• Under The Hood Of Google’s TPU2 Machine Learning Clusters

    May 22, 2017 Paul Teich

    As we previously reported, Google unveiled its second-generation TensorFlow Processing Unit (TPU2) at Google I/O last week. Google calls this new generation “Google Cloud TPUs”, but provided very little information about the TPU2 chip and the systems that use it other than to provide a few colorful photos. Pictures do say more than words, so in this article we will dig into the photos and provide our thoughts based the pictures and on the few bits of detail Google did provide.

    To start with, it is unlikely that Google will sell TPU-based chips, boards, or servers – TPU2 …

    Read more

  • Does Google’s TPU Investment Make Sense Going Forward?

    April 12, 2017

    Google created quite a stir when it released architectural details and performance metrics for its homegrown Tensor Processing Unit (TPU) accelerator for machine learning algorithms last week. But as we (and many of you reading) pointed out, comparing the TPU to earlier “Kepler” generation GPUs from Nvidia was not exactly a fair comparison. Nvidia has done much in the “Maxwell” and “Pascal” GPU generations specifically to boost machine learning performance.

    To set the record straight, Nvidia took some time and ran some benchmarks of its own to put the performance of its latest Pascal accelerators, particularly the ones it aims …

    Read more

  • First In-Depth Look at Google’s TPU Architecture

    April 5, 2017

    Four years ago, Google started to see the real potential for deploying neural networks to support a large number of new services. During that time it was also clear that, given the existing hardware, if people did voice searches for three minutes per day or dictated to their phone for short periods, Google would have to double the number of datacenters just to run machine learning models.

    The need for a new architectural approach was clear, Google distinguished hardware engineer, Norman Jouppi, tells The Next Platform, but it required some radical thinking. As it turns out, that’s exactly …

    Read more

  • Why Google Is Driving Compute Diversity

    January 10, 2017

    In the ideal hyperscaler and cloud world, there would be one processor type with one server configuration and it would run any workload that could be thrown at it. Earth is not an ideal world, though, and it takes different machines to run different kinds of workloads.

    In fact, if Google is any measure – and we believe that it is – then the number of different types of compute that needs to be deployed in the datacenter to run an increasingly diverse application stack is growing, not shrinking. It is the end of the General Purpose Era, which began …

    Read more

  • Google Takes Unconventional Route with Homegrown Machine Learning Chips

    May 19, 2016 Stacey Higginbotham

    At the tail end of Google’s keynote speech at its developer conference Wednesday, Sundar Pichai, Google’s CEO mentioned that Google had built its own chip for machine learning jobs that it calls a Tensor Processing Unit, or TPU.

    The boast was that the TPU offered “an order of magnitude” improvement in the performance per watt for machine learning. Any company building a custom chip for a dedicated workload is worth noting, because building a new processor is a multimillion-dollar effort when you consider hiring a design team, the cost of getting a chip to production and building the hardware and …

    Read more

Mellanox

The Next Platform Weekly

Tap the stack to painlessly subscribe for a weekly email from The Next Platform, featuring highlights, analysis, and stories from the week directly from us to your inbox with nothing in between.