Published in Graphics

Intel does not think you need a GPU for HPC

by on02 June 2016


Nvidia is losing ground to the coprocessor

Nvidia might have scored a few wins by touting its GPU’s in the HPC market, but it is starting to lose ground to the co-processor, according to Intel’s Diane Bryant.

In an IDC interview Intel’s data centre boss said that Nvidia gained an early lead in the market for accelerated HPC workloads when it positioned its GPUs for that task several years ago. However there is a perception that processors used for machine learning today are GPUs like those from Nvidia and AMD.

Bryant was a bit miffed when she was asked how Intel can compete in this market without a GPU. She said that the general purpose GPU, or GPGPU was just another type of accelerator and not one that’s uniquely suited to machine learning.
It is better to look at Knights Landing which is a coprocessor, but it’s an accelerator for floating point operations, and that’s what a GPGPU too.

She said that since the release of the first Xeon Phi in 2014, Intel now clawed back 33 percent of the market for HPC workloads that use a floating point accelerator.

“So we’ve won share against Nvidia, and we’ll continue to win share,” she said.

She said that Chipzilla’s share of the machine learning business may be much smaller, but the market is still young.

“Less than one percent of all the servers that shipped last year were applied to machine learning, so to hear Nvidia is beating us in a market that barely exists yet makes me a little crazy,” she says.

Intel will continue to evolve Xeon Phi to make it better at machine learning tasks. She said that there are two aspects to machine learning – training the algorithmic models, and applying those models to the real world in front-end applications. Intel’s FPGAs and its Xeon processors mean Intel has both sides of the equation covered.

But Nvidia’s GPUs are harder for programmers to work with which could give Intel an edge as ordinary businesses need to adopt machine learning. Knights Landing is "self-booting," which means customers don't need to pair it with a regular Xeon to boot an OS.
However Intel’s newest Xeon Phi has a floating point performance of about 3 teraflops, which is a little slow compared to the five teraflops for Nvidia’s new GP100.

Last modified on 02 June 2016
Rate this item
(13 votes)

Read more about: