RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00
Code Issues Projects Releases Wiki Activity

[AArch64] Add check for widening instruction for SVE.

Browse Source 
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
This commit is contained in:
Caroline Concatto 2020-11-11 14:41:01 +00:00
parent 1460ef2da3
commit 5d2395e6d6
2 changed files with 25 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
lib/Target/AArch64/AArch64TargetTransformInfo.cpp
View File

@ -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.

21
test/Analysis/CostModel/AArch64/sve-widening-instruction.ll Normal file
View File

@ -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
}