[llvm-branch-commits] [llvm-branch] r311478 - Merging r311263:

[Hans Wennborg via llvm-branch-commits]

Author: hans
Date: Tue Aug 22 10:44:59 2017
New Revision: 311478

URL: http://llvm.org/viewvc/llvm-project?rev=311478&view=rev
Log:
Merging r311263:
------------------------------------------------------------------------
r311263 | ctopper | 2017-08-19 15:02:02 -0700 (Sat, 19 Aug 2017) | 1 line

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

Modified:
    llvm/branches/release_50/   (props changed)
    llvm/branches/release_50/lib/Target/X86/X86InstrAVX512.td
    llvm/branches/release_50/test/CodeGen/X86/avx512-extract-subvector.ll

Propchange: llvm/branches/release_50/
------------------------------------------------------------------------------
--- svn:mergeinfo (original)
+++ svn:mergeinfo Tue Aug 22 10:44:59 2017
@@ -1,3 +1,3 @@
 /llvm/branches/Apple/Pertwee:110850,110961
 /llvm/branches/type-system-rewrite:133420-134817
-/llvm/trunk:155241,308483-308484,308503,308808,308813,308847,308891,308906,308950,308963,308978,308986,309044,309071,309113,309120,309122,309140,309227,309302,309321,309323,309325,309330,309343,309353,309355,309422,309481,309483,309495,309555,309561,309594,309614,309651,309744,309758,309849,309928,309930,309945,310066,310071,310190,310240-310242,310250,310253,310262,310267,310481,310492,310498,310510,310534,310552,310604,310712,310779,310784,310796,310842,310906,310926,310939,310979,310988,310990-310991,311061,311068,311071,311087,311229,311258,311429
+/llvm/trunk:155241,308483-308484,308503,308808,308813,308847,308891,308906,308950,308963,308978,308986,309044,309071,309113,309120,309122,309140,309227,309302,309321,309323,309325,309330,309343,309353,309355,309422,309481,309483,309495,309555,309561,309594,309614,309651,309744,309758,309849,309928,309930,309945,310066,310071,310190,310240-310242,310250,310253,310262,310267,310481,310492,310498,310510,310534,310552,310604,310712,310779,310784,310796,310842,310906,310926,310939,310979,310988,310990-310991,311061,311068,311071,311087,311229,311258,311263,311429

Modified: llvm/branches/release_50/lib/Target/X86/X86InstrAVX512.td
URL: http://llvm.org/viewvc/llvm-project/llvm/branches/release_50/lib/Target/X86/X86InstrAVX512.td?rev=311478&r1=311477&r2=311478&view=diff
==============================================================================
--- llvm/branches/release_50/lib/Target/X86/X86InstrAVX512.td (original)
+++ llvm/branches/release_50/lib/Target/X86/X86InstrAVX512.td Tue Aug 22 10:44:59 2017
@@ -3619,8 +3619,8 @@ 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/branches/release_50/test/CodeGen/X86/avx512-extract-subvector.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/branches/release_50/test/CodeGen/X86/avx512-extract-subvector.ll?rev=311478&r1=311477&r2=311478&view=diff
==============================================================================
--- llvm/branches/release_50/test/CodeGen/X86/avx512-extract-subvector.ll (original)
+++ llvm/branches/release_50/test/CodeGen/X86/avx512-extract-subvector.ll Tue Aug 22 10:44:59 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: