Back to Table of contents

Primeur weekly 2020-05-18

Focus

SiPearl's chip will be a platform open to other start-ups to develop accelerators for - An interview with Philippe Notton from SiPearl ...

Exascale supercomputing

Atos launches first supercomputer equipped with NVIDIA A100 GPU ...

Quantum computing

Start of the Fraunhofer Competence Center "Quantum Computing Baden-Württemberg" ...

ADVA brings post-quantum security to packet networks ...

Atos delivers its Quantum Learning Machine to Japan ...

Machine learning cracks quantum chemistry conundrum ...

Making quantum 'waves' in ultrathin materials ...

Seeqc UK awarded GBP 1,8 million in grants to advance quantum computing initiatives ...

Rising investments in quantum technology to boost market growth ...

Total is exploring quantum algorithms to improve CO2 capture ...

Middleware

Mentor Graphics and the University of Basel join the OpenMP effort ...

Hardware

NVIDIA's new Ampere data centre GPU in full production ...

Karlsruhe Institute of Technology procures new supercomputer ...

DDN announces A3I suppport for NVIDIA DGX A100 ...

Yvonne Walker recognized as one of CRN's 2020 Women of the Channel ...

Supermicro expands portfolio with fully integrated NVIDIA A100 GPU-powered systems delivering 5 Petaflop/s of AI performance in a single 4U server ...

Artificial synapses on design ...

Light, fantastic: the path ahead for faster, smaller computer processors ...

OpenFabrics Alliance (OFA) and Gen-Z Consortium announce MoU agreement ...

Tachyum achieves 90 percent of silicon laid for its Prodigy Universal Processor ...

Intel Capital invests $132 million in 11 disruptive technology start-ups ...

Inspur releases five new AI servers powered by NVIDIA A100 Tensor Core GPUs ...

Research and Markets issues Global High-Performance Computing as a Service Market Analysis and Industry Forecasts to 2026 ...

Asperitas and maincubes partner to deliver immersion cooling solutions in dedicated colocation suites ...

Delivery of supercomputer Fugaku completed ...

Applications

Supercomputer simulations help advance electrochemical reaction research ...

3D-printed nuclear reactor promises faster, more economical path to nuclear energy ...

GCS centres support research to mitigate impact of COVID-19 pandemic ...

NIST scientists create new recipe for single-atom transistors ...

ACM service awards recognize leaders who strengthen the computing community ...

New research launched on airborne virus transmission in buildings ...

Seeing the universe through new lenses ...

Liqid delivers industry's fastest single-socket server ...

National Science Foundation grant backs funcX: A smart, automated delegator for computational research ...

Educating the next generation of supercomputer users with Blue Waters ...

The Cloud

Innovium introduces TERALYNX 8, world's highest performance programmable switch for data centre networks with 25,6 Tbps throughput and support for 112 Gbps SerDes I/O ...

Wiwynn unveils standalone rack-level liquid cooling solution for OCP ORV3 at 2020 OCP Virtual Summit ...

Crowd Machine Platform is powered by Oracle Cloud and now available in the Oracle Cloud Marketplace ...

Tachyum achieves 90 percent of silicon laid for its Prodigy Universal Processor


12 May 2020 Santa Clara - Semiconductor start-up Tachyum Inc. has achieved, on schedule, a major milestone in the detailed physical design of its Prodigy Universal Processor. Tachyum now has a complete chip layout, with a verified detailed physical design of more than 90 percent of the design silicon area.

Tachyum's Prodigy is the world's first Universal Processor, combining general-purpose processors, high-performance computing (HPC), artificial intelligence (AI), deep machine learning (ML), explainable AI, bio AI and other AI disciplines within a single chip. This latest milestone achieved integration of key, high-quality Tachyum IP within a multiprocessor environment, and with DDR4/DDR5 DRAM controllers, PCIE 5.0, 112Gb SERDES, USB, GPIO, PLLs and various I/Os. Results of the layout indicate that Prodigy's die size is within product design goals with top-level clocking results that are better than expected.

"Next-generation leading-edge AI CPU SoCs need to integrate high-performance IP solutions that meet a range of specialized processing, memory performance and real-time data connectivity design requirements inclusive of high-speed 112G PAM4 SerDes", stated Rishi Chugh, vice president of product marketing, IP Group at Cadence. "Cadence's best-in-class IP portfolio solutions are silicon proven in advanced process nodes and deliver optimal design productivity, enabling Tachyum to accelerate their development cycle and differentiate in the fast-moving AI market."

"With die size and clock speed both being on target, we are confident in our ability to deliver the world's first universal processor. It will radically improve compute performance and efficiency for data centre, AI and HPC workloads", stated Tachyum CEO Dr. Radoslav Danilak.

Prodigy, the company's 64-core flagship product, is scheduled for high-rate production in 2021. It outperforms the fastest Xeon processors at 10x lower power (core vs. core) on data centre workloads, as well as outperforming NVIDIA's fastest GPU on neural net AI training and inference. Due to its high computational density and I/O bandwidth, networks of Prodigy processors comprising of just 125 HPC racks, can deliver an ExaFLOPS (a billion, billion floating point operations per second) of capacity. Prodigy's 3x lower cost per MIPS, compared to other CPU competition, coupled with its 10x processor power savings translates to a 4x reduction in Data Center TCO (Annual Total Cost of Ownership: CAPEX + OPEX). Even at 50 percent Prodigy attach rates, this translates to billions of dollars per year in real savings for hyperscalers such as Google, Facebook, and Amazon.

Since Prodigy can seamlessly and dynamically switch from data centre workloads to AI or HPC workloads, unused servers can be powered up, on demand, as ad hoc AI or HPC networks - CAPEX free, since the servers themselves are already purchased. Every Prodigy-provisioned data centre, by definition, becomes a low-cost AI center of excellence, and a low-cost HPC system.

Source: Tachyum

Back to Table of contents

Primeur weekly 2020-05-18

Focus

SiPearl's chip will be a platform open to other start-ups to develop accelerators for - An interview with Philippe Notton from SiPearl ...

Exascale supercomputing

Atos launches first supercomputer equipped with NVIDIA A100 GPU ...

Quantum computing

Start of the Fraunhofer Competence Center "Quantum Computing Baden-Württemberg" ...

ADVA brings post-quantum security to packet networks ...

Atos delivers its Quantum Learning Machine to Japan ...

Machine learning cracks quantum chemistry conundrum ...

Making quantum 'waves' in ultrathin materials ...

Seeqc UK awarded GBP 1,8 million in grants to advance quantum computing initiatives ...

Rising investments in quantum technology to boost market growth ...

Total is exploring quantum algorithms to improve CO2 capture ...

Middleware

Mentor Graphics and the University of Basel join the OpenMP effort ...

Hardware

NVIDIA's new Ampere data centre GPU in full production ...

Karlsruhe Institute of Technology procures new supercomputer ...

DDN announces A3I suppport for NVIDIA DGX A100 ...

Yvonne Walker recognized as one of CRN's 2020 Women of the Channel ...

Supermicro expands portfolio with fully integrated NVIDIA A100 GPU-powered systems delivering 5 Petaflop/s of AI performance in a single 4U server ...

Artificial synapses on design ...

Light, fantastic: the path ahead for faster, smaller computer processors ...

OpenFabrics Alliance (OFA) and Gen-Z Consortium announce MoU agreement ...

Tachyum achieves 90 percent of silicon laid for its Prodigy Universal Processor ...

Intel Capital invests $132 million in 11 disruptive technology start-ups ...

Inspur releases five new AI servers powered by NVIDIA A100 Tensor Core GPUs ...

Research and Markets issues Global High-Performance Computing as a Service Market Analysis and Industry Forecasts to 2026 ...

Asperitas and maincubes partner to deliver immersion cooling solutions in dedicated colocation suites ...

Delivery of supercomputer Fugaku completed ...

Applications

Supercomputer simulations help advance electrochemical reaction research ...

3D-printed nuclear reactor promises faster, more economical path to nuclear energy ...

GCS centres support research to mitigate impact of COVID-19 pandemic ...

NIST scientists create new recipe for single-atom transistors ...

ACM service awards recognize leaders who strengthen the computing community ...

New research launched on airborne virus transmission in buildings ...

Seeing the universe through new lenses ...

Liqid delivers industry's fastest single-socket server ...

National Science Foundation grant backs funcX: A smart, automated delegator for computational research ...

Educating the next generation of supercomputer users with Blue Waters ...

The Cloud

Innovium introduces TERALYNX 8, world's highest performance programmable switch for data centre networks with 25,6 Tbps throughput and support for 112 Gbps SerDes I/O ...

Wiwynn unveils standalone rack-level liquid cooling solution for OCP ORV3 at 2020 OCP Virtual Summit ...

Crowd Machine Platform is powered by Oracle Cloud and now available in the Oracle Cloud Marketplace ...