The v3.1 iteration of the benchmark suite has seen record participation, boasting over 13,500 performance results and delivering up to a 40 percent improvement in performance. 

What sets this achievement apart is the diverse pool of 26 different submitters and over 2,000 power results, demonstrating the broad spectrum of industry players investing in AI innovation.

Among the list of submitters are tech giants like Google, Intel, and NVIDIA, as well as newcomers Connect Tech, Nutanix, Oracle, and TTA, who are participating in the MLPerf Inference benchmark for the first time.

David Kanter, Executive Director of MLCommons, highlighted the significance of this achievement:

“Submitting to MLPerf is not trivial. It’s a significant accomplishment, as this is not a simple point-and-click benchmark. It requires real engineering work and is a testament to our submitters’ commitment to AI, to their customers, and to ML.”

MLPerf Inference is a critical benchmark suite that measures the speed at which AI systems can execute models in various deployment scenarios. These scenarios span from the latest generative AI chatbots to the safety-enhancing features in vehicles, such as automatic lane-keeping and speech-to-text interfaces.

The spotlight of MLPerf Inference v3.1 shines on the introduction of two new benchmarks:

• An LLM utilising the GPT-J reference model to summarise CNN news articles garnered submissions from 15 different participants, showcasing the rapid adoption of generative AI.

• An updated recommender benchmark – refined to align more closely with industry practices – employs the DLRM-DCNv2 reference model and larger datasets, attracting nine submissions. These new benchmarks are designed to push the boundaries of AI and ensure that industry-standard benchmarks remain aligned with the latest trends in AI adoption, serving as a valuable guide for customers, vendors, and researchers alike.

Mitchelle Rasquinha, co-chair of the MLPerf Inference Working Group, commented: “The submissions for MLPerf Inference v3.1 are indicative of a wide range of accelerators being developed to serve ML workloads.

“The current benchmark suite has broad coverage among ML domains, and the most recent addition of GPT-J is a welcome contribution to the generative AI space. The results should be very helpful to users when selecting the best accelerators for their respective domains.”

MLPerf Inference benchmarks primarily focus on datacenter and edge systems. The v3.1 submissions showcase various processors and accelerators across use cases in computer vision, recommender systems, and language processing.

The benchmark suite encompasses both open and closed submissions in the performance, power, and networking categories. Closed submissions employ the same reference model to ensure a level playing field across systems, while participants in the open division are permitted to submit a variety of models.

As AI continues to permeate various aspects of our lives, MLPerf’s benchmarks serve as vital tools for evaluating and shaping the future of AI technology.

Find the detailed results of MLPerf Inference v3.1 here.

(Photo by Mauro Sbicego on Unsplash)

See also: GitLab: Developers view AI as ‘essential’ despite concerns

Want to learn more about AI and big data from industry leaders? Check out AI & Big Data Expo taking place in Amsterdam, California, and London. The comprehensive event is co-located with Digital Transformation Week.

Explore other upcoming enterprise technology events and webinars powered by TechForge here.

The post MLPerf Inference v3.1 introduces new LLM and recommendation benchmarks appeared first on AI News.

MLPerf Training is a full system benchmark that tests machine learning models, software, and hardware.

The results are split into two divisions: closed and open. Closed submissions are better for comparing like-for-like performance as they use the same reference model to ensure a level playing field. Open submissions, meanwhile, allow participants to submit a variety of models.

In the image classification benchmark, Google is the winner with its preview tpu-v4-6912 system that uses an incredible 1728 AMD Rome processors and 3456 TPU accelerators. Google’s system completed the benchmark in just 23 seconds.

“We showcased the record-setting performance and scalability of our fourth-generation Tensor Processing Units (TPU v4), along with the versatility of our machine learning frameworks and accompanying software stack. Best of all, these capabilities will soon be available to our cloud customers,” Google said.

“We achieved a roughly 1.7x improvement in our top-line submissions compared to last year’s results using new, large-scale TPU v4 Pods with 4,096 TPU v4 chips each. Using 3,456 TPU v4 chips in a single TPU v4 Pod slice, many models that once trained in days or weeks now train in a few seconds.”

Of the systems that are available on-premise, NVIDIA’s dgxa100_n310_ngc21.05_mxnet system came out on top with its 620 AMD EPYC 7742 processors and 2480 NVIDIA A100-SXM4-80GB (400W) accelerators completing the benchmark in 40 seconds.

“In the last 2.5 years since the first MLPerf training benchmark launched, NVIDIA performance has increased by up to 6.5x per GPU, increasing by up to 2.1x with A100 from the last round,” said NVIDIA.

“We demonstrated scaling to 4096 GPUs which enabled us to train all benchmarks in less than 16 minutes and 4 out of 8 in less than a minute. The NVIDIA platform excels in both performance and usability, offering a single leadership platform from data centre to edge to cloud.”

Across the board, MLCommons says that benchmark results have improved by up to 2.1x compared to the last submission round. This shows the incredible advancements that are being made in hardware, software, and system scale.

Victor Bittorf, Co-Chair of the MLPerf Training Working Group, said:

“We’re thrilled to see the continued growth and enthusiasm from the MLPerf community, especially as we’re able to measure significant improvement across the industry with the MLPerf Training benchmark suite.

Congratulations to all of our submitters in this v1.0 round – we’re excited to continue our work together, bringing transparency across machine learning system capabilities.”

For its latest benchmark, MLCommons added two new benchmarks for measuring the performance of performance for speech-to-text and 3D medical imaging. These new benchmarks leverage the following reference models: 

• Speech-to-Text with RNN-T: RNN-T: Recurrent Neural Network Transducer is an automatic speech recognition (ASR) model that is trained on a subset of LibriSpeech. Given a sequence of speech input, it predicts the corresponding text. RNN-T is MLCommons’ reference model and commonly used in production for speech-to-text systems.

• 3D Medical Imaging with 3D U-Net: The 3D U-Net architecture is trained on the KiTS 19 dataset to find and segment cancerous cells in the kidneys. The model identifies whether each voxel within a CT scan belongs to a healthy tissue or a tumour, and is representative of many medical imaging tasks.

“The training benchmark suite is at the centre of MLCommon’s mission to push machine learning innovation forward for everyone, and we’re incredibly pleased with the engagement from this round’s submissions,” commented John Tran, Co-Chair of the MLPerf Training Working Group.

The full MLPerf Training benchmark results can be explored here.

(Photo by Alora Griffiths on Unsplash)

Find out more about Digital Transformation Week North America, taking place on November 9-10 2021, a virtual event and conference exploring advanced DTX strategies for a ‘digital everything’ world.

The post MLCommons releases latest MLPerf Training benchmark results appeared first on AI News.