[llvm] r311263 - [AVX512] Use alignedstore256 in a pattern that's emitting a 256-bit movaps from an extract subvector operation.

[Craig Topper via llvm-commits]

Author: ctopper
Date: Sat Aug 19 15:02:02 2017
New Revision: 311263

URL: http://llvm.org/viewvc/llvm-project?rev=311263&view=rev
Log:
[AVX512] Use alignedstore256 in a pattern that's emitting a 256-bit movaps from an extract subvector operation.

Modified:
    llvm/trunk/lib/Target/X86/X86InstrAVX512.td
    llvm/trunk/test/CodeGen/X86/avx512-extract-subvector.ll

Modified: llvm/trunk/lib/Target/X86/X86InstrAVX512.td
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86InstrAVX512.td?rev=311263&r1=311262&r2=311263&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86InstrAVX512.td (original)
+++ llvm/trunk/lib/Target/X86/X86InstrAVX512.td Sat Aug 19 15:02:02 2017
@@ -3721,8 +3721,8 @@ let Predicates = [HasVLX] in {
   def : Pat<(alignedstore256 (v4f64 (extract_subvector
                                      (v8f64 VR512:$src), (iPTR 0))), addr:$dst),
      (VMOVAPDZ256mr addr:$dst, (v4f64 (EXTRACT_SUBREG VR512:$src,sub_ymm)))>;
-  def : Pat<(alignedstore (v8f32 (extract_subvector
-                                  (v16f32 VR512:$src), (iPTR 0))), addr:$dst),
+  def : Pat<(alignedstore256 (v8f32 (extract_subvector
+                                     (v16f32 VR512:$src), (iPTR 0))), addr:$dst),
      (VMOVAPSZ256mr addr:$dst, (v8f32 (EXTRACT_SUBREG VR512:$src,sub_ymm)))>;
   def : Pat<(alignedstore256 (v4i64 (extract_subvector
                                      (v8i64 VR512:$src), (iPTR 0))), addr:$dst),

Modified: llvm/trunk/test/CodeGen/X86/avx512-extract-subvector.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/avx512-extract-subvector.ll?rev=311263&r1=311262&r2=311263&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/avx512-extract-subvector.ll (original)
+++ llvm/trunk/test/CodeGen/X86/avx512-extract-subvector.ll Sat Aug 19 15:02:02 2017
@@ -493,7 +493,7 @@ entry:
 define void @extract_subvector512_v8f32_store_lo_align_16(float* nocapture %addr, <16 x float> %a) nounwind uwtable ssp {
 ; SKX-LABEL: extract_subvector512_v8f32_store_lo_align_16:
 ; SKX:       ## BB#0: ## %entry
-; SKX-NEXT:    vmovaps %ymm0, (%rdi)
+; SKX-NEXT:    vmovups %ymm0, (%rdi)
 ; SKX-NEXT:    vzeroupper
 ; SKX-NEXT:    retq
 entry: