Purdue Researchers Peer into the ‘Fog of the Machine Learning Accelerator War’

By John Russell

September 27, 2021

Making sense of ML performance and benchmark data is an ongoing challenge. In light of last week’s release of the most recent MLPerf (v1.1) inference results, now is perhaps a good time to review how valuable (or not) such ML benchmarks are and the challenges they face. Two researchers from Purdue University recently tackled this issue in a fascinating blog on ACM SIGARCH – An Academic’s Attempt to Clear the Fog of the Machine Learning Accelerator War.

Tim Rogers and Mahmoud Khairy wrote, “At its core, all engineering is science optimized (or perverted) by economics. As academics in computer science and engineering, we have a symbiotic relationship with industry. Still, it is often necessary for us to peel back the marketing noise and understand precisely what companies are building, why their offering is better than their competitors, and how we can innovate beyond what industrial state-of-the-art provides.

“The more immediately relevant a problem is, the more funding and innovation the solutions will receive, at the cost of increased noise for both customers deciding where to place investments and researchers attempting to innovate without bias. In 2021, the raging machine learning accelerator war is now a well-established battleground of processors, ideas, and noise.”

With that the researchers plunge into describing the two dominant approaches (data parallelism and model parallelism) to solving ML problems and how they match to different chip/system architectures and different problem types and sizes.

Rogers and Khairy credit MLPerf for providing “a SPEC-like benchmark suite that we hope will eventually provide clarity on the best-performing machine learning systems,” but then recognize many companies don’t participate for a variety of economic and other reasons. The larger question they pose is, “In the coming age of customized accelerators, do standardized benchmark suites make sense at all anymore? Broadly, this is likely to be a challenge, but in the context of GEMM-heavy machine learning workloads, we think standardization is both possible and necessary.”

Shown below is a chart they prepared comparing several accelerators including Cerebras and Graphcore, which have not competed in MLPerf. Khairy dug through a variety of public documentation to pull together this “apples-to-apples comparison of 16-bit mixed-precision training:”

The meat of the post is about data parallelism and model parallelism and Rogers and Khairy dig in and provide some comparison metrics. Here’s a summary description of the approaches excerpted from the blog:

  • Data Parallelism. “Generally both NVIDIA and Google rely on data parallelism to scale performance. In this context, data parallelism refers to replicating the network model on different accelerators and assigning a fraction of each training batch to each node (Figure 2). The relatively large DRAM capacity of the TPU and GPU makes network replication feasible, and the dedicated hardware for dense GEMM operations make large batch training efficient. Both vendors have also invested significant effort in making the reduction operation across nodes as efficient as possible. However, the key to exploiting data parallelism is achieving efficient training with a large batch size, which requires a non-trivial amount of hyper-parameter tuning.
  • Model Parallelism. “Cerebras and Graphcore take a different approach, focusing heavily on model parallelism. In model parallelism, each layer of a single model is mapped to hardware, and data flows between each layer, ideally to processing units on the same chip. To exploit this philosophy, both Graphcore and Cerebras devote a large portion of their silicon area to SRAM cells such that large models are placed entirely in SRAM. Cerebras achieves this with its wafer-scale chip, while Graphcore’s IPU servers consist of smaller chips linked via a ring interconnect.”

They emphasize it’s not, strictly-peaking, an either-or question. GPUs and TPUs can exploit model parallelism, and Cerebras/Graphcore servers can exploit data parallelism.

“However, each offering has a particular type of parallelism where its design has an advantage. It seems that one open question academics can help answer is what the right balance between model and data parallelism should be. Data parallelism is difficult to scale, and excessive hyperparameter tuning gives a clear advantage to more prominent players with the time and resources to tune them. In contrast, model parallelism requires less tuning, but as soon as the model no longer fits on-chip or on-node, most of the advantages are lost,” they wrote.

Their blog is a quick read and worth the effort (apologies for excerpting so much material). They emphasize their intent is not to predict the war’s winner but rather predict what weapons will turn the tide: “Academically, the data versus model parallelism tradeoff is interesting. If models continue to grow, exploiting model parallelism on the same chip, wafer-scale or not, will be infeasible. Conversely, increasing the batch size to exploit data parallelism is difficult, and larger models won’t make this easier. It seems that a hybrid approach will be the solution, and hardware that can effectively adapt to different model/data parallelism levels will likely have the most impact.”

Link to ACM SIGARCH blog: https://www.sigarch.org/an-academics-attempt-to-clear-the-fog-of-the-machine-learning-accelerator-war/

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!

Energy Exascale Earth System Model Version 2 Promises Twice the Speed

October 18, 2021

The Energy Exascale Earth System Model (E3SM) is an ongoing Department of Energy (DOE) earth system modeling, simulation and prediction project aiming to “assert and maintain an international scientific leadership posi 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…

Royalty-free stock illustration ID: 1938746143

MosaicML, Led by Naveen Rao, Comes Out of Stealth Aiming to Ease Model Training

October 15, 2021

With more and more enterprises turning to AI for a myriad of tasks, companies quickly find out that training AI models is expensive, difficult and time-consuming. Finding a new approach to deal with those cascading challenges is the aim of a new startup, MosaicML, that just came out of stealth... Read more…

NSF Awards $11M to SDSC, MIT and Univ. of Oregon to Secure the Internet

October 14, 2021

From a security standpoint, the internet is a problem. The infrastructure developed decades ago has cracked, leaked and been patched up innumerable times, leaving vulnerabilities that are difficult to address due to cost Read more…

SC21 Announces Science and Beyond Plenary: the Intersection of Ethics and HPC

October 13, 2021

The Intersection of Ethics and HPC will be the guiding topic of SC21's Science & Beyond plenary, inspired by the event tagline of the same name. The evening event will be moderated by Daniel Reed with panelists Crist Read more…

AWS Solution Channel

Cost optimizing Ansys LS-Dyna on AWS

Organizations migrate their high performance computing (HPC) workloads from on-premises infrastructure to Amazon Web Services (AWS) for advantages such as high availability, elastic capacity, latest processors, storage, and networking technologies; Read more…

Quantum Workforce – NSTC Report Highlights Need for International Talent

October 13, 2021

Attracting and training the needed quantum workforce to fuel the ongoing quantum information sciences (QIS) revolution is a hot topic these days. Last week, the U.S. National Science and Technology Council issued a report – The Role of International Talent in Quantum Information Science... 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…

Royalty-free stock illustration ID: 1938746143

MosaicML, Led by Naveen Rao, Comes Out of Stealth Aiming to Ease Model Training

October 15, 2021

With more and more enterprises turning to AI for a myriad of tasks, companies quickly find out that training AI models is expensive, difficult and time-consuming. Finding a new approach to deal with those cascading challenges is the aim of a new startup, MosaicML, that just came out of stealth... Read more…

Quantum Workforce – NSTC Report Highlights Need for International Talent

October 13, 2021

Attracting and training the needed quantum workforce to fuel the ongoing quantum information sciences (QIS) revolution is a hot topic these days. Last week, the U.S. National Science and Technology Council issued a report – The Role of International Talent in Quantum Information Science... Read more…

Eni Returns to HPE for ‘HPC4’ Refresh via GreenLake

October 13, 2021

Italian energy company Eni is upgrading its HPC4 system with new gear from HPE that will be installed in Eni’s Green Data Center in Ferrera Erbognone (a provi Read more…

The Blueprint for the National Strategic Computing Reserve

October 12, 2021

Over the last year, the HPC community has been buzzing with the possibility of a National Strategic Computing Reserve (NSCR). An in-utero brainchild of the COVID-19 High-Performance Computing Consortium, an NSCR would serve as a Merchant Marine for urgent computing... Read more…

UCLA Researchers Report Largest Chiplet Design and Early Prototyping

October 12, 2021

What’s the best path forward for large-scale chip/system integration? Good question. Cerebras has set a high bar with its wafer scale engine 2 (WSE-2); it has 2.6 trillion transistors, including 850,000 cores, and was fabricated using TSMC’s 7nm process on a roughly 8” x 8” silicon footprint. Read more…

What’s Next for EuroHPC: an Interview with EuroHPC Exec. Dir. Anders Dam Jensen

October 7, 2021

One year after taking the post as executive director of the EuroHPC JU, Anders Dam Jensen reviews the project's accomplishments and details what's ahead as EuroHPC's operating period has now been extended out to the year 2027. Read more…

University of Bath Unveils Janus, an Azure-Based Cloud HPC Environment

October 6, 2021

The University of Bath is upgrading its HPC infrastructure, which it says “supports a growing and wide range of research activities across the University.” 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…

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…

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... 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…

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…

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…

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

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…

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…

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…

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…

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…

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…

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 i Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire