Home Hardware Nvidia sets six AI benchmark records

GPU vendor Nvidia has set six records on the new MLPerf AI benchmark suite.

The MLPerf benchmark suite has the backing of AMD, Arm, Baidu, Google, Intel, Microsoft, Nvidia and other technology leaders.

It covers various workloads including computer vision, language translation, personalised recommendations, and reinforcement learning tasks.

Nvidia submitted six benchmark results — image classification, object instance segmentation, object detection, non-recurrent translation, recurrent translation, and recommendation systems — running on configurations ranging from 16 GPUs on one node to 640 GPUs across 80 nodes, and achieved the fastest performance on all six.

Among the results, an 80 DGX-1 cluster (with 640 chips) achieved 1424.4 times the performance of the reference system which is based on a single Pascal P100 chip (another Nvidia product). The closest competitor was a Google system using 260 chips (a mix of TPU v3.512 and v2.8) to achieve 1243.8 times the baseline performance.

Nvidia was the only company to enter six benchmarks.

The seventh category — reinforcement learning — does not yet take advantage of GPU acceleration.

Nvidia's benchmark results were achieved on DGX systems, including the DGX-2 which is said to be the world's most powerful AI system, with 16 fully connected V100 Tensor Core GPUs.

"The new MLPerf benchmarks demonstrate the unmatched performance and versatility of NVIDIA's Tensor Core GPUs," said Nvidia vice-president and general manager of accelerated computing, Ian Buck.

"Exceptionally affordable and available in every geography from every cloud service provider and every computer maker, our Tensor Core GPUs are helping developers around the world advance AI at every stage of development."

The 18.11 release of the deep learning containers available from the Nvidia GPU Cloud registry include the exact software used to achieve the MLPerf results.

The containers include Nvidia's complete software stack along with Nvidia-optimised versions of the top AI frameworks.


Our Mesh WiFi system MW3 is the first in Australia market with price below AUD$200 for a set of three.

· Best valued product
· Strong signal covering up to 300m2 for MW3 and 500m2 for MW6
· Aesthetically pleasing and light weigh (blend into any room deco)
· Wireline backhauls supported
· Product units are pre-paired and easy to setup
· Not requiring phone number or email address to set up
· Wall penetration (better than other similar brands)
· Seamless WiFi roaming
· User friendly app with controls to setup a guest network, parental controls for disabling groups of devices you allocate to individuals, QoS and more



Australia is a cyber espionage hot spot.

As we automate, script and move to the cloud, more and more businesses are reliant on infrastructure that has the high potential to be exposed to risk.

It only takes one awry email to expose an accounts’ payable process, and for cyber attackers to cost a business thousands of dollars.

In the free white paper ‘6 Steps to Improve your Business Cyber Security’ you’ll learn some simple steps you should be taking to prevent devastating and malicious cyber attacks from destroying your business.

Cyber security can no longer be ignored, in this white paper you’ll learn:

· How does business security get breached?
· What can it cost to get it wrong?
· 6 actionable tips


Stephen Withers

joomla visitors

Stephen Withers is one of Australia¹s most experienced IT journalists, having begun his career in the days of 8-bit 'microcomputers'. He covers the gamut from gadgets to enterprise systems. In previous lives he has been an academic, a systems programmer, an IT support manager, and an online services manager. Stephen holds an honours degree in Management Sciences and a PhD in Industrial and Business Studies.


Popular News




Sponsored News