6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-09-23 01:25:32 +00:00
Code Issues Projects Releases Wiki Activity

[X86] Disable loop unrolling in loop vectorization pass when VF is 1.

Browse Source 
The patch disabled unrolling in loop vectorization pass when VF==1 on x86 architecture,
by setting MaxInterleaveFactor to 1. Unrolling in loop vectorization pass may introduce
the cost of overflow check, memory boundary check and extra prologue/epilogue code when
regular unroller will unroll the loop another time. Disable it when VF==1 remove the
unnecessary cost on x86. The same can be done for other platforms after verifying
interleaving/memory bound checking to be not perf critical on those platforms.

Differential Revision: http://reviews.llvm.org/D9515


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@236613 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Wei Mi
2015-05-06 17:12:25 +00:00
parent 530a574a9d
commit cac51be31f
16 changed files with 64 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
test/Transforms/LoopVectorize/X86/unroll-small-loops.ll
View File

@@ -47,9 +47,11 @@ define i32 @foo(i32* nocapture %A) nounwind uwtable ssp {
; CHECK-VECTOR: store <4 x i32>
; CHECK-VECTOR: ret
;
; For x86, loop unroll in loop vectorizer is disabled when VF==1.
;
; CHECK-SCALAR-LABEL: @bar(
; CHECK-SCALAR: store i32
; CHECK-SCALAR: store i32
; CHECK-SCALAR-NOT: store i32
; CHECK-SCALAR: ret
define i32 @bar(i32* nocapture %A, i32 %n) nounwind uwtable ssp {
%1 = icmp sgt i32 %n, 0

37
test/Transforms/LoopVectorize/unroll.ll Normal file
View File

@@ -0,0 +1,37 @@
; This test makes sure that loop will not be unrolled in vectorization if VF computed
; equals to 1.
; RUN: opt < %s -loop-vectorize -S | FileCheck %s
; Make sure there are no geps being merged.
; CHECK-LABEL: @foo(
; CHECK: getelementptr
; CHECK-NOT: getelementptr
@N = common global i32 0, align 4
@a = common global [1000 x i32] zeroinitializer, align 16
define void @foo() #0 {
entry:
%0 = load i32, i32* @N, align 4
%cmp5 = icmp sgt i32 %0, 0
br i1 %cmp5, label %for.body.lr.ph, label %for.end
for.body.lr.ph: ; preds = %entry
%conv = sext i32 %0 to i64
br label %for.body
for.body: ; preds = %for.body.lr.ph, %for.body
%i.06 = phi i64 [ 0, %for.body.lr.ph ], [ %inc, %for.body ]
%mul = mul nuw nsw i64 %i.06, 7
%arrayidx = getelementptr inbounds [1000 x i32], [1000 x i32]* @a, i64 0, i64 %mul
store i32 3, i32* %arrayidx, align 4
%inc = add nuw nsw i64 %i.06, 1
%cmp = icmp slt i64 %inc, %conv
br i1 %cmp, label %for.body, label %for.end.loopexit
for.end.loopexit: ; preds = %for.body
br label %for.end
for.end: ; preds = %for.end.loopexit, %entry
ret void
}