Each time that the United States has figured out that it needed to do export controls on massively parallel compute engines to try to discourage China from buying such gear and building supercomputers with them, it has already been too late to have much of a long term effect on China’s ability to run the advanced HPC simulations and AI training workloads that we were worried would be enabled by such computing oomph. …
For the past five years, since Nvidia acquired InfiniBand and Ethernet switch and network interface card supplier Mellanox, people have been wondering what the split is between compute and networking in the Nvidia datacenter business that has exploded in growth and now represents most of revenue for each quarter. …
Today is the ribbon-cutting ceremony for the “Venado” supercomputer, which was hinted at back in April 2021 when Nvidia announced its plans for its first datacenter-class Arm server CPU and which was talked about in some detail – but not really enough to suit our taste for speeds and feeds – back in May 2022 by the folks at Los Alamos National Laboratory where Venado is situated. …
We have said it before, and we will say it again right here: If you can make a matrix math engine that runs the PyTorch framework and the Llama large language model, both of which are open source and both of which come out of Meta Platforms and both of which will be widely adopted by enterprises, then you can sell that matrix math engine. …
Here is a history question for you: How many IT suppliers who do a reasonable portion of their business in the commercial IT sector – and a lot of that in the datacenter – have ever broken through the $100 billion barrier? …
For a lot of state universities in the United States, and their equivalent political organizations of regions or provinces in other nations across the globe, it is a lot easier to find extremely interested undergraduate and graduate students who want to contribute to the font of knowledge in high performance computing than it is to find the budget to build a top-notch supercomputer of reasonable scale. …
We have five decades of very fine-grained analysis of CPU compute engines in the datacenter, and changes come at a steady but glacial pace when it comes to CPU serving. …
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. …
The exorbitant cost of GPU-accelerated systems for training and inference and latest to rush to find gold in mountains of corporate data are combining to exert tectonic forces on the datacenter landscape and push up a new Himalaya range – with Nvidia as its steepest and highest peak. …
In a world where allocations of “Hopper” H100 GPUs coming out of Nvidia’s factories are going out well into 2024, and the allocations for the impending “Antares” MI300X and MI300A GPUs are probably long since spoken for, anyone trying to build a GPU cluster to power a large language model for training or inference has to think outside of the box. …
All Content Copyright The Next Platform