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!

The Case for an Edge-Driven Future for Supercomputing

September 24, 2021

“Exascale only becomes valuable when it’s creating and using data that we care about,” said Pete Beckman, co-director of the Northwestern-Argonne Institute of Science and Engineering (NAISE), at the most recent HPC Read more…

Three Universities Team for NSF-Funded ‘ACES’ Reconfigurable Supercomputer Prototype

September 23, 2021

As Moore’s law slows, HPC developers are increasingly looking for speed gains in specialized code and specialized hardware – but this specialization, in turn, can make testing and deploying code trickier than ever. Now, researchers from Texas A&M University, the University of Illinois at Urbana... Read more…

Qubit Stream: Monte Carlo Advance, Infosys Joins the Fray, D-Wave Meeting Plans, and More

September 23, 2021

It seems the stream of quantum computing reports never ceases. This week – IonQ and Goldman Sachs tackle Monte Carlo on quantum hardware, Cambridge Quantum pushes chemistry calculations forward, D-Wave prepares for its Read more…

Asetek Announces It Is Exiting HPC to Protect Future Profitability

September 22, 2021

Liquid cooling specialist Asetek, well-known in HPC circles for its direct-to-chip cooling technology that is inside some of the fastest supercomputers in the world, announced today that it is exiting the HPC space amid multiple supply chain issues related to the pandemic. Although pandemic supply chain... Read more…

TACC Supercomputer Delves Into Protein Interactions

September 22, 2021

Adenosine triphosphate (ATP) is a compound used to funnel energy from mitochondria to other parts of the cell, enabling energy-driven functions like muscle contractions. For ATP to flow, though, the interaction between the hexokinase-II (HKII) enzyme and the proteins found in a specific channel on the mitochondria’s outer membrane. Now, simulations conducted on supercomputers at the Texas Advanced Computing Center (TACC) have simulated... Read more…

AWS Solution Channel

Introducing AWS ParallelCluster 3

Running HPC workloads, like computational fluid dynamics (CFD), molecular dynamics, or weather forecasting typically involves a lot of moving parts. You need a hundreds or thousands of compute cores, a job scheduler for keeping them fed, a shared file system that’s tuned for throughput or IOPS (or both), loads of libraries, a fast network, and a head node to make sense of all this. 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-apples) datacenter and edge categories. Perhaps more interesti Read more…

The Case for an Edge-Driven Future for Supercomputing

September 24, 2021

“Exascale only becomes valuable when it’s creating and using data that we care about,” said Pete Beckman, co-director of the Northwestern-Argonne Institut Read more…

Three Universities Team for NSF-Funded ‘ACES’ Reconfigurable Supercomputer Prototype

September 23, 2021

As Moore’s law slows, HPC developers are increasingly looking for speed gains in specialized code and specialized hardware – but this specialization, in turn, can make testing and deploying code trickier than ever. Now, researchers from Texas A&M University, the University of Illinois at Urbana... Read more…

Qubit Stream: Monte Carlo Advance, Infosys Joins the Fray, D-Wave Meeting Plans, and More

September 23, 2021

It seems the stream of quantum computing reports never ceases. This week – IonQ and Goldman Sachs tackle Monte Carlo on quantum hardware, Cambridge Quantum pu Read more…

Asetek Announces It Is Exiting HPC to Protect Future Profitability

September 22, 2021

Liquid cooling specialist Asetek, well-known in HPC circles for its direct-to-chip cooling technology that is inside some of the fastest supercomputers in the world, announced today that it is exiting the HPC space amid multiple supply chain issues related to the pandemic. Although pandemic supply chain... Read more…

TACC Supercomputer Delves Into Protein Interactions

September 22, 2021

Adenosine triphosphate (ATP) is a compound used to funnel energy from mitochondria to other parts of the cell, enabling energy-driven functions like muscle contractions. For ATP to flow, though, the interaction between the hexokinase-II (HKII) enzyme and the proteins found in a specific channel on the mitochondria’s outer membrane. Now, simulations conducted on supercomputers at the Texas Advanced Computing Center (TACC) have simulated... 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…

Why HPC Storage Matters More Now Than Ever: Analyst Q&A

September 17, 2021

With soaring data volumes and insatiable computing driving nearly every facet of economic, social and scientific progress, data storage is seizing the spotlight. Hyperion Research analyst and noted storage expert Mark Nossokoff looks at key storage trends in the context of the evolving HPC (and AI) landscape... Read more…

GigaIO Gets $14.7M in Series B Funding to Expand Its Composable Fabric Technology to Customers

September 16, 2021

Just before the COVID-19 pandemic began in March 2020, GigaIO introduced its Universal Composable Fabric technology, which allows enterprises to bring together 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 called Dojo to process truly vast amounts of video data. It’s a beast! … A truly useful exaflop at de facto FP32.” 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. “We’ve been scaling our neural network training compute dramatically over the last few years,” said Milan Kovac, Tesla’s director of autopilot engineering. 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…

CentOS Replacement Rocky Linux Is Now in GA and Under Independent Control

June 21, 2021

The Rocky Enterprise Software Foundation (RESF) is announcing the general availability of Rocky Linux, release 8.4, designed as a drop-in replacement for the soon-to-be discontinued CentOS. The GA release is launching six-and-a-half months after Red Hat deprecated its support for the widely popular, free CentOS server operating system. The Rocky Linux development effort... 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…

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…

AMD-Xilinx Deal Gains UK, EU Approvals — China’s Decision Still Pending

July 1, 2021

AMD’s planned acquisition of FPGA maker Xilinx is now in the hands of Chinese regulators after needed antitrust approvals for the $35 billion deal were receiv Read more…

Google Launches TPU v4 AI Chips

May 20, 2021

Google CEO Sundar Pichai spoke for only one minute and 42 seconds about the company’s latest TPU v4 Tensor Processing Units during his keynote at the Google I Read more…

Leading Solution Providers

Contributors

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…

10nm, 7nm, 5nm…. Should the Chip Nanometer Metric Be Replaced?

June 1, 2020

The biggest cool factor in server chips is the nanometer. AMD beating Intel to a CPU built on a 7nm process node* – with 5nm and 3nm on the way – has been i Read more…

Julia Update: Adoption Keeps Climbing; Is It a Python Challenger?

January 13, 2021

The rapid adoption of Julia, the open source, high level programing language with roots at MIT, shows no sign of slowing according to data from Julialang.org. I Read more…

Quantum Roundup: IBM, Rigetti, Phasecraft, Oxford QC, China, and More

July 13, 2021

IBM yesterday announced a proof for a quantum ML algorithm. A week ago, it unveiled a new topology for its quantum processors. Last Friday, the Technical Univer Read more…

Intel Launches 10nm ‘Ice Lake’ Datacenter CPU with Up to 40 Cores

April 6, 2021

The wait is over. Today Intel officially launched its 10nm datacenter CPU, the third-generation Intel Xeon Scalable processor, codenamed Ice Lake. With up to 40 Read more…

Frontier to Meet 20MW Exascale Power Target Set by DARPA in 2008

July 14, 2021

After more than a decade of planning, the United States’ first exascale computer, Frontier, is set to arrive at Oak Ridge National Laboratory (ORNL) later this year. Crossing this “1,000x” horizon required overcoming four major challenges: power demand, reliability, extreme parallelism and data movement. Read more…

Intel Unveils New Node Names; Sapphire Rapids Is Now an ‘Intel 7’ CPU

July 27, 2021

What's a preeminent chip company to do when its process node technology lags the competition by (roughly) one generation, but outmoded naming conventions make it seem like it's two nodes behind? For Intel, the response was to change how it refers to its nodes with the aim of better reflecting its positioning within the leadership semiconductor manufacturing space. Intel revealed its new node nomenclature, and... Read more…

Intel Announces Sapphire Rapids with HBM, Reveals Ponte Vecchio Form Factors

June 28, 2021

From the ISC 2021 Digital event, Intel announced it will offer Sapphire Rapids with integrated HBM, detailed new Xe-HPC GPU form factors, and introduced commercial support for DAOS (distributed application object storage). Intel also announced a new Ethernet solution, aimed at smaller-scale HPC. With integrated High Bandwidth Memory (HBM), the forthcoming Intel Xeon Scalable processors... Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire