From: Simon Pilgrim Date: Thu, 2 Feb 2017 18:26:28 +0000 (+0000) Subject: [X86][XOP] Added FIXME comments to missed shuffle combine opportunities X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=2a8f190124a7ceb2c4c26cdb9756f78e33822207;p=llvm [X86][XOP] Added FIXME comments to missed shuffle combine opportunities Requested by @silvas git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@293916 91177308-0d34-0410-b5e6-96231b3b80d8 --- diff --git a/test/CodeGen/X86/vector-shuffle-combining-xop.ll b/test/CodeGen/X86/vector-shuffle-combining-xop.ll index 16878c32638..eef7d5a1366 100644 --- a/test/CodeGen/X86/vector-shuffle-combining-xop.ll +++ b/test/CodeGen/X86/vector-shuffle-combining-xop.ll @@ -318,6 +318,7 @@ define <4 x i32> @combine_vpperm_10zz32BA(<4 x i32> %a0, <4 x i32> %a1) { ret <4 x i32> %res3 } +; FIXME: Duplicated load in i686 define void @buildvector_v4f32_0404(float %a, float %b, <4 x float>* %ptr) { ; X32-LABEL: buildvector_v4f32_0404: ; X32: # BB#0: @@ -341,6 +342,7 @@ define void @buildvector_v4f32_0404(float %a, float %b, <4 x float>* %ptr) { ret void } +; FIXME: Failed to fold to vpermil2ps define void @buildvector_v4f32_07z6(float %a, <4 x float> %b, <4 x float>* %ptr) { ; X32-LABEL: buildvector_v4f32_07z6: ; X32: # BB#0: