Intel launches new Emerald Rapids Xeon CPUs with fast cadence

Last week, Intel released 4nm Meteor Lake processors with long-awaited chiplet architecture. At the same time, Intel is also releasing the second generation of chiplet Xeons called “Emerald Rapids”. It follows very quickly after the previous “Sapphire Rapids” and, along with various improvements and fixes, it curiously walks back on chiplets a bit, as it uses only two instead of four. This has not only reduced costs but also power draw. Read more “Intel launches new Emerald Rapids Xeon CPUs with fast cadence” »

Amazon unveils 96-core ARM Graviton4 CPU and Trainium2 AI chip

Last month, Microsoft unveiled their first custom processors being developed for datacenter and Azure services. Also Amazon, which was the first of these US hyperscalers to go the custom hardware route, is now launching new CPUs for its servers. And with it Trainium2, already the second generation of an in-house developed AI accelerator. Amazon also revealed that it has already produced over two million of its CPUs. Read more “Amazon unveils 96-core ARM Graviton4 CPU and Trainium2 AI chip” »

Nvidia’s new fastest AI GPU: H200 with 141GB of HBM3E memory

Last year, Nvidia launched the 4nm H100 accelerator with Hopper architecture. It has since been the company’s fastest GPU for AI. Now the company is launching its successor dubbed H200. It isn’t quite a new generation yet, but something of a refresh that will lead Nvidia’s lineup until the next generation with the Blackwell architecture is released. The H200 relies on the use of faster memory, but that should also lift overall performance. Read more “Nvidia’s new fastest AI GPU: H200 with 141GB of HBM3E memory” »

AMD launches Epyc 8004: lower-cost, lower-power SP6 platform

This year, AMD has already released the Epyc 9004 “Genoa”, a 96-core server version of the Zen 4 architecture and even the HPC Genoa-X models equipped with 3D V-Cache. Now they are joined by a separate family – processors codenamed Siena, which are specifically designed for lower power draw and lower cost. They have their own SP6 platform with six-channel memory controller (so the boards should cost less too) and TDPs starting from 70W. Read more “AMD launches Epyc 8004: lower-cost, lower-power SP6 platform” »

Jim Keller’s new firm plans RISC-V CPUs with Apple-like wide cores

RISC-V processors are still yet to reach above the embedded sector, but with the current developments around ARM, they may be closer to that goal than we think. They ISA might even come to the highest performance processor segment currently ruled by Intel and AMD that ARM itself (with the exception of Apple) is still just trying to crack. Tenstorrent, led by Jim Keller, is now developing processors that could be close to those from Apple. Read more “Jim Keller’s new firm plans RISC-V CPUs with Apple-like wide cores” »

Russia has local Baikal-S server CPUs. 6nm 128-core in the works

In the summer we reported that Russia is now making (or rather designing, as fabbing will happen at TSMC) its own ARM Baikal-M CPUs, which are also being used in computers intended for state administration. It was an outdated SoC with Cortex-A57, the very first 64-bit ARM cores. But now the same company has a much cooler processor: a 48-core with a newer architecture that could replace the cheaper server Xeons and Epycs. Read more “Russia has local Baikal-S server CPUs. 6nm 128-core in the works” »