AMD Courts HPC with 11.5 Teraflops Instinct MI100 GPU

By Tiffany Trader

November 16, 2020

AMD today announced the new MI100 Instinct accelerator, billing it as “the world’s fastest HPC GPU” with 11.5 teraflops of peak double-precision floating point performance. A follow on to the MI50 and MI60 Instinct accelerators launched two years ago (the “world’s first 7nm datacenter GPUs”), the MI100 is also manufactured on TSMC’s 7nm process, but boasts twice as many compute units as the previous generation within the same 300-watt power envelope.

Block diagram of the AMD Instinct MI100 accelerator, powered by the AMD CDNA architecture

The MI100 GPU is the first to incorporate AMD’s Compute DNA (CDNA) architecture with 120 CUs organized into four arrays. An evolution of AMD’s earlier GCN architecture, CDNA includes new matrix core engines that boost computational throughput for different numerical formats.

Going down the spec sheet, the MI100 offers 46.1 teraflops peak single-precision matrix (FP32), 23.1 teraflops peak single-precision (FP32), 184.6 teraflops peak half-precision (FP16) floating-point performance, and 92.3 peak teraflops of bfloat16 performance.

The new AMD matrix core technology provides the MI100 with 7x greater peak half-precision floating point performance compared to the MI50, according to AMD. Brad McCredie (corporate vice president of datacenter GPU and accelerated processing at AMD) told HPCwire the company is exploring other emerging numerical formats that target AI and ML workloads, but doesn’t want to get too far out in front of the industry.

AMD’s MI100 GPU presents a competitive alternative to Nvidia’s A100 GPU, rated at 9.7 teraflops of peak theoretical performance. However, the A100 is returning even higher performance than that on its FP64 Linpack runs. (Yes, you heard right.) The A100 GPU is achieving ~12 double-precision Linpack teraflops (see Selene, for example), and Nvidia confirmed to me they use a different double-precision peak for their marketing material and for their Top500 rMax (9.7 versus 15.1 teraflops, respectively).

As new numerical formats optimized for AI/ML gain traction, performance comparisons – already a challenging, if not dark, art – are becoming more confounding. As always the only sound comparisons rest on cost-performance and real-world evaluations for real-world applications. While prices for the MI100 have not been publicly disclosed and Nvidia does not advertise a list price for its A100s, AMD is claiming a 1.8x to 2.1x flops-per-dollar advantage over its competitor.

Fully connected 4-GPU Infinity Fabric technology hives with the AMD Instinct MI100 GPUs

Implementing the second-generation AMD Infinity Fabric Technology, AMD says the MI100 provides ~2x the peer-to-peer peak I/O bandwidth over PCIe 4.0 with up to 340 Gbps of aggregate bandwidth per card. AMD’s bridging device (see graphic) joins four MI100 PCIe cards into a single coherent scale-up solution. In a server, the MI100 GPUs can be configured with up to two integrated quad GPU hives, each providing up to 552 Gbps of peer-to-peer I/O bandwidth, according to AMD.

“We did four cards [fully-linked] because we think that is the sweet spot for HPC deployments, this four-to-one GPU to CPU ratio,” said McCredie.

Four stacks of 8GB HBM2 memory provide 32GB HBM2 memory on each MI100 GPU. At a clock rate of 1.2 GHz, that’s 1.23 Tbps of memory bandwidth. As with the MI50, the MI100’s support for PCIe Gen 4.0 technology enables 64 Gbps peak theoretical transport data bandwidth between CPU and GPU.

AMD said it has no plans for custom mezzanine form factors with this generation – but AMD does see a role for those form factors going forward as you might expect given their exascale wins (Frontier and El Capitan). While detailed node structures have not been publicly disclosed, both of these designs employ a four-to-one GPU to CPU ratio.

Source: AMD Financial Analyst Day slide (March 2020) – link to coverage

HPC market watcher Addison Snell, CEO of Intersect360 Research, remarked on AMD’s HPC focus and the implementation of its datacenter-centric CDNA architecture, distinct from the gaming-oriented RDNA (Radeon DNA) architecture.

“With the MI100 GPU, AMD is staying pure to its corporate focus on HPC,” said Snell. “While Nvidia’s messaging and benchmarking have been AI-heavy, AMD is hitting HPC hard, with 11.5 teraflops of double-precision performance as the marquee stat.”

“AMD is also emphasizing its new CDNA architecture as the focus for computing versus graphics; that’s where we find the GPU-to-GPU communication on the second-generation Infinity architecture.”

Prominent HPC sites Oak Ridge National Laboratory, the University of Pittsburgh and Pawsey Supercomputing Center evaluated the new GPUs along with AMD’s software frameworks. Their reports are positive.

“We’ve received early access to the MI100 accelerator, and the preliminary results are very encouraging. We’ve typically seen significant performance boosts, up to 2-3x compared to other GPUs,” said Bronson Messer, director of science, Oak Ridge Leadership Computing Facility. “What’s also important to recognize is the impact software has on performance. The fact that the ROCm open software platform and HIP developer tool are open source and work on a variety of platforms, it is something that we have been absolutely almost obsessed with since we fielded the very first hybrid CPU/GPU system.”

Oak Ridge National Laboratory: NAMD 2.14, STMV 1.06M atoms benchmark, 2x EPYC 7742 + MI100 vs 2x Power9 + V100 SXM, Cholla, Total Run measured. 2x EPYC 7742 + MI100 vs 2x EPYC 7742 + V100, PIConGPU, Total Run measured. 2x EPYC 7742 + MI100 vs 2x EPYC 7742 + V100, GESTS, Total Run measured, 2x EPYC 7742 + MI100 vs 2x EPYC 7742 + V100 (Source: Oak Ridge and AMD)

AMD is preparing ROCm – its open source toolset consisting of compilers, programming APIs and libraries – to be foundational for exascale computing. The recently released ROCm 4.0 has upgraded the compiler to be open source and unified to support both OpenMP 5.0 and HIP, said AMD. HIP (AMD’s heterogeneous-compute interface for portability) is a C++ runtime API that allows developers to write single-source code that can run on AMD and Nvidia GPUs (and possibly future Intel ones as well).

AMD reported that MI100-based systems will start shipping this month from a number of partners, among them Dell, Gigabyte, Hewlett Packard Enterprise and Supermicro.

 

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

SC21 Was Unlike Any Other — Was That a Good Thing?

December 3, 2021

For a long time, the promised in-person SC21 seemed like an impossible fever dream, the assurances of a prominent physical component persisting across years of canceled conferences, including two virtual ISCs and the virtual SC20. With the advent of the Delta variant, Covid surges in St. Louis and contention over vaccine requirements... Read more…

The Green500’s Crystal Anniversary Sees MN-3 Crystallize Its Winning Streak

December 2, 2021

“This is the 30th Green500,” said Wu Feng, custodian of the Green500 list, at the list’s SC21 birds-of-a-feather session. “You could say 15 years of Green500, which makes it, I guess, the crystal anniversary.” Indeed, HPCwire marked the 15th anniversary of the Green500 – which ranks supercomputers by flops-per-watt, rather than just by flops – earlier this year with... Read more…

AWS Arm-based Graviton3 Instances Now in Preview

December 1, 2021

Three years after unveiling the first generation of its AWS Graviton chip-powered instances in 2018, Amazon Web Services announced that the third generation of the processors – the AWS Graviton3 – will power all-new Amazon Elastic Compute 2 (EC2) C7g instances that are now available in preview. Debuting at the AWS re:Invent 2021... Read more…

Nvidia Dominates Latest MLPerf Results but Competitors Start Speaking Up

December 1, 2021

MLCommons today released its fifth round of MLPerf training benchmark results with Nvidia GPUs again dominating. That said, a few other AI accelerator companies participated and, one of them, Graphcore, even held a separ Read more…

HPC Career Notes: December 2021 Edition

December 1, 2021

In this monthly feature, we’ll keep you up-to-date on the latest career developments for individuals in the high-performance computing community. Whether it’s a promotion, new company hire, or even an accolade, we’ Read more…

AWS Solution Channel

Running a 3.2M vCPU HPC Workload on AWS with YellowDog

Historically, advances in fields such as meteorology, healthcare, and engineering, were achieved through large investments in on-premises computing infrastructure. Upfront capital investment and operational complexity have been the accepted norm of large-scale HPC research. Read more…

At SC21, Experts Ask: Can Fast HPC Be Green?

November 30, 2021

HPC is entering a new era: exascale is (somewhat) officially here, but Moore’s law is ending. Power consumption and other sustainability concerns loom over the enormous systems and chips of this new epoch, for both cost and compliance reasons. Reconciling the need to continue the supercomputer scale-up while reducing HPC’s environmental impacts... Read more…

SC21 Was Unlike Any Other — Was That a Good Thing?

December 3, 2021

For a long time, the promised in-person SC21 seemed like an impossible fever dream, the assurances of a prominent physical component persisting across years of canceled conferences, including two virtual ISCs and the virtual SC20. With the advent of the Delta variant, Covid surges in St. Louis and contention over vaccine requirements... Read more…

The Green500’s Crystal Anniversary Sees MN-3 Crystallize Its Winning Streak

December 2, 2021

“This is the 30th Green500,” said Wu Feng, custodian of the Green500 list, at the list’s SC21 birds-of-a-feather session. “You could say 15 years of Green500, which makes it, I guess, the crystal anniversary.” Indeed, HPCwire marked the 15th anniversary of the Green500 – which ranks supercomputers by flops-per-watt, rather than just by flops – earlier this year with... Read more…

Nvidia Dominates Latest MLPerf Results but Competitors Start Speaking Up

December 1, 2021

MLCommons today released its fifth round of MLPerf training benchmark results with Nvidia GPUs again dominating. That said, a few other AI accelerator companies Read more…

At SC21, Experts Ask: Can Fast HPC Be Green?

November 30, 2021

HPC is entering a new era: exascale is (somewhat) officially here, but Moore’s law is ending. Power consumption and other sustainability concerns loom over the enormous systems and chips of this new epoch, for both cost and compliance reasons. Reconciling the need to continue the supercomputer scale-up while reducing HPC’s environmental impacts... Read more…

Raja Koduri and Satoshi Matsuoka Discuss the Future of HPC at SC21

November 29, 2021

HPCwire's Managing Editor sits down with Intel's Raja Koduri and Riken's Satoshi Matsuoka in St. Louis for an off-the-cuff conversation about their SC21 experience, what comes after exascale and why they are collaborating. Koduri, senior vice president and general manager of Intel's accelerated computing systems and graphics (AXG) group, leads the team... Read more…

Jack Dongarra on SC21, the Top500 and His Retirement Plans

November 29, 2021

HPCwire's Managing Editor sits down with Jack Dongarra, Top500 co-founder and Distinguished Professor at the University of Tennessee, during SC21 in St. Louis to discuss the 2021 Top500 list, the outlook for global exascale computing, and what exactly is going on in that Viking helmet photo. Read more…

SC21: Larry Smarr on The Rise of Supernetwork Data Intensive Computing

November 26, 2021

Larry Smarr, founding director of Calit2 (now Distinguished Professor Emeritus at the University of California San Diego) and the first director of NCSA, is one of the seminal figures in the U.S. supercomputing community. What began as a personal drive, shared by others, to spur the creation of supercomputers in the U.S. for scientific use, later expanded into a... Read more…

Three Chinese Exascale Systems Detailed at SC21: Two Operational and One Delayed

November 24, 2021

Details about two previously rumored Chinese exascale systems came to light during last week’s SC21 proceedings. Asked about these systems during the Top500 media briefing on Monday, Nov. 15, list author and co-founder Jack Dongarra indicated he was aware of some very impressive results, but withheld comment when asked directly if he had... Read more…

IonQ Is First Quantum Startup to Go Public; Will It be First to Deliver Profits?

November 3, 2021

On October 1 of this year, IonQ became the first pure-play quantum computing start-up to go public. At this writing, the stock (NYSE: IONQ) was around $15 and its market capitalization was roughly $2.89 billion. Co-founder and chief scientist Chris Monroe says it was fun to have a few of the company’s roughly 100 employees travel to New York to ring the opening bell of the New York Stock... Read more…

Enter Dojo: Tesla Reveals Design for Modular Supercomputer & D1 Chip

August 20, 2021

Two months ago, Tesla revealed a massive GPU cluster that it said was “roughly the number five supercomputer in the world,” and which was just a precursor to Tesla’s real supercomputing moonshot: the long-rumored, little-detailed Dojo system. Read more…

Esperanto, Silicon in Hand, Champions the Efficiency of Its 1,092-Core RISC-V Chip

August 27, 2021

Esperanto Technologies made waves last December when it announced ET-SoC-1, a new RISC-V-based chip aimed at machine learning that packed nearly 1,100 cores onto a package small enough to fit six times over on a single PCIe card. Now, Esperanto is back, silicon in-hand and taking aim... Read more…

US Closes in on Exascale: Frontier Installation Is Underway

September 29, 2021

At the Advanced Scientific Computing Advisory Committee (ASCAC) meeting, held by Zoom this week (Sept. 29-30), it was revealed that the Frontier supercomputer is currently being installed at Oak Ridge National Laboratory in Oak Ridge, Tenn. The staff at the Oak Ridge Leadership... Read more…

AMD Launches Milan-X CPU with 3D V-Cache and Multichip Instinct MI200 GPU

November 8, 2021

At a virtual event this morning, AMD CEO Lisa Su unveiled the company’s latest and much-anticipated server products: the new Milan-X CPU, which leverages AMD’s new 3D V-Cache technology; and its new Instinct MI200 GPU, which provides up to 220 compute units across two Infinity Fabric-connected dies, delivering an astounding 47.9 peak double-precision teraflops. “We're in a high-performance computing megacycle, driven by the growing need to deploy additional compute performance... Read more…

Intel Reorgs HPC Group, Creates Two ‘Super Compute’ Groups

October 15, 2021

Following on changes made in June that moved Intel’s HPC unit out of the Data Platform Group and into the newly created Accelerated Computing Systems and Graphics (AXG) business unit, led by Raja Koduri, Intel is making further updates to the HPC group and announcing... Read more…

Intel Completes LLVM Adoption; Will End Updates to Classic C/C++ Compilers in Future

August 10, 2021

Intel reported in a blog this week that its adoption of the open source LLVM architecture for Intel’s C/C++ compiler is complete. The transition is part of In Read more…

Killer Instinct: AMD’s Multi-Chip MI200 GPU Readies for a Major Global Debut

October 21, 2021

AMD’s next-generation supercomputer GPU is on its way – and by all appearances, it’s about to make a name for itself. The AMD Radeon Instinct MI200 GPU (a successor to the MI100) will, over the next year, begin to power three massive systems on three continents: the United States’ exascale Frontier system; the European Union’s pre-exascale LUMI system; and Australia’s petascale Setonix system. Read more…

Leading Solution Providers

Contributors

Hot Chips: Here Come the DPUs and IPUs from Arm, Nvidia and Intel

August 25, 2021

The emergence of data processing units (DPU) and infrastructure processing units (IPU) as potentially important pieces in cloud and datacenter architectures was Read more…

D-Wave Embraces Gate-Based Quantum Computing; Charts Path Forward

October 21, 2021

Earlier this month D-Wave Systems, the quantum computing pioneer that has long championed quantum annealing-based quantum computing (and sometimes taken heat fo Read more…

HPE Wins $2B GreenLake HPC-as-a-Service Deal with NSA

September 1, 2021

In the heated, oft-contentious, government IT space, HPE has won a massive $2 billion contract to provide HPC and AI services to the United States’ National Security Agency (NSA). Following on the heels of the now-canceled $10 billion JEDI contract (reissued as JWCC) and a $10 billion... Read more…

The Latest MLPerf Inference Results: Nvidia GPUs Hold Sway but Here Come CPUs and Intel

September 22, 2021

The latest round of MLPerf inference benchmark (v 1.1) results was released today and Nvidia again dominated, sweeping the top spots in the closed (apples-to-ap Read more…

Ahead of ‘Dojo,’ Tesla Reveals Its Massive Precursor Supercomputer

June 22, 2021

In spring 2019, Tesla made cryptic reference to a project called Dojo, a “super-powerful training computer” for video data processing. Then, in summer 2020, Tesla CEO Elon Musk tweeted: “Tesla is developing a [neural network] training computer... Read more…

Three Chinese Exascale Systems Detailed at SC21: Two Operational and One Delayed

November 24, 2021

Details about two previously rumored Chinese exascale systems came to light during last week’s SC21 proceedings. Asked about these systems during the Top500 media briefing on Monday, Nov. 15, list author and co-founder Jack Dongarra indicated he was aware of some very impressive results, but withheld comment when asked directly if he had... Read more…

2021 Gordon Bell Prize Goes to Exascale-Powered Quantum Supremacy Challenge

November 18, 2021

Today at the hybrid virtual/in-person SC21 conference, the organizers announced the winners of the 2021 ACM Gordon Bell Prize: a team of Chinese researchers leveraging the new exascale Sunway system to simulate quantum circuits. The Gordon Bell Prize, which comes with an award of $10,000 courtesy of HPC pioneer Gordon Bell, is awarded annually... Read more…

Quantum Computer Market Headed to $830M in 2024

September 13, 2021

What is one to make of the quantum computing market? Energized (lots of funding) but still chaotic and advancing in unpredictable ways (e.g. competing qubit tec Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire