[llvm] 6c4d8f4 - [AArch64] Add check for widening instruction for SVE.

[Caroline Concatto via llvm-commits]

Author: Caroline Concatto
Date: 2020-11-16T12:30:08Z
New Revision: 6c4d8f4651fd46b93ef16f4fc9115881eb0ea0b2

URL: https://github.com/llvm/llvm-project/commit/6c4d8f4651fd46b93ef16f4fc9115881eb0ea0b2
DIFF: https://github.com/llvm/llvm-project/commit/6c4d8f4651fd46b93ef16f4fc9115881eb0ea0b2.diff

LOG: [AArch64] Add check for widening instruction for SVE.

This patch fixes the function isWideningInstruction for scalable vectors.
Now the cost model can check the widening pattern for SVE.

Differential Revision: https://reviews.llvm.org/D91260

Added: 
    llvm/test/Analysis/CostModel/AArch64/sve-widening-instruction.ll

Modified: 
    llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 4f7ebff2b44f..54bb3d0c7781 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -240,8 +240,8 @@ bool AArch64TTIImpl::isWideningInstruction(Type *DstTy, unsigned Opcode,
   // A helper that returns a vector type from the given type. The number of
   // elements in type Ty determine the vector width.
   auto toVectorTy = [&](Type *ArgTy) {
-    return FixedVectorType::get(ArgTy->getScalarType(),
-                                cast<FixedVectorType>(DstTy)->getNumElements());
+    return VectorType::get(ArgTy->getScalarType(),
+                           cast<VectorType>(DstTy)->getElementCount());
   };
 
   // Exit early if DstTy is not a vector type whose elements are at least
@@ -290,8 +290,8 @@ bool AArch64TTIImpl::isWideningInstruction(Type *DstTy, unsigned Opcode,
     return false;
 
   // Get the total number of vector elements in the legalized types.
-  unsigned NumDstEls = DstTyL.first * DstTyL.second.getVectorNumElements();
-  unsigned NumSrcEls = SrcTyL.first * SrcTyL.second.getVectorNumElements();
+  unsigned NumDstEls = DstTyL.first * DstTyL.second.getVectorMinNumElements();
+  unsigned NumSrcEls = SrcTyL.first * SrcTyL.second.getVectorMinNumElements();
 
   // Return true if the legalized types have the same number of vector elements
   // and the destination element type size is twice that of the source type.

diff  --git a/llvm/test/Analysis/CostModel/AArch64/sve-widening-instruction.ll b/llvm/test/Analysis/CostModel/AArch64/sve-widening-instruction.ll
new file mode 100644
index 000000000000..50225a0616e1
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-widening-instruction.ll
@@ -0,0 +1,21 @@
+; Checks if widening instructions works for SVE
+
+; RUN: opt  -cost-model -analyze -mtriple=aarch64--linux-gnu -mattr=+sve < %s 2>%t | FileCheck %s
+; RUN: FileCheck --check-prefix=WARN --allow-empty %s <%t
+
+; If this check fails please read test/CodeGen/AArch64/README for instructions on how to resolve it.
+; WARN-NOT: warning
+
+define <vscale x 4 x i32> @widening(<vscale x 16 x i8> %in, <vscale x 4 x i16> %in2) {
+
+; CHECK-LABEL: 'widening':
+; CHECK: Cost Model: Found an estimated cost of {{[0-9]+}} for instruction:   %in.bc = bitcast <vscale x 16 x i8> %in to <vscale x 4 x i32>
+; CHECK-NEXT: Cost Model: Found an estimated cost of {{[0-9]+}} for instruction:   %in2.ext = zext <vscale x 4 x i16> %in2 to <vscale x 4 x i32>
+; CHECK-NEXT: Cost Model: Found an estimated cost of {{[0-9]+}} for instruction:   %in.add = add <vscale x 4 x i32> %in.bc, %in2.ext
+; CHECK-NEXT: Cost Model: Found an estimated cost of {{[0-9]+}} for instruction:   ret <vscale x 4 x i32> %in.add
+
+  %in.bc = bitcast <vscale x 16 x i8> %in to <vscale x 4 x i32>
+  %in2.ext = zext <vscale x 4 x i16> %in2 to <vscale x 4 x i32>
+  %in.add = add <vscale x 4 x i32> %in.bc, %in2.ext
+  ret <vscale x 4 x i32> %in.add
+}