Qianshui-Jiang commented on PR #15685: URL: https://github.com/apache/tvm/pull/15685#issuecomment-1717046584
@cbalint13 @vvchernov big thanks for your hard work and dicussion! Here is few comments. Actually before the CasecadeLake we use avx512 to handle the 8bit and 16bit integer, so pmaddubs used here is for `SkyLake`. And start from `CasecadeLake` we have `avx512vnni`, so there is other more instrcutions like `vpdpbusd` and `vpdpwssd`, it fused some of `pmadd` instruction we used before, Now when we move to `SapphireRapids`， we have `amx-vnni`, which use amx instrctions to handle the 8bit integer. Yes ur right, `avxvnni` in `AlderLake` is due to the lack of its avx512 instruction set in 12th client CPU. I support to expose interface for fetch all the features in particular arch, but still suggest to let TVM detect the feature throught the arch name some thing like `AlderLake` or `IceLake`. cuz users may not clear of the instuction set equipment of their platform but clear of the name. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
