forked from OSchip/llvm-project
[PhaseOrdering] add test to show combined result of reassociate+instcombine+vectorizers; NFC
This commit is contained in:
Sanjay Patel
parent
3d10a0bdab
commit
8d9527a0bf
|
|
@ -0,0 +1,115 @@
|
||||||
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
||||||
|
; RUN: opt -O2 -S < %s | FileCheck %s
|
||||||
|
; RUN: opt -passes='default<O2>' -S < %s | FileCheck %s
|
||||||
|
|
||||||
|
; https://llvm.org/PR49055
|
||||||
|
;
|
||||||
|
; void loop_or(const unsigned char* __restrict pIn, unsigned int* __restrict pOut, int s) {
|
||||||
|
; for (int i = 0; i < s; i++) {
|
||||||
|
; unsigned int pixelChar = pIn[i];
|
||||||
|
; unsigned int pixel = pixelChar | (pixelChar << 8) | (pixelChar << 16) | (255 << 24);
|
||||||
|
; pOut[i] = pixel;
|
||||||
|
; }
|
||||||
|
; }
|
||||||
|
|
||||||
|
target datalayout = "e-m:o-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
|
||||||
|
target triple = "x86_64-apple-macosx10.15.0"
|
||||||
|
|
||||||
|
define void @loop_or(i8* noalias %pIn, i32* noalias %pOut, i32 %s) {
|
||||||
|
; CHECK-LABEL: @loop_or(
|
||||||
|
; CHECK-NEXT: entry:
|
||||||
|
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[S:%.*]], 0
|
||||||
|
; CHECK-NEXT: br i1 [[CMP1]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END:%.*]]
|
||||||
|
; CHECK: for.body.preheader:
|
||||||
|
; CHECK-NEXT: [[WIDE_TRIP_COUNT:%.*]] = zext i32 [[S]] to i64
|
||||||
|
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[S]], 8
|
||||||
|
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[FOR_BODY_PREHEADER4:%.*]], label [[VECTOR_PH:%.*]]
|
||||||
|
; CHECK: vector.ph:
|
||||||
|
; CHECK-NEXT: [[N_VEC:%.*]] = and i64 [[WIDE_TRIP_COUNT]], 4294967288
|
||||||
|
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
|
||||||
|
; CHECK: vector.body:
|
||||||
|
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
|
||||||
|
; CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[PIN:%.*]], i64 [[INDEX]]
|
||||||
|
; CHECK-NEXT: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <4 x i8>*
|
||||||
|
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i8>, <4 x i8>* [[TMP1]], align 1
|
||||||
|
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i8, i8* [[TMP0]], i64 4
|
||||||
|
; CHECK-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to <4 x i8>*
|
||||||
|
; CHECK-NEXT: [[WIDE_LOAD3:%.*]] = load <4 x i8>, <4 x i8>* [[TMP3]], align 1
|
||||||
|
; CHECK-NEXT: [[TMP4:%.*]] = zext <4 x i8> [[WIDE_LOAD]] to <4 x i32>
|
||||||
|
; CHECK-NEXT: [[TMP5:%.*]] = zext <4 x i8> [[WIDE_LOAD3]] to <4 x i32>
|
||||||
|
; CHECK-NEXT: [[TMP6:%.*]] = shl nuw nsw <4 x i32> [[TMP4]], <i32 8, i32 8, i32 8, i32 8>
|
||||||
|
; CHECK-NEXT: [[TMP7:%.*]] = shl nuw nsw <4 x i32> [[TMP5]], <i32 8, i32 8, i32 8, i32 8>
|
||||||
|
; CHECK-NEXT: [[TMP8:%.*]] = shl nuw nsw <4 x i32> [[TMP4]], <i32 16, i32 16, i32 16, i32 16>
|
||||||
|
; CHECK-NEXT: [[TMP9:%.*]] = shl nuw nsw <4 x i32> [[TMP5]], <i32 16, i32 16, i32 16, i32 16>
|
||||||
|
; CHECK-NEXT: [[TMP10:%.*]] = or <4 x i32> [[TMP6]], [[TMP4]]
|
||||||
|
; CHECK-NEXT: [[TMP11:%.*]] = or <4 x i32> [[TMP7]], [[TMP5]]
|
||||||
|
; CHECK-NEXT: [[TMP12:%.*]] = or <4 x i32> [[TMP10]], [[TMP8]]
|
||||||
|
; CHECK-NEXT: [[TMP13:%.*]] = or <4 x i32> [[TMP11]], [[TMP9]]
|
||||||
|
; CHECK-NEXT: [[TMP14:%.*]] = or <4 x i32> [[TMP12]], <i32 -16777216, i32 -16777216, i32 -16777216, i32 -16777216>
|
||||||
|
; CHECK-NEXT: [[TMP15:%.*]] = or <4 x i32> [[TMP13]], <i32 -16777216, i32 -16777216, i32 -16777216, i32 -16777216>
|
||||||
|
; CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, i32* [[POUT:%.*]], i64 [[INDEX]]
|
||||||
|
; CHECK-NEXT: [[TMP17:%.*]] = bitcast i32* [[TMP16]] to <4 x i32>*
|
||||||
|
; CHECK-NEXT: store <4 x i32> [[TMP14]], <4 x i32>* [[TMP17]], align 4
|
||||||
|
; CHECK-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, i32* [[TMP16]], i64 4
|
||||||
|
; CHECK-NEXT: [[TMP19:%.*]] = bitcast i32* [[TMP18]] to <4 x i32>*
|
||||||
|
; CHECK-NEXT: store <4 x i32> [[TMP15]], <4 x i32>* [[TMP19]], align 4
|
||||||
|
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 8
|
||||||
|
; CHECK-NEXT: [[TMP20:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
|
||||||
|
; CHECK-NEXT: br i1 [[TMP20]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP0:!llvm.loop !.*]]
|
||||||
|
; CHECK: middle.block:
|
||||||
|
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N_VEC]], [[WIDE_TRIP_COUNT]]
|
||||||
|
; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_END]], label [[FOR_BODY_PREHEADER4]]
|
||||||
|
; CHECK: for.body.preheader4:
|
||||||
|
; CHECK-NEXT: [[INDVARS_IV_PH:%.*]] = phi i64 [ 0, [[FOR_BODY_PREHEADER]] ], [ [[N_VEC]], [[MIDDLE_BLOCK]] ]
|
||||||
|
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
|
||||||
|
; CHECK: for.body:
|
||||||
|
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ], [ [[INDVARS_IV_PH]], [[FOR_BODY_PREHEADER4]] ]
|
||||||
|
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8, i8* [[PIN]], i64 [[INDVARS_IV]]
|
||||||
|
; CHECK-NEXT: [[TMP21:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
|
||||||
|
; CHECK-NEXT: [[CONV:%.*]] = zext i8 [[TMP21]] to i32
|
||||||
|
; CHECK-NEXT: [[SHL:%.*]] = shl nuw nsw i32 [[CONV]], 8
|
||||||
|
; CHECK-NEXT: [[SHL1:%.*]] = shl nuw nsw i32 [[CONV]], 16
|
||||||
|
; CHECK-NEXT: [[OR:%.*]] = or i32 [[SHL]], [[CONV]]
|
||||||
|
; CHECK-NEXT: [[OR2:%.*]] = or i32 [[OR]], [[SHL1]]
|
||||||
|
; CHECK-NEXT: [[OR3:%.*]] = or i32 [[OR2]], -16777216
|
||||||
|
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, i32* [[POUT]], i64 [[INDVARS_IV]]
|
||||||
|
; CHECK-NEXT: store i32 [[OR3]], i32* [[ARRAYIDX5]], align 4
|
||||||
|
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
|
||||||
|
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]]
|
||||||
|
; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], [[LOOP2:!llvm.loop !.*]]
|
||||||
|
; CHECK: for.end:
|
||||||
|
; CHECK-NEXT: ret void
|
||||||
|
;
|
||||||
|
entry:
|
||||||
|
br label %for.cond
|
||||||
|
|
||||||
|
for.cond:
|
||||||
|
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
|
||||||
|
%cmp = icmp slt i32 %i.0, %s
|
||||||
|
br i1 %cmp, label %for.body, label %for.cond.cleanup
|
||||||
|
|
||||||
|
for.cond.cleanup:
|
||||||
|
br label %for.end
|
||||||
|
|
||||||
|
for.body:
|
||||||
|
%idxprom = sext i32 %i.0 to i64
|
||||||
|
%arrayidx = getelementptr inbounds i8, i8* %pIn, i64 %idxprom
|
||||||
|
%0 = load i8, i8* %arrayidx, align 1
|
||||||
|
%conv = zext i8 %0 to i32
|
||||||
|
%shl = shl i32 %conv, 8
|
||||||
|
%or = or i32 %conv, %shl
|
||||||
|
%shl1 = shl i32 %conv, 16
|
||||||
|
%or2 = or i32 %or, %shl1
|
||||||
|
%or3 = or i32 %or2, -16777216
|
||||||
|
%idxprom4 = sext i32 %i.0 to i64
|
||||||
|
%arrayidx5 = getelementptr inbounds i32, i32* %pOut, i64 %idxprom4
|
||||||
|
store i32 %or3, i32* %arrayidx5, align 4
|
||||||
|
br label %for.inc
|
||||||
|
|
||||||
|
for.inc:
|
||||||
|
%inc = add nsw i32 %i.0, 1
|
||||||
|
br label %for.cond
|
||||||
|
|
||||||
|
for.end:
|
||||||
|
ret void
|
||||||
|
}
|
||||||
Loading…
Reference in New Issue