mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 03:02:36 +01:00
fa1c32679f
This opens up more optimization opportunities in passes that already handle MemCpyInst's. Differential revision: https://reviews.llvm.org/D105247
65 lines
3.1 KiB
LLVM
65 lines
3.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -loop-idiom < %s -S | FileCheck %s
|
|
|
|
%struct.S = type { i32, i32, i8 }
|
|
|
|
; unsigned copy_noalias(S* __restrict a, S *b, int n) {
|
|
; for (int i = 0; i < n; i++) {
|
|
; a[i] = b[i];
|
|
; }
|
|
; return sizeof(a[0]);
|
|
; }
|
|
|
|
; Function Attrs: nofree nounwind uwtable mustprogress
|
|
define dso_local i32 @copy_noalias(%struct.S* noalias nocapture %a, %struct.S* nocapture readonly %b, i32 %n) local_unnamed_addr #0 {
|
|
; CHECK-LABEL: @copy_noalias(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[CMP7:%.*]] = icmp sgt i32 [[N:%.*]], 0
|
|
; CHECK-NEXT: br i1 [[CMP7]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
|
|
; CHECK: for.body.preheader:
|
|
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
|
|
; CHECK: for.cond.cleanup.loopexit:
|
|
; CHECK-NEXT: br label [[FOR_COND_CLEANUP]]
|
|
; CHECK: for.cond.cleanup:
|
|
; CHECK-NEXT: ret i32 12
|
|
; CHECK: for.body:
|
|
; CHECK-NEXT: [[I_08:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
|
|
; CHECK-NEXT: [[IDXPROM:%.*]] = zext i32 [[I_08]] to i64
|
|
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[B:%.*]], i64 [[IDXPROM]]
|
|
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[A:%.*]], i64 [[IDXPROM]]
|
|
; CHECK-NEXT: [[TMP0:%.*]] = bitcast %struct.S* [[ARRAYIDX2]] to i8*
|
|
; CHECK-NEXT: [[TMP1:%.*]] = bitcast %struct.S* [[ARRAYIDX]] to i8*
|
|
; CHECK-NEXT: call void @llvm.memcpy.inline.p0i8.p0i8.i64(i8* nonnull align 4 dereferenceable(12) [[TMP0]], i8* nonnull align 4 dereferenceable(12) [[TMP1]], i64 12, i1 false)
|
|
; CHECK-NEXT: [[INC]] = add nuw nsw i32 [[I_08]], 1
|
|
; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[INC]], [[N]]
|
|
; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]]
|
|
;
|
|
entry:
|
|
%cmp7 = icmp sgt i32 %n, 0
|
|
br i1 %cmp7, label %for.body.preheader, label %for.cond.cleanup
|
|
|
|
for.body.preheader: ; preds = %entry
|
|
br label %for.body
|
|
|
|
for.cond.cleanup.loopexit: ; preds = %for.body
|
|
br label %for.cond.cleanup
|
|
|
|
for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
|
|
ret i32 12
|
|
|
|
for.body: ; preds = %for.body.preheader, %for.body
|
|
%i.08 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
|
|
%idxprom = zext i32 %i.08 to i64
|
|
%arrayidx = getelementptr inbounds %struct.S, %struct.S* %b, i64 %idxprom
|
|
%arrayidx2 = getelementptr inbounds %struct.S, %struct.S* %a, i64 %idxprom
|
|
%0 = bitcast %struct.S* %arrayidx2 to i8*
|
|
%1 = bitcast %struct.S* %arrayidx to i8*
|
|
call void @llvm.memcpy.inline.p0i8.p0i8.i64(i8* nonnull align 4 dereferenceable(12) %0, i8* nonnull align 4 dereferenceable(12) %1, i64 12, i1 false)
|
|
%inc = add nuw nsw i32 %i.08, 1
|
|
%cmp = icmp slt i32 %inc, %n
|
|
br i1 %cmp, label %for.body, label %for.cond.cleanup.loopexit
|
|
}
|
|
|
|
; Function Attrs: argmemonly nofree nosync nounwind willreturn
|
|
declare void @llvm.memcpy.inline.p0i8.p0i8.i64(i8* noalias nocapture writeonly, i8* noalias nocapture readonly, i64, i1 immarg) #1
|