dcn-as logo
Story image

NVIDIA smashes MLPerf benchmarks for AI

08 Nov 2019

NVIDIA has achieved its fastest results yet for its AI inference workloads in data centers and the edge.

MLPerf Inference 0.5 is the industry’s first independent suite of AI benchmarks for inference. The benchmarks cover a range of form factors and inferencing scenarios for AI operations such as image classification, object detection, and translation.

NVIDIA Turing GPUs for data centers and NVIDIA Xavier system-on-a-chip for edge computing topped all five MLPerf benchmark tests, the company reports.

NVIDIA was the only AI platform company to submit results across all five MLPerf benchmarks.

Turing GPUs reportedly provided the highest performance per processor amongst commercially available entries; while Xavier performed highest amongst commercially available edge and mobile SoCs under both edge-focused scenarios (single-stream and multi-stream).

All of NVIDIA’s MLPerf results were achieved using NVIDIA TensorRT 6, which is a high-performance deep learning inference software that optimizes and deploys AI applications easily in production from the data center to the edge. New TensorRT optimizations are also available as open source in the GitHub repository.

NVIDIA’s general manager and vice president of accelerated computing, Ian Buck, says AI is now at a tipping point as it moves from research to large-scale deployment for real applications.

“AI inference is a tremendous computational challenge. Combining the industry’s most advanced programmable accelerator, the CUDA-X suite of AI algorithms and our deep expertise in AI computing, NVIDIA can help data centers deploy their large and growing body of complex AI models.”

NVIDIA says that GPUs accelerate large-scale inference workloads in the world’s largest cloud infrastructures, including Alibaba Cloud, AWS, Google Cloud Platform, Microsoft Azure and Tencent. AI is now moving to the edge at the point of action and data creation.

NVIDIA also announced Jetson Xavier NX, which is a small and powerful AI supercomputer for robotic and embedded computing devices at the edge.  It joins other solutions in the Jetson family, including the Jetson Nano, Jetson AGX Xavier series, and the Jetson TX2 series.

The Xavier NX is designed to help create embedded edge computing devices that demand increased performance but are constrained by size, weight, power budgets or cost. These include small commercial robots, drones, intelligent high-resolution sensors for factory logistics and production lines, optical inspection, network video recorders, portable medical devices and other industrial IoT systems.

The Jetson Xavier NX module will be available in March from NVIDIA’s distribution channels for companies looking to create high-volume production edge systems.

Story image
The ghost in the machine that maximizes uptime
Intel MFP uses machine learning to improve the performance and reliability of server memory to predict potential failures and prevent downtime.More
Story image
Google Cloud says it's ready for the coming strain on infrastructure
The cloud giant says that they are working with governments and network operators around the world to minimise stress on the system.More
Story image
Energy efficiency, decent budgets and strong teams crucial for data centre projects
“Having the key personnel and external partners is critical to the long-term success of any data centre project, so the time required to assemble that team needs to be factored into any transformation project.”More
Story image
Schneider Electric launches data centre cooling solution for the edge
“Simply put, our new vendor-neutral, rack mounted cooling solution is right-sized for edge micro data centres and provides the right answer for cooling today's critical edge technology."More
Story image
Interview: ManageEngine's VP says legacy remote solutions aren't cutting it
Techday spoke with ManageEngine vice president Rajesh Ganesan on the company’s solutions to the rapid changes and issues facing workforces around the globe as millions upon millions pack up their offices and work from home.More
Story image
China's cloud companies support fight against COVID-19
Canalys states that all three cloud companies have responded quickly to COVID-19, providing governments, businesses, research institutions and students access to services such as on-demand compute and artificial intelligence.More