Story image

GTC18 - NVIDIA ready to go all out on inferencing

28 Mar 18

NVIDIA has announced a series of new technologies and partnerships that expand its potential inference market while lowering the cost of delivering deep learning-powered services.

An inference engine is the aspect of AI that allows a device to figure out new information based on a set of rules and what it already knows.

"GPU acceleration for production deep learning inference enables even the largest neural networks to be run in real-time and at the lowest cost," says NVIDIA accelerated computing vice president and general manager lan Buck.

"With rapidly expanding support for more intelligent applications and frameworks, we can now improve the quality of deep learning and help reduce the cost for 30 million hyperscale servers."

TensorRT 4, the latest iteration of the inference optimiser, offers highly accurate INT8 and FP16 network execution and can be used to optimise, validate and deploy trained neural networks in hyperscale data centers.

NVIDIA Tesla GPU-accelerated servers can replace several racks of CPU servers for deep learning inference applications and services, freeing up rack space and reducing energy and cooling requirements.

The company says that the new software delivers up to 190x faster deep learning inference compared with CPUs for common applications such as computer vision, neural machine translation, automatic speech recognition, speech synthesis and recommendation systems.

Google and NVIDIA engineers have also integrated TensorRT into TensorFlow 1.7, making it easier to run deep learning inference applications on GPUs.

“The TensorFlow team is collaborating very closely with NVIDIA to bring the best performance possible on NVIDIA GPUs to the deep learning community,” says Google engineering director Rajat Monga.

“TensorFlow's integration with TensorRT now delivers up to 8x higher inference throughput (compared to regular GPU execution within a low latency target) on NVIDIA deep learning platforms with Volta Tensor Core technology, enabling the highest performance for GPU inference within TensorFlow."

NVIDIA engineers have worked with Amazon, Facebook and Microsoft to ensure developers using ONNX frameworks such as Caffe 2, Chainer, CNTK, MXNet and Pytorch can now deploy to NVIDIA deep learning platforms.

NVIDIA partnered with Microsoft to build GPU-accelerated tools to help developers incorporate more intelligent features in Windows applications.

GPU acceleration for Kubernetes was also announced, which will facilitate enterprise inference deployment on multi-cloud GPU clusters.

NVIDIA is contributing GPU enhancements to the open-source community to support the Kubernetes ecosystem.

In addition, MathWorks announced TensorRT integration with MATLAB.

Engineers and scientists can now automatically generate high-performance inference engines from MATLAB for Jetson, NVIDIA Drive and Tesla platforms.

TensorRT can also be deployed on NVIDIA Drive autonomous vehicles and NVIDIA Jetson embedded platforms.

Deep neural networks on every framework can be trained on NVIDIA DGX systems in the data center and then deployed into all types of devices for real-time inferencing at the edge.

Is Supermicro innocent? 3rd party test finds no malicious hardware
One of the larger scandals within IT circles took place this year with Bloomberg firing shots at Supermicro - now Supermicro is firing back.
Record revenues from servers selling like hot cakes
The relentless demand for data has resulted in another robust quarter for the global server market with impressive growth.
Opinion: Critical data centre operations is just like F1
Schneider's David Gentry believes critical data centre operations share many parallels to a formula 1 race car team.
MulteFire announces industrial IoT network specification
The specification aims to deliver robust wireless network capabilities for Industrial IoT and enterprises.
Google Cloud, Palo Alto Networks extend partnership
Google Cloud and Palo Alto Networks have extended their partnership to include more security features and customer support for all major public clouds.
DigiCert conquers Google's distrust of Symantec certs
“This could have been an extremely disruptive event to online commerce," comments DigiCert CEO John Merrill. 
Schneider Electric's bets for the 2019 data centre industry
From IT and telco merging to the renaissance of liquid cooling, here are the company's top predictions for the year ahead.
China to usurp Europe in becoming AI research world leader
A new study has found China is outpacing Europe and the US in terms of AI research output and growth.