NVIDIA A100 Aces Throughput, Latency Results in Key Inference Benchmark for Financial Services Industry

02/02/2023

NVIDIA A100 Tensor Core GPUs running on Supermicro servers have captured leading results for inference in the latest STAC-ML Markets benchmark, a key technology performance gauge for the financial services industry.

The results show NVIDIA demonstrating unrivaled throughput - serving up thousands of inferences per second on the most demanding models - and top latency on the latest STAC-ML inference standard.

The results are closely followed by financial institutions, three-quarters of which rely on machine learning, deep learning or high performance computing, according to a recent survey.

NVIDIA A100: Top Latency Results The STAC-ML inference benchmark is designed to measure the latency of long short-term memory (LSTM) model inference - the time from receiving new input data until the model output is computed. LSTM is a key model approach used to discover financial time-series data like asset prices.

The benchmark includes three LSTM models of increasing complexity. NVIDIA A100 GPUs, running in a Supermicro Ultra SuperServer, demonstrated low latencies in the 99th percentile.

Accelerated Computing for STAC-ML and STAC-A2, STAC-A3 Benchmarks Considering the A100 performance on STAC-ML for inference - in addition to its record-setting performance in the STAC-A2 benchmark for option price discovery and the STAC-A3 benchmark for model backtesting - provides a glimpse at how NVIDIA AI computing can accelerate a pipeline of modern trading environments.

It also shows A100 GPUs deliver leading performance and workload versatility for financial institutions.

Predictable Performance for Consistent Low Latency Predictable performance is crucial for low-latency environments in finance, as extreme outliers can cause substantial losses during fast market moves.

Notably, there were no large outliers in NVIDIA's latency, as the maximum latency was no more than 2.3x the median latency across all LSTMs and the number of model instances, ranging up to 32 concurrent instances.1

NVIDIA is the first to submit performance results for what's known as the Tacana Suite of the benchmark. Tacana is for inference performed on a sliding window, where a new timestep is added and the oldest removed for each inference operation. This is helpful for high-frequency trading, where inference needs to be performed on every market data update.

A second suite, Sumaco, performs inference on an entirely new set of data, which reflects the use case where an event prompts inference based on recent history.

Leading Throughput in Benchmark Results NVIDIA also submitted a throughput-optimized configuration on the same hardware for the Sumaco Suite in FP16 precision.2

On the least complex LSTM in the benchmark, A100 GPUs on Supermicro servers helped serve up more than 1.7 million inferences per second.3

For the most complex LSTM, these systems handled as many as 12,800 inferences per second.4

NVIDIA A100: Performance and Versatility NVIDIA GPUs offer multiple advantages that lower the total cost of ownership for electronic trading stacks.

For one, NVIDIA AI provides a single platform for training and inference. Whether developing, backtesting or deploying an AI model, NVIDIA AI delivers leading performance - and developers don't need to learn different programming languages and frameworks for research and trading.

Moreover, the NVIDIA CUDA programming model enables development, optimization and deployment of applications across GPU-accelerated embedded systems, desktop workstations, enterprise data centers, cloud-based platforms and HPC supercomputers.

Efficiencies for Reduced Operating Expenses The financial services industry stands to benefit from not only data throughput advances but also improved operational efficiencies.

Reduced energy and square footage usage for systems in data centers can make a big difference in operating expenses. That's especially pressing as IT organizations make the case for budgetary outlays to cover new high-performance systems.

On the most demanding LSTM model, NVIDIA A100 exceeded 17,700 inferences per second per kilowatt while consuming 722 watts, offering leading energy efficiency.5

The benchmark results confirm that NVIDIA GPUs are unrivaled in terms of throughput and energy efficiency for workloads like backtesting and simulation.

Learn about NVIDIA delivering smarter, more secure financial services.

[1] SUT ID NVDA221118b, max of STAC-ML.Markets.Inf.T.LSTM_A.2.LAT.v1

[2] SUT ID NVDA221118a

[3] STAC-ML.Markets.Inf.S.LSTM_A.4.TPUT.v1

[4] STAC-ML.Markets.Inf.S.LSTM_C.[1,2,4].TPUT.v1

[5] SUT ID NVDA221118a, STAC-ML.Markets.Inf.S.LSTM_C.[1,2,4].ENERG_EFF.v1

LINK:	https://blogs.nvidia.com/blog/2023/02/02/stac-ml-inference-gpu/...
	See more stories from nvidia

Most recent headlines

05/01/2027

Worlds first 802.15.4ab-UWB chip verified by Calterah and Rohde & Schwarz to be demoed at CES 2026

Worlds first 802.15.4ab-UWB chip verified by Calterah and Rohde & Schwarz to be ...

01/06/2026

Dolby Sets the New Standard for Premium Entertainment at CES 2026

January 6 2026, 05:30 (PST) Dolby Sets the New Standard for Premium Entertainment at CES 2026 Throughout the week, Dolby brings to life the latest innovatio...

02/05/2026

Dalet Flex LTS Delivers Smarter Search, Faster Editing, and an AI-Ready Foundation for Modern Media

Dalet, a leading technology and service provider for media-rich organizations, t...

01/05/2026

NBCUniversal's Peacock to Be First Streamer to Integrate Dolby's Full Suite of Premium Picture and Sound Innovations

January 5 2026, 18:30 (PST) NBCUniversal's Peacock to Be First Streamer to ...

01/04/2026

DOLBY AND DOUYIN EMPOWER THE NEXT GENERATON OF CREATORS WITH DOLBY VISION

January 4 2026, 18:00 (PST) DOLBY AND DOUYIN EMPOWER THE NEXT GENERATON OF CREATORS WITH DOLBY VISION Douyin Users Can Now Create And Share Videos With Stun...

18/03/2026

Net Insight Names Larissa GrnerMeeus CPO

Newly named chief product officer (CPO), Larissa G rner Meeus will return to Net Insight on May 4. Larissa G rner Meeus will become CPO of Net Insight on May 4...

18/03/2026

SVG Europe's The Football Summit 2026: Select Sessions Now Available to Watch on SVG PLAY

SVG Europe's The Football Summit 2026 explored how the sports broadcasting i...

18/03/2026

SVG's SportsTech@NABShow Blog Goes Live as Countdown to Vegas Heats Up

The 2026 NAB Show kicks off one month from today and SVG is once again set to cover the show from every angle. SVG's SportsTech@NAB Show Blog is now live - ...

18/03/2026

The Premiere of Dead Lover Showcases Grave Robbing and Sex With a Giant Finger

(L-R) The cast and crew of Dead Lover at The Ray Theater for its premiere at the 2025 Sundance Film Festival. (Photo by Robin Marshall/Shutterstock for Sundan...

18/03/2026

Music Row Piano from Wiltone Productions

Yamaha C7 captured in Nashville Wiltone Productions have announced the release of Music Row Piano, a deeply sampled Yamaha C7 piano library that's been ...

18/03/2026

Techivation introduce T-Warmer Mk2

Bass-enhancement plug-in upgraded Along with a steady stream of new releases, Techivation have recently been revisiting some of the older plug-ins in their ...

18/03/2026

Tonal Balance Control 3 from iZotope

Mix-reference plug-in overhauled iZotope's powerful mix-referencing plug-in has just reached its third major version, and now boasts a new capture proce...

18/03/2026

Toontrack Transistor Organ EKX

Latest EZKeys 2 expansion arrives Toontrack's staggering collection of EZKeys 2 expansions has grown once again, and the latest instalment delivers a on...

18/03/2026

Jess Ho explores the politics of food in new SBS Audio podcast For The Culture

Jess Ho explores the politics of food in new SBS Audio podcast For The Culture 18 March, 2026 Media releases New SBS Audio podcast For The Culture, hosted ...

18/03/2026

Future-ready broadcasts with ATSC 3.0 and enhanced services from Rohde & Schwarz at NAB 2026

Future-ready broadcasts with ATSC 3.0 and enhanced services from Rohde & Schwarz...

18/03/2026

LCTWS 2026

London Calling - When The Industry Convened to Help Streaming Find its MoJo In this blog, Laura Rognoni reflects on key discussions from the Connected TV World...

18/03/2026

SMPTE Unveils 2026 NAB Show Educational Presentations

SMPTE Unveils 2026 NAB Show Educational Presentations Brie Clayton March 18, 2026 0 Comments SMPTE , the home of media professionals, technologists, a...

18/03/2026

Auditel Ad Campaign Shot on Blackmagic PYXIS 12K

Auditel Ad Campaign Shot on Blackmagic PYXIS 12K Brie Clayton March 18, 2026 0 Comments LED wall virtual production blends 12K open gate acquisition w...

18/03/2026