================
@@ -26,7 +26,9 @@ define bfloat @return_arg_bf16(bfloat %x) #0 {
; FAST_ISEL_AVX512BF16-LABEL: return_arg_bf16:
; FAST_ISEL_AVX512BF16: # %bb.0:
; FAST_ISEL_AVX512BF16-NEXT: vpslld $16, %xmm0, %xmm0
-; FAST_ISEL_AVX512BF16-NEXT: vcvtneps2bf16 %xmm0, %xmm0
+; FAST_ISEL_AVX512BF16-NEXT: vmovd %xmm0, %eax
+; FAST_ISEL_AVX512BF16-NEXT: shrl $16, %eax
----------------
Andarwinux wrote:
Thanks! According to data from uops.info, with #230698, this is not a
regression anymore.
https://github.com/llvm/llvm-project/pull/230557
_______________________________________________
llvm-branch-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
