From f8d1d0019094acb3979aee60f98d11abe6cc92cf Mon Sep 17 00:00:00 2001
From: Simon Pilgrim <llvm-dev@redking.me.uk>
Date: Sat, 31 Aug 2019 16:21:31 +0000
Subject: [PATCH] [X86] EltsFromConsecutiveLoads - Don't confuse elt count with
 vector element count (PR43170)

EltsFromConsecutiveLoads was assuming that the number of input elts was the same as the number of elements in the output vector type when creating a zeroing shuffle, causing an assert when subvectors were being combined instead of just scalars.

llvm-svn: 370592
---
 llvm/lib/Target/X86/X86ISelLowering.cpp       | 25 +++++++-----
 .../test/CodeGen/X86/vector-shuffle-avx512.ll | 38 +++++++++++++++++++
 2 files changed, 53 insertions(+), 10 deletions(-)

diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 5812cc39b2ee..c603aa51efca 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -7832,17 +7832,22 @@ static SDValue EltsFromConsecutiveLoads(EVT VT, ArrayRef<SDValue> Elts,
     // IsConsecutiveLoadWithZeros - we need to create a shuffle of the loaded
     // vector and a zero vector to clear out the zero elements.
     if (!isAfterLegalize && VT.isVector()) {
-      SmallVector<int, 4> ClearMask(NumElems, -1);
-      for (unsigned i = 0; i < NumElems; ++i) {
-        if (ZeroMask[i])
-          ClearMask[i] = i + NumElems;
-        else if (LoadMask[i])
-          ClearMask[i] = i;
+      unsigned NumMaskElts = VT.getVectorNumElements();
+      if ((NumMaskElts % NumElems) == 0) {
+        unsigned Scale = NumMaskElts / NumElems;
+        SmallVector<int, 4> ClearMask(NumMaskElts, -1);
+        for (unsigned i = 0; i < NumElems; ++i) {
+          if (UndefMask[i])
+            continue;
+          int Offset = ZeroMask[i] ? NumMaskElts : 0;
+          for (unsigned j = 0; j != Scale; ++j)
+            ClearMask[(i * Scale) + j] = (i * Scale) + j + Offset;
+        }
+        SDValue V = CreateLoad(VT, LDBase);
+        SDValue Z = VT.isInteger() ? DAG.getConstant(0, DL, VT)
+                                   : DAG.getConstantFP(0.0, DL, VT);
+        return DAG.getVectorShuffle(VT, DL, V, Z, ClearMask);
       }
-      SDValue V = CreateLoad(VT, LDBase);
-      SDValue Z = VT.isInteger() ? DAG.getConstant(0, DL, VT)
-                                 : DAG.getConstantFP(0.0, DL, VT);
-      return DAG.getVectorShuffle(VT, DL, V, Z, ClearMask);
     }
   }
 
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-avx512.ll b/llvm/test/CodeGen/X86/vector-shuffle-avx512.ll
index 45f9306326f4..c669562dcac2 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-avx512.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-avx512.ll
@@ -527,3 +527,41 @@ define <16 x float> @test_masked_permps_v16f32(<16 x float>* %vp, <16 x float> %
   %res = select <16 x i1> <i1 1, i1 1, i1 1, i1 0, i1 1, i1 1, i1 0, i1 0, i1 1, i1 1, i1 1, i1 0, i1 1, i1 0, i1 1, i1 0>, <16 x float> %shuf, <16 x float> %vec2
   ret <16 x float> %res
 }
+
+%union1= type { <16 x float> }
+@src1 = external dso_local local_unnamed_addr global %union1, align 64
+
+define void @PR43170(<16 x float>* %a0) {
+; SKX64-LABEL: PR43170:
+; SKX64:       # %bb.0: # %entry
+; SKX64-NEXT:    vmovaps {{.*}}(%rip), %ymm0
+; SKX64-NEXT:    vmovaps %zmm0, (%rdi)
+; SKX64-NEXT:    vzeroupper
+; SKX64-NEXT:    retq
+;
+; KNL64-LABEL: PR43170:
+; KNL64:       # %bb.0: # %entry
+; KNL64-NEXT:    vmovaps {{.*}}(%rip), %ymm0
+; KNL64-NEXT:    vmovaps %zmm0, (%rdi)
+; KNL64-NEXT:    retq
+;
+; SKX32-LABEL: PR43170:
+; SKX32:       # %bb.0: # %entry
+; SKX32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; SKX32-NEXT:    vmovaps src1, %ymm0
+; SKX32-NEXT:    vmovaps %zmm0, (%eax)
+; SKX32-NEXT:    vzeroupper
+; SKX32-NEXT:    retl
+;
+; KNL32-LABEL: PR43170:
+; KNL32:       # %bb.0: # %entry
+; KNL32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; KNL32-NEXT:    vmovaps src1, %ymm0
+; KNL32-NEXT:    vmovaps %zmm0, (%eax)
+; KNL32-NEXT:    retl
+entry:
+  %0 = load <8 x float>, <8 x float>* bitcast (%union1* @src1 to <8 x float>*), align 64
+  %1 = shufflevector <8 x float> %0, <8 x float> zeroinitializer, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+  store <16 x float> %1, <16 x float>* %a0, align 64
+  ret void
+}