6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-01-01 00:33:09 +00:00
Code Issues Projects Releases Wiki Activity

This commit allows vectorized loops to be unrolled by a factor of 2 for AArch64.

Browse Source 
A new test case is also added for ARM64.

Patched by Z.Zheng



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@206563 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Jiangning Liu 2014-04-18 07:57:54 +00:00
parent 1b16515971
commit a1da819896
3 changed files with 85 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
lib/Target/AArch64/AArch64TargetTransformInfo.cpp
View File

@ -92,6 +92,7 @@ public:
return 64;
}
unsigned getMaximumUnrollFactor() const override { return 2; }
/// @}
};

42
test/Transforms/LoopVectorize/AArch64/aarch64-unroll.ll Normal file
View File

@ -0,0 +1,42 @@
; RUN: opt < %s -loop-vectorize -mtriple=aarch64-none-linux-gnu -mattr=+neon -S | FileCheck %s
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
; 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: load <4 x i32>
;CHECK: load <4 x i32>
;CHECK: add nsw <4 x i32>
;CHECK: add nsw <4 x i32>
;CHECK: store <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* %a, i64 %indvars.iv
%0 = load i32* %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32* %b, i64 %indvars.iv
%1 = load i32* %arrayidx2, align 4
%add = add nsw i32 %1, %0
%arrayidx4 = getelementptr inbounds 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
}

42
test/Transforms/LoopVectorize/ARM64/arm64-unroll.ll Normal file
View File

@ -0,0 +1,42 @@
; RUN: opt < %s -loop-vectorize -mtriple=arm64-none-linux-gnu -mattr=+neon -S | FileCheck %s
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
; 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: load <4 x i32>
;CHECK: load <4 x i32>
;CHECK: add nsw <4 x i32>
;CHECK: add nsw <4 x i32>
;CHECK: store <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* %a, i64 %indvars.iv
%0 = load i32* %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32* %b, i64 %indvars.iv
%1 = load i32* %arrayidx2, align 4
%add = add nsw i32 %1, %0
%arrayidx4 = getelementptr inbounds 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
}