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

By Oliver Peckham

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. “We’ve been scaling our neural network training compute dramatically over the last few years,” said Milan Kovac, Tesla’s director of autopilot engineering. “Today, we’re barely shy of ten thousand GPUs. … But that’s not enough.”

Enter Dojo, the design for which was revealed during Tesla’s AI Day event, along with the design for its constituent D1 chip.

Dreaming of Dojo

“There’s an insatiable demand for speed, as well as capacity, for neural network training,” said Ganesh Venkataramanan, Tesla’s senior director for autopilot hardware. To that end, a few years ago, Tesla CEO and co-founder Elon Musk asked Venkataramanan’s team to build the company a “super-fast” training computer, aiming to achieve the best AI training performance, enable larger and more complex neural net models and achieve both power efficiency and cost efficiency.

“For Dojo, we envisioned a large compute plane filled with very robust compute elements, packed with a large pool of memory, and interconnected with very high-bandwidth and low-latency fabric,” Venkataramanan said. “We wanted to attack this all the way – top to bottom of the stack – and remove all the bottlenecks at any of these levels.”

Tesla’s D1 chip. Image courtesy of Tesla.

The D1 chip & training tile

The aforementioned precursor cluster relied predominantly on Nvidia’s A100 GPUs for acceleration. Not so for Dojo, which will consist almost entirely of Tesla’s decidedly unique D1 chip. D1, Venkataramanan said, supported FP32, BFP16 (aka bfloat16 or brain floating point) and a new format called CFP8 (“configurable FP8”). Optimized for machine learning workloads, D1 (which consists of 354 “training nodes”) is manufactured using a 7nm process and, at just 645 square millimeters, contains 50 billion transistors. “There is no dark silicon, there is no legacy support,” Venkataramanan said of the chip, designed completely by Tesla’s internal engineers. “This is a pure machine learning machine. … This chip [has] GPU-level compute with CPU-level flexibility.”

The integrated training tile, which contained 25 D1 chips. Image courtesy of Tesla.

Tesla put a strong emphasis on modularity across the hardware. D1 is equipped with 4TBps off-chip bandwidth on each of its lateral edges – all four equipped with connectors – allowing it to connect to and scale with other D1 chips without sacrificing speed.

The next step up is Tesla’s “training tile,” a wedge less than a cubic foot in size that contains 25 of the D1 chips. The training tile operates with similar modularity to the chip itself: power and cooling are conducted through the top of the tile, allowing its four lateral edges to be outfitted with high-output connectors designed for maximum bandwidth (a total of 36TB/s of off-tile bandwidth).

Dojo

“By now, you must have realized our modularity story is pretty strong,” Venkataramanan said. “We just put together some tiles. We just tile together tiles!” And, indeed, it’s modularity all the way down: 354 training nodes make a D1 chip; 25 D1s in a training tile; six training tiles (2×3) in a “training matrix,” which constitutes a tray; two trays in a cabinet; and ten cabinets in what Venkataramanan calls the ExaPOD, a massive machine learning machine with uniform bandwidth. (How many ExaPODs Dojo will contain is unclear.)

Details on the ExaPOD. Image courtesy of Tesla.

With each D1 chip providing 22.6 teraflops of FP32 performance, each training tile will provide 565 teraflops and each cabinet (containing 12 tiles) will provide 6.78 petaflops – meaning that one ExaPOD alone will deliver a maximum theoretical performance of 67.8 FP32 petaflops. (Tesla preferred to offer performance in BFP16 and CFP8, and by those metrics, an ExaPOD will deliver 1.1 exaflops – hence the name.) All of this performance, Venkataramanan said, will be made accessible through a high-performing compiler, which operates automatically without human involvement and requires minimal effort to initiate on the researchers’ part.

“This is what [Dojo] will be,” Venkataramanan said. “It will be the fastest AI training computer.”

Dojo, however, hasn’t arrived just yet – in fact, Venkataramanan said that the first functional training tile had only arrived the previous week. Next up, he said, they were building the cabinets (“pretty soon”).

“And,” he continued, “we’re not done.” Tesla, Venkataramanan said, had a “whole next-generation plan already,” with their eyes set on the next tenfold increase in performance.

Learn more

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

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!

Royalty-free stock illustration ID: 1675260034

Solving Heterogeneous Programming Challenges with SYCL

December 8, 2021

In the first of a series of guest posts on heterogenous computing, James Reinders, who returned to Intel last year after a short "retirement," considers how SYCL will contribute to a heterogeneous future for C++. Reinde Read more…

Quantinuum Debuts Quantum-based Cryptographic Key Service – Is this Quantum Advantage?

December 7, 2021

Quantinuum – the newly-named company resulting from the merger of Honeywell’s quantum computing division and UK-based Cambridge Quantum – today launched Quantum Origin, a service to deliver “completely unpredicta 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…

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…

AWS Solution Channel

Introducing AWS HPC Connector for NICE EnginFrame

HPC customers regularly tell us about their excitement when they’re starting to use the cloud for the first time. In conversations, we always want to dig a bit deeper to find out how we can improve those initial experiences and deliver on the potential they see. 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…

Royalty-free stock illustration ID: 1675260034

Solving Heterogeneous Programming Challenges with SYCL

December 8, 2021

In the first of a series of guest posts on heterogenous computing, James Reinders, who returned to Intel last year after a short "retirement," considers how SYC Read more…

Quantinuum Debuts Quantum-based Cryptographic Key Service – Is this Quantum Advantage?

December 7, 2021

Quantinuum – the newly-named company resulting from the merger of Honeywell’s quantum computing division and UK-based Cambridge Quantum – today launched Q 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…

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…

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…

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…

Leading Solution Providers

Contributors

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…

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…

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…

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…

IBM Introduces its First Power10-based Server, the Power E1080; Targets Hybrid Cloud

September 8, 2021

IBM today introduced the Power E1080 server, its first system powered by a Power10 IBM microprocessor. The new system reinforces IBM’s emphasis on hybrid cloud markets and the new chip beefs up its inference capabilities. IBM – like other CPU makers – is hoping to make inferencing a core capability... Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire