Timothy Prickett Morgan

Through the many years that we have been following the OS/400 and IBM i platform, we have always been an advocate for powerful entry machines that act as a feeder into the larger machines into which customers might grow. Somewhere between 1988 and 2008, Moore’s Law outpaced the capacity increases that most small IBM i shops needed, and it has been difficult to make a machine that is small enough to be useful and cheap enough to be attractive yet expensive enough to make it all worth IBM’s while.

Today’s pace of business requires companies to find faster ways to serve customers, gather actionable insights, increase operational efficiency, and

Just about everybody, including Nvidia, thinks that in the long run, most people running most AI training and inference workloads at any appreciable scale – hundreds to millions of datacenter devices – will want a cheaper alternative for networking AI accelerators than InfiniBand.

It has taken almost two years to complete the Power10 server set and it has been almost four years since we first wrote about the details of the Power10 processor, but with the launch of the “Bonnell” Power S1012 entry server last week, which will start shipping on June 14, the set is indeed complete. Unless something weird happens, there will be no additional Power Systems servers announced until the Power11 iron starts rolling out sometime in 2025.

If high bandwidth memory was widely available and we had cheap and reliable fusion power, there never would have been a move to use GPU and other compute engines as vector and matrix math offload engines. But unfortunately for Earth and very fortunately for Nvidia – and now, to a certain extent, AMD – neither HBM nor electricity are cheap, which means supercomputer architecture has been shifting to an accelerated model that pairs the CPUs we all know and love with a massively parallel offload engine of some kind.

Very few organizations have enough iron to train a large language model in a reasonably short amount of time, and that is why most will be grabbing

The difference between “high performance computing” in the general way that many thousands of organizations run traditional simulation and modeling applications and the kind of exascale computing that is only now becoming a little more commonplace is like the difference between a single, two door coupe that goes 65 miles per hour (most of the time) and a fleet of bullet trains that can each hold over 1,300 people and move at more than 300 miles per hour, connecting a country or a continent.

We think that waferscale computing is an interesting and even an inevitable concept for certain kinds of compute and memory. But inevitably, the work you

If you stare at something for a little bit of time and let your mind wander, you can think of a new way to analyze something that you have looked at a

If you look at the financial results for Cisco Systems over more than a decade, it is hard to tell one year from the other. The company has gone through