[LoopVectorize][SVE] Fix crash when vectorising FP negation

This patch fixes a crash encountered when vectorising the following loop:

 void foo(float *dst, float *src, long long n) {
   for (long long i = 0; i < n; i++)
     dst[i] = -src[i];
 }

using scalable vectors. I've added a test to

 Transforms/LoopVectorize/AArch64/sve-basic-vec.ll

as well as cleaned up the other tests in the same file.

Differential Revision: https://reviews.llvm.org/D98054

diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 2878101..2e249d7 100644 (file)
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -7549,7 +7549,6 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, ElementCount VF,
         Op2VK, TargetTransformInfo::OP_None, Op2VP, Operands, I);
   }
   case Instruction::FNeg: {
-    assert(!VF.isScalable() && "VF is assumed to be non scalable.");
     return TTI.getArithmeticInstrCost(
         I->getOpcode(), VectorTy, CostKind, TargetTransformInfo::OK_AnyValue,
         TargetTransformInfo::OK_AnyValue, TargetTransformInfo::OP_None,

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-basic-vec.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-basic-vec.ll
index d548ca7..ad6f42b 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-basic-vec.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-basic-vec.ll
@@ -14,8 +14,7 @@ define void @cmpsel_i32(i32* noalias nocapture %a, i32* noalias nocapture readon
 ; CHECK:         store <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32>* {{.*}}, align 4
 ;
 entry:
-  %cmp7 = icmp sgt i64 %n, 0
-  br i1 %cmp7, label %for.body, label %for.end
+  br label %for.body
 
 for.body:                                         ; preds = %entry, %for.body
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
@@ -46,8 +45,7 @@ define void @cmpsel_f32(float* noalias nocapture %a, float* noalias nocapture re
 ; CHECK:         store <vscale x 4 x float> [[TMP2]], <vscale x 4 x float>* {{.*}}, align 4
 
 entry:
-  %cmp8 = icmp sgt i64 %n, 0
-  br i1 %cmp8, label %for.body, label %for.end
+  br label %for.body
 
 for.body:                                         ; preds = %entry, %for.body
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
@@ -59,7 +57,33 @@ for.body:                                         ; preds = %entry, %for.body
   store float %conv, float* %arrayidx3, align 4
   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
   %exitcond.not = icmp eq i64 %indvars.iv.next, %n
-  br i1 %exitcond.not, label %for.end, label %for.body, !llvm.loop !6
+  br i1 %exitcond.not, label %for.end, label %for.body, !llvm.loop !0
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+define void @fneg_f32(float* noalias nocapture %a, float* noalias nocapture readonly %b, i64 %n) {
+; CHECK-LABEL: @fneg_f32(
+; CHECK-NEXT:  entry:
+; CHECK:       vector.body:
+; CHECK:         [[WIDE_LOAD:%.*]] = load <vscale x 4 x float>, <vscale x 4 x float>* {{.*}}, align 4
+; CHECK-NEXT:    [[TMP1:%.*]] = fneg <vscale x 4 x float> [[WIDE_LOAD]]
+; CHECK:         store <vscale x 4 x float> [[TMP1]], <vscale x 4 x float>* {{.*}}, align 4
+
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds float, float* %b, i64 %indvars.iv
+  %0 = load float, float* %arrayidx, align 4
+  %fneg = fneg float %0
+  %arrayidx3 = getelementptr inbounds float, float* %a, i64 %indvars.iv
+  store float %fneg, float* %arrayidx3, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond.not = icmp eq i64 %indvars.iv.next, %n
+  br i1 %exitcond.not, label %for.end, label %for.body, !llvm.loop !0
 
 for.end:                                          ; preds = %for.body, %entry
   ret void
@@ -71,4 +95,3 @@ for.end:                                          ; preds = %for.body, %entry
 !3 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}
 !4 = !{!"llvm.loop.interleave.count", i32 1}
 !5 = !{!"llvm.loop.vectorize.enable", i1 true}
-!6 = distinct !{!6, !1, !2, !3, !4, !5}