[llvm] r296411 - [SLP] Load sorting should not try to sort things that aren't loads.

[Michael Kuperstein via llvm-commits]

Author: mkuper
Date: Mon Feb 27 17:18:11 2017
New Revision: 296411

URL: http://llvm.org/viewvc/llvm-project?rev=296411&view=rev
Log:
[SLP] Load sorting should not try to sort things that aren't loads.

We may get a VL where the first element is a load, but the others
aren't. Trying to sort such VLs can only lead to sorrow.

Added:
    llvm/trunk/test/Transforms/SLPVectorizer/X86/jumbled-same.ll
Modified:
    llvm/trunk/lib/Analysis/LoopAccessAnalysis.cpp

Modified: llvm/trunk/lib/Analysis/LoopAccessAnalysis.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Analysis/LoopAccessAnalysis.cpp?rev=296411&r1=296410&r2=296411&view=diff
==============================================================================
--- llvm/trunk/lib/Analysis/LoopAccessAnalysis.cpp (original)
+++ llvm/trunk/lib/Analysis/LoopAccessAnalysis.cpp Mon Feb 27 17:18:11 2017
@@ -1052,7 +1052,12 @@ bool llvm::sortMemAccesses(ArrayRef<Valu
   Value *Obj0 = GetUnderlyingObject(Ptr0, DL);
 
   for (auto *Val : VL) {
+    // The only kind of access we care about here is load.
+    if (!isa<LoadInst>(Val))
+      return false;
+
     Value *Ptr = getPointerOperand(Val);
+    assert(Ptr && "Expected value to have a pointer operand.");
 
     // If a pointer refers to a different underlying object, bail - the
     // pointers are by definition incomparable.

Added: llvm/trunk/test/Transforms/SLPVectorizer/X86/jumbled-same.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/SLPVectorizer/X86/jumbled-same.ll?rev=296411&view=auto
==============================================================================
--- llvm/trunk/test/Transforms/SLPVectorizer/X86/jumbled-same.ll (added)
+++ llvm/trunk/test/Transforms/SLPVectorizer/X86/jumbled-same.ll Mon Feb 27 17:18:11 2017
@@ -0,0 +1,43 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -slp-vectorizer -S -mtriple=x86_64-unknown-linux -mattr=+sse4.2 | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+ at a = common local_unnamed_addr global [4 x i32] zeroinitializer, align 4
+ at b = common local_unnamed_addr global [4 x i32] zeroinitializer, align 4
+
+define i32 @fn1() {
+; CHECK-LABEL: @fn1(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x i32>, <4 x i32>* bitcast ([4 x i32]* @b to <4 x i32>*), align 4
+; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> undef, <4 x i32> <i32 1, i32 2, i32 3, i32 0>
+; CHECK-NEXT:    [[TMP2:%.*]] = icmp sgt <4 x i32> [[TMP1]], zeroinitializer
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x i32> [[TMP0]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> undef, i32 [[TMP3]], i32 0
+; CHECK-NEXT:    [[TMP5:%.*]] = insertelement <4 x i32> [[TMP4]], i32 ptrtoint (i32 ()* @fn1 to i32), i32 1
+; CHECK-NEXT:    [[TMP6:%.*]] = insertelement <4 x i32> [[TMP5]], i32 ptrtoint (i32 ()* @fn1 to i32), i32 2
+; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x i32> [[TMP6]], i32 8, i32 3
+; CHECK-NEXT:    [[TMP8:%.*]] = select <4 x i1> [[TMP2]], <4 x i32> [[TMP7]], <4 x i32> <i32 6, i32 0, i32 0, i32 0>
+; CHECK-NEXT:    store <4 x i32> [[TMP8]], <4 x i32>* bitcast ([4 x i32]* @a to <4 x i32>*), align 4
+; CHECK-NEXT:    ret i32 0
+;
+entry:
+  %0 = load i32, i32* getelementptr ([4 x i32], [4 x i32]* @b, i64 0, i32 0), align 4
+  %cmp = icmp sgt i32 %0, 0
+  %cond = select i1 %cmp, i32 8, i32 0
+  store i32 %cond, i32* getelementptr inbounds ([4 x i32], [4 x i32]* @a, i64 0, i32 3), align 4
+  %1 = load i32, i32* getelementptr ([4 x i32], [4 x i32]* @b, i64 0, i32 1), align 4
+  %cmp1 = icmp sgt i32 %1, 0
+  %. = select i1 %cmp1, i32 %1, i32 6
+  store i32 %., i32* getelementptr inbounds ([4 x i32], [4 x i32]* @a, i64 0, i32 0), align 4
+  %2 = load i32, i32* getelementptr ([4 x i32], [4 x i32]* @b, i64 0, i32 2), align 4
+  %cmp4 = icmp sgt i32 %2, 0
+  %3 = select i1 %cmp4, i32 ptrtoint (i32 ()* @fn1 to i32), i32 0
+  store i32 %3, i32* getelementptr inbounds ([4 x i32], [4 x i32]* @a, i64 0, i32 1), align 4
+  %4 = load i32, i32* getelementptr ([4 x i32], [4 x i32]* @b, i64 0, i32 3), align 4
+  %cmp6 = icmp sgt i32 %4, 0
+  %5 = select i1 %cmp6, i32 ptrtoint (i32 ()* @fn1 to i32), i32 0
+  store i32 %5, i32* getelementptr inbounds ([4 x i32], [4 x i32]* @a, i64 0, i32 2), align 4
+  ret i32 0
+}