[PATCH] D99152: [AMX] Prototype for vector and amx bitcast.

[LuoYuanke via Phabricator via llvm-commits]

LuoYuanke created this revision.
Herald added a subscriber: pengfei.
LuoYuanke requested review of this revision.
Herald added projects: clang, LLVM.
Herald added subscribers: llvm-commits, cfe-commits.

Introduce new intrinsic to cast vector and amx. This can prevent
middle-end optimization on bitcast. However sometimes we need the
optimizaton for bitcast. For inner_product of amx_cast.c, we have to
deal with llvm.x86.vector.amx.cast.v256i32.x86amx by ourselves.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D99152

Files:
  clang/lib/CodeGen/CGBuiltin.cpp
  clang/test/CodeGen/X86/amx_cast.c
  llvm/include/llvm/IR/IntrinsicsX86.td

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D99152.332553.patch
Type: text/x-patch
Size: 7383 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210323/54e2b8b7/attachment.bin>