MLPerf Releases First Inference Benchmark Results; Nvidia Touts its Showing

By John Russell

November 6, 2019

MLPerf.org, the young AI-benchmarking consortium, today issued the first round of results for its inference test suite. Among organizations with submissions were Nvidia, Intel, Alibaba, Supermicro, Google, Huawei, Dell and others. Not bad considering the inference suite (v.5) itself was just introduced in June. Perhaps predictably, GPU powerhouse Nvidia quickly claimed early victory issuing a press release coincident with the MLPerf announcement – “NVIDIA today posted the fastest results on new benchmarks measuring the performance of AI inference workloads” – though without much detail.

Actually, navigating the results takes some effort because of the diversity of systems (cloud to servers to mobile devices) and accelerators (GPUs, FPGA, DPS, TPUs, ASICs) covered. Along with the results, MLPerf issued detailed paper explaining the benchmark just as it did for its training test suite. Noteworthy, organizations perform their own testing using the MLPerf suite and results are validated as part of that process. Among accelerators used by systems tested were Nvidia T4s, Arm variants, Habana’s Goya inference processor, Alibaba’s HanGuang, the Hailo8 chip, and others.

Making apples to apples comparisons requires some effort. Different form factors, system sizes, CPU and accelerator counts, frameworks used, all matter. Of the over 500 benchmark results released today, 182 are in the so-called Closed Division (defined below[i]) intended for direct comparison of systems. The results span 44 different systems. The benchmarks show a five-order-of-magnitude difference in performance and a three-order-of-magnitude range in estimated power consumption and range from embedded devices and smartphones to large-scale data center systems. The remaining 429 open results are in the Open Division and show a more diverse range of models, including low precision implementations and alternative models.

As you can see digging out meaningful results will take some work. One of the more accessible comparisons is looking at accelerator performance differences, said David Kanter, co-chair of the MLPerf inference working group, in a pre-briefing with HPCwire, “With respect to the number of accelerators [in a system], one of the things is that [they are] explicitly parallel. So, in some sense, the performance per chip should be the same whether you have 8, 20, 4, or one accelerators. In many respects, I think the way I conceptualize these results is to look at it on a performance per chip basis.”

Wearing his MLPerf neutral hat, Kanter was reluctant to say much about particular entries but did say, “I was impressed with the number of early prototypes and experimental systems. We specifically designed the open division for this purpose, so it was great to see people who were experimenting with ultra-low latency, reduced precision, and other novel techniques that will push the industry forward.”

It’s best to spend time with the spreadsheet to answer particular questions.

MLPerf first jumped into the AI benchmarking arena with a training test suite in May of 2018 and has issued two rounds of public results since, the most recent in July. Today’s release of inferencing test results, posted on MLPerf.org, was a long-planned step on MLPerf’s roadmap and on schedule.

The v.5 inference test suite, acknowledged Kanter, is modest covering three tasks and uses five well-established models (see chart below):

“We chose tasks that reflect major commercial and research scenarios for a large class of submitters and that capture a broad set of computing motifs. To focus on the realistic rules and testing infrastructure, we selected a minimum-viable-benchmark approach to accelerate the development process. Where possible, we adopted models that were part of the MLPerf Training v0.6 suite, thereby amortizing the benchmark-development effort,” reports MLPerf.

Four different test scenarios are employed and each has somewhat different metric. Here’s an excerpt, lightly edited, from the MLPerf paper describing the them with a chart below.

  • Single-stream. It represents one inference-query stream with a query sample size of one, reflecting the many client applications where responsiveness is critical. An example is offline voice transcription on Google’s Pixel 4 smartphone. To measure performance, the LoadGen injects. The performance metric is the integer number of streams that the system supports while meeting the QoS requirement.
  • Multistream. It represents applications with a stream of queries, but each query comprises multiple inferences, reflecting a variety of industrial-automation and remote-sensing applications. For example, many autonomous vehicles have six to eight cameras streaming simultaneously and analyze the set of frames for hazards. The performance metric is the integer number of streams that the system supports while meeting the QoS requirement.
  • Server. It represents online server applications where query arrival is random and latency is important. Almost every consumer-facing website is a good example of this scenario, including services such as online translation from Baidu, Google, and Microsoft. The server scenario’s performance metric is the Poisson parameter that indicates the queries per second achievable while meeting the QoS requirement. The performance metric is the integer number of streams that the system supports while meeting the QoS requirement.
  • Offline. It represents batch-processing applications where all the input data is immediately available and latency is unconstrained. An example is identifying the people and locations in a photo album. The metric for the offline scenario is throughput measured in samples per second.

MLPerf submitters are also required to choose one of three categories for their entries: Available– basically systems one could use or buy (cloud and on-premise) in which the systems must use a “publicly available software stack consisting of the software components that substantially determine ML performance but are absent from the source code.”; Preview–  systems must “contain components that will meet the criteria for the available category within 180 days or by the next submission cycle, whichever is later,”; and Research & Development– prototype or proof of concept system with one or more R&D component. “These components submitted in one cycle may not be submitted as available until the third cycle or until 181 days have passed, whichever is later.”

The idea is to let potential users know the state of systems being tested and also offer technology providers the opportunity to showcase developing ideas. The first round of results in the closed division had 29 available submissions, five preview systems, and three in the R&D category.

Talking about the inference testing challenge, Kanter noted, “The problem is that inference encompasses everything from 300 watt monster GPUs and accelerators down to 200 milliwatt smartphones and other low power chips. I was thrilled with the response [to this first benchmark]. We got a good variety of processors, DSPs, FPGAs, CPUs, and GPUs, so pretty much everything under the sun. The only things we’re missing are analog or neuromorphic chips [and currently] there’s no such thing as a neuromorphic processor that’s actually in production.”

It’s not quite right to say, “let the AI benchmarking wars begin.” There are of course many AI benchmark efforts underway each with distinct strengths. That said, MLPerf is backed by a broad membership (~50) from industry and academia seems to have steadily gained traction as the AI community seeks a mechanism for comparing performance between various systems and components.

Training, of course, is generally the more compute intensive task in AI, but inferencing is the workhorse function and not only represents a larger market in terms of devices deployed but also a tremendous variety of deployment environments with widely ranging power requirements. MLPerf estimates over 100 companies are producing or are on the verge of producing optimized inference chips while only about 20 companies target training.

Kanter expects the release cadence to speed up. “Broadly speaking, the schedule that I’m anticipating is we believe we can do benchmark results once a quarter. And it’s going to alternate between training and inference. Long term, we’d love to move to a model that’s more like Spec where it’s just, you know, every week or so. Obviously because we got in around 600 results, we needed to review them all. If we can break up that work and make it so that you aren’t tied to our schedule, that would be great. There’s things that are missing, there’s things we know we need to fix, once we start getting more mature, I think it would be an interesting exercise to think about what would happen if we just allowed you to drop in your results whenever and see if that’s something that would really scale and work for us as an organization.”

It’s still early days for MLPerf much as it is for the AI renaissance generally taking hold. Stay tuned

[i]

Submitters are also required enter in one of two ‘divisions’ (descriptions from the inference paper):

Closed division. “The closed division enables comparisons of different systems. Submitters employ the same models, data sets, and quality targets to ensure comparability across wildly different architectures. This division requires pre-processing, post-processing, and a model that is equivalent to the reference implementation. It also permits calibration for quantization (using the calibration data set we provide) and prohibits retraining.”

Open division. “The open division fosters innovation in ML systems, algorithms, optimization, and hardware/software co-design. Submitters must still perform the same ML task, but they may change the model architecture and use different quality targets. This division allows arbitrary pre- and post-processing and arbitrary models, including techniques such as retraining. In general, submissions are not directly comparable with each other or with closed submissions. Each open submission must include documentation about how it deviates from the closed division. Caveat emptor!”

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!

Amid Upbeat Earnings, Intel to Cut 1% of Employees, Add as Many

January 24, 2020

For all the sniping two tech old timers take, both IBM and Intel announced surprisingly upbeat earnings this week. IBM CEO Ginny Rometty was all smiles at this week’s World Economic Forum in Davos, Switzerland, after  Read more…

By Doug Black

Indiana University Dedicates ‘Big Red 200’ Cray Shasta Supercomputer

January 24, 2020

After six months of celebrations, Indiana University (IU) officially marked its bicentennial on Monday – and it saved the best for last, inaugurating Big Red 200, a new AI-focused supercomputer that joins the ranks of Read more…

By Staff report

What’s New in HPC Research: Tsunamis, Wildfires, the Large Hadron Collider & More

January 24, 2020

In this bimonthly feature, HPCwire highlights newly published research in the high-performance computing community and related domains. From parallel programming to exascale to quantum computing, the details are here. Read more…

By Oliver Peckham

Toshiba Promises Quantum-Like Advantage on Standard Hardware

January 23, 2020

Toshiba has invented an algorithm that it says delivers a 10-fold improvement for a select class of computational problems, without the need for exotic hardware. In fact, the company's simulated bifurcation algorithm is Read more…

By Tiffany Trader

Energy Research Combines HPC, 3D Manufacturing

January 23, 2020

A federal energy research initiative is gaining momentum with the release of a contract award aimed at using supercomputing to harness 3D printing technology that would boost the performance of power generators. Partn Read more…

By George Leopold

AWS Solution Channel

Challenging the barriers to High Performance Computing in the Cloud

Cloud computing helps democratize High Performance Computing by placing powerful computational capabilities in the hands of more researchers, engineers, and organizations who may lack access to sufficient on-premises infrastructure. Read more…

IBM Accelerated Insights

Intelligent HPC – Keeping Hard Work at Bay(es)

Since the dawn of time, humans have looked for ways to make their lives easier. Over the centuries human ingenuity has given us inventions such as the wheel and simple machines – which help greatly with tasks that would otherwise be extremely laborious. Read more…

TACC Highlights Its Upcoming ‘IsoBank’ Isotope Database

January 22, 2020

Isotopes – elemental variations that contain different numbers of neutrons – can help researchers unearth the past of an object, especially the few hundred isotopes that are known to be stable over time. However, iso Read more…

By Oliver Peckham

Toshiba Promises Quantum-Like Advantage on Standard Hardware

January 23, 2020

Toshiba has invented an algorithm that it says delivers a 10-fold improvement for a select class of computational problems, without the need for exotic hardware Read more…

By Tiffany Trader

In Advanced Computing and HPC, Dell EMC Sets Sights on the Broader Market Middle 

January 22, 2020

If the leading advanced computing/HPC server vendors were in the batting lineup of a baseball team, Dell EMC would be going for lots of singles and doubles – Read more…

By Doug Black

DNA-Based Storage Nears Scalable Reality with New $25 Million Project

January 21, 2020

DNA-based storage, which involves storing binary code in the four nucleotides that constitute DNA, has been a moonshot for high-density data storage since the 1960s. Since the first successful experiments in the 1980s, researchers have made a series of major strides toward implementing DNA-based storage at scale, such as improving write times and storage density and enabling easier file identification and extraction. Now, a new $25 million... Read more…

By Oliver Peckham

AMD Recruits Intel, IBM Execs; Pending Layoffs Reported at Intel Data Platform Group

January 17, 2020

AMD has raided Intel and IBM for new senior managers, one of whom will replace an AMD executive who has played a prominent role during the company’s recharged Read more…

By Doug Black

Atos-AMD System to Quintuple Supercomputing Power at European Centre for Medium-Range Weather Forecasts

January 15, 2020

The United Kingdom-based European Centre for Medium-Range Weather Forecasts (ECMWF), a supercomputer-powered weather forecasting organization backed by most of Read more…

By Oliver Peckham

Julia Programming’s Dramatic Rise in HPC and Elsewhere

January 14, 2020

Back in 2012 a paper by four computer scientists including Alan Edelman of MIT introduced Julia, A Fast Dynamic Language for Technical Computing. At the time, t Read more…

By John Russell

White House AI Regulatory Guidelines: ‘Remove Impediments to Private-sector AI Innovation’

January 9, 2020

When it comes to new technology, it’s been said government initially stays uninvolved – then gets too involved. The White House’s guidelines for federal a Read more…

By Doug Black

IBM Touts Quantum Network Growth, Improving QC Quality, and Battery Research

January 8, 2020

IBM today announced its Q (quantum) Network community had grown to 100-plus – Delta Airlines and Los Alamos National Laboratory are among most recent addition Read more…

By John Russell

Using AI to Solve One of the Most Prevailing Problems in CFD

October 17, 2019

How can artificial intelligence (AI) and high-performance computing (HPC) solve mesh generation, one of the most commonly referenced problems in computational engineering? A new study has set out to answer this question and create an industry-first AI-mesh application... Read more…

By James Sharpe

SC19: IBM Changes Its HPC-AI Game Plan

November 25, 2019

It’s probably fair to say IBM is known for big bets. Summit supercomputer – a big win. Red Hat acquisition – looking like a big win. OpenPOWER and Power processors – jury’s out? At SC19, long-time IBMer Dave Turek sketched out a different kind of bet for Big Blue – a small ball strategy, if you’ll forgive the baseball analogy... Read more…

By John Russell

Cray, Fujitsu Both Bringing Fujitsu A64FX-based Supercomputers to Market in 2020

November 12, 2019

The number of top-tier HPC systems makers has shrunk due to a steady march of M&A activity, but there is increased diversity and choice of processing compon Read more…

By Tiffany Trader

Julia Programming’s Dramatic Rise in HPC and Elsewhere

January 14, 2020

Back in 2012 a paper by four computer scientists including Alan Edelman of MIT introduced Julia, A Fast Dynamic Language for Technical Computing. At the time, t Read more…

By John Russell

Crystal Ball Gazing: IBM’s Vision for the Future of Computing

October 14, 2019

Dario Gil, IBM’s relatively new director of research, painted a intriguing portrait of the future of computing along with a rough idea of how IBM thinks we’ Read more…

By John Russell

Intel Debuts New GPU – Ponte Vecchio – and Outlines Aspirations for oneAPI

November 17, 2019

Intel today revealed a few more details about its forthcoming Xe line of GPUs – the top SKU is named Ponte Vecchio and will be used in Aurora, the first plann Read more…

By John Russell

Dell Ramps Up HPC Testing of AMD Rome Processors

October 21, 2019

Dell Technologies is wading deeper into the AMD-based systems market with a growing evaluation program for the latest Epyc (Rome) microprocessors from AMD. In a Read more…

By John Russell

D-Wave’s Path to 5000 Qubits; Google’s Quantum Supremacy Claim

September 24, 2019

On the heels of IBM’s quantum news last week come two more quantum items. D-Wave Systems today announced the name of its forthcoming 5000-qubit system, Advantage (yes the name choice isn’t serendipity), at its user conference being held this week in Newport, RI. Read more…

By John Russell

Leading Solution Providers

SC 2019 Virtual Booth Video Tour

AMD
AMD
ASROCK RACK
ASROCK RACK
AWS
AWS
CEJN
CJEN
CRAY
CRAY
DDN
DDN
DELL EMC
DELL EMC
IBM
IBM
MELLANOX
MELLANOX
ONE STOP SYSTEMS
ONE STOP SYSTEMS
PANASAS
PANASAS
SIX NINES IT
SIX NINES IT
VERNE GLOBAL
VERNE GLOBAL
WEKAIO
WEKAIO

IBM Unveils Latest Achievements in AI Hardware

December 13, 2019

“The increased capabilities of contemporary AI models provide unprecedented recognition accuracy, but often at the expense of larger computational and energet Read more…

By Oliver Peckham

SC19: Welcome to Denver

November 17, 2019

A significant swath of the HPC community has come to Denver for SC19, which began today (Sunday) with a rich technical program. As is customary, the ribbon cutt Read more…

By Tiffany Trader

Jensen Huang’s SC19 – Fast Cars, a Strong Arm, and Aiming for the Cloud(s)

November 20, 2019

We’ve come to expect Nvidia CEO Jensen Huang’s annual SC keynote to contain stunning graphics and lively bravado (with plenty of examples) in support of GPU Read more…

By John Russell

Top500: US Maintains Performance Lead; Arm Tops Green500

November 18, 2019

The 54th Top500, revealed today at SC19, is a familiar list: the U.S. Summit (ORNL) and Sierra (LLNL) machines, offering 148.6 and 94.6 petaflops respectively, Read more…

By Tiffany Trader

51,000 Cloud GPUs Converge to Power Neutrino Discovery at the South Pole

November 22, 2019

At the dead center of the South Pole, thousands of sensors spanning a cubic kilometer are buried thousands of meters beneath the ice. The sensors are part of Ic Read more…

By Oliver Peckham

Azure Cloud First with AMD Epyc Rome Processors

November 6, 2019

At Ignite 2019 this week, Microsoft's Azure cloud team and AMD announced an expansion of their partnership that began in 2017 when Azure debuted Epyc-backed instances for storage workloads. The fourth-generation Azure D-series and E-series virtual machines previewed at the Rome launch in August are now generally available. Read more…

By Tiffany Trader

Intel’s New Hyderabad Design Center Targets Exascale Era Technologies

December 3, 2019

Intel's Raja Koduri was in India this week to help launch a new 300,000 square foot design and engineering center in Hyderabad, which will focus on advanced com Read more…

By Tiffany Trader

Summit Has Real-Time Analytics: Here’s How It Happened and What’s Next

October 3, 2019

Summit – the world’s fastest publicly-ranked supercomputer – now has real-time streaming analytics. At the 2019 HPC User Forum at Argonne National Laborat Read more…

By Oliver Peckham

  • arrow
  • Click Here for More Headlines
  • arrow
Do NOT follow this link or you will be banned from the site!
Share This