When Dense Matrix Representations Beat Sparse

By James Reinders

September 9, 2019

In our world filled with unintended consequences, it turns out that saving memory space to help deal with GPU limitations, knowing it introduces performance penalties on matrix operations, can end up costing both performance and memory space.

As reported in a paper at ISC19, researchers[i] recently rethought use of sparse matrix representations, originally motivated by GPU memory constraints, to use dense matrices in order to benefit from the larger memory capacities and scale-out capabilities of CPUs. The result was  not only superior performance and scaling using CPUs, it also (perhaps surprisingly) included a reduction in memory footprint because of the interplay between using sparse representations to reduce memory and the increased memory usage due to algorithm inefficiencies.

The researchers demonstrated the positive effects of their work in Horovod – an open source distributed Deep Learning framework for TensorFlow created by Uber Engineering. They also demonstrated its outstanding ability to scale-out, proving it using supercomputers run with large numbers of CPUs. Their work has been incorporated into Horovod 0.15.2 and later, allowing anyone to benefit from their approach. The researchers encourage others to think as they have, because they believe that their rethinking of such work has applicability to other frameworks and libraries, such as BERT (Bidirectional Encoder Representations from Transformers).

The science – NMT

Neural machine translation (NMT) — using neural networks to translate human language — is an area of active research with the goal of dramatically improving machine translation performance. Current state-of-the-art approaches have hit roadblocks due to excessive memory use (a graph shared later in this article shows their scaling results on 8 nodes, proving how badly the original code fails to scale even at such low levels). Researchers made modifications to reduce memory usage for transformer models by converting assumed-sparse tensors to dense tensors, and subsequently replacing sparse gradient gather with dense gradient reduction. NMT now reaches new heights by leaning on CPU capabilities including superior memory capacity.

Being dense has its advantages

Dense Matrix representations consume more memory than sparse representations for many real-world matrices. As a result, many Deep Learning and AI algorithms err on the side of using sparse matrix representations to deal with the small local memories available when using GPUs. Unfortunately, while often saving memory they come with a non-trivial performance penalty, and coding complexity, for many matrix operations. This is markedly different than CPU programmers who tend to err on the side of using dense matrix representations because operations on them remain straightforward and simple to program and maintain.

Common wisdom questioned: GPUs like sparse, CPUs like dense

Originally, the researchers were looking to undo the performance degradations associated with sparse matrix representations — motivated by the GPU port of the code, and unnecessary for a CPU port of the code. The researcher suspected the matrices might not be as sparse as originally assumed (hence they emphasize “assumed sparse” in their discussions), and they knew the benefits on memory savings in such cases are diminished as they can be easily overwhelmed by the additional costs of matrix operations.

In the particular case they investigated, the distributed learning algorithm utilized an accumulation instead of a reduction operation because that is more practical when using sparse matrix representations. However, this approach dramatically contributes to increased memory utilization because it accumulated results instead of holding down the memory footprint of results through reductions. In this case, the interplay of algorithm choice and memory layout, combined with the denseness of these assumed sparse matrices, led to a benefit for both GPU and CPU in terms memory footprint — while unleashing the full potential of CPU based systems to scale-out with this simpler to understand algorithm (uncomplicated by the GPU inspired use of sparse matrices).

Unleashing CPU scaling

Once the researchers shifted to dense matrix representations, their new implementation opened the door for much improved scaling. What would take one month when using a single node, is now reduced to slightly over 6 hours when using 200 nodes (121 times faster). This result can significantly increase the productivity for NMT researchers by allowing the use of CPU-based HPC infrastructures. Researchers reported that their ability to maintain very high scaling efficiencies up to the 300-node level that they tested, suggests that continued scale-out is worthwhile beyond what they have tried thus far. That is certainly far better than the inability to scale beyond 8 nodes effectively when they started!

Even at only 8 nodes, the rapid decline in scaling of the original (sparse) approach dooms any high degree of scale-out — so runs at higher levels would be a waste of money and compute resources. The new approach (dense) shows enough promise here, that researchers later show exceptional scaling results above 256 nodes.

Results — faster execution and smaller memory footprint

Their code using a dense representation resulted in a more than 82x reduction (11446MB to 139MB) in the amount of memory required on 64-node run. It also, saw a more than 25x reduction in time required for the accumulation operation (4321ms to 169ms).

Space/time for tensor accumulated (sparse gather vs. dense reduce)

Model training experiments were run on the Zenith cluster in the Dell EMC HPC & AI Innovation Lab, as well as the Stampede2 cluster at the Texas Advanced Computing Center (TACC) in Austin, Texas, both featuring Intel processors and Intel Omni-Path fabric. In both cases, the researchers used Python 2.7, with Intel’s MKL-optimized version of TensorFlow (1.12), and modifications to Horovod that are available to everyone now in the versions 0.15.2  and  later.

Each Zenith node consists of dual Intel Xeon Scalable Gold 6148/F processors, 192GB of memory, and an M.2 boot drive to house the operating system that does not provide user-accessible local storage. Nodes are interconnected by a 100Gbps Intel Omni-path fabric, and shared storage is provided by a combination of NFS (for HOME directories) and Lustre filesystems.

Work on the Stampede2, used the Skylake (SKX) partition, which consists of 1,736 nodes. Each node is outfitted with dual Intel Xeon Scalable Platinum 8160 processors, 192GB of memory, and 200GB internal SSD drive for the operating system and local /tmp. All nodes are interconnected with 100Gbps Intel Omni-Path fabric and connected to Lustre-based shared filesystems.

The researchers summarized their work in a paper at ISC19. The software changes which they discuss in their paper have been incorporated into Horovod  0.15.2  and  later,  providing  other  researchers  the  opportunity  to apply their approach on any models that may benefit.

[i] Valeriu Codreanu and Damian Podareanu of SURFsara, Derya Cavdar, Can Karakus, and Victor Suthichai of Amazon, Alexander Sergeev of Uber, Vikram Saletore of Intel, and John A. Lockman III, Don D. Smith II, Quy Ta, Srinivas Varadharajan, Lucas A. Wilson, Rengan Xu, and Pei Yang of Dell EMC.

About the Author

James Reinders likes fast computers and the software tools to make them speedy. With over 30 years in High Performance Computing (HPC) and Parallel Computing including 27 Years at Intel Corporation (retired June 2016), he is also the author of nine books in the HPC field, numerous papers and blogs.

Subscribe to HPCwire's Weekly Update!

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

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion XL — were added to the benchmark suite as MLPerf continues Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Leading Solution Providers

Contributors

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire