maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[RISCV] Enable fixed-length vectorization of LoopVectorizer for RISC-V Vector 

By implementing the method "unsigned RISCVTTIImpl::getRegisterBitWidth(bool Vector)",
fixed-length vectorization is enabled when possible. Without this method, the
"#pragma clang loop" directive is needed to enable vectorization(or the cost model
may inform LLVM that "Vectorization is possible but not beneficial").

Reviewed By: frasercrmck

Differential Revision: https://reviews.llvm.org/D97549
This commit is contained in:
Luke 2021-02-26 22:10:30 +08:00
parent 2357d29335
commit d28297ff68
2 changed files with 47 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
View File

@ -51,6 +51,15 @@ public:
bool shouldExpandReduction(const IntrinsicInst *II) const;
bool supportsScalableVectors() const { return ST->hasStdExtV(); }
Optional<unsigned> getMaxVScale() const;
unsigned getRegisterBitWidth(bool Vector) const {
if (Vector) {
if (ST->hasStdExtV())
return ST->getMinRVVVectorSizeInBits();
return 0;
}
return ST->getXLen();
}
};
} // end namespace llvm

38
llvm/test/Transforms/LoopVectorize/RISCV/riscv-unroll.ll Normal file
View File

@ -0,0 +1,38 @@
; RUN: opt < %s -loop-vectorize -mtriple=riscv64 -mattr=+experimental-v -riscv-v-vector-bits-min=128 -S | FileCheck %s
; RUN: opt < %s -loop-vectorize -mtriple=riscv32 -mattr=+experimental-v -riscv-v-vector-bits-min=128 -S | FileCheck %s
; Function Attrs: nounwind
define i32* @array_add(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32* %c, i32 %size) {
;CHECK-LABEL: array_add
;CHECK: load <4 x i32>
;CHECK: load <4 x i32>
;CHECK: add nsw <4 x i32>
;CHECK: store <4 x i32>
;CHECK: ret
entry:
%cmp10 = icmp sgt i32 %size, 0
br i1 %cmp10, label %for.body.preheader, label %for.end
for.body.preheader: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.preheader, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
%1 = load i32, i32* %arrayidx2, align 4
%add = add nsw i32 %1, %0
%arrayidx4 = getelementptr inbounds i32, i32* %c, i64 %indvars.iv
store i32 %add, i32* %arrayidx4, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %size
br i1 %exitcond, label %for.end.loopexit, label %for.body
for.end.loopexit: ; preds = %for.body
br label %for.end
for.end: ; preds = %for.end.loopexit, %entry
ret i32* %c
}