No matter how elegant and clever the design is for a compute engine, the difficulty and cost of moving existing – and sometimes very old – code from the device it currently runs on to that new compute engine is a very big barrier to adoption. …
Updated: Here is something we don’t see much anymore when it comes to AI systems: list prices for the accelerators and the base motherboards that glue a bunch of them together into a shared compute complex. …
There was a time – and it doesn’t seem like that long ago – that the datacenter chip market was a big-money but relatively simple landscape, with CPUs from Intel and AMD and Arm looking to muscle its way in and GPUs mostly from Nvidia with some from AMD and Intel looking to muscle its way in. …
If you want to take on Nvidia on its home turf of AI processing, then you had better bring more than your A game. …
Spoiler alert!
A lot of neat things have just been added to the Arm Neoverse datacenter compute roadmap, but one of them is not a datacenter-class, discrete GPU accelerator. …
Since the advent of distributed computing, there has been a tension between the tight coherency of memory and its compute within a node – the base level of a unit of compute – and the looser coherency over the network across those nodes. …
A year ago, at its Google I/O 2022 event, Google revealed to the world that it had eight pods of TPUv4 accelerators, with a combined 32,768 of its fourth generation, homegrown matrix math accelerators, running in a machine learning hub located in its Mayes County, Oklahoma datacenter. …
Two decades ago, all the chip makers, including Intel, had to buy Unix machines, usually massive ranks of Sparc/Solaris systems, to do electronic design automation to design and test their chip designs. …
It seems like we have been talking about Google’s TPUv4 machine learning accelerators for a long time, and that is because we have been. …
It was absolutely inevitable that China would try to create its own GPU compute engines. …
All Content Copyright The Next Platform