

Key Points: 
  • The key factors contributing to the growth of the data center accelerator market include growth of cloud-based services, focus on parallel computing in AI data center and deep learning usage in big data analytics, However, The burgeoning application of AI in various sectors has enhanced consumer perception and expectations from AI technologies.
  • Various AI technologies built to date have failed to make a larger impact in the AI market.
  • For instance, owing to the high cost of data center accelerators such as NVIDIA Tesla products, a majority of data center manufacturers are reluctant about adopting those accelerators in their products.
  • With the exponential data growth, data center operators have to establish a balance between the need for the performance at scale and the operational efficiencies.

Data Center Accelerator Market worth $65.3 billion by 2026 - Exclusive Report by MarketsandMarkets™

Retrieved on: 
Thursday, July 15, 2021
Computing, Concurrent computing, Technology, Coprocessors, Data management, Technology forecasting, Nvidia, Artificial intelligence, Big data, AI accelerator

The key factors contributing to the growth of the data center accelerator market include growth of cloud-based services, focus on parallel computing in AI data center and deep learning usage in big data analytics, However, The burgeoning application of AI in various sectors has enhanced consumer perception and expectations from AI technologies.

Key Points: 
  • The key factors contributing to the growth of the data center accelerator market include growth of cloud-based services, focus on parallel computing in AI data center and deep learning usage in big data analytics, However, The burgeoning application of AI in various sectors has enhanced consumer perception and expectations from AI technologies.
  • Various AI technologies built to date have failed to make a larger impact in the AI market.
  • For instance, owing to the high cost of data center accelerators such as NVIDIA Tesla products, a majority of data center manufacturers are reluctant about adopting those accelerators in their products.
  • With the exponential data growth, data center operators have to establish a balance between the need for the performance at scale and the operational efficiencies.

Inspur Releases Liquid Cooled AI Server With NVIDIA A100 GPUs at ISC High Performance Digital 2021

Retrieved on: 
Monday, June 28, 2021
Networks, Internet, Hardware, Electronic design automation, Data management, Consumer electronics, Technology, Other Technology, Computing, Computer engineering, Technology, GPGPU, Fabless semiconductor companies, Application-specific integrated circuits, Graphics hardware, Coprocessors, Nvidia, Inspur, Graphics processing unit, Advanced Micro Devices

Today at ISC High Performance 2021 Digital , the event for high performance computing, machine learning, and data analytics, Inspur Information, a leading IT infrastructure solution provider, announces its new liquid cooling AI server, NF5488LA5.

Key Points: 
  • Today at ISC High Performance 2021 Digital , the event for high performance computing, machine learning, and data analytics, Inspur Information, a leading IT infrastructure solution provider, announces its new liquid cooling AI server, NF5488LA5.
  • NF5488LA5 is equipped with two AMD EYPC 7003 series processors and eight NVIDIA A100 Tensor GPUs in a 4U chassis fully connected by NVSwitch.
  • The system topology adopts an ultra-low latency design to maximize the communication performance between the processor and the AI accelerator.
  • It is also the only GPU server submitted that ran the NVIDIA A100 GPU at 500W TDP via liquid cooling technology.

NEC Earns Acclaim from Frost & Sullivan for Adopting a Vector-based Approach to High-performance Computing with its SX-Aurora TSUBASA

Retrieved on: 
Monday, March 22, 2021
Parallel computing, Coprocessors, Computing, Companies, Computer architecture, Central processing unit, Vector processor, NEC SX-Aurora TSUBASA, SX, NEC

SX-Aurora TSUBASA's pioneering vector-based architecture, reliable performance, and low-latency processing help end-users tackle frontline computational challenges.

Key Points: 
  • SX-Aurora TSUBASA's pioneering vector-based architecture, reliable performance, and low-latency processing help end-users tackle frontline computational challenges.
  • "The next-generation SX-Aurora TSUBASAHPC solution is designed to meet the requirements of the entire vector engine for processing.
  • "Its vector processing unit carries a single-thread per core processing architecture, unlike competing products that employ multiple threads.
  • "NEC aims to break traditional computing barriers by accelerating HPC's adoption in industrial and energy market applications.

NEC Earns Acclaim from Frost & Sullivan for Adopting a Vector-based Approach to High-performance Computing with its SX-Aurora TSUBASA

Retrieved on: 
Monday, March 22, 2021
Parallel computing, Coprocessors, Computing, Companies, Computer architecture, Central processing unit, Vector processor, NEC SX-Aurora TSUBASA, SX, NEC

SX-Aurora TSUBASA's pioneering vector-based architecture, reliable performance, and low-latency processing help end-users tackle frontline computational challenges.

Key Points: 
  • SX-Aurora TSUBASA's pioneering vector-based architecture, reliable performance, and low-latency processing help end-users tackle frontline computational challenges.
  • "The next-generation SX-Aurora TSUBASAHPC solution is designed to meet the requirements of the entire vector engine for processing.
  • "Its vector processing unit carries a single-thread per core processing architecture, unlike competing products that employ multiple threads.
  • "NEC aims to break traditional computing barriers by accelerating HPC's adoption in industrial and energy market applications.

AWS Leverages Habana Gaudi AI Processors

Retrieved on: 
Tuesday, December 1, 2020
Semiconductor, Data management, Technology, Software, Internet, Hardware, Computing, Computer architecture, Computer engineering, Coprocessors, AI accelerator, Computer optimization, Intel, Amazon Web Services, Xeon

View the full release here: https://www.businesswire.com/news/home/20201201006008/en/

Key Points: 
  • View the full release here: https://www.businesswire.com/news/home/20201201006008/en/
    A photo shows Habana Labs' HL-205 Gaudi Mezzanine Card.
  • (Credit: Habana Labs)
    We are proud that AWS has chosen Habana Gaudi processors for its forthcoming EC2 training instances.
  • How It Fits in Intels AI and XPU Vision: Intel acquired Habana in 2019 to advance its AI strategy and strengthen its portfolio of AI accelerators for the cloud and data center.
  • Cloud providers today are broadly using the built-in AI performance of our Intel Xeon processors to tackle AI inference workloads.

NEC to Launch PCIe-based Vector Engine Card to Explore New Opportunities in the SME Market

Retrieved on: 
Friday, November 20, 2020
Concurrent computing, Parallel computing, Coprocessors, NEC SX-Aurora TSUBASA, NEC, FLOPS, Supercomputer, NEC SX-ACE

TOKYO, Nov 20, 2020 - (JCN Newswire) - NEC Corporation (TSE: 6701) today announced the global launch of a PCIe-based Vector Engine card (Vector Engine) to tap into the growing demand for High Performance Computing (HPC) from Small and Medium-sized Enterprises (SMEs).

Key Points: 
  • TOKYO, Nov 20, 2020 - (JCN Newswire) - NEC Corporation (TSE: 6701) today announced the global launch of a PCIe-based Vector Engine card (Vector Engine) to tap into the growing demand for High Performance Computing (HPC) from Small and Medium-sized Enterprises (SMEs).
  • The Vector Engine is the core component of NEC's SX-Aurora TSUBASA vector supercomputer, which has been deployed to more than 100 customers worldwide since 2018.
  • The Vector Engine provides a 2.45 TeraFlops computation capability and a 1.53 TeraBytes/second memory bandwidth with around 200W power consumption for processing scientific applications.
  • Sourcing the Vector Engine from NEC allows system integrators to offer vector computing systems by combining the Vector Engine and general x86 servers from other IT vendors while enabling server manufacturers to develop and market their own-branded vector computing servers using the Vector Engine.

Synopsys Helps Advance IBM's Vision of 1,000 Times Improvement in AI Compute Performance during the Coming Decade

Retrieved on: 
Wednesday, October 21, 2020
Computing, Computer engineering, Articles, Cloud infrastructure, Application-specific integrated circuits, AI accelerator, Computer optimization, Coprocessors, Cloud computing, Artificial intelligence

Synopsys is working closely with IBM to implement the latest AI Hardware Center technologies in full chip solutions, which could be commercialized in the near future.

Key Points: 
  • Synopsys is working closely with IBM to implement the latest AI Hardware Center technologies in full chip solutions, which could be commercialized in the near future.
  • The overarching goal of the work with IBM is to achieve a continued trend of annual doubling of the AI compute performance for a decade or more.
  • "To achieve this, we need to build a new class of AI hardware accelerators that increase compute power without the demand for more energy.
  • Additionally, developing new AI chip architectures will enable companies to dynamically run large AI workloads in the hybrid cloud.

Gyrfalcon Showcases New Tech at 2020 Embedded Vision Summit

Retrieved on: 
Tuesday, September 15, 2020
Articles, Science and technology, Computing, Application-specific integrated circuits, Computational neuroscience, AI accelerator, Computer optimization, Coprocessors, Artificial intelligence, Vision

MILPITAS, Calif., Sept. 15, 2020 /PRNewswire/ -- Gyrfalcon Technology (GTI) today announced it is showcasing enhancements to its Lightspeeur portfolio at 2020 Embedded Vision Summit , the premier event for innovators adding computer vision and Artificial Intelligence (AI)to products.

Key Points: 
  • MILPITAS, Calif., Sept. 15, 2020 /PRNewswire/ -- Gyrfalcon Technology (GTI) today announced it is showcasing enhancements to its Lightspeeur portfolio at 2020 Embedded Vision Summit , the premier event for innovators adding computer vision and Artificial Intelligence (AI)to products.
  • Gyrfalcon technology provides processing power for AI and ML workloads for almost every application, from machine-to-machine/human visions to voice interface.
  • The Embedded Vision Summit is the only event focused exclusively on deployable computer vision and visual AI.
  • Gyrfalcon Technology Inc. (GTI) is the world's leading developer of high-performance AI Accelerators that use low power, packaged in low-cost and small-sized chips.