[PATCH] D63386: [LV] Deny irregular types in interleavedAccessCanBeWidened

[Bjorn Pettersson via Phabricator via llvm-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rL363547: [LV] Deny irregular types in interleavedAccessCanBeWidened (authored by bjope, committed by ).

Changed prior to commit:
  https://reviews.llvm.org/D63386?vs=204951&id=205038#toc

Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D63386/new/

https://reviews.llvm.org/D63386

Files:
  llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
  llvm/trunk/test/Transforms/LoopVectorize/X86/x86_fp80-interleaved-access.ll


Index: llvm/trunk/test/Transforms/LoopVectorize/X86/x86_fp80-interleaved-access.ll
===================================================================
--- llvm/trunk/test/Transforms/LoopVectorize/X86/x86_fp80-interleaved-access.ll
+++ llvm/trunk/test/Transforms/LoopVectorize/X86/x86_fp80-interleaved-access.ll
@@ -0,0 +1,29 @@
+; RUN: opt < %s -enable-interleaved-mem-accesses=true -force-vector-width=4 -loop-vectorize -S | FileCheck %s
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.7.0"
+
+; Verify that we do not get any loads of vectors with x86_fp80 elements.
+;
+; CHECK-NOT: load {{.*}} x x86_fp80
+define x86_fp80 @foo(x86_fp80* %a) {
+entry:
+  br label %for.body
+
+for.cond.cleanup:
+  ret x86_fp80 %3
+
+for.body:
+  %i.09 = phi i16 [ 0, %entry ], [ %add3, %for.body ]
+  %res.08 = phi x86_fp80 [ undef, %entry ], [ %3, %for.body ]
+  %arrayidx = getelementptr inbounds x86_fp80, x86_fp80* %a, i16 %i.09
+  %0 = load x86_fp80, x86_fp80* %arrayidx, align 1
+  %add = or i16 %i.09, 1
+  %arrayidx2 = getelementptr inbounds x86_fp80, x86_fp80* %a, i16 %add
+  %1 = load x86_fp80, x86_fp80* %arrayidx2, align 1
+  %2 = fadd fast x86_fp80 %0, %res.08
+  %3 = fadd fast x86_fp80 %2, %1
+  %add3 = add nuw nsw i16 %i.09, 2
+  %cmp = icmp ult i16 %add3, 400
+  br i1 %cmp, label %for.body, label %for.cond.cleanup
+}
Index: llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
===================================================================
--- llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -4412,6 +4412,13 @@
   auto *Group = getInterleavedAccessGroup(I);
   assert(Group && "Must have a group.");
 
+  // If the instruction's allocated size doesn't equal it's type size, it
+  // requires padding and will be scalarized.
+  auto &DL = I->getModule()->getDataLayout();
+  auto *ScalarTy = getMemInstValueType(I);
+  if (hasIrregularType(ScalarTy, DL, VF))
+    return false;
+
   // Check if masking is required.
   // A Group may need masking for one of two reasons: it resides in a block that
   // needs predication, or it was decided to use masking to deal with gaps.


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D63386.205038.patch
Type: text/x-patch
Size: 2318 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190617/4dc5c979/attachment.bin>