Comments on: Move Over X86, Amazon’s Arm HPC instances Are Live https://www.nextplatform.com/2023/06/22/move-over-x86-amazons-arm-hpc-instances-are-live/ In-depth coverage of high-end computing at large enterprises, supercomputing centers, hyperscale data centers, and public clouds. Fri, 23 Jun 2023 21:45:44 +0000 hourly 1 https://wordpress.org/?v=6.7.1 By: Hubert https://www.nextplatform.com/2023/06/22/move-over-x86-amazons-arm-hpc-instances-are-live/#comment-210311 Fri, 23 Jun 2023 21:45:44 +0000 https://www.nextplatform.com/?p=142577#comment-210311 If I remember, A64FX has 2x512b (2x64Bytes), Neoverse V1 (Graviton 3) has 2x256b (2x32B) and V2 (Grace) has 4x128b (4x16B). The Neoverses match the common cache line size of 64B (A64FX’s SVE data would require 2 lines) and should consume much less than Fugaku’s SVE units (where energetic efficiency was not as good as some other HPC machines).

]]> By: Timothy Prickett Morgan https://www.nextplatform.com/2023/06/22/move-over-x86-amazons-arm-hpc-instances-are-live/#comment-210298 Fri, 23 Jun 2023 11:52:01 +0000 https://www.nextplatform.com/?p=142577#comment-210298 In reply to Shreshth Dharm-Datta.

I think by definition it has the Neoverse V1 vector engines, not the ones used in A64FX.

]]> By: Shreshth Dharm-Datta https://www.nextplatform.com/2023/06/22/move-over-x86-amazons-arm-hpc-instances-are-live/#comment-210282 Thu, 22 Jun 2023 18:56:21 +0000 https://www.nextplatform.com/?p=142577#comment-210282 Does the Graviton3E also have the SVE vector width of the A64? (For code compatibility with the Virtual Fugaku)?

]]>