Comments on: Google Covers Its Compute Engine Bases Because It Has To https://www.nextplatform.com/2024/10/31/google-covers-its-compute-engine-bases-because-it-has-to/ In-depth coverage of high-end computing at large enterprises, supercomputing centers, hyperscale data centers, and public clouds. Tue, 12 Nov 2024 14:10:43 +0000 hourly 1 https://wordpress.org/?v=6.7.1 By: Slim Albert https://www.nextplatform.com/2024/10/31/google-covers-its-compute-engine-bases-because-it-has-to/#comment-238929 Fri, 01 Nov 2024 16:17:33 +0000 https://www.nextplatform.com/?p=144925#comment-238929 I have to concur, it’ll be great to get the lowdown on these Cheeky Olympian cut-and-paste CSS Neoverse V2 Demeter chips from the usual hyperscaler suspects! My file on them is a bit holey and in need of update … there’s the 2×48-core Graviton4 with 4×128-bit vector units, the 2×64-core Cobalt 100 (with vectors?), this here 1×72 or 2×36-core Axion (it seems; vectors?), and of course the 72-core Grace with 2x128b or 4x128b vectors (which is it though?). I guess their amount of L2 cache and number of memory channels vary, and they may not have HBM that might be found instead on their paired accelerators (Trainium2, Maia 100, Trillium TPU v6, Hopper/Blackwell).

So many details to be filled in … “Inquisition minds” …

P.S. The big table does show better Price/Peak Perf (in green) for TPU v6 than v1-V5, which is nice (in my understanding)!

]]>
By: HuMo https://www.nextplatform.com/2024/10/31/google-covers-its-compute-engine-bases-because-it-has-to/#comment-238920 Fri, 01 Nov 2024 14:31:05 +0000 https://www.nextplatform.com/?p=144925#comment-238920 In reply to Eric Olson.

Most likely an entangled qubit of superposed decoherent FLINTs (the mixed FLoat/INt teleportation state)! 8^b

]]>
By: Eric Olson https://www.nextplatform.com/2024/10/31/google-covers-its-compute-engine-bases-because-it-has-to/#comment-238851 Thu, 31 Oct 2024 22:47:48 +0000 https://www.nextplatform.com/?p=144925#comment-238851 I read “474 petaflops at INT8 precision” and wonder what an INT8 precision floating point number might actually be.

]]>