da1cdffbb1
For a simple loop like:
```
struct S {
int x;
int y;
char b;
};
unsigned foo(S* __restrict__ a, S* b, int n) {
for (int i = 0; i < n; i++)
a[i] = b[i];
return sizeof(a[0]);
}
```
We could eliminate the loop and convert it to a large memcpy of 12*n bytes. Currently this is not handled. Output of `opt -loop-idiom -S < memcpy_before.ll`
```
%struct.S = type { i32, i32, i8 }
define dso_local i32 @_Z3fooP1SS0_i(%struct.S* noalias nocapture %a, %struct.S* nocapture readonly %b, i32 %n) local_unnamed_addr {
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, %for.body.preheader
%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.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.p0i8.p0i8.i64(i8* noalias nocapture writeonly, i8* noalias nocapture readonly, i64, i1 immarg) #0
attributes #0 = { argmemonly nofree nosync nounwind willreturn }
```
The loop idiom pass currently only handles load and store instructions. Since struct S is too big to fit in a register, the loop body contains a memcpy intrinsic.
With this change, re-run `opt -loop-idiom -S < memcpy_before.ll`. The loop memcpy is promoted to loop preheader. For this trivial case, the loop is dead and will be removed by another pass.
```
%struct.S = type { i32, i32, i8 }
define dso_local i32 @_Z3fooP1SS0_i(%struct.S* noalias nocapture %a, %struct.S* nocapture readonly %b, i32 %n) local_unnamed_addr {
entry:
%a1 = bitcast %struct.S* %a to i8*
%b2 = bitcast %struct.S* %b to i8*
%cmp7 = icmp sgt i32 %n, 0
br i1 %cmp7, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader: ; preds = %entry
%0 = zext i32 %n to i64
%1 = mul nuw nsw i64 %0, 12
call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %a1, i8* align 4 %b2, i64 %1, i1 false)
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, %for.body.preheader
%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
%2 = bitcast %struct.S* %arrayidx2 to i8*
%3 = bitcast %struct.S* %arrayidx to i8*
%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.p0i8.p0i8.i64(i8* noalias nocapture writeonly, i8* noalias nocapture readonly, i64, i1 immarg) #0
attributes #0 = { argmemonly nofree nosync nounwind willreturn }
```
Reviewed By: zino
Differential Revision: https://reviews.llvm.org/D97667
56 lines
3.0 KiB
LLVM
56 lines
3.0 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -basic-aa -debugify -loop-idiom -pass-remarks=loop-idiom -pass-remarks-analysis=loop-idiom -verify -verify-each -verify-dom-info -verify-loop-info < %s -S 2>&1 | FileCheck %s
|
|
|
|
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-unknown-linux-gnu"
|
|
|
|
; Check that everything still works when debuginfo is present, and that it is reasonably propagated.
|
|
|
|
; void my_basic_memset(char* begin, char* end, char value) {
|
|
; for( ; begin != end; ++begin)
|
|
; *begin = value;
|
|
; }
|
|
|
|
; CHECK: remark: <stdin>:4:1: Transformed loop-strided store in _Z15my_basic_memsetPcS_c function into a call to llvm.memset.p0i8.i64() intrinsic
|
|
|
|
define void @_Z15my_basic_memsetPcS_c(i8* %ptr, i8* %end, i8 %value) {
|
|
; CHECK-LABEL: @_Z15my_basic_memsetPcS_c(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[PTR1:%.*]] = ptrtoint i8* [[PTR:%.*]] to i64
|
|
; CHECK-NEXT: [[CMP3:%.*]] = icmp eq i8* [[PTR]], [[END:%.*]], !dbg !15
|
|
; CHECK-NEXT: call void @llvm.dbg.value(metadata i1 [[CMP3]], metadata !9, metadata !DIExpression()), !dbg !15
|
|
; CHECK-NEXT: br i1 [[CMP3]], label [[FOR_END:%.*]], label [[FOR_BODY_PREHEADER:%.*]], !dbg !16
|
|
; CHECK: for.body.preheader:
|
|
; CHECK-NEXT: [[TMP0:%.*]] = sub i64 0, [[PTR1]], !dbg !17
|
|
; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, i8* [[END]], i64 [[TMP0]], !dbg !17
|
|
; CHECK-NEXT: [[SCEVGEP2:%.*]] = ptrtoint i8* [[SCEVGEP]] to i64
|
|
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 1 [[PTR]], i8 [[VALUE:%.*]], i64 [[SCEVGEP2]], i1 false), !dbg !18
|
|
; CHECK-NEXT: br label [[FOR_BODY:%.*]], !dbg !17
|
|
; CHECK: for.body:
|
|
; CHECK-NEXT: [[PTR_ADDR_04:%.*]] = phi i8* [ [[INCDEC_PTR:%.*]], [[FOR_BODY]] ], [ [[PTR]], [[FOR_BODY_PREHEADER]] ], !dbg !19
|
|
; CHECK-NEXT: call void @llvm.dbg.value(metadata i8* [[PTR_ADDR_04]], metadata !11, metadata !DIExpression()), !dbg !19
|
|
; CHECK-NEXT: [[INCDEC_PTR]] = getelementptr inbounds i8, i8* [[PTR_ADDR_04]], i64 1, !dbg !20
|
|
; CHECK-NEXT: call void @llvm.dbg.value(metadata i8* [[INCDEC_PTR]], metadata !13, metadata !DIExpression()), !dbg !20
|
|
; CHECK-NEXT: [[CMP:%.*]] = icmp eq i8* [[INCDEC_PTR]], [[END]], !dbg !21
|
|
; CHECK-NEXT: call void @llvm.dbg.value(metadata i1 [[CMP]], metadata !14, metadata !DIExpression()), !dbg !21
|
|
; CHECK-NEXT: br i1 [[CMP]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]], !dbg !17
|
|
; CHECK: for.end.loopexit:
|
|
; CHECK-NEXT: br label [[FOR_END]], !dbg !22
|
|
; CHECK: for.end:
|
|
; CHECK-NEXT: ret void, !dbg !22
|
|
;
|
|
entry:
|
|
%cmp3 = icmp eq i8* %ptr, %end
|
|
br i1 %cmp3, label %for.end, label %for.body
|
|
|
|
for.body: ; preds = %entry, %for.body
|
|
%ptr.addr.04 = phi i8* [ %incdec.ptr, %for.body ], [ %ptr, %entry ]
|
|
store i8 %value, i8* %ptr.addr.04, align 1
|
|
%incdec.ptr = getelementptr inbounds i8, i8* %ptr.addr.04, i64 1
|
|
%cmp = icmp eq i8* %incdec.ptr, %end
|
|
br i1 %cmp, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body, %entry
|
|
ret void
|
|
}
|