[PATCH] D132329: [X86][RFC] Using `__bf16` for AVX512_BF16 intrinsics

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon added a comment.

A few minors - and this probably needs a release notes entry for 16.x?



================
Comment at: llvm/lib/Target/X86/X86ISelLowering.cpp:2185
+    addRegisterClass(MVT::v32bf16, &X86::VR512RegClass);
+    setOperationAction(ISD::BUILD_VECTOR, MVT::bf16, Custom);
+    setOperationAction(ISD::BUILD_VECTOR, MVT::v8bf16, Custom);
----------------
Isn't MVT::bf16 scalar? 


================
Comment at: llvm/test/CodeGen/X86/avx512bf16-intrinsics-upgrade.ll:30
 ; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
-; X64-NEXT:    vcvtne2ps2bf16 %zmm1, %zmm0, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7f,0xc9,0x72,0xc1]
+; X64-NEXT:    vmovdqu16 %zmm0, %zmm0 {%k1} {z} # encoding: [0x62,0xf1,0xff,0xc9,0x6f,0xc0]
 ; X64-NEXT:    retq # encoding: [0xc3]
----------------
any chance we can recover the predicated instruction?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D132329/new/

https://reviews.llvm.org/D132329