diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp --- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp +++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp @@ -10356,8 +10356,8 @@ const std::string DebugLocStr = getDebugLocString(L); #endif /* NDEBUG */ - LLVM_DEBUG(dbgs() << "\nLV: Checking a loop in \"" - << L->getHeader()->getParent()->getName() << "\" from " + LLVM_DEBUG(dbgs() << "\nLV: Checking a loop in '" + << L->getHeader()->getParent()->getName() << "' from " << DebugLocStr << "\n"); LoopVectorizeHints Hints(L, InterleaveOnlyWhenForced, *ORE, TTI); diff --git a/llvm/test/Analysis/CostModel/X86/gather-i16-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/gather-i16-with-i8-index.ll --- a/llvm/test/Analysis/CostModel/X86/gather-i16-with-i8-index.ll +++ b/llvm/test/Analysis/CostModel/X86/gather-i16-with-i8-index.ll @@ -14,7 +14,7 @@ @B = global [1024 x i16] zeroinitializer, align 128 @C = global [1024 x i16] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i16, i16* %inB, align 2 ; SSE2: LV: Found an estimated cost of 24 for VF 2 For instruction: %valB = load i16, i16* %inB, align 2 diff --git a/llvm/test/Analysis/CostModel/X86/gather-i32-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/gather-i32-with-i8-index.ll --- a/llvm/test/Analysis/CostModel/X86/gather-i32-with-i8-index.ll +++ b/llvm/test/Analysis/CostModel/X86/gather-i32-with-i8-index.ll @@ -14,7 +14,7 @@ @B = global [1024 x i32] zeroinitializer, align 128 @C = global [1024 x i32] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i32, i32* %inB, align 4 ; SSE2: LV: Found an estimated cost of 25 for VF 2 For instruction: %valB = load i32, i32* %inB, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/gather-i64-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/gather-i64-with-i8-index.ll --- a/llvm/test/Analysis/CostModel/X86/gather-i64-with-i8-index.ll +++ b/llvm/test/Analysis/CostModel/X86/gather-i64-with-i8-index.ll @@ -14,7 +14,7 @@ @B = global [1024 x i64] zeroinitializer, align 128 @C = global [1024 x i64] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i64, i64* %inB, align 8 ; SSE2: LV: Found an estimated cost of 25 for VF 2 For instruction: %valB = load i64, i64* %inB, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/gather-i8-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/gather-i8-with-i8-index.ll --- a/llvm/test/Analysis/CostModel/X86/gather-i8-with-i8-index.ll +++ b/llvm/test/Analysis/CostModel/X86/gather-i8-with-i8-index.ll @@ -14,7 +14,7 @@ @B = global [1024 x i8] zeroinitializer, align 128 @C = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i8, i8* %inB, align 1 ; SSE2: LV: Found an estimated cost of 25 for VF 2 For instruction: %valB = load i8, i8* %inB, align 1 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-2.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-2.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-2.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-2.ll @@ -10,7 +10,7 @@ @A = global [1024 x float] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, float* %in0, align 4 ; SSE2: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load float, float* %in0, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-3.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-3.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-3.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-3.ll @@ -10,7 +10,7 @@ @A = global [1024 x float] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, float* %in0, align 4 ; SSE2: LV: Found an estimated cost of 9 for VF 2 For instruction: %v0 = load float, float* %in0, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-4.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-4.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-4.ll @@ -10,7 +10,7 @@ @A = global [1024 x float] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, float* %in0, align 4 ; SSE2: LV: Found an estimated cost of 12 for VF 2 For instruction: %v0 = load float, float* %in0, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-6.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-6.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f32-stride-6.ll @@ -10,7 +10,7 @@ @A = global [1024 x float] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, float* %in0, align 4 ; SSE2: LV: Found an estimated cost of 18 for VF 2 For instruction: %v0 = load float, float* %in0, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-2.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-2.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-2.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-2.ll @@ -10,7 +10,7 @@ @A = global [1024 x double] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, double* %in0, align 8 ; SSE2: LV: Found an estimated cost of 4 for VF 2 For instruction: %v0 = load double, double* %in0, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-3.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-3.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-3.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-3.ll @@ -10,7 +10,7 @@ @A = global [1024 x double] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, double* %in0, align 8 ; SSE2: LV: Found an estimated cost of 9 for VF 2 For instruction: %v0 = load double, double* %in0, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-4.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-4.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-4.ll @@ -10,7 +10,7 @@ @A = global [1024 x double] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, double* %in0, align 8 ; SSE2: LV: Found an estimated cost of 12 for VF 2 For instruction: %v0 = load double, double* %in0, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-6.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-6.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-6.ll @@ -10,7 +10,7 @@ @A = global [1024 x double] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, double* %in0, align 8 ; SSE2: LV: Found an estimated cost of 18 for VF 2 For instruction: %v0 = load double, double* %in0, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-2.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-2.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-2.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-2.ll @@ -10,7 +10,7 @@ @A = global [1024 x i16] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2 ; SSE2: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-3.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-3.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-3.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-3.ll @@ -10,7 +10,7 @@ @A = global [1024 x i16] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2 ; SSE2: LV: Found an estimated cost of 18 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-4.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-4.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-4.ll @@ -10,7 +10,7 @@ @A = global [1024 x i16] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2 ; SSE2: LV: Found an estimated cost of 17 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-5.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-5.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-5.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-5.ll @@ -10,7 +10,7 @@ @A = global [1024 x i16] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2 ; SSE2: LV: Found an estimated cost of 22 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-6.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-6.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-6.ll @@ -10,7 +10,7 @@ @A = global [1024 x i16] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2 ; SSE2: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-2-indices-0u.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-2-indices-0u.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-2-indices-0u.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-2-indices-0u.ll @@ -10,7 +10,7 @@ @A = global [1024 x i32] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4 ; SSE2: LV: Found an estimated cost of 2 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-2.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-2.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-2.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-2.ll @@ -10,7 +10,7 @@ @A = global [1024 x i32] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4 ; SSE2: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3-indices-01u.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3-indices-01u.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3-indices-01u.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3-indices-01u.ll @@ -10,7 +10,7 @@ @A = global [1024 x i32] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4 ; SSE2: LV: Found an estimated cost of 14 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3-indices-0uu.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3-indices-0uu.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3-indices-0uu.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3-indices-0uu.ll @@ -10,7 +10,7 @@ @A = global [1024 x i32] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4 ; SSE2: LV: Found an estimated cost of 8 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3.ll @@ -10,7 +10,7 @@ @A = global [1024 x i32] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4 ; SSE2: LV: Found an estimated cost of 21 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-012u.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-012u.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-012u.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-012u.ll @@ -10,7 +10,7 @@ @A = global [1024 x i32] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4 ; SSE2: LV: Found an estimated cost of 21 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-01uu.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-01uu.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-01uu.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-01uu.ll @@ -10,7 +10,7 @@ @A = global [1024 x i32] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4 ; SSE2: LV: Found an estimated cost of 14 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-0uuu.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-0uuu.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-0uuu.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-0uuu.ll @@ -10,7 +10,7 @@ @A = global [1024 x i32] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4 ; SSE2: LV: Found an estimated cost of 7 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4.ll @@ -10,7 +10,7 @@ @A = global [1024 x i32] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4 ; SSE2: LV: Found an estimated cost of 28 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-6.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-6.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-6.ll @@ -10,7 +10,7 @@ @A = global [1024 x i32] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4 ; SSE2: LV: Found an estimated cost of 42 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-2.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-2.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-2.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-2.ll @@ -10,7 +10,7 @@ @A = global [1024 x i64] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, i64* %in0, align 8 ; SSE2: LV: Found an estimated cost of 4 for VF 2 For instruction: %v0 = load i64, i64* %in0, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-3.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-3.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-3.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-3.ll @@ -10,7 +10,7 @@ @A = global [1024 x i64] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, i64* %in0, align 8 ; SSE2: LV: Found an estimated cost of 21 for VF 2 For instruction: %v0 = load i64, i64* %in0, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-4.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-4.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-4.ll @@ -10,7 +10,7 @@ @A = global [1024 x i64] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, i64* %in0, align 8 ; SSE2: LV: Found an estimated cost of 28 for VF 2 For instruction: %v0 = load i64, i64* %in0, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-6.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-6.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-6.ll @@ -10,7 +10,7 @@ @A = global [1024 x i64] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, i64* %in0, align 8 ; SSE2: LV: Found an estimated cost of 42 for VF 2 For instruction: %v0 = load i64, i64* %in0, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-2.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-2.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-2.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-2.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, i8* %in0, align 1 ; SSE2: LV: Found an estimated cost of 14 for VF 2 For instruction: %v0 = load i8, i8* %in0, align 1 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-3.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-3.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-3.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-3.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, i8* %in0, align 1 ; SSE2: LV: Found an estimated cost of 23 for VF 2 For instruction: %v0 = load i8, i8* %in0, align 1 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-4.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-4.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-4.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, i8* %in0, align 1 ; SSE2: LV: Found an estimated cost of 28 for VF 2 For instruction: %v0 = load i8, i8* %in0, align 1 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-6.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-6.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i8-stride-6.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, i8* %in0, align 1 ; SSE2: LV: Found an estimated cost of 47 for VF 2 For instruction: %v0 = load i8, i8* %in0, align 1 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-2.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-2.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-2.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-2.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x float] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store float %v1, float* %out1, align 4 ; SSE2: LV: Found an estimated cost of 2 for VF 2 For instruction: store float %v1, float* %out1, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-3.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-3.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-3.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-3.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x float] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store float %v2, float* %out2, align 4 ; SSE2: LV: Found an estimated cost of 11 for VF 2 For instruction: store float %v2, float* %out2, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-4.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-4.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-4.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x float] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store float %v3, float* %out3, align 4 ; SSE2: LV: Found an estimated cost of 12 for VF 2 For instruction: store float %v3, float* %out3, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-6.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-6.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-f32-stride-6.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x float] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store float %v5, float* %out5, align 4 ; SSE2: LV: Found an estimated cost of 21 for VF 2 For instruction: store float %v5, float* %out5, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-2.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-2.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-2.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-2.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x double] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v1, double* %out1, align 8 ; SSE2: LV: Found an estimated cost of 6 for VF 2 For instruction: store double %v1, double* %out1, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-3.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-3.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-3.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-3.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x double] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v2, double* %out2, align 8 ; SSE2: LV: Found an estimated cost of 10 for VF 2 For instruction: store double %v2, double* %out2, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-4.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-4.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-4.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x double] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v3, double* %out3, align 8 ; SSE2: LV: Found an estimated cost of 12 for VF 2 For instruction: store double %v3, double* %out3, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-6.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-6.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-f64-stride-6.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x double] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v5, double* %out5, align 8 ; SSE2: LV: Found an estimated cost of 20 for VF 2 For instruction: store double %v5, double* %out5, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-2.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-2.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-2.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-2.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i16] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %v1, i16* %out1, align 2 ; SSE2: LV: Found an estimated cost of 2 for VF 2 For instruction: store i16 %v1, i16* %out1, align 2 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-3.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-3.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-3.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-3.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i16] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %v2, i16* %out2, align 2 ; SSE2: LV: Found an estimated cost of 16 for VF 2 For instruction: store i16 %v2, i16* %out2, align 2 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-4.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-4.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-4.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i16] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %v3, i16* %out3, align 2 ; SSE2: LV: Found an estimated cost of 17 for VF 2 For instruction: store i16 %v3, i16* %out3, align 2 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-5.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-5.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-5.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-5.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i16] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %v4, i16* %out4, align 2 ; SSE2: LV: Found an estimated cost of 22 for VF 2 For instruction: store i16 %v4, i16* %out4, align 2 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-6.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-6.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-6.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i16] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %v5, i16* %out5, align 2 ; SSE2: LV: Found an estimated cost of 26 for VF 2 For instruction: store i16 %v5, i16* %out5, align 2 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-2.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-2.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-2.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-2.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i32] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %v1, i32* %out1, align 4 ; SSE2: LV: Found an estimated cost of 2 for VF 2 For instruction: store i32 %v1, i32* %out1, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-3.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-3.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-3.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-3.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i32] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %v2, i32* %out2, align 4 ; SSE2: LV: Found an estimated cost of 23 for VF 2 For instruction: store i32 %v2, i32* %out2, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-4.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-4.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-4.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i32] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %v3, i32* %out3, align 4 ; SSE2: LV: Found an estimated cost of 28 for VF 2 For instruction: store i32 %v3, i32* %out3, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-6.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-6.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i32-stride-6.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i32] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %v5, i32* %out5, align 4 ; SSE2: LV: Found an estimated cost of 45 for VF 2 For instruction: store i32 %v5, i32* %out5, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-2.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-2.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-2.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-2.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i64] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v1, i64* %out1, align 8 ; SSE2: LV: Found an estimated cost of 14 for VF 2 For instruction: store i64 %v1, i64* %out1, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-3.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-3.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-3.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-3.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i64] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v2, i64* %out2, align 8 ; SSE2: LV: Found an estimated cost of 22 for VF 2 For instruction: store i64 %v2, i64* %out2, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-4.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-4.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-4.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i64] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v3, i64* %out3, align 8 ; SSE2: LV: Found an estimated cost of 28 for VF 2 For instruction: store i64 %v3, i64* %out3, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-6.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-6.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i64-stride-6.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i64] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v5, i64* %out5, align 8 ; SSE2: LV: Found an estimated cost of 44 for VF 2 For instruction: store i64 %v5, i64* %out5, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i8-stride-2.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i8-stride-2.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i8-stride-2.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i8-stride-2.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i8 %v1, i8* %out1, align 1 ; SSE2: LV: Found an estimated cost of 2 for VF 2 For instruction: store i8 %v1, i8* %out1, align 1 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i8-stride-3.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i8-stride-3.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i8-stride-3.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i8-stride-3.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i8 %v2, i8* %out2, align 1 ; SSE2: LV: Found an estimated cost of 25 for VF 2 For instruction: store i8 %v2, i8* %out2, align 1 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i8-stride-4.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i8-stride-4.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i8-stride-4.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i8-stride-4.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i8 %v3, i8* %out3, align 1 ; SSE2: LV: Found an estimated cost of 28 for VF 2 For instruction: store i8 %v3, i8* %out3, align 1 diff --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i8-stride-6.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i8-stride-6.ll --- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i8-stride-6.ll +++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i8-stride-6.ll @@ -10,7 +10,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i8 %v5, i8* %out5, align 1 ; SSE2: LV: Found an estimated cost of 49 for VF 2 For instruction: store i8 %v5, i8* %out5, align 1 diff --git a/llvm/test/Analysis/CostModel/X86/masked-gather-i32-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/masked-gather-i32-with-i8-index.ll --- a/llvm/test/Analysis/CostModel/X86/masked-gather-i32-with-i8-index.ll +++ b/llvm/test/Analysis/CostModel/X86/masked-gather-i32-with-i8-index.ll @@ -14,7 +14,7 @@ @B = global [1024 x i32] zeroinitializer, align 128 @C = global [1024 x i32] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, i32* %inB, align 4 ; SSE2: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i32, i32* %inB, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/masked-gather-i64-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/masked-gather-i64-with-i8-index.ll --- a/llvm/test/Analysis/CostModel/X86/masked-gather-i64-with-i8-index.ll +++ b/llvm/test/Analysis/CostModel/X86/masked-gather-i64-with-i8-index.ll @@ -14,7 +14,7 @@ @B = global [1024 x i64] zeroinitializer, align 128 @C = global [1024 x i64] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, i64* %inB, align 8 ; SSE2: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i64, i64* %inB, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/masked-interleaved-load-i16.ll b/llvm/test/Analysis/CostModel/X86/masked-interleaved-load-i16.ll --- a/llvm/test/Analysis/CostModel/X86/masked-interleaved-load-i16.ll +++ b/llvm/test/Analysis/CostModel/X86/masked-interleaved-load-i16.ll @@ -17,7 +17,7 @@ ; } ; (relates to the testcase in PR50566) -; DISABLED_MASKED_STRIDED: LV: Checking a loop in "test1" +; DISABLED_MASKED_STRIDED: LV: Checking a loop in 'test1' ; ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i2 = load i16, i16* %arrayidx2, align 2 ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i4 = load i16, i16* %arrayidx7, align 2 @@ -34,7 +34,7 @@ ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 62 for VF 16 For instruction: %i2 = load i16, i16* %arrayidx2, align 2 ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 62 for VF 16 For instruction: %i4 = load i16, i16* %arrayidx7, align 2 -; ENABLED_MASKED_STRIDED: LV: Checking a loop in "test1" +; ENABLED_MASKED_STRIDED: LV: Checking a loop in 'test1' ; ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i2 = load i16, i16* %arrayidx2, align 2 ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i4 = load i16, i16* %arrayidx7, align 2 @@ -84,7 +84,7 @@ ; y[i] = points[i*4 + 1]; ; } -; DISABLED_MASKED_STRIDED: LV: Checking a loop in "test2" +; DISABLED_MASKED_STRIDED: LV: Checking a loop in 'test2' ; ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i2 = load i16, i16* %arrayidx2, align 2 ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i4 = load i16, i16* %arrayidx7, align 2 @@ -101,7 +101,7 @@ ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %i2 = load i16, i16* %arrayidx2, align 2 ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %i4 = load i16, i16* %arrayidx7, align 2 -; ENABLED_MASKED_STRIDED: LV: Checking a loop in "test2" +; ENABLED_MASKED_STRIDED: LV: Checking a loop in 'test2' ; ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i2 = load i16, i16* %arrayidx2, align 2 ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i4 = load i16, i16* %arrayidx7, align 2 @@ -161,7 +161,7 @@ ; x[i] = points[i*3]; ; } -; DISABLED_MASKED_STRIDED: LV: Checking a loop in "test" +; DISABLED_MASKED_STRIDED: LV: Checking a loop in 'test' ; ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i4 = load i16, i16* %arrayidx6, align 2 ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %i4 = load i16, i16* %arrayidx6, align 2 @@ -169,7 +169,7 @@ ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %i4 = load i16, i16* %arrayidx6, align 2 ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %i4 = load i16, i16* %arrayidx6, align 2 -; ENABLED_MASKED_STRIDED: LV: Checking a loop in "test" +; ENABLED_MASKED_STRIDED: LV: Checking a loop in 'test' ; ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: %i4 = load i16, i16* %arrayidx6, align 2 ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 7 for VF 2 For instruction: %i4 = load i16, i16* %arrayidx6, align 2 diff --git a/llvm/test/Analysis/CostModel/X86/masked-interleaved-store-i16.ll b/llvm/test/Analysis/CostModel/X86/masked-interleaved-store-i16.ll --- a/llvm/test/Analysis/CostModel/X86/masked-interleaved-store-i16.ll +++ b/llvm/test/Analysis/CostModel/X86/masked-interleaved-store-i16.ll @@ -17,7 +17,7 @@ ; } ; (relates to the testcase in PR50566) -; DISABLED_MASKED_STRIDED: LV: Checking a loop in "test1" +; DISABLED_MASKED_STRIDED: LV: Checking a loop in 'test1' ; ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, i16* %arrayidx2, align 2 ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %2, i16* %arrayidx7, align 2 @@ -34,7 +34,7 @@ ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 68 for VF 16 For instruction: store i16 %0, i16* %arrayidx2, align 2 ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 68 for VF 16 For instruction: store i16 %2, i16* %arrayidx7, align 2 -; ENABLED_MASKED_STRIDED: LV: Checking a loop in "test1" +; ENABLED_MASKED_STRIDED: LV: Checking a loop in 'test1' ; ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, i16* %arrayidx2, align 2 ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %2, i16* %arrayidx7, align 2 @@ -84,7 +84,7 @@ ; points[i*4 + 1] = y[i]; ; } -; DISABLED_MASKED_STRIDED: LV: Checking a loop in "test2" +; DISABLED_MASKED_STRIDED: LV: Checking a loop in 'test2' ; ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, i16* %arrayidx2, align 2 ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %2, i16* %arrayidx7, align 2 @@ -101,7 +101,7 @@ ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 50 for VF 16 For instruction: store i16 %0, i16* %arrayidx2, align 2 ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 3000000 for VF 16 For instruction: store i16 %2, i16* %arrayidx7, align 2 -; ENABLED_MASKED_STRIDED: LV: Checking a loop in "test2" +; ENABLED_MASKED_STRIDED: LV: Checking a loop in 'test2' ; ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, i16* %arrayidx2, align 2 ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %2, i16* %arrayidx7, align 2 @@ -161,7 +161,7 @@ ; points[i*3] = x[i]; ; } -; DISABLED_MASKED_STRIDED: LV: Checking a loop in "test" +; DISABLED_MASKED_STRIDED: LV: Checking a loop in 'test' ; ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, i16* %arrayidx6, align 2 ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 2 for VF 2 For instruction: store i16 %0, i16* %arrayidx6, align 2 @@ -169,7 +169,7 @@ ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 8 for VF 8 For instruction: store i16 %0, i16* %arrayidx6, align 2 ; DISABLED_MASKED_STRIDED: LV: Found an estimated cost of 20 for VF 16 For instruction: store i16 %0, i16* %arrayidx6, align 2 -; ENABLED_MASKED_STRIDED: LV: Checking a loop in "test" +; ENABLED_MASKED_STRIDED: LV: Checking a loop in 'test' ; ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %0, i16* %arrayidx6, align 2 ; ENABLED_MASKED_STRIDED: LV: Found an estimated cost of 2 for VF 2 For instruction: store i16 %0, i16* %arrayidx6, align 2 diff --git a/llvm/test/Analysis/CostModel/X86/masked-load-i16.ll b/llvm/test/Analysis/CostModel/X86/masked-load-i16.ll --- a/llvm/test/Analysis/CostModel/X86/masked-load-i16.ll +++ b/llvm/test/Analysis/CostModel/X86/masked-load-i16.ll @@ -13,7 +13,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @C = global [1024 x i16] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i16, i16* %inB, align 2 ; SSE2: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i16, i16* %inB, align 2 diff --git a/llvm/test/Analysis/CostModel/X86/masked-load-i32.ll b/llvm/test/Analysis/CostModel/X86/masked-load-i32.ll --- a/llvm/test/Analysis/CostModel/X86/masked-load-i32.ll +++ b/llvm/test/Analysis/CostModel/X86/masked-load-i32.ll @@ -13,7 +13,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @C = global [1024 x i32] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, i32* %inB, align 4 ; SSE2: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i32, i32* %inB, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/masked-load-i64.ll b/llvm/test/Analysis/CostModel/X86/masked-load-i64.ll --- a/llvm/test/Analysis/CostModel/X86/masked-load-i64.ll +++ b/llvm/test/Analysis/CostModel/X86/masked-load-i64.ll @@ -13,7 +13,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @C = global [1024 x i64] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, i64* %inB, align 8 ; SSE2: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i64, i64* %inB, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/masked-load-i8.ll b/llvm/test/Analysis/CostModel/X86/masked-load-i8.ll --- a/llvm/test/Analysis/CostModel/X86/masked-load-i8.ll +++ b/llvm/test/Analysis/CostModel/X86/masked-load-i8.ll @@ -13,7 +13,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @C = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i8, i8* %inB, align 1 ; SSE2: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i8, i8* %inB, align 1 diff --git a/llvm/test/Analysis/CostModel/X86/masked-scatter-i32-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/masked-scatter-i32-with-i8-index.ll --- a/llvm/test/Analysis/CostModel/X86/masked-scatter-i32-with-i8-index.ll +++ b/llvm/test/Analysis/CostModel/X86/masked-scatter-i32-with-i8-index.ll @@ -14,7 +14,7 @@ @B = global [1024 x i32] zeroinitializer, align 128 @C = global [1024 x i32] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4 ; SSE2: LV: Found an estimated cost of 2 for VF 2 For instruction: store i32 %valB, i32* %out, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/masked-scatter-i64-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/masked-scatter-i64-with-i8-index.ll --- a/llvm/test/Analysis/CostModel/X86/masked-scatter-i64-with-i8-index.ll +++ b/llvm/test/Analysis/CostModel/X86/masked-scatter-i64-with-i8-index.ll @@ -14,7 +14,7 @@ @B = global [1024 x i64] zeroinitializer, align 128 @C = global [1024 x i64] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8 ; SSE2: LV: Found an estimated cost of 2 for VF 2 For instruction: store i64 %valB, i64* %out, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/masked-store-i16.ll b/llvm/test/Analysis/CostModel/X86/masked-store-i16.ll --- a/llvm/test/Analysis/CostModel/X86/masked-store-i16.ll +++ b/llvm/test/Analysis/CostModel/X86/masked-store-i16.ll @@ -13,7 +13,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i16] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %valB, i16* %out, align 2 ; SSE2: LV: Found an estimated cost of 2 for VF 2 For instruction: store i16 %valB, i16* %out, align 2 diff --git a/llvm/test/Analysis/CostModel/X86/masked-store-i32.ll b/llvm/test/Analysis/CostModel/X86/masked-store-i32.ll --- a/llvm/test/Analysis/CostModel/X86/masked-store-i32.ll +++ b/llvm/test/Analysis/CostModel/X86/masked-store-i32.ll @@ -13,7 +13,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i32] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4 ; SSE2: LV: Found an estimated cost of 2 for VF 2 For instruction: store i32 %valB, i32* %out, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/masked-store-i64.ll b/llvm/test/Analysis/CostModel/X86/masked-store-i64.ll --- a/llvm/test/Analysis/CostModel/X86/masked-store-i64.ll +++ b/llvm/test/Analysis/CostModel/X86/masked-store-i64.ll @@ -13,7 +13,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i64] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8 ; SSE2: LV: Found an estimated cost of 2 for VF 2 For instruction: store i64 %valB, i64* %out, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/masked-store-i8.ll b/llvm/test/Analysis/CostModel/X86/masked-store-i8.ll --- a/llvm/test/Analysis/CostModel/X86/masked-store-i8.ll +++ b/llvm/test/Analysis/CostModel/X86/masked-store-i8.ll @@ -13,7 +13,7 @@ @A = global [1024 x i8] zeroinitializer, align 128 @B = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i8 %valB, i8* %out, align 1 ; SSE2: LV: Found an estimated cost of 2 for VF 2 For instruction: store i8 %valB, i8* %out, align 1 diff --git a/llvm/test/Analysis/CostModel/X86/scatter-i16-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/scatter-i16-with-i8-index.ll --- a/llvm/test/Analysis/CostModel/X86/scatter-i16-with-i8-index.ll +++ b/llvm/test/Analysis/CostModel/X86/scatter-i16-with-i8-index.ll @@ -14,7 +14,7 @@ @B = global [1024 x i16] zeroinitializer, align 128 @C = global [1024 x i16] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %valB, i16* %out, align 2 ; SSE2: LV: Found an estimated cost of 28 for VF 2 For instruction: store i16 %valB, i16* %out, align 2 diff --git a/llvm/test/Analysis/CostModel/X86/scatter-i32-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/scatter-i32-with-i8-index.ll --- a/llvm/test/Analysis/CostModel/X86/scatter-i32-with-i8-index.ll +++ b/llvm/test/Analysis/CostModel/X86/scatter-i32-with-i8-index.ll @@ -14,7 +14,7 @@ @B = global [1024 x i32] zeroinitializer, align 128 @C = global [1024 x i32] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, i32* %out, align 4 ; SSE2: LV: Found an estimated cost of 29 for VF 2 For instruction: store i32 %valB, i32* %out, align 4 diff --git a/llvm/test/Analysis/CostModel/X86/scatter-i64-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/scatter-i64-with-i8-index.ll --- a/llvm/test/Analysis/CostModel/X86/scatter-i64-with-i8-index.ll +++ b/llvm/test/Analysis/CostModel/X86/scatter-i64-with-i8-index.ll @@ -14,7 +14,7 @@ @B = global [1024 x i64] zeroinitializer, align 128 @C = global [1024 x i64] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, i64* %out, align 8 ; SSE2: LV: Found an estimated cost of 29 for VF 2 For instruction: store i64 %valB, i64* %out, align 8 diff --git a/llvm/test/Analysis/CostModel/X86/scatter-i8-with-i8-index.ll b/llvm/test/Analysis/CostModel/X86/scatter-i8-with-i8-index.ll --- a/llvm/test/Analysis/CostModel/X86/scatter-i8-with-i8-index.ll +++ b/llvm/test/Analysis/CostModel/X86/scatter-i8-with-i8-index.ll @@ -14,7 +14,7 @@ @B = global [1024 x i8] zeroinitializer, align 128 @C = global [1024 x i8] zeroinitializer, align 128 -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i8 %valB, i8* %out, align 1 ; SSE2: LV: Found an estimated cost of 29 for VF 2 For instruction: store i8 %valB, i8* %out, align 1 diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/interleaved_cost.ll b/llvm/test/Transforms/LoopVectorize/AArch64/interleaved_cost.ll --- a/llvm/test/Transforms/LoopVectorize/AArch64/interleaved_cost.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/interleaved_cost.ll @@ -12,12 +12,12 @@ entry: br label %for.body -; VF_8-LABEL: Checking a loop in "i8_factor_2" +; VF_8-LABEL: Checking a loop in 'i8_factor_2' ; VF_8: Found an estimated cost of 2 for VF 8 For instruction: %tmp2 = load i8, i8* %tmp0, align 1 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load i8, i8* %tmp1, align 1 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i8 0, i8* %tmp0, align 1 ; VF_8-NEXT: Found an estimated cost of 2 for VF 8 For instruction: store i8 0, i8* %tmp1, align 1 -; VF_16-LABEL: Checking a loop in "i8_factor_2" +; VF_16-LABEL: Checking a loop in 'i8_factor_2' ; VF_16: Found an estimated cost of 2 for VF 16 For instruction: %tmp2 = load i8, i8* %tmp0, align 1 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp3 = load i8, i8* %tmp1, align 1 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i8 0, i8* %tmp0, align 1 @@ -43,17 +43,17 @@ entry: br label %for.body -; VF_4-LABEL: Checking a loop in "i16_factor_2" +; VF_4-LABEL: Checking a loop in 'i16_factor_2' ; VF_4: Found an estimated cost of 2 for VF 4 For instruction: %tmp2 = load i16, i16* %tmp0, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load i16, i16* %tmp1, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i16 0, i16* %tmp0, align 2 ; VF_4-NEXT: Found an estimated cost of 2 for VF 4 For instruction: store i16 0, i16* %tmp1, align 2 -; VF_8-LABEL: Checking a loop in "i16_factor_2" +; VF_8-LABEL: Checking a loop in 'i16_factor_2' ; VF_8: Found an estimated cost of 2 for VF 8 For instruction: %tmp2 = load i16, i16* %tmp0, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load i16, i16* %tmp1, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i16 0, i16* %tmp0, align 2 ; VF_8-NEXT: Found an estimated cost of 2 for VF 8 For instruction: store i16 0, i16* %tmp1, align 2 -; VF_16-LABEL: Checking a loop in "i16_factor_2" +; VF_16-LABEL: Checking a loop in 'i16_factor_2' ; VF_16: Found an estimated cost of 4 for VF 16 For instruction: %tmp2 = load i16, i16* %tmp0, align 2 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp3 = load i16, i16* %tmp1, align 2 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i16 0, i16* %tmp0, align 2 @@ -79,22 +79,22 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "i32_factor_2" +; VF_2-LABEL: Checking a loop in 'i32_factor_2' ; VF_2: Found an estimated cost of 2 for VF 2 For instruction: %tmp2 = load i32, i32* %tmp0, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load i32, i32* %tmp1, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp0, align 4 ; VF_2-NEXT: Found an estimated cost of 2 for VF 2 For instruction: store i32 0, i32* %tmp1, align 4 -; VF_4-LABEL: Checking a loop in "i32_factor_2" +; VF_4-LABEL: Checking a loop in 'i32_factor_2' ; VF_4: Found an estimated cost of 2 for VF 4 For instruction: %tmp2 = load i32, i32* %tmp0, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load i32, i32* %tmp1, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i32 0, i32* %tmp0, align 4 ; VF_4-NEXT: Found an estimated cost of 2 for VF 4 For instruction: store i32 0, i32* %tmp1, align 4 -; VF_8-LABEL: Checking a loop in "i32_factor_2" +; VF_8-LABEL: Checking a loop in 'i32_factor_2' ; VF_8: Found an estimated cost of 4 for VF 8 For instruction: %tmp2 = load i32, i32* %tmp0, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load i32, i32* %tmp1, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i32 0, i32* %tmp0, align 4 ; VF_8-NEXT: Found an estimated cost of 4 for VF 8 For instruction: store i32 0, i32* %tmp1, align 4 -; VF_16-LABEL: Checking a loop in "i32_factor_2" +; VF_16-LABEL: Checking a loop in 'i32_factor_2' ; VF_16: Found an estimated cost of 8 for VF 16 For instruction: %tmp2 = load i32, i32* %tmp0, align 4 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp3 = load i32, i32* %tmp1, align 4 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i32 0, i32* %tmp0, align 4 @@ -120,22 +120,22 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "i64_factor_2" +; VF_2-LABEL: Checking a loop in 'i64_factor_2' ; VF_2: Found an estimated cost of 2 for VF 2 For instruction: %tmp2 = load i64, i64* %tmp0, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load i64, i64* %tmp1, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i64 0, i64* %tmp0, align 8 ; VF_2-NEXT: Found an estimated cost of 2 for VF 2 For instruction: store i64 0, i64* %tmp1, align 8 -; VF_4-LABEL: Checking a loop in "i64_factor_2" +; VF_4-LABEL: Checking a loop in 'i64_factor_2' ; VF_4: Found an estimated cost of 4 for VF 4 For instruction: %tmp2 = load i64, i64* %tmp0, align 8 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load i64, i64* %tmp1, align 8 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i64 0, i64* %tmp0, align 8 ; VF_4-NEXT: Found an estimated cost of 4 for VF 4 For instruction: store i64 0, i64* %tmp1, align 8 -; VF_8-LABEL: Checking a loop in "i64_factor_2" +; VF_8-LABEL: Checking a loop in 'i64_factor_2' ; VF_8: Found an estimated cost of 8 for VF 8 For instruction: %tmp2 = load i64, i64* %tmp0, align 8 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load i64, i64* %tmp1, align 8 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i64 0, i64* %tmp0, align 8 ; VF_8-NEXT: Found an estimated cost of 8 for VF 8 For instruction: store i64 0, i64* %tmp1, align 8 -; VF_16-LABEL: Checking a loop in "i64_factor_2" +; VF_16-LABEL: Checking a loop in 'i64_factor_2' ; VF_16: Found an estimated cost of 16 for VF 16 For instruction: %tmp2 = load i64, i64* %tmp0, align 8 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp3 = load i64, i64* %tmp1, align 8 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i64 0, i64* %tmp0, align 8 @@ -167,7 +167,7 @@ ; stores do not form a legal interleaved group because the group would contain ; gaps. ; -; VF_2-LABEL: Checking a loop in "i64_factor_8" +; VF_2-LABEL: Checking a loop in 'i64_factor_8' ; VF_2: Found an estimated cost of 10 for VF 2 For instruction: %tmp2 = load i64, i64* %tmp0, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load i64, i64* %tmp1, align 8 ; VF_2-NEXT: Found an estimated cost of 7 for VF 2 For instruction: store i64 0, i64* %tmp0, align 8 diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/masked-op-cost.ll b/llvm/test/Transforms/LoopVectorize/AArch64/masked-op-cost.ll --- a/llvm/test/Transforms/LoopVectorize/AArch64/masked-op-cost.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/masked-op-cost.ll @@ -4,7 +4,7 @@ target triple = "aarch64-unknown-linux-gnu" -; CHECK-COST: Checking a loop in "fixed_width" +; CHECK-COST: Checking a loop in 'fixed_width' ; CHECK-COST: Found an estimated cost of 11 for VF 2 For instruction: store i32 2, i32* %arrayidx1, align 4 ; CHECK-COST: Found an estimated cost of 25 for VF 4 For instruction: store i32 2, i32* %arrayidx1, align 4 ; CHECK-COST: Selecting VF: 1. @@ -45,7 +45,7 @@ } -; CHECK-COST: Checking a loop in "scalable" +; CHECK-COST: Checking a loop in 'scalable' ; CHECK-COST: Found an estimated cost of 2 for VF vscale x 4 For instruction: store i32 2, i32* %arrayidx1, align 4 define void @scalable(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i64 %n) #0 { diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-vectorization.ll b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-vectorization.ll --- a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-vectorization.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-vectorization.ll @@ -7,7 +7,7 @@ ; is calculated as vscale x 4 (max legal SVE vector size) or vscale x 16 ; (maximized bandwidth for i8 in the loop). define void @test0(i32* %a, i8* %b, i32* %c) #0 { -; CHECK: LV: Checking a loop in "test0" +; CHECK: LV: Checking a loop in 'test0' ; CHECK_SCALABLE_ON: LV: Found feasible scalable VF = vscale x 4 ; CHECK_SCALABLE_ON: LV: Selecting VF: vscale x 4 ; CHECK_SCALABLE_DISABLED-NOT: LV: Found feasible scalable VF @@ -38,7 +38,7 @@ ; Test that the MaxVF for the following loop, with a dependence distance ; of 64 elements, is calculated as (maxvscale = 16) * 4. define void @test1(i32* %a, i8* %b) #0 { -; CHECK: LV: Checking a loop in "test1" +; CHECK: LV: Checking a loop in 'test1' ; CHECK_SCALABLE_ON: LV: Found feasible scalable VF = vscale x 4 ; CHECK_SCALABLE_ON: LV: Selecting VF: vscale x 4 ; CHECK_SCALABLE_DISABLED-NOT: LV: Found feasible scalable VF @@ -70,7 +70,7 @@ ; Test that the MaxVF for the following loop, with a dependence distance ; of 32 elements, is calculated as (maxvscale = 16) * 2. define void @test2(i32* %a, i8* %b) #0 { -; CHECK: LV: Checking a loop in "test2" +; CHECK: LV: Checking a loop in 'test2' ; CHECK_SCALABLE_ON: LV: Found feasible scalable VF = vscale x 2 ; CHECK_SCALABLE_ON: LV: Selecting VF: vscale x 2 ; CHECK_SCALABLE_DISABLED-NOT: LV: Found feasible scalable VF @@ -102,7 +102,7 @@ ; Test that the MaxVF for the following loop, with a dependence distance ; of 16 elements, is calculated as (maxvscale = 16) * 1. define void @test3(i32* %a, i8* %b) #0 { -; CHECK: LV: Checking a loop in "test3" +; CHECK: LV: Checking a loop in 'test3' ; CHECK_SCALABLE_ON: LV: Found feasible scalable VF = vscale x 1 ; CHECK_SCALABLE_ON: LV: Selecting VF: 4 ; CHECK_SCALABLE_DISABLED-NOT: LV: Found feasible scalable VF @@ -134,7 +134,7 @@ ; Test the fallback mechanism when scalable vectors are not feasible due ; to e.g. dependence distance. define void @test4(i32* %a, i32* %b) #0 { -; CHECK: LV: Checking a loop in "test4" +; CHECK: LV: Checking a loop in 'test4' ; CHECK_SCALABLE_ON-NOT: LV: Found feasible scalable VF ; CHECK_SCALABLE_ON-NOT: LV: Found feasible scalable VF ; CHECK_SCALABLE_ON: LV: Selecting VF: 4 diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-vf-hint.ll b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-vf-hint.ll --- a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-vf-hint.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-vf-hint.ll @@ -37,7 +37,7 @@ ; unless max(vscale)=2 it's unsafe to vectorize. For SVE max(vscale)=16, check ; fixed-width vectorization is used instead. -; CHECK-DBG: LV: Checking a loop in "test1" +; CHECK-DBG: LV: Checking a loop in 'test1' ; CHECK-DBG: LV: Scalable vectorization is available ; CHECK-DBG: LV: Max legal vector width too small, scalable vectorization unfeasible. ; CHECK-DBG: remark: :0:0: Max legal vector width too small, scalable vectorization unfeasible. @@ -82,7 +82,7 @@ ; } ; } -; CHECK-DBG: LV: Checking a loop in "test2" +; CHECK-DBG: LV: Checking a loop in 'test2' ; CHECK-DBG: LV: Scalable vectorization is available ; CHECK-DBG: LV: Max legal vector width too small, scalable vectorization unfeasible. ; CHECK-DBG: LV: The max safe fixed VF is: 4. @@ -132,7 +132,7 @@ ; ; Max fixed VF=32, Max scalable VF=2, safe to vectorize. -; CHECK-DBG-LABEL: LV: Checking a loop in "test3" +; CHECK-DBG-LABEL: LV: Checking a loop in 'test3' ; CHECK-DBG: LV: Scalable vectorization is available ; CHECK-DBG: LV: The max safe scalable VF is: vscale x 2. ; CHECK-DBG: LV: Using user VF vscale x 2. @@ -181,7 +181,7 @@ ; ; Max fixed VF=32, Max scalable VF=2, unsafe to vectorize. -; CHECK-DBG-LABEL: LV: Checking a loop in "test4" +; CHECK-DBG-LABEL: LV: Checking a loop in 'test4' ; CHECK-DBG: LV: Scalable vectorization is available ; CHECK-DBG: LV: The max safe scalable VF is: vscale x 2. ; CHECK-DBG: LV: User VF=vscale x 4 is unsafe. Ignoring scalable UserVF. @@ -232,7 +232,7 @@ ; ; Max fixed VF=128, Max scalable VF=8, safe to vectorize. -; CHECK-DBG-LABEL: LV: Checking a loop in "test5" +; CHECK-DBG-LABEL: LV: Checking a loop in 'test5' ; CHECK-DBG: LV: Scalable vectorization is available ; CHECK-DBG: LV: The max safe scalable VF is: vscale x 8. ; CHECK-DBG: LV: Using user VF vscale x 4 @@ -280,7 +280,7 @@ ; ; Max fixed VF=128, Max scalable VF=8, unsafe to vectorize. -; CHECK-DBG-LABEL: LV: Checking a loop in "test6" +; CHECK-DBG-LABEL: LV: Checking a loop in 'test6' ; CHECK-DBG: LV: Scalable vectorization is available ; CHECK-DBG: LV: The max safe scalable VF is: vscale x 8. ; CHECK-DBG: LV: User VF=vscale x 16 is unsafe. Ignoring scalable UserVF. @@ -315,7 +315,7 @@ !16 = !{!"llvm.loop.vectorize.width", i32 16} !17 = !{!"llvm.loop.vectorize.scalable.enable", i1 true} -; CHECK-NO-SVE-REMARKS-LABEL: LV: Checking a loop in "test_no_sve" +; CHECK-NO-SVE-REMARKS-LABEL: LV: Checking a loop in 'test_no_sve' ; CHECK-NO-SVE-REMARKS: LV: User VF=vscale x 4 is ignored because scalable vectors are not available. ; CHECK-NO-SVE-REMARKS: remark: :0:0: User-specified vectorization factor vscale x 4 is ignored because the target does not support scalable vectors. The compiler will pick a more suitable value. ; CHECK-NO-SVE-REMARKS: LV: Selecting VF: 4. @@ -349,7 +349,7 @@ ; Test the LV falls back to fixed-width vectorization if scalable vectors are ; supported but max vscale is undefined. ; -; CHECK-DBG-LABEL: LV: Checking a loop in "test_no_max_vscale" +; CHECK-DBG-LABEL: LV: Checking a loop in 'test_no_max_vscale' ; CHECK-DBG: LV: Scalable vectorization is available ; CHECK-DBG: The max safe fixed VF is: 4. ; CHECK-DBG: LV: User VF=vscale x 4 is unsafe. Ignoring scalable UserVF. diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/smallest-and-widest-types.ll b/llvm/test/Transforms/LoopVectorize/AArch64/smallest-and-widest-types.ll --- a/llvm/test/Transforms/LoopVectorize/AArch64/smallest-and-widest-types.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/smallest-and-widest-types.ll @@ -4,7 +4,7 @@ target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128" target triple = "aarch64--linux-gnu" -; CHECK-LABEL: Checking a loop in "interleaved_access" +; CHECK-LABEL: Checking a loop in 'interleaved_access' ; CHECK: The Smallest and Widest types: 64 / 64 bits ; define void @interleaved_access(i8** %A, i64 %N) { @@ -36,7 +36,7 @@ ; determined by looking through the recurrences, which allows a sensible VF to be ; chosen. The following 3 cases check different combinations of widths. -; CHECK-LABEL: Checking a loop in "no_loads_stores_32" +; CHECK-LABEL: Checking a loop in 'no_loads_stores_32' ; CHECK: The Smallest and Widest types: 4294967295 / 32 bits ; CHECK: Selecting VF: 4 @@ -59,7 +59,7 @@ ret double %.lcssa } -; CHECK-LABEL: Checking a loop in "no_loads_stores_16" +; CHECK-LABEL: Checking a loop in 'no_loads_stores_16' ; CHECK: The Smallest and Widest types: 4294967295 / 16 bits ; CHECK: Selecting VF: 8 @@ -81,7 +81,7 @@ ret double %.lcssa } -; CHECK-LABEL: Checking a loop in "no_loads_stores_8" +; CHECK-LABEL: Checking a loop in 'no_loads_stores_8' ; CHECK: The Smallest and Widest types: 4294967295 / 8 bits ; CHECK: Selecting VF: 16 diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll --- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll @@ -7,11 +7,11 @@ target triple = "aarch64-linux-gnu" -; DEBUG: LV: Checking a loop in "main_vf_vscale_x_16" +; DEBUG: LV: Checking a loop in 'main_vf_vscale_x_16' ; DEBUG: Create Skeleton for epilogue vectorized loop (first pass) ; DEBUG: Main Loop VF:vscale x 16, Main Loop UF:2, Epilogue Loop VF:vscale x 8, Epilogue Loop UF:1 -; DEBUG-FORCED: LV: Checking a loop in "main_vf_vscale_x_16" +; DEBUG-FORCED: LV: Checking a loop in 'main_vf_vscale_x_16' ; DEBUG-FORCED: LEV: Epilogue vectorization factor is forced. ; DEBUG-FORCED: Create Skeleton for epilogue vectorized loop (first pass) ; DEBUG-FORCED: Main Loop VF:vscale x 16, Main Loop UF:2, Epilogue Loop VF:8, Epilogue Loop UF:1 @@ -194,11 +194,11 @@ } -; DEBUG: LV: Checking a loop in "main_vf_vscale_x_2" +; DEBUG: LV: Checking a loop in 'main_vf_vscale_x_2' ; DEBUG: Create Skeleton for epilogue vectorized loop (first pass) ; DEBUG: Main Loop VF:vscale x 2, Main Loop UF:2, Epilogue Loop VF:8, Epilogue Loop UF:1 -; DEBUG-FORCED: LV: Checking a loop in "main_vf_vscale_x_2" +; DEBUG-FORCED: LV: Checking a loop in 'main_vf_vscale_x_2' ; DEBUG-FORCED: LEV: Epilogue vectorization factor is forced. ; DEBUG-FORCED: Create Skeleton for epilogue vectorized loop (first pass) ; DEBUG-FORCED: Main Loop VF:vscale x 2, Main Loop UF:2, Epilogue Loop VF:8, Epilogue Loop UF:1 diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter-cost.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter-cost.ll --- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter-cost.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-gather-scatter-cost.ll @@ -3,7 +3,7 @@ target triple="aarch64--linux-gnu" -; CHECK: LV: Checking a loop in "gather_nxv4i32_loaded_index" +; CHECK: LV: Checking a loop in 'gather_nxv4i32_loaded_index' ; CHECK: LV: Found an estimated cost of 81 for VF vscale x 4 For instruction: %1 = load float, float* %arrayidx3, align 4 define void @gather_nxv4i32_loaded_index(float* noalias nocapture readonly %a, i64* noalias nocapture readonly %b, float* noalias nocapture %c, i64 %n) #0 { entry: @@ -25,7 +25,7 @@ ret void } -; CHECK: LV: Checking a loop in "scatter_nxv4i32_loaded_index" +; CHECK: LV: Checking a loop in 'scatter_nxv4i32_loaded_index' ; CHECK: LV: Found an estimated cost of 81 for VF vscale x 4 For instruction: store float %1, float* %arrayidx5, align 4 define void @scatter_nxv4i32_loaded_index(float* noalias nocapture readonly %a, i64* noalias nocapture readonly %b, float* noalias nocapture %c, i64 %n) #0 { entry: @@ -49,7 +49,7 @@ ; NOTE: For runtime-determined strides the vectoriser versions the loop and adds SCEV checks ; to ensure the stride value is always 1. Therefore, it can assume a contiguous load and a cost of 1. -; CHECK: LV: Checking a loop in "gather_nxv4i32_unknown_stride" +; CHECK: LV: Checking a loop in 'gather_nxv4i32_unknown_stride' ; CHECK: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: %0 = load float, float* %arrayidx, align 4 define void @gather_nxv4i32_unknown_stride(float* noalias nocapture readonly %a, float* noalias nocapture %b, i64 %stride, i64 %n) #0 { entry: @@ -72,7 +72,7 @@ ; NOTE: For runtime-determined strides the vectoriser versions the loop and adds SCEV checks ; to ensure the stride value is always 1. Therefore, it can assume a contiguous load and cost is 1. -; CHECK: LV: Checking a loop in "scatter_nxv4i32_unknown_stride" +; CHECK: LV: Checking a loop in 'scatter_nxv4i32_unknown_stride' ; CHECK: LV: Found an estimated cost of 1 for VF vscale x 4 For instruction: store float %0, float* %arrayidx2, align 4 define void @scatter_nxv4i32_unknown_stride(float* noalias nocapture readonly %a, float* noalias nocapture %b, i64 %stride, i64 %n) #0 { entry: @@ -93,7 +93,7 @@ ret void } -; CHECK: LV: Checking a loop in "gather_nxv4i32_stride2" +; CHECK: LV: Checking a loop in 'gather_nxv4i32_stride2' ; CHECK: LV: Found an estimated cost of 81 for VF vscale x 4 For instruction: %0 = load float, float* %arrayidx, align 4 define void @gather_nxv4i32_stride2(float* noalias nocapture readonly %a, float* noalias nocapture readonly %b, i64 %n) #0 { entry: @@ -114,7 +114,7 @@ ret void } -; CHECK: LV: Checking a loop in "scatter_nxv4i32_stride2" +; CHECK: LV: Checking a loop in 'scatter_nxv4i32_stride2' ; CHECK: LV: Found an estimated cost of 81 for VF vscale x 4 For instruction: store float %0, float* %arrayidx2, align 4 define void @scatter_nxv4i32_stride2(float* noalias nocapture readonly %a, float* noalias nocapture readonly %b, i64 %n) #0 { entry: @@ -136,7 +136,7 @@ } -; CHECK: LV: Checking a loop in "gather_nxv4i32_stride64" +; CHECK: LV: Checking a loop in 'gather_nxv4i32_stride64' ; CHECK: LV: Found an estimated cost of 81 for VF vscale x 4 For instruction: %0 = load float, float* %arrayidx, align 4 define void @gather_nxv4i32_stride64(float* noalias nocapture readonly %a, float* noalias nocapture readonly %b, i64 %n) #0 { entry: @@ -157,7 +157,7 @@ ret void } -; CHECK: LV: Checking a loop in "scatter_nxv4i32_stride64" +; CHECK: LV: Checking a loop in 'scatter_nxv4i32_stride64' ; CHECK: LV: Found an estimated cost of 81 for VF vscale x 4 For instruction: store float %0, float* %arrayidx2, align 4 define void @scatter_nxv4i32_stride64(float* noalias nocapture readonly %a, float* noalias nocapture readonly %b, i64 %n) #0 { entry: diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-widen-gep.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-widen-gep.ll --- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-widen-gep.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-widen-gep.ll @@ -4,7 +4,7 @@ target triple = "aarch64-unknown-linux-gnu" -; CHECK-LABEL: LV: Checking a loop in "pointer_induction_used_as_vector" +; CHECK-LABEL: LV: Checking a loop in 'pointer_induction_used_as_vector' ; CHECK-NOT: LV: Found {{.*}} scalar instruction: %ptr.iv.2.next = getelementptr inbounds i8, i8* %ptr.iv.2, i64 1 ; ; CHECK: VPlan 'Initial VPlan for VF={vscale x 2},UF>=1' { diff --git a/llvm/test/Transforms/LoopVectorize/ARM/arm-ieee-vectorize.ll b/llvm/test/Transforms/LoopVectorize/ARM/arm-ieee-vectorize.ll --- a/llvm/test/Transforms/LoopVectorize/ARM/arm-ieee-vectorize.ll +++ b/llvm/test/Transforms/LoopVectorize/ARM/arm-ieee-vectorize.ll @@ -14,7 +14,7 @@ ; are allowed, even without -ffast-math. ; Integer loops are always vectorizeable -; CHECK: Checking a loop in "sumi" +; CHECK: Checking a loop in 'sumi' ; CHECK: We can vectorize this loop! define void @sumi(i32* noalias nocapture readonly %A, i32* noalias nocapture readonly %B, i32* noalias nocapture %C, i32 %N) { entry: @@ -45,11 +45,11 @@ } ; Floating-point loops need fast-math to be vectorizeable -; LINUX: Checking a loop in "sumf" +; LINUX: Checking a loop in 'sumf' ; LINUX: Potentially unsafe FP op prevents vectorization -; MVE: Checking a loop in "sumf" +; MVE: Checking a loop in 'sumf' ; MVE: We can vectorize this loop! -; DARWIN: Checking a loop in "sumf" +; DARWIN: Checking a loop in 'sumf' ; DARWIN: We can vectorize this loop! define void @sumf(float* noalias nocapture readonly %A, float* noalias nocapture readonly %B, float* noalias nocapture %C, i32 %N) { entry: @@ -80,7 +80,7 @@ } ; Integer loops are always vectorizeable -; CHECK: Checking a loop in "redi" +; CHECK: Checking a loop in 'redi' ; CHECK: We can vectorize this loop! define i32 @redi(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32 %N) { entry: @@ -113,11 +113,11 @@ } ; Floating-point loops need fast-math to be vectorizeable -; LINUX: Checking a loop in "redf" +; LINUX: Checking a loop in 'redf' ; LINUX: Potentially unsafe FP op prevents vectorization -; MVE: Checking a loop in "redf" +; MVE: Checking a loop in 'redf' ; MVE: We can vectorize this loop! -; DARWIN: Checking a loop in "redf" +; DARWIN: Checking a loop in 'redf' ; DARWIN: We can vectorize this loop! define float @redf(float* noalias nocapture readonly %a, float* noalias nocapture readonly %b, i32 %N) { entry: @@ -150,9 +150,9 @@ } ; Make sure calls that turn into builtins are also covered -; LINUX: Checking a loop in "fabs" +; LINUX: Checking a loop in 'fabs' ; LINUX: Potentially unsafe FP op prevents vectorization -; DARWIN: Checking a loop in "fabs" +; DARWIN: Checking a loop in 'fabs' ; DARWIN: We can vectorize this loop! define void @fabs(float* noalias nocapture readonly %A, float* noalias nocapture readonly %B, float* noalias nocapture %C, i32 %N) { entry: @@ -178,7 +178,7 @@ } ; Integer loops are always vectorizeable -; CHECK: Checking a loop in "sumi_fast" +; CHECK: Checking a loop in 'sumi_fast' ; CHECK: We can vectorize this loop! define void @sumi_fast(i32* noalias nocapture readonly %A, i32* noalias nocapture readonly %B, i32* noalias nocapture %C, i32 %N) { entry: @@ -209,7 +209,7 @@ } ; Floating-point loops can be vectorizeable with fast-math -; CHECK: Checking a loop in "sumf_fast" +; CHECK: Checking a loop in 'sumf_fast' ; CHECK: We can vectorize this loop! define void @sumf_fast(float* noalias nocapture readonly %A, float* noalias nocapture readonly %B, float* noalias nocapture %C, i32 %N) { entry: @@ -240,7 +240,7 @@ } ; Integer loops are always vectorizeable -; CHECK: Checking a loop in "redi_fast" +; CHECK: Checking a loop in 'redi_fast' ; CHECK: We can vectorize this loop! define i32 @redi_fast(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32 %N) { entry: @@ -273,7 +273,7 @@ } ; Floating-point loops can be vectorizeable with fast-math -; CHECK: Checking a loop in "redf_fast" +; CHECK: Checking a loop in 'redf_fast' ; CHECK: We can vectorize this loop! define float @redf_fast(float* noalias nocapture readonly %a, float* noalias nocapture readonly %b, i32 %N) { entry: @@ -306,7 +306,7 @@ } ; Make sure calls that turn into builtins are also covered -; CHECK: Checking a loop in "fabs_fast" +; CHECK: Checking a loop in 'fabs_fast' ; CHECK: We can vectorize this loop! define void @fabs_fast(float* noalias nocapture readonly %A, float* noalias nocapture readonly %B, float* noalias nocapture %C, i32 %N) { entry: diff --git a/llvm/test/Transforms/LoopVectorize/ARM/interleaved_cost.ll b/llvm/test/Transforms/LoopVectorize/ARM/interleaved_cost.ll --- a/llvm/test/Transforms/LoopVectorize/ARM/interleaved_cost.ll +++ b/llvm/test/Transforms/LoopVectorize/ARM/interleaved_cost.ll @@ -12,12 +12,12 @@ entry: br label %for.body -; VF_8-LABEL: Checking a loop in "i8_factor_2" +; VF_8-LABEL: Checking a loop in 'i8_factor_2' ; VF_8: Found an estimated cost of 2 for VF 8 For instruction: %tmp2 = load i8, i8* %tmp0, align 1 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load i8, i8* %tmp1, align 1 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i8 0, i8* %tmp0, align 1 ; VF_8-NEXT: Found an estimated cost of 2 for VF 8 For instruction: store i8 0, i8* %tmp1, align 1 -; VF_16-LABEL: Checking a loop in "i8_factor_2" +; VF_16-LABEL: Checking a loop in 'i8_factor_2' ; VF_16: Found an estimated cost of 2 for VF 16 For instruction: %tmp2 = load i8, i8* %tmp0, align 1 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp3 = load i8, i8* %tmp1, align 1 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i8 0, i8* %tmp0, align 1 @@ -43,17 +43,17 @@ entry: br label %for.body -; VF_4-LABEL: Checking a loop in "i16_factor_2" +; VF_4-LABEL: Checking a loop in 'i16_factor_2' ; VF_4: Found an estimated cost of 2 for VF 4 For instruction: %tmp2 = load i16, i16* %tmp0, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load i16, i16* %tmp1, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i16 0, i16* %tmp0, align 2 ; VF_4-NEXT: Found an estimated cost of 2 for VF 4 For instruction: store i16 0, i16* %tmp1, align 2 -; VF_8-LABEL: Checking a loop in "i16_factor_2" +; VF_8-LABEL: Checking a loop in 'i16_factor_2' ; VF_8: Found an estimated cost of 2 for VF 8 For instruction: %tmp2 = load i16, i16* %tmp0, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load i16, i16* %tmp1, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i16 0, i16* %tmp0, align 2 ; VF_8-NEXT: Found an estimated cost of 2 for VF 8 For instruction: store i16 0, i16* %tmp1, align 2 -; VF_16-LABEL: Checking a loop in "i16_factor_2" +; VF_16-LABEL: Checking a loop in 'i16_factor_2' ; VF_16: Found an estimated cost of 4 for VF 16 For instruction: %tmp2 = load i16, i16* %tmp0, align 2 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp3 = load i16, i16* %tmp1, align 2 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i16 0, i16* %tmp0, align 2 @@ -79,22 +79,22 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "i32_factor_2" +; VF_2-LABEL: Checking a loop in 'i32_factor_2' ; VF_2: Found an estimated cost of 2 for VF 2 For instruction: %tmp2 = load i32, i32* %tmp0, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load i32, i32* %tmp1, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp0, align 4 ; VF_2-NEXT: Found an estimated cost of 2 for VF 2 For instruction: store i32 0, i32* %tmp1, align 4 -; VF_4-LABEL: Checking a loop in "i32_factor_2" +; VF_4-LABEL: Checking a loop in 'i32_factor_2' ; VF_4: Found an estimated cost of 2 for VF 4 For instruction: %tmp2 = load i32, i32* %tmp0, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load i32, i32* %tmp1, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i32 0, i32* %tmp0, align 4 ; VF_4-NEXT: Found an estimated cost of 2 for VF 4 For instruction: store i32 0, i32* %tmp1, align 4 -; VF_8-LABEL: Checking a loop in "i32_factor_2" +; VF_8-LABEL: Checking a loop in 'i32_factor_2' ; VF_8: Found an estimated cost of 4 for VF 8 For instruction: %tmp2 = load i32, i32* %tmp0, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load i32, i32* %tmp1, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i32 0, i32* %tmp0, align 4 ; VF_8-NEXT: Found an estimated cost of 4 for VF 8 For instruction: store i32 0, i32* %tmp1, align 4 -; VF_16-LABEL: Checking a loop in "i32_factor_2" +; VF_16-LABEL: Checking a loop in 'i32_factor_2' ; VF_16: Found an estimated cost of 8 for VF 16 For instruction: %tmp2 = load i32, i32* %tmp0, align 4 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp3 = load i32, i32* %tmp1, align 4 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i32 0, i32* %tmp0, align 4 @@ -120,12 +120,12 @@ entry: br label %for.body -; VF_4-LABEL: Checking a loop in "half_factor_2" +; VF_4-LABEL: Checking a loop in 'half_factor_2' ; VF_4: Found an estimated cost of 40 for VF 4 For instruction: %tmp2 = load half, half* %tmp0, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load half, half* %tmp1, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store half 0xH0000, half* %tmp0, align 2 ; VF_4-NEXT: Found an estimated cost of 32 for VF 4 For instruction: store half 0xH0000, half* %tmp1, align 2 -; VF_8-LABEL: Checking a loop in "half_factor_2" +; VF_8-LABEL: Checking a loop in 'half_factor_2' ; VF_8: Found an estimated cost of 80 for VF 8 For instruction: %tmp2 = load half, half* %tmp0, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load half, half* %tmp1, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store half 0xH0000, half* %tmp0, align 2 diff --git a/llvm/test/Transforms/LoopVectorize/ARM/mve-interleaved-cost.ll b/llvm/test/Transforms/LoopVectorize/ARM/mve-interleaved-cost.ll --- a/llvm/test/Transforms/LoopVectorize/ARM/mve-interleaved-cost.ll +++ b/llvm/test/Transforms/LoopVectorize/ARM/mve-interleaved-cost.ll @@ -14,22 +14,22 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "i8_factor_2" +; VF_2-LABEL: Checking a loop in 'i8_factor_2' ; VF_2: Found an estimated cost of 24 for VF 2 For instruction: %tmp2 = load i8, i8* %tmp0, align 1 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load i8, i8* %tmp1, align 1 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i8 0, i8* %tmp0, align 1 ; VF_2-NEXT: Found an estimated cost of 8 for VF 2 For instruction: store i8 0, i8* %tmp1, align 1 -; VF_4-LABEL: Checking a loop in "i8_factor_2" +; VF_4-LABEL: Checking a loop in 'i8_factor_2' ; VF_4: Found an estimated cost of 4 for VF 4 For instruction: %tmp2 = load i8, i8* %tmp0, align 1 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load i8, i8* %tmp1, align 1 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i8 0, i8* %tmp0, align 1 ; VF_4-NEXT: Found an estimated cost of 4 for VF 4 For instruction: store i8 0, i8* %tmp1, align 1 -; VF_8-LABEL: Checking a loop in "i8_factor_2" +; VF_8-LABEL: Checking a loop in 'i8_factor_2' ; VF_8: Found an estimated cost of 4 for VF 8 For instruction: %tmp2 = load i8, i8* %tmp0, align 1 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load i8, i8* %tmp1, align 1 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i8 0, i8* %tmp0, align 1 ; VF_8-NEXT: Found an estimated cost of 4 for VF 8 For instruction: store i8 0, i8* %tmp1, align 1 -; VF_16-LABEL: Checking a loop in "i8_factor_2" +; VF_16-LABEL: Checking a loop in 'i8_factor_2' ; VF_16: Found an estimated cost of 4 for VF 16 For instruction: %tmp2 = load i8, i8* %tmp0, align 1 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp3 = load i8, i8* %tmp1, align 1 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i8 0, i8* %tmp0, align 1 @@ -55,22 +55,22 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "i16_factor_2" +; VF_2-LABEL: Checking a loop in 'i16_factor_2' ; VF_2: Found an estimated cost of 24 for VF 2 For instruction: %tmp2 = load i16, i16* %tmp0, align 2 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load i16, i16* %tmp1, align 2 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i16 0, i16* %tmp0, align 2 ; VF_2-NEXT: Found an estimated cost of 8 for VF 2 For instruction: store i16 0, i16* %tmp1, align 2 -; VF_4-LABEL: Checking a loop in "i16_factor_2" +; VF_4-LABEL: Checking a loop in 'i16_factor_2' ; VF_4: Found an estimated cost of 4 for VF 4 For instruction: %tmp2 = load i16, i16* %tmp0, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load i16, i16* %tmp1, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i16 0, i16* %tmp0, align 2 ; VF_4-NEXT: Found an estimated cost of 4 for VF 4 For instruction: store i16 0, i16* %tmp1, align 2 -; VF_8-LABEL: Checking a loop in "i16_factor_2" +; VF_8-LABEL: Checking a loop in 'i16_factor_2' ; VF_8: Found an estimated cost of 4 for VF 8 For instruction: %tmp2 = load i16, i16* %tmp0, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load i16, i16* %tmp1, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i16 0, i16* %tmp0, align 2 ; VF_8-NEXT: Found an estimated cost of 4 for VF 8 For instruction: store i16 0, i16* %tmp1, align 2 -; VF_16-LABEL: Checking a loop in "i16_factor_2" +; VF_16-LABEL: Checking a loop in 'i16_factor_2' ; VF_16: Found an estimated cost of 8 for VF 16 For instruction: %tmp2 = load i16, i16* %tmp0, align 2 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp3 = load i16, i16* %tmp1, align 2 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i16 0, i16* %tmp0, align 2 @@ -96,22 +96,22 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "i32_factor_2" +; VF_2-LABEL: Checking a loop in 'i32_factor_2' ; VF_2: Found an estimated cost of 24 for VF 2 For instruction: %tmp2 = load i32, i32* %tmp0, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load i32, i32* %tmp1, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp0, align 4 ; VF_2-NEXT: Found an estimated cost of 8 for VF 2 For instruction: store i32 0, i32* %tmp1, align 4 -; VF_4-LABEL: Checking a loop in "i32_factor_2" +; VF_4-LABEL: Checking a loop in 'i32_factor_2' ; VF_4: Found an estimated cost of 4 for VF 4 For instruction: %tmp2 = load i32, i32* %tmp0, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load i32, i32* %tmp1, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i32 0, i32* %tmp0, align 4 ; VF_4-NEXT: Found an estimated cost of 4 for VF 4 For instruction: store i32 0, i32* %tmp1, align 4 -; VF_8-LABEL: Checking a loop in "i32_factor_2" +; VF_8-LABEL: Checking a loop in 'i32_factor_2' ; VF_8: Found an estimated cost of 8 for VF 8 For instruction: %tmp2 = load i32, i32* %tmp0, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load i32, i32* %tmp1, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i32 0, i32* %tmp0, align 4 ; VF_8-NEXT: Found an estimated cost of 8 for VF 8 For instruction: store i32 0, i32* %tmp1, align 4 -; VF_16-LABEL: Checking a loop in "i32_factor_2" +; VF_16-LABEL: Checking a loop in 'i32_factor_2' ; VF_16: Found an estimated cost of 16 for VF 16 For instruction: %tmp2 = load i32, i32* %tmp0, align 4 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp3 = load i32, i32* %tmp1, align 4 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i32 0, i32* %tmp0, align 4 @@ -137,22 +137,22 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "i64_factor_2" +; VF_2-LABEL: Checking a loop in 'i64_factor_2' ; VF_2: Found an estimated cost of 44 for VF 2 For instruction: %tmp2 = load i64, i64* %tmp0, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load i64, i64* %tmp1, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i64 0, i64* %tmp0, align 8 ; VF_2-NEXT: Found an estimated cost of 12 for VF 2 For instruction: store i64 0, i64* %tmp1, align 8 -; VF_4-LABEL: Checking a loop in "i64_factor_2" +; VF_4-LABEL: Checking a loop in 'i64_factor_2' ; VF_4: Found an estimated cost of 88 for VF 4 For instruction: %tmp2 = load i64, i64* %tmp0, align 8 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load i64, i64* %tmp1, align 8 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i64 0, i64* %tmp0, align 8 ; VF_4-NEXT: Found an estimated cost of 24 for VF 4 For instruction: store i64 0, i64* %tmp1, align 8 -; VF_8-LABEL: Checking a loop in "i64_factor_2" +; VF_8-LABEL: Checking a loop in 'i64_factor_2' ; VF_8: Found an estimated cost of 176 for VF 8 For instruction: %tmp2 = load i64, i64* %tmp0, align 8 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load i64, i64* %tmp1, align 8 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i64 0, i64* %tmp0, align 8 ; VF_8-NEXT: Found an estimated cost of 48 for VF 8 For instruction: store i64 0, i64* %tmp1, align 8 -; VF_16-LABEL: Checking a loop in "i64_factor_2" +; VF_16-LABEL: Checking a loop in 'i64_factor_2' ; VF_16: Found an estimated cost of 352 for VF 16 For instruction: %tmp2 = load i64, i64* %tmp0, align 8 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp3 = load i64, i64* %tmp1, align 8 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i64 0, i64* %tmp0, align 8 @@ -178,22 +178,22 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "f16_factor_2" +; VF_2-LABEL: Checking a loop in 'f16_factor_2' ; VF_2: Found an estimated cost of 12 for VF 2 For instruction: %tmp2 = load half, half* %tmp0, align 2 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load half, half* %tmp1, align 2 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store half 0xH0000, half* %tmp0, align 2 ; VF_2-NEXT: Found an estimated cost of 8 for VF 2 For instruction: store half 0xH0000, half* %tmp1, align 2 -; VF_4-LABEL: Checking a loop in "f16_factor_2" +; VF_4-LABEL: Checking a loop in 'f16_factor_2' ; VF_4: Found an estimated cost of 18 for VF 4 For instruction: %tmp2 = load half, half* %tmp0, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load half, half* %tmp1, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store half 0xH0000, half* %tmp0, align 2 ; VF_4-NEXT: Found an estimated cost of 16 for VF 4 For instruction: store half 0xH0000, half* %tmp1, align 2 -; VF_8-LABEL: Checking a loop in "f16_factor_2" +; VF_8-LABEL: Checking a loop in 'f16_factor_2' ; VF_8: Found an estimated cost of 4 for VF 8 For instruction: %tmp2 = load half, half* %tmp0, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load half, half* %tmp1, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store half 0xH0000, half* %tmp0, align 2 ; VF_8-NEXT: Found an estimated cost of 4 for VF 8 For instruction: store half 0xH0000, half* %tmp1, align 2 -; VF_16-LABEL: Checking a loop in "f16_factor_2" +; VF_16-LABEL: Checking a loop in 'f16_factor_2' ; VF_16: Found an estimated cost of 8 for VF 16 For instruction: %tmp2 = load half, half* %tmp0, align 2 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp3 = load half, half* %tmp1, align 2 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store half 0xH0000, half* %tmp0, align 2 @@ -219,22 +219,22 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "f32_factor_2" +; VF_2-LABEL: Checking a loop in 'f32_factor_2' ; VF_2: Found an estimated cost of 10 for VF 2 For instruction: %tmp2 = load float, float* %tmp0, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load float, float* %tmp1, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store float 0.000000e+00, float* %tmp0, align 4 ; VF_2-NEXT: Found an estimated cost of 8 for VF 2 For instruction: store float 0.000000e+00, float* %tmp1, align 4 -; VF_4-LABEL: Checking a loop in "f32_factor_2" +; VF_4-LABEL: Checking a loop in 'f32_factor_2' ; VF_4: Found an estimated cost of 4 for VF 4 For instruction: %tmp2 = load float, float* %tmp0, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load float, float* %tmp1, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store float 0.000000e+00, float* %tmp0, align 4 ; VF_4-NEXT: Found an estimated cost of 4 for VF 4 For instruction: store float 0.000000e+00, float* %tmp1, align 4 -; VF_8-LABEL: Checking a loop in "f32_factor_2" +; VF_8-LABEL: Checking a loop in 'f32_factor_2' ; VF_8: Found an estimated cost of 8 for VF 8 For instruction: %tmp2 = load float, float* %tmp0, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load float, float* %tmp1, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store float 0.000000e+00, float* %tmp0, align 4 ; VF_8-NEXT: Found an estimated cost of 8 for VF 8 For instruction: store float 0.000000e+00, float* %tmp1, align 4 -; VF_16-LABEL: Checking a loop in "f32_factor_2" +; VF_16-LABEL: Checking a loop in 'f32_factor_2' ; VF_16: Found an estimated cost of 16 for VF 16 For instruction: %tmp2 = load float, float* %tmp0, align 4 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp3 = load float, float* %tmp1, align 4 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store float 0.000000e+00, float* %tmp0, align 4 @@ -260,22 +260,22 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "f64_factor_2" +; VF_2-LABEL: Checking a loop in 'f64_factor_2' ; VF_2: Found an estimated cost of 12 for VF 2 For instruction: %tmp2 = load double, double* %tmp0, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load double, double* %tmp1, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store double 0.000000e+00, double* %tmp0, align 8 ; VF_2-NEXT: Found an estimated cost of 8 for VF 2 For instruction: store double 0.000000e+00, double* %tmp1, align 8 -; VF_4-LABEL: Checking a loop in "f64_factor_2" +; VF_4-LABEL: Checking a loop in 'f64_factor_2' ; VF_4: Found an estimated cost of 24 for VF 4 For instruction: %tmp2 = load double, double* %tmp0, align 8 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load double, double* %tmp1, align 8 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store double 0.000000e+00, double* %tmp0, align 8 ; VF_4-NEXT: Found an estimated cost of 16 for VF 4 For instruction: store double 0.000000e+00, double* %tmp1, align 8 -; VF_8-LABEL: Checking a loop in "f64_factor_2" +; VF_8-LABEL: Checking a loop in 'f64_factor_2' ; VF_8: Found an estimated cost of 48 for VF 8 For instruction: %tmp2 = load double, double* %tmp0, align 8 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load double, double* %tmp1, align 8 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store double 0.000000e+00, double* %tmp0, align 8 ; VF_8-NEXT: Found an estimated cost of 32 for VF 8 For instruction: store double 0.000000e+00, double* %tmp1, align 8 -; VF_16-LABEL: Checking a loop in "f64_factor_2" +; VF_16-LABEL: Checking a loop in 'f64_factor_2' ; VF_16: Found an estimated cost of 96 for VF 16 For instruction: %tmp2 = load double, double* %tmp0, align 8 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp3 = load double, double* %tmp1, align 8 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store double 0.000000e+00, double* %tmp0, align 8 @@ -305,28 +305,28 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "i8_factor_3" +; VF_2-LABEL: Checking a loop in 'i8_factor_3' ; VF_2: Found an estimated cost of 36 for VF 2 For instruction: %tmp3 = load i8, i8* %tmp0, align 1 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp4 = load i8, i8* %tmp1, align 1 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load i8, i8* %tmp2, align 1 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i8 0, i8* %tmp0, align 1 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i8 0, i8* %tmp1, align 1 ; VF_2-NEXT: Found an estimated cost of 12 for VF 2 For instruction: store i8 0, i8* %tmp2, align 1 -; VF_4-LABEL: Checking a loop in "i8_factor_3" +; VF_4-LABEL: Checking a loop in 'i8_factor_3' ; VF_4: Found an estimated cost of 72 for VF 4 For instruction: %tmp3 = load i8, i8* %tmp0, align 1 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp4 = load i8, i8* %tmp1, align 1 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load i8, i8* %tmp2, align 1 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i8 0, i8* %tmp0, align 1 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i8 0, i8* %tmp1, align 1 ; VF_4-NEXT: Found an estimated cost of 24 for VF 4 For instruction: store i8 0, i8* %tmp2, align 1 -; VF_8-LABEL: Checking a loop in "i8_factor_3" +; VF_8-LABEL: Checking a loop in 'i8_factor_3' ; VF_8: Found an estimated cost of 144 for VF 8 For instruction: %tmp3 = load i8, i8* %tmp0, align 1 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp4 = load i8, i8* %tmp1, align 1 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i8, i8* %tmp2, align 1 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i8 0, i8* %tmp0, align 1 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i8 0, i8* %tmp1, align 1 ; VF_8-NEXT: Found an estimated cost of 48 for VF 8 For instruction: store i8 0, i8* %tmp2, align 1 -; VF_16-LABEL: Checking a loop in "i8_factor_3" +; VF_16-LABEL: Checking a loop in 'i8_factor_3' ; VF_16: Found an estimated cost of 288 for VF 16 For instruction: %tmp3 = load i8, i8* %tmp0, align 1 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp4 = load i8, i8* %tmp1, align 1 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i8, i8* %tmp2, align 1 @@ -357,28 +357,28 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "i16_factor_3" +; VF_2-LABEL: Checking a loop in 'i16_factor_3' ; VF_2: Found an estimated cost of 36 for VF 2 For instruction: %tmp3 = load i16, i16* %tmp0, align 2 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp4 = load i16, i16* %tmp1, align 2 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load i16, i16* %tmp2, align 2 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i16 0, i16* %tmp0, align 2 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i16 0, i16* %tmp1, align 2 ; VF_2-NEXT: Found an estimated cost of 12 for VF 2 For instruction: store i16 0, i16* %tmp2, align 2 -; VF_4-LABEL: Checking a loop in "i16_factor_3" +; VF_4-LABEL: Checking a loop in 'i16_factor_3' ; VF_4: Found an estimated cost of 72 for VF 4 For instruction: %tmp3 = load i16, i16* %tmp0, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp4 = load i16, i16* %tmp1, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load i16, i16* %tmp2, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i16 0, i16* %tmp0, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i16 0, i16* %tmp1, align 2 ; VF_4-NEXT: Found an estimated cost of 24 for VF 4 For instruction: store i16 0, i16* %tmp2, align 2 -; VF_8-LABEL: Checking a loop in "i16_factor_3" +; VF_8-LABEL: Checking a loop in 'i16_factor_3' ; VF_8: Found an estimated cost of 144 for VF 8 For instruction: %tmp3 = load i16, i16* %tmp0, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp4 = load i16, i16* %tmp1, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i16, i16* %tmp2, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i16 0, i16* %tmp0, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i16 0, i16* %tmp1, align 2 ; VF_8-NEXT: Found an estimated cost of 48 for VF 8 For instruction: store i16 0, i16* %tmp2, align 2 -; VF_16-LABEL: Checking a loop in "i16_factor_3" +; VF_16-LABEL: Checking a loop in 'i16_factor_3' ; VF_16: Found an estimated cost of 288 for VF 16 For instruction: %tmp3 = load i16, i16* %tmp0, align 2 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp4 = load i16, i16* %tmp1, align 2 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i16, i16* %tmp2, align 2 @@ -409,28 +409,28 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "i32_factor_3" +; VF_2-LABEL: Checking a loop in 'i32_factor_3' ; VF_2: Found an estimated cost of 36 for VF 2 For instruction: %tmp3 = load i32, i32* %tmp0, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp4 = load i32, i32* %tmp1, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load i32, i32* %tmp2, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp0, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp1, align 4 ; VF_2-NEXT: Found an estimated cost of 12 for VF 2 For instruction: store i32 0, i32* %tmp2, align 4 -; VF_4-LABEL: Checking a loop in "i32_factor_3" +; VF_4-LABEL: Checking a loop in 'i32_factor_3' ; VF_4: Found an estimated cost of 24 for VF 4 For instruction: %tmp3 = load i32, i32* %tmp0, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp4 = load i32, i32* %tmp1, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load i32, i32* %tmp2, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i32 0, i32* %tmp0, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i32 0, i32* %tmp1, align 4 ; VF_4-NEXT: Found an estimated cost of 24 for VF 4 For instruction: store i32 0, i32* %tmp2, align 4 -; VF_8-LABEL: Checking a loop in "i32_factor_3" +; VF_8-LABEL: Checking a loop in 'i32_factor_3' ; VF_8: Found an estimated cost of 144 for VF 8 For instruction: %tmp3 = load i32, i32* %tmp0, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp4 = load i32, i32* %tmp1, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i32, i32* %tmp2, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i32 0, i32* %tmp0, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i32 0, i32* %tmp1, align 4 ; VF_8-NEXT: Found an estimated cost of 48 for VF 8 For instruction: store i32 0, i32* %tmp2, align 4 -; VF_16-LABEL: Checking a loop in "i32_factor_3" +; VF_16-LABEL: Checking a loop in 'i32_factor_3' ; VF_16: Found an estimated cost of 288 for VF 16 For instruction: %tmp3 = load i32, i32* %tmp0, align 4 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp4 = load i32, i32* %tmp1, align 4 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i32, i32* %tmp2, align 4 @@ -461,28 +461,28 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "i64_factor_3" +; VF_2-LABEL: Checking a loop in 'i64_factor_3' ; VF_2: Found an estimated cost of 66 for VF 2 For instruction: %tmp3 = load i64, i64* %tmp0, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp4 = load i64, i64* %tmp1, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load i64, i64* %tmp2, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i64 0, i64* %tmp0, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i64 0, i64* %tmp1, align 8 ; VF_2-NEXT: Found an estimated cost of 18 for VF 2 For instruction: store i64 0, i64* %tmp2, align 8 -; VF_4-LABEL: Checking a loop in "i64_factor_3" +; VF_4-LABEL: Checking a loop in 'i64_factor_3' ; VF_4: Found an estimated cost of 132 for VF 4 For instruction: %tmp3 = load i64, i64* %tmp0, align 8 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp4 = load i64, i64* %tmp1, align 8 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load i64, i64* %tmp2, align 8 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i64 0, i64* %tmp0, align 8 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i64 0, i64* %tmp1, align 8 ; VF_4-NEXT: Found an estimated cost of 36 for VF 4 For instruction: store i64 0, i64* %tmp2, align 8 -; VF_8-LABEL: Checking a loop in "i64_factor_3" +; VF_8-LABEL: Checking a loop in 'i64_factor_3' ; VF_8: Found an estimated cost of 264 for VF 8 For instruction: %tmp3 = load i64, i64* %tmp0, align 8 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp4 = load i64, i64* %tmp1, align 8 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i64, i64* %tmp2, align 8 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i64 0, i64* %tmp0, align 8 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i64 0, i64* %tmp1, align 8 ; VF_8-NEXT: Found an estimated cost of 72 for VF 8 For instruction: store i64 0, i64* %tmp2, align 8 -; VF_16-LABEL: Checking a loop in "i64_factor_3" +; VF_16-LABEL: Checking a loop in 'i64_factor_3' ; VF_16: Found an estimated cost of 528 for VF 16 For instruction: %tmp3 = load i64, i64* %tmp0, align 8 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp4 = load i64, i64* %tmp1, align 8 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i64, i64* %tmp2, align 8 @@ -513,28 +513,28 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "f16_factor_3" +; VF_2-LABEL: Checking a loop in 'f16_factor_3' ; VF_2: Found an estimated cost of 18 for VF 2 For instruction: %tmp3 = load half, half* %tmp0, align 2 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp4 = load half, half* %tmp1, align 2 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load half, half* %tmp2, align 2 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store half 0xH0000, half* %tmp0, align 2 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store half 0xH0000, half* %tmp1, align 2 ; VF_2-NEXT: Found an estimated cost of 12 for VF 2 For instruction: store half 0xH0000, half* %tmp2, align 2 -; VF_4-LABEL: Checking a loop in "f16_factor_3" +; VF_4-LABEL: Checking a loop in 'f16_factor_3' ; VF_4: Found an estimated cost of 28 for VF 4 For instruction: %tmp3 = load half, half* %tmp0, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp4 = load half, half* %tmp1, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load half, half* %tmp2, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store half 0xH0000, half* %tmp0, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store half 0xH0000, half* %tmp1, align 2 ; VF_4-NEXT: Found an estimated cost of 24 for VF 4 For instruction: store half 0xH0000, half* %tmp2, align 2 -; VF_8-LABEL: Checking a loop in "f16_factor_3" +; VF_8-LABEL: Checking a loop in 'f16_factor_3' ; VF_8: Found an estimated cost of 56 for VF 8 For instruction: %tmp3 = load half, half* %tmp0, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp4 = load half, half* %tmp1, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load half, half* %tmp2, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store half 0xH0000, half* %tmp0, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store half 0xH0000, half* %tmp1, align 2 ; VF_8-NEXT: Found an estimated cost of 48 for VF 8 For instruction: store half 0xH0000, half* %tmp2, align 2 -; VF_16-LABEL: Checking a loop in "f16_factor_3" +; VF_16-LABEL: Checking a loop in 'f16_factor_3' ; VF_16: Found an estimated cost of 112 for VF 16 For instruction: %tmp3 = load half, half* %tmp0, align 2 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp4 = load half, half* %tmp1, align 2 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load half, half* %tmp2, align 2 @@ -565,28 +565,28 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "f32_factor_3" +; VF_2-LABEL: Checking a loop in 'f32_factor_3' ; VF_2: Found an estimated cost of 16 for VF 2 For instruction: %tmp3 = load float, float* %tmp0, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp4 = load float, float* %tmp1, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load float, float* %tmp2, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store float 0.000000e+00, float* %tmp0, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store float 0.000000e+00, float* %tmp1, align 4 ; VF_2-NEXT: Found an estimated cost of 12 for VF 2 For instruction: store float 0.000000e+00, float* %tmp2, align 4 -; VF_4-LABEL: Checking a loop in "f32_factor_3" +; VF_4-LABEL: Checking a loop in 'f32_factor_3' ; VF_4: Found an estimated cost of 24 for VF 4 For instruction: %tmp3 = load float, float* %tmp0, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp4 = load float, float* %tmp1, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load float, float* %tmp2, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store float 0.000000e+00, float* %tmp0, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store float 0.000000e+00, float* %tmp1, align 4 ; VF_4-NEXT: Found an estimated cost of 24 for VF 4 For instruction: store float 0.000000e+00, float* %tmp2, align 4 -; VF_8-LABEL: Checking a loop in "f32_factor_3" +; VF_8-LABEL: Checking a loop in 'f32_factor_3' ; VF_8: Found an estimated cost of 64 for VF 8 For instruction: %tmp3 = load float, float* %tmp0, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp4 = load float, float* %tmp1, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load float, float* %tmp2, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store float 0.000000e+00, float* %tmp0, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store float 0.000000e+00, float* %tmp1, align 4 ; VF_8-NEXT: Found an estimated cost of 48 for VF 8 For instruction: store float 0.000000e+00, float* %tmp2, align 4 -; VF_16-LABEL: Checking a loop in "f32_factor_3" +; VF_16-LABEL: Checking a loop in 'f32_factor_3' ; VF_16: Found an estimated cost of 128 for VF 16 For instruction: %tmp3 = load float, float* %tmp0, align 4 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp4 = load float, float* %tmp1, align 4 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load float, float* %tmp2, align 4 @@ -617,28 +617,28 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "f64_factor_3" +; VF_2-LABEL: Checking a loop in 'f64_factor_3' ; VF_2: Found an estimated cost of 18 for VF 2 For instruction: %tmp3 = load double, double* %tmp0, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp4 = load double, double* %tmp1, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load double, double* %tmp2, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store double 0.000000e+00, double* %tmp0, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store double 0.000000e+00, double* %tmp1, align 8 ; VF_2-NEXT: Found an estimated cost of 12 for VF 2 For instruction: store double 0.000000e+00, double* %tmp2, align 8 -; VF_4-LABEL: Checking a loop in "f64_factor_3" +; VF_4-LABEL: Checking a loop in 'f64_factor_3' ; VF_4: Found an estimated cost of 36 for VF 4 For instruction: %tmp3 = load double, double* %tmp0, align 8 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp4 = load double, double* %tmp1, align 8 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load double, double* %tmp2, align 8 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store double 0.000000e+00, double* %tmp0, align 8 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store double 0.000000e+00, double* %tmp1, align 8 ; VF_4-NEXT: Found an estimated cost of 24 for VF 4 For instruction: store double 0.000000e+00, double* %tmp2, align 8 -; VF_8-LABEL: Checking a loop in "f64_factor_3" +; VF_8-LABEL: Checking a loop in 'f64_factor_3' ; VF_8: Found an estimated cost of 72 for VF 8 For instruction: %tmp3 = load double, double* %tmp0, align 8 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp4 = load double, double* %tmp1, align 8 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load double, double* %tmp2, align 8 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store double 0.000000e+00, double* %tmp0, align 8 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store double 0.000000e+00, double* %tmp1, align 8 ; VF_8-NEXT: Found an estimated cost of 48 for VF 8 For instruction: store double 0.000000e+00, double* %tmp2, align 8 -; VF_16-LABEL: Checking a loop in "f64_factor_3" +; VF_16-LABEL: Checking a loop in 'f64_factor_3' ; VF_16: Found an estimated cost of 144 for VF 16 For instruction: %tmp3 = load double, double* %tmp0, align 8 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp4 = load double, double* %tmp1, align 8 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load double, double* %tmp2, align 8 @@ -672,7 +672,7 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "i8_factor_4" +; VF_2-LABEL: Checking a loop in 'i8_factor_4' ; VF_2: Found an estimated cost of 48 for VF 2 For instruction: %tmp4 = load i8, i8* %tmp0, align 1 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load i8, i8* %tmp1, align 1 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp6 = load i8, i8* %tmp2, align 1 @@ -681,7 +681,7 @@ ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i8 0, i8* %tmp1, align 1 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i8 0, i8* %tmp2, align 1 ; VF_2-NEXT: Found an estimated cost of 16 for VF 2 For instruction: store i8 0, i8* %tmp3, align 1 -; VF_4-LABEL: Checking a loop in "i8_factor_4" +; VF_4-LABEL: Checking a loop in 'i8_factor_4' ; VF_4: Found an estimated cost of 96 for VF 4 For instruction: %tmp4 = load i8, i8* %tmp0, align 1 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load i8, i8* %tmp1, align 1 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp6 = load i8, i8* %tmp2, align 1 @@ -690,7 +690,7 @@ ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i8 0, i8* %tmp1, align 1 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i8 0, i8* %tmp2, align 1 ; VF_4-NEXT: Found an estimated cost of 32 for VF 4 For instruction: store i8 0, i8* %tmp3, align 1 -; VF_8-LABEL: Checking a loop in "i8_factor_4" +; VF_8-LABEL: Checking a loop in 'i8_factor_4' ; VF_8: Found an estimated cost of 192 for VF 8 For instruction: %tmp4 = load i8, i8* %tmp0, align 1 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i8, i8* %tmp1, align 1 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp6 = load i8, i8* %tmp2, align 1 @@ -699,7 +699,7 @@ ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i8 0, i8* %tmp1, align 1 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i8 0, i8* %tmp2, align 1 ; VF_8-NEXT: Found an estimated cost of 64 for VF 8 For instruction: store i8 0, i8* %tmp3, align 1 -; VF_16-LABEL: Checking a loop in "i8_factor_4" +; VF_16-LABEL: Checking a loop in 'i8_factor_4' ; VF_16: Found an estimated cost of 384 for VF 16 For instruction: %tmp4 = load i8, i8* %tmp0, align 1 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i8, i8* %tmp1, align 1 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp6 = load i8, i8* %tmp2, align 1 @@ -735,7 +735,7 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "i16_factor_4" +; VF_2-LABEL: Checking a loop in 'i16_factor_4' ; VF_2: Found an estimated cost of 48 for VF 2 For instruction: %tmp4 = load i16, i16* %tmp0, align 2 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load i16, i16* %tmp1, align 2 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp6 = load i16, i16* %tmp2, align 2 @@ -744,7 +744,7 @@ ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i16 0, i16* %tmp1, align 2 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i16 0, i16* %tmp2, align 2 ; VF_2-NEXT: Found an estimated cost of 16 for VF 2 For instruction: store i16 0, i16* %tmp3, align 2 -; VF_4-LABEL: Checking a loop in "i16_factor_4" +; VF_4-LABEL: Checking a loop in 'i16_factor_4' ; VF_4: Found an estimated cost of 96 for VF 4 For instruction: %tmp4 = load i16, i16* %tmp0, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load i16, i16* %tmp1, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp6 = load i16, i16* %tmp2, align 2 @@ -753,7 +753,7 @@ ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i16 0, i16* %tmp1, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i16 0, i16* %tmp2, align 2 ; VF_4-NEXT: Found an estimated cost of 32 for VF 4 For instruction: store i16 0, i16* %tmp3, align 2 -; VF_8-LABEL: Checking a loop in "i16_factor_4" +; VF_8-LABEL: Checking a loop in 'i16_factor_4' ; VF_8: Found an estimated cost of 192 for VF 8 For instruction: %tmp4 = load i16, i16* %tmp0, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i16, i16* %tmp1, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp6 = load i16, i16* %tmp2, align 2 @@ -762,7 +762,7 @@ ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i16 0, i16* %tmp1, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i16 0, i16* %tmp2, align 2 ; VF_8-NEXT: Found an estimated cost of 64 for VF 8 For instruction: store i16 0, i16* %tmp3, align 2 -; VF_16-LABEL: Checking a loop in "i16_factor_4" +; VF_16-LABEL: Checking a loop in 'i16_factor_4' ; VF_16: Found an estimated cost of 384 for VF 16 For instruction: %tmp4 = load i16, i16* %tmp0, align 2 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i16, i16* %tmp1, align 2 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp6 = load i16, i16* %tmp2, align 2 @@ -798,7 +798,7 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "i32_factor_4" +; VF_2-LABEL: Checking a loop in 'i32_factor_4' ; VF_2: Found an estimated cost of 48 for VF 2 For instruction: %tmp4 = load i32, i32* %tmp0, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load i32, i32* %tmp1, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp6 = load i32, i32* %tmp2, align 4 @@ -807,7 +807,7 @@ ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp1, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp2, align 4 ; VF_2-NEXT: Found an estimated cost of 16 for VF 2 For instruction: store i32 0, i32* %tmp3, align 4 -; VF_4-LABEL: Checking a loop in "i32_factor_4" +; VF_4-LABEL: Checking a loop in 'i32_factor_4' ; VF_4: Found an estimated cost of 32 for VF 4 For instruction: %tmp4 = load i32, i32* %tmp0, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load i32, i32* %tmp1, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp6 = load i32, i32* %tmp2, align 4 @@ -816,7 +816,7 @@ ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i32 0, i32* %tmp1, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i32 0, i32* %tmp2, align 4 ; VF_4-NEXT: Found an estimated cost of 32 for VF 4 For instruction: store i32 0, i32* %tmp3, align 4 -; VF_8-LABEL: Checking a loop in "i32_factor_4" +; VF_8-LABEL: Checking a loop in 'i32_factor_4' ; VF_8: Found an estimated cost of 192 for VF 8 For instruction: %tmp4 = load i32, i32* %tmp0, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i32, i32* %tmp1, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp6 = load i32, i32* %tmp2, align 4 @@ -825,7 +825,7 @@ ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i32 0, i32* %tmp1, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i32 0, i32* %tmp2, align 4 ; VF_8-NEXT: Found an estimated cost of 64 for VF 8 For instruction: store i32 0, i32* %tmp3, align 4 -; VF_16-LABEL: Checking a loop in "i32_factor_4" +; VF_16-LABEL: Checking a loop in 'i32_factor_4' ; VF_16: Found an estimated cost of 384 for VF 16 For instruction: %tmp4 = load i32, i32* %tmp0, align 4 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i32, i32* %tmp1, align 4 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp6 = load i32, i32* %tmp2, align 4 @@ -861,7 +861,7 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "i64_factor_4" +; VF_2-LABEL: Checking a loop in 'i64_factor_4' ; VF_2: Found an estimated cost of 88 for VF 2 For instruction: %tmp4 = load i64, i64* %tmp0, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load i64, i64* %tmp1, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp6 = load i64, i64* %tmp2, align 8 @@ -870,7 +870,7 @@ ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i64 0, i64* %tmp1, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i64 0, i64* %tmp2, align 8 ; VF_2-NEXT: Found an estimated cost of 24 for VF 2 For instruction: store i64 0, i64* %tmp3, align 8 -; VF_4-LABEL: Checking a loop in "i64_factor_4" +; VF_4-LABEL: Checking a loop in 'i64_factor_4' ; VF_4: Found an estimated cost of 176 for VF 4 For instruction: %tmp4 = load i64, i64* %tmp0, align 8 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load i64, i64* %tmp1, align 8 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp6 = load i64, i64* %tmp2, align 8 @@ -879,7 +879,7 @@ ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i64 0, i64* %tmp1, align 8 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i64 0, i64* %tmp2, align 8 ; VF_4-NEXT: Found an estimated cost of 48 for VF 4 For instruction: store i64 0, i64* %tmp3, align 8 -; VF_8-LABEL: Checking a loop in "i64_factor_4" +; VF_8-LABEL: Checking a loop in 'i64_factor_4' ; VF_8: Found an estimated cost of 352 for VF 8 For instruction: %tmp4 = load i64, i64* %tmp0, align 8 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i64, i64* %tmp1, align 8 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp6 = load i64, i64* %tmp2, align 8 @@ -888,7 +888,7 @@ ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i64 0, i64* %tmp1, align 8 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i64 0, i64* %tmp2, align 8 ; VF_8-NEXT: Found an estimated cost of 96 for VF 8 For instruction: store i64 0, i64* %tmp3, align 8 -; VF_16-LABEL: Checking a loop in "i64_factor_4" +; VF_16-LABEL: Checking a loop in 'i64_factor_4' ; VF_16: Found an estimated cost of 704 for VF 16 For instruction: %tmp4 = load i64, i64* %tmp0, align 8 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i64, i64* %tmp1, align 8 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp6 = load i64, i64* %tmp2, align 8 @@ -924,7 +924,7 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "f16_factor_4" +; VF_2-LABEL: Checking a loop in 'f16_factor_4' ; VF_2: Found an estimated cost of 18 for VF 2 For instruction: %tmp4 = load half, half* %tmp0, align 2 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load half, half* %tmp1, align 2 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp6 = load half, half* %tmp2, align 2 @@ -933,7 +933,7 @@ ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store half 0xH0000, half* %tmp1, align 2 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store half 0xH0000, half* %tmp2, align 2 ; VF_2-NEXT: Found an estimated cost of 16 for VF 2 For instruction: store half 0xH0000, half* %tmp3, align 2 -; VF_4-LABEL: Checking a loop in "f16_factor_4" +; VF_4-LABEL: Checking a loop in 'f16_factor_4' ; VF_4: Found an estimated cost of 36 for VF 4 For instruction: %tmp4 = load half, half* %tmp0, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load half, half* %tmp1, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp6 = load half, half* %tmp2, align 2 @@ -942,7 +942,7 @@ ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store half 0xH0000, half* %tmp1, align 2 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store half 0xH0000, half* %tmp2, align 2 ; VF_4-NEXT: Found an estimated cost of 32 for VF 4 For instruction: store half 0xH0000, half* %tmp3, align 2 -; VF_8-LABEL: Checking a loop in "f16_factor_4" +; VF_8-LABEL: Checking a loop in 'f16_factor_4' ; VF_8: Found an estimated cost of 72 for VF 8 For instruction: %tmp4 = load half, half* %tmp0, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load half, half* %tmp1, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp6 = load half, half* %tmp2, align 2 @@ -951,7 +951,7 @@ ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store half 0xH0000, half* %tmp1, align 2 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store half 0xH0000, half* %tmp2, align 2 ; VF_8-NEXT: Found an estimated cost of 64 for VF 8 For instruction: store half 0xH0000, half* %tmp3, align 2 -; VF_16-LABEL: Checking a loop in "f16_factor_4" +; VF_16-LABEL: Checking a loop in 'f16_factor_4' ; VF_16: Found an estimated cost of 144 for VF 16 For instruction: %tmp4 = load half, half* %tmp0, align 2 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load half, half* %tmp1, align 2 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp6 = load half, half* %tmp2, align 2 @@ -987,7 +987,7 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "f32_factor_4" +; VF_2-LABEL: Checking a loop in 'f32_factor_4' ; VF_2: Found an estimated cost of 20 for VF 2 For instruction: %tmp4 = load float, float* %tmp0, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load float, float* %tmp1, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp6 = load float, float* %tmp2, align 4 @@ -996,7 +996,7 @@ ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store float 0.000000e+00, float* %tmp1, align 4 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store float 0.000000e+00, float* %tmp2, align 4 ; VF_2-NEXT: Found an estimated cost of 16 for VF 2 For instruction: store float 0.000000e+00, float* %tmp3, align 4 -; VF_4-LABEL: Checking a loop in "f32_factor_4" +; VF_4-LABEL: Checking a loop in 'f32_factor_4' ; VF_4: Found an estimated cost of 32 for VF 4 For instruction: %tmp4 = load float, float* %tmp0, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load float, float* %tmp1, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp6 = load float, float* %tmp2, align 4 @@ -1005,7 +1005,7 @@ ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store float 0.000000e+00, float* %tmp1, align 4 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store float 0.000000e+00, float* %tmp2, align 4 ; VF_4-NEXT: Found an estimated cost of 32 for VF 4 For instruction: store float 0.000000e+00, float* %tmp3, align 4 -; VF_8-LABEL: Checking a loop in "f32_factor_4" +; VF_8-LABEL: Checking a loop in 'f32_factor_4' ; VF_8: Found an estimated cost of 80 for VF 8 For instruction: %tmp4 = load float, float* %tmp0, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load float, float* %tmp1, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp6 = load float, float* %tmp2, align 4 @@ -1014,7 +1014,7 @@ ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store float 0.000000e+00, float* %tmp1, align 4 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store float 0.000000e+00, float* %tmp2, align 4 ; VF_8-NEXT: Found an estimated cost of 64 for VF 8 For instruction: store float 0.000000e+00, float* %tmp3, align 4 -; VF_16-LABEL: Checking a loop in "f32_factor_4" +; VF_16-LABEL: Checking a loop in 'f32_factor_4' ; VF_16: Found an estimated cost of 160 for VF 16 For instruction: %tmp4 = load float, float* %tmp0, align 4 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load float, float* %tmp1, align 4 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp6 = load float, float* %tmp2, align 4 @@ -1050,7 +1050,7 @@ entry: br label %for.body -; VF_2-LABEL: Checking a loop in "f64_factor_4" +; VF_2-LABEL: Checking a loop in 'f64_factor_4' ; VF_2: Found an estimated cost of 24 for VF 2 For instruction: %tmp4 = load double, double* %tmp0, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load double, double* %tmp1, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp6 = load double, double* %tmp2, align 8 @@ -1059,7 +1059,7 @@ ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store double 0.000000e+00, double* %tmp1, align 8 ; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store double 0.000000e+00, double* %tmp2, align 8 ; VF_2-NEXT: Found an estimated cost of 16 for VF 2 For instruction: store double 0.000000e+00, double* %tmp3, align 8 -; VF_4-LABEL: Checking a loop in "f64_factor_4" +; VF_4-LABEL: Checking a loop in 'f64_factor_4' ; VF_4: Found an estimated cost of 48 for VF 4 For instruction: %tmp4 = load double, double* %tmp0, align 8 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load double, double* %tmp1, align 8 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp6 = load double, double* %tmp2, align 8 @@ -1068,7 +1068,7 @@ ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store double 0.000000e+00, double* %tmp1, align 8 ; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store double 0.000000e+00, double* %tmp2, align 8 ; VF_4-NEXT: Found an estimated cost of 32 for VF 4 For instruction: store double 0.000000e+00, double* %tmp3, align 8 -; VF_8-LABEL: Checking a loop in "f64_factor_4" +; VF_8-LABEL: Checking a loop in 'f64_factor_4' ; VF_8: Found an estimated cost of 96 for VF 8 For instruction: %tmp4 = load double, double* %tmp0, align 8 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load double, double* %tmp1, align 8 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp6 = load double, double* %tmp2, align 8 @@ -1077,7 +1077,7 @@ ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store double 0.000000e+00, double* %tmp1, align 8 ; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store double 0.000000e+00, double* %tmp2, align 8 ; VF_8-NEXT: Found an estimated cost of 64 for VF 8 For instruction: store double 0.000000e+00, double* %tmp3, align 8 -; VF_16-LABEL: Checking a loop in "f64_factor_4" +; VF_16-LABEL: Checking a loop in 'f64_factor_4' ; VF_16: Found an estimated cost of 192 for VF 16 For instruction: %tmp4 = load double, double* %tmp0, align 8 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load double, double* %tmp1, align 8 ; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp6 = load double, double* %tmp2, align 8 diff --git a/llvm/test/Transforms/LoopVectorize/SystemZ/mem-interleaving-costs-02.ll b/llvm/test/Transforms/LoopVectorize/SystemZ/mem-interleaving-costs-02.ll --- a/llvm/test/Transforms/LoopVectorize/SystemZ/mem-interleaving-costs-02.ll +++ b/llvm/test/Transforms/LoopVectorize/SystemZ/mem-interleaving-costs-02.ll @@ -10,7 +10,7 @@ ; registers. Each of the 4 vector values must then be constructed from the ; two vector registers using one vperm each, which gives a cost of 2 + 4 = 6. ; -; CHECK: LV: Checking a loop in "fun0" +; CHECK: LV: Checking a loop in 'fun0' ; CHECK: LV: Found an estimated cost of 6 for VF 4 For instruction: %ld0 = load i16 ; CHECK: LV: Found an estimated cost of 0 for VF 4 For instruction: %ld1 = load i16 ; CHECK: LV: Found an estimated cost of 0 for VF 4 For instruction: %ld2 = load i16 @@ -48,7 +48,7 @@ ; 3 vector registers, and then constructing the vector value with two vperms, ; which gives a cost of 5. ; -; CHECK: LV: Checking a loop in "fun1" +; CHECK: LV: Checking a loop in 'fun1' ; CHECK: LV: Found an estimated cost of 5 for VF 16 For instruction: %ld0 = load i8 define void @fun1(i8 *%ptr, i8 *%dst) { entry: @@ -74,7 +74,7 @@ ; 32. At VF=2, this means loading 2 vector registers, and using 4 vperms to ; produce the vector values, which gives a cost of 6. ; -; CHECK: LV: Checking a loop in "fun2" +; CHECK: LV: Checking a loop in 'fun2' ; CHECK: LV: Found an estimated cost of 6 for VF 2 For instruction: %ld0 = load i8 ; CHECK: LV: Found an estimated cost of 0 for VF 2 For instruction: %ld1 = load i8 ; CHECK: LV: Found an estimated cost of 0 for VF 2 For instruction: %ld2 = load i8 @@ -114,7 +114,7 @@ ; as in fun2, except the stride makes the second iterations values overlap a ; vector register boundary. ; -; CHECK: LV: Checking a loop in "fun3" +; CHECK: LV: Checking a loop in 'fun3' ; CHECK: LV: Found an estimated cost of 7 for VF 2 For instruction: %ld0 = load i8 ; CHECK: LV: Found an estimated cost of 0 for VF 2 For instruction: %ld1 = load i8 ; CHECK: LV: Found an estimated cost of 0 for VF 2 For instruction: %ld2 = load i8 diff --git a/llvm/test/Transforms/LoopVectorize/X86/already-vectorized.ll b/llvm/test/Transforms/LoopVectorize/X86/already-vectorized.ll --- a/llvm/test/Transforms/LoopVectorize/X86/already-vectorized.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/already-vectorized.ll @@ -12,7 +12,7 @@ ; Function Attrs: nounwind readonly uwtable define i32 @vect() { -; CHECK: LV: Checking a loop in "vect" +; CHECK: LV: Checking a loop in 'vect' entry: br label %for.body diff --git a/llvm/test/Transforms/LoopVectorize/X86/reg-usage-debug.ll b/llvm/test/Transforms/LoopVectorize/X86/reg-usage-debug.ll --- a/llvm/test/Transforms/LoopVectorize/X86/reg-usage-debug.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/reg-usage-debug.ll @@ -21,7 +21,7 @@ target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" target triple = "x86_64-unknown-linux-gnu" -; CHECK: LV: Checking a loop in "test_g" +; CHECK: LV: Checking a loop in 'test_g' ; CHECK: LV(REG): Found max usage: 2 item ; CHECK-NEXT: LV(REG): RegisterClass: Generic::ScalarRC, 2 registers ; CHECK-NEXT: LV(REG): RegisterClass: Generic::VectorRC, 2 registers @@ -63,7 +63,7 @@ ret i32 %r.0.lcssa, !dbg !38 } -; CHECK: LV: Checking a loop in "test" +; CHECK: LV: Checking a loop in 'test' ; CHECK: LV(REG): Found max usage: 2 item ; CHECK-NEXT: LV(REG): RegisterClass: Generic::ScalarRC, 2 registers ; CHECK-NEXT: LV(REG): RegisterClass: Generic::VectorRC, 2 registers diff --git a/llvm/test/Transforms/LoopVectorize/X86/uniformshift.ll b/llvm/test/Transforms/LoopVectorize/X86/uniformshift.ll --- a/llvm/test/Transforms/LoopVectorize/X86/uniformshift.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/uniformshift.ll @@ -1,10 +1,10 @@ ; RUN: opt -mtriple=x86_64-apple-darwin -mattr=+sse2 -loop-vectorize -debug-only=loop-vectorize -S < %s 2>&1 | FileCheck %s ; REQUIRES: asserts -; CHECK: "foo" +; CHECK: 'foo' ; CHECK: LV: Found an estimated cost of 1 for VF 4 For instruction: %shift = ashr i32 %val, %k define void @foo(i32* nocapture %p, i32 %k) local_unnamed_addr #0 { -entry: +entry: br label %body body: diff --git a/llvm/test/Transforms/LoopVectorize/X86/vector-scalar-select-cost.ll b/llvm/test/Transforms/LoopVectorize/X86/vector-scalar-select-cost.ll --- a/llvm/test/Transforms/LoopVectorize/X86/vector-scalar-select-cost.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/vector-scalar-select-cost.ll @@ -9,7 +9,7 @@ @b = common global [2048 x i32] zeroinitializer, align 16 @c = common global [2048 x i32] zeroinitializer, align 16 -; CHECK: Checking a loop in "scalarselect" +; CHECK: Checking a loop in 'scalarselect' define void @scalarselect(i1 %cond) { br label %1 @@ -36,7 +36,7 @@ ret void } -; CHECK: Checking a loop in "vectorselect" +; CHECK: Checking a loop in 'vectorselect' define void @vectorselect(i1 %cond) { br label %1 diff --git a/llvm/test/Transforms/LoopVectorize/icmp-uniforms.ll b/llvm/test/Transforms/LoopVectorize/icmp-uniforms.ll --- a/llvm/test/Transforms/LoopVectorize/icmp-uniforms.ll +++ b/llvm/test/Transforms/LoopVectorize/icmp-uniforms.ll @@ -35,7 +35,7 @@ } ; Check for crash exposed by D76992. -; CHECK-LABEL: "test" +; CHECK-LABEL: 'test' ; CHECK: VPlan 'Initial VPlan for VF={4},UF>=1' { ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count ; CHECK-EMPTY: diff --git a/llvm/test/Transforms/LoopVectorize/interleaved-accesses-masked-group.ll b/llvm/test/Transforms/LoopVectorize/interleaved-accesses-masked-group.ll --- a/llvm/test/Transforms/LoopVectorize/interleaved-accesses-masked-group.ll +++ b/llvm/test/Transforms/LoopVectorize/interleaved-accesses-masked-group.ll @@ -30,11 +30,11 @@ ;} -; STRIDED_UNMASKED: LV: Checking a loop in "masked_strided1" +; STRIDED_UNMASKED: LV: Checking a loop in 'masked_strided1' ; STRIDED_UNMASKED: LV: Analyzing interleaved accesses... ; STRIDED_UNMASKED-NOT: LV: Creating an interleave group -; STRIDED_MASKED: LV: Checking a loop in "masked_strided1" +; STRIDED_MASKED: LV: Checking a loop in 'masked_strided1' ; STRIDED_MASKED: LV: Analyzing interleaved accesses... ; STRIDED_MASKED-NEXT: LV: Creating an interleave group with: store i8 %{{.*}}, i8* %{{.*}}, align 1 ; STRIDED_MASKED-NEXT: LV: Inserted: store i8 %{{.*}}, i8* %{{.*}}, align 1 @@ -63,13 +63,13 @@ ; } ;} -; STRIDED_UNMASKED: LV: Checking a loop in "masked_strided2" +; STRIDED_UNMASKED: LV: Checking a loop in 'masked_strided2' ; STRIDED_UNMASKED: LV: Analyzing interleaved accesses... ; STRIDED_UNMASKED-NEXT: LV: Creating an interleave group with: store i8 1, i8* %{{.*}}, align 1 ; STRIDED_UNMASKED-NEXT: LV: Invalidate candidate interleaved store group due to gaps. ; STRIDED_UNMASKED-NOT: LV: Creating an interleave group -; STRIDED_MASKED: LV: Checking a loop in "masked_strided2" +; STRIDED_MASKED: LV: Checking a loop in 'masked_strided2' ; STRIDED_MASKED: LV: Analyzing interleaved accesses... ; STRIDED_MASKED-NEXT: LV: Creating an interleave group with: store i8 2, i8* %{{.*}}, align 1 ; STRIDED_MASKED-NEXT: LV: Creating an interleave group with: store i8 1, i8* %{{.*}}, align 1 @@ -97,11 +97,11 @@ ;} -; STRIDED_UNMASKED: LV: Checking a loop in "masked_strided3" +; STRIDED_UNMASKED: LV: Checking a loop in 'masked_strided3' ; STRIDED_UNMASKED: LV: Analyzing interleaved accesses... ; STRIDED_UNMASKED-NOT: LV: Creating an interleave group -; STRIDED_MASKED: LV: Checking a loop in "masked_strided3" +; STRIDED_MASKED: LV: Checking a loop in 'masked_strided3' ; STRIDED_MASKED: LV: Analyzing interleaved accesses... ; STRIDED_MASKED-NEXT: LV: Creating an interleave group with: store i8 2, i8* %{{.*}}, align 1 ; STRIDED_MASKED-NEXT: LV: Creating an interleave group with: store i8 1, i8* %{{.*}}, align 1 diff --git a/llvm/test/Transforms/LoopVectorize/loop-legality-checks.ll b/llvm/test/Transforms/LoopVectorize/loop-legality-checks.ll --- a/llvm/test/Transforms/LoopVectorize/loop-legality-checks.ll +++ b/llvm/test/Transforms/LoopVectorize/loop-legality-checks.ll @@ -2,7 +2,7 @@ ; REQUIRES: asserts ; Make sure LV legal bails out when there is a non-int, non-ptr phi -; CHECK-LABEL: "invalid_phi_types" +; CHECK-LABEL: 'invalid_phi_types' ; CHECK: LV: Not vectorizing: Found a non-int non-pointer PHI. define i32 @invalid_phi_types() { entry: @@ -21,7 +21,7 @@ ; D40973 ; Make sure LV legal bails out when the loop doesn't have a legal pre-header. -; CHECK-LABEL: "inc" +; CHECK-LABEL: 'inc' ; CHECK: LV: Not vectorizing: Loop doesn't have a legal pre-header. define void @inc(i32 %n, i8* %P) { %1 = icmp sgt i32 %n, 0 diff --git a/llvm/test/Transforms/LoopVectorize/nounroll.ll b/llvm/test/Transforms/LoopVectorize/nounroll.ll --- a/llvm/test/Transforms/LoopVectorize/nounroll.ll +++ b/llvm/test/Transforms/LoopVectorize/nounroll.ll @@ -3,7 +3,7 @@ target datalayout = "e-m:e-i64:64-n32:64-S128-v256:256:256-v512:512:512" -; CHECK: LV: Checking a loop in "f1" +; CHECK: LV: Checking a loop in 'f1' ; CHECK: LV: Loop hints: force=? width=0 interleave=1 define dso_local void @f1(i32 signext %n, i32* %A) { entry: @@ -30,7 +30,7 @@ ret void } -; CHECK: LV: Checking a loop in "f2" +; CHECK: LV: Checking a loop in 'f2' ; CHECK: LV: Loop hints: force=? width=0 interleave=4 define dso_local void @f2(i32 signext %n, i32* %A) { entry: @@ -57,7 +57,7 @@ ret void } -; CHECK: LV: Checking a loop in "f3" +; CHECK: LV: Checking a loop in 'f3' ; CHECK: LV: Loop hints: force=? width=0 interleave=1 define dso_local void @f3(i32 signext %n, i32* %A) { entry: diff --git a/llvm/test/Transforms/LoopVectorize/optimal-epilog-vectorization-limitations.ll b/llvm/test/Transforms/LoopVectorize/optimal-epilog-vectorization-limitations.ll --- a/llvm/test/Transforms/LoopVectorize/optimal-epilog-vectorization-limitations.ll +++ b/llvm/test/Transforms/LoopVectorize/optimal-epilog-vectorization-limitations.ll @@ -4,7 +4,7 @@ target datalayout = "e-m:e-i64:64-n32:64-v256:256:256-v512:512:512" ; Currently we cannot handle live-out variables that are recurrences. -; CHECK: LV: Checking a loop in "f2" +; CHECK: LV: Checking a loop in 'f2' ; CHECK: LEV: Unable to vectorize epilogue because the loop is not a supported candidate. define signext i32 @f2(i8* noalias %A, i32 signext %n) { @@ -38,7 +38,7 @@ } ; Currently we cannot handle widended/truncated inductions. -; CHECK: LV: Checking a loop in "f3" +; CHECK: LV: Checking a loop in 'f3' ; CHECK: LEV: Unable to vectorize epilogue because the loop is not a supported candidate. define void @f3(i8* noalias %A, i32 signext %n) { diff --git a/llvm/test/Transforms/LoopVectorize/optimal-epilog-vectorization-scalable.ll b/llvm/test/Transforms/LoopVectorize/optimal-epilog-vectorization-scalable.ll --- a/llvm/test/Transforms/LoopVectorize/optimal-epilog-vectorization-scalable.ll +++ b/llvm/test/Transforms/LoopVectorize/optimal-epilog-vectorization-scalable.ll @@ -4,7 +4,7 @@ target datalayout = "e-m:e-i64:64-n32:64-v256:256:256-v512:512:512" ; Currently we cannot handle scalable vectorization factors. -; CHECK: LV: Checking a loop in "f1" +; CHECK: LV: Checking a loop in 'f1' ; CHECK: LEV: Epilogue vectorization factor is forced. ; CHECK: Epilogue Loop VF:2, Epilogue Loop UF:1 diff --git a/llvm/test/Transforms/LoopVectorize/pr39099.ll b/llvm/test/Transforms/LoopVectorize/pr39099.ll --- a/llvm/test/Transforms/LoopVectorize/pr39099.ll +++ b/llvm/test/Transforms/LoopVectorize/pr39099.ll @@ -6,7 +6,7 @@ ; Ensure that we don't create interleave groups for predicated ; strided accesses. -; CHECK: LV: Checking a loop in "masked_strided" +; CHECK: LV: Checking a loop in 'masked_strided' ; CHECK: LV: Analyzing interleaved accesses... ; CHECK-NOT: LV: Creating an interleave group diff --git a/llvm/test/Transforms/LoopVectorize/vect.omp.persistence.ll b/llvm/test/Transforms/LoopVectorize/vect.omp.persistence.ll --- a/llvm/test/Transforms/LoopVectorize/vect.omp.persistence.ll +++ b/llvm/test/Transforms/LoopVectorize/vect.omp.persistence.ll @@ -1,7 +1,7 @@ ; RUN: opt < %s -O2 -force-vector-interleave=2 -force-vector-width=4 -debug-only=loop-vectorize -S 2>&1 | FileCheck %s ; REQUIRES: asserts -; CHECK: LV: Checking a loop in "foo" +; CHECK: LV: Checking a loop in 'foo' ; CHECK: LV: Loop hints: force=enabled 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" diff --git a/llvm/test/Transforms/LoopVectorize/vplan-printing.ll b/llvm/test/Transforms/LoopVectorize/vplan-printing.ll --- a/llvm/test/Transforms/LoopVectorize/vplan-printing.ll +++ b/llvm/test/Transforms/LoopVectorize/vplan-printing.ll @@ -7,7 +7,7 @@ ; Tests for printing VPlans. define void @print_call_and_memory(i64 %n, float* noalias %y, float* noalias %x) nounwind uwtable { -; CHECK-LABEL: Checking a loop in "print_call_and_memory" +; CHECK-LABEL: Checking a loop in 'print_call_and_memory' ; CHECK: VPlan 'Initial VPlan for VF={4},UF>=1' { ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count ; CHECK-EMPTY: @@ -47,7 +47,7 @@ } define void @print_widen_gep_and_select(i64 %n, float* noalias %y, float* noalias %x, float* %z) nounwind uwtable { -; CHECK-LABEL: Checking a loop in "print_widen_gep_and_select" +; CHECK-LABEL: Checking a loop in 'print_widen_gep_and_select' ; CHECK: VPlan 'Initial VPlan for VF={4},UF>=1' { ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count ; CHECK-EMPTY: @@ -91,7 +91,7 @@ } define float @print_reduction(i64 %n, float* noalias %y) { -; CHECK-LABEL: Checking a loop in "print_reduction" +; CHECK-LABEL: Checking a loop in 'print_reduction' ; CHECK: VPlan 'Initial VPlan for VF={4},UF>=1' { ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count ; CHECK-EMPTY: @@ -128,7 +128,7 @@ } define void @print_replicate_predicated_phi(i64 %n, i64* %x) { -; CHECK-LABEL: Checking a loop in "print_replicate_predicated_phi" +; CHECK-LABEL: Checking a loop in 'print_replicate_predicated_phi' ; CHECK: VPlan 'Initial VPlan for VF={4},UF>=1' { ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count ; CHECK-EMPTY: @@ -201,7 +201,7 @@ @CD = common global [1024 x i32] zeroinitializer, align 4 define void @print_interleave_groups(i32 %C, i32 %D) { -; CHECK-LABEL: Checking a loop in "print_interleave_groups" +; CHECK-LABEL: Checking a loop in 'print_interleave_groups' ; CHECK: VPlan 'Initial VPlan for VF={4},UF>=1' { ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count ; CHECK-EMPTY: @@ -261,7 +261,7 @@ } define float @print_fmuladd_strict(float* %a, float* %b, i64 %n) { -; CHECK-LABEL: Checking a loop in "print_fmuladd_strict" +; CHECK-LABEL: Checking a loop in 'print_fmuladd_strict' ; CHECK: VPlan 'Initial VPlan for VF={4},UF>=1' { ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count ; CHECK-EMPTY: @@ -301,7 +301,7 @@ } define void @debug_loc_vpinstruction(i32* nocapture %asd, i32* nocapture %bsd) !dbg !5 { -; CHECK-LABEL: Checking a loop in "debug_loc_vpinstruction" +; CHECK-LABEL: Checking a loop in 'debug_loc_vpinstruction' ; CHECK: VPlan 'Initial VPlan for VF={4},UF>=1' { ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count ; CHECK-EMPTY: diff --git a/llvm/test/Transforms/LoopVectorize/vplan-sink-scalars-and-merge.ll b/llvm/test/Transforms/LoopVectorize/vplan-sink-scalars-and-merge.ll --- a/llvm/test/Transforms/LoopVectorize/vplan-sink-scalars-and-merge.ll +++ b/llvm/test/Transforms/LoopVectorize/vplan-sink-scalars-and-merge.ll @@ -9,7 +9,7 @@ @c = common global [2048 x i32] zeroinitializer, align 16 -; CHECK-LABEL: LV: Checking a loop in "sink1" +; CHECK-LABEL: LV: Checking a loop in 'sink1' ; CHECK: VPlan 'Initial VPlan for VF={2},UF>=1' { ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count ; CHECK-EMPTY: @@ -75,7 +75,7 @@ ret void } -; CHECK-LABEL: LV: Checking a loop in "sink2" +; CHECK-LABEL: LV: Checking a loop in 'sink2' ; CHECK: VPlan 'Initial VPlan for VF={2},UF>=1' { ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count ; CHECK-EMPTY: @@ -154,7 +154,7 @@ ret void } -; CHECK-LABEL: LV: Checking a loop in "sink3" +; CHECK-LABEL: LV: Checking a loop in 'sink3' ; CHECK: VPlan 'Initial VPlan for VF={2},UF>=1' { ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count ; CHECK-EMPTY: @@ -235,7 +235,7 @@ ; Make sure we do not sink uniform instructions. define void @uniform_gep(i64 %k, i16* noalias %A, i16* noalias %B) { -; CHECK-LABEL: LV: Checking a loop in "uniform_gep" +; CHECK-LABEL: LV: Checking a loop in 'uniform_gep' ; CHECK: VPlan 'Initial VPlan for VF={2},UF>=1' { ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count ; CHECK-EMPTY: @@ -325,7 +325,7 @@ ; Loop with predicated load. define void @pred_cfg1(i32 %k, i32 %j) { -; CHECK-LABEL: LV: Checking a loop in "pred_cfg1" +; CHECK-LABEL: LV: Checking a loop in 'pred_cfg1' ; CHECK: VPlan 'Initial VPlan for VF={2},UF>=1' { ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count ; CHECK-EMPTY: @@ -426,7 +426,7 @@ ; Loop with predicated load and store in separate blocks, store depends on ; loaded value. define void @pred_cfg2(i32 %k, i32 %j) { -; CHECK-LABEL: LV: Checking a loop in "pred_cfg2" +; CHECK-LABEL: LV: Checking a loop in 'pred_cfg2' ; CHECK: VPlan 'Initial VPlan for VF={2},UF>=1' { ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count ; CHECK-EMPTY: @@ -542,7 +542,7 @@ ; Loop with predicated load and store in separate blocks, store does not depend ; on loaded value. define void @pred_cfg3(i32 %k, i32 %j) { -; CHECK-LABEL: LV: Checking a loop in "pred_cfg3" +; CHECK-LABEL: LV: Checking a loop in 'pred_cfg3' ; CHECK: VPlan 'Initial VPlan for VF={2},UF>=1' { ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count ; CHECK-EMPTY: @@ -652,7 +652,7 @@ } define void @merge_3_replicate_region(i32 %k, i32 %j) { -; CHECK-LABEL: LV: Checking a loop in "merge_3_replicate_region" +; CHECK-LABEL: LV: Checking a loop in 'merge_3_replicate_region' ; CHECK: VPlan 'Initial VPlan for VF={2},UF>=1' { ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count ; CHECK-EMPTY: @@ -767,7 +767,7 @@ define void @update_2_uses_in_same_recipe_in_merged_block(i32 %k) { -; CHECK-LABEL: LV: Checking a loop in "update_2_uses_in_same_recipe_in_merged_block" +; CHECK-LABEL: LV: Checking a loop in 'update_2_uses_in_same_recipe_in_merged_block' ; CHECK: VPlan 'Initial VPlan for VF={2},UF>=1' { ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count ; CHECK-EMPTY: @@ -834,7 +834,7 @@ } define void @recipe_in_merge_candidate_used_by_first_order_recurrence(i32 %k) { -; CHECK-LABEL: LV: Checking a loop in "recipe_in_merge_candidate_used_by_first_order_recurrence" +; CHECK-LABEL: LV: Checking a loop in 'recipe_in_merge_candidate_used_by_first_order_recurrence' ; CHECK: VPlan 'Initial VPlan for VF={2},UF>=1' { ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count ; CHECK-EMPTY: @@ -918,7 +918,7 @@ } define void @update_multiple_users(i16* noalias %src, i8* noalias %dst, i1 %c) { -; CHECK-LABEL: LV: Checking a loop in "update_multiple_users" +; CHECK-LABEL: LV: Checking a loop in 'update_multiple_users' ; CHECK: VPlan 'Initial VPlan for VF={2},UF>=1' { ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count ; CHECK-EMPTY: @@ -989,7 +989,7 @@ } define void @sinking_requires_duplication(float* %addr) { -; CHECK-LABEL: LV: Checking a loop in "sinking_requires_duplication" +; CHECK-LABEL: LV: Checking a loop in 'sinking_requires_duplication' ; CHECK: VPlan 'Initial VPlan for VF={2},UF>=1' { ; CHECK-NEXT: Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count ; CHECK-EMPTY: