llvm-project/llvm/test/Transforms/DeadStoreElimination/multiblock-overlap.ll

145 lines
6.9 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -dse %s -S | FileCheck --check-prefixes=CHECK %s
%struct.ham = type { [3 x double], [3 x double]}
declare void @may_throw()
declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i1 immarg)
; We miss this case, because of an aggressive limit of partial overlap analysis.
; With a larger partial store limit, we remove the memset.
define void @overlap1(%struct.ham* %arg, i1 %cond) {
; CHECK-LABEL: @overlap1(
; CHECK-NEXT: bb:
; CHECK-NEXT: [[TMP:%.*]] = getelementptr inbounds [[STRUCT_HAM:%.*]], %struct.ham* [[ARG:%.*]], i64 0, i32 0, i64 2
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 0, i64 1
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 0, i64 0
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 1, i64 2
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 1, i64 1
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 1, i32 0
; CHECK-NEXT: br i1 [[COND:%.*]], label [[BB7:%.*]], label [[BB8:%.*]]
; CHECK: bb7:
; CHECK-NEXT: br label [[BB9:%.*]]
; CHECK: bb8:
; CHECK-NEXT: br label [[BB9]]
; CHECK: bb9:
; CHECK-NEXT: store double 1.000000e+00, double* [[TMP2]], align 8
; CHECK-NEXT: store double 2.000000e+00, double* [[TMP1]], align 8
; CHECK-NEXT: store double 3.000000e+00, double* [[TMP]], align 8
; CHECK-NEXT: store double 4.000000e+00, double* [[TMP5]], align 8
; CHECK-NEXT: store double 5.000000e+00, double* [[TMP4]], align 8
; CHECK-NEXT: store double 6.000000e+00, double* [[TMP3]], align 8
; CHECK-NEXT: ret void
;
bb:
%tmp = getelementptr inbounds %struct.ham, %struct.ham* %arg, i64 0, i32 0, i64 2
%tmp1 = getelementptr inbounds %struct.ham, %struct.ham* %arg, i64 0, i32 0, i64 1
%tmp2 = getelementptr inbounds %struct.ham, %struct.ham* %arg, i64 0, i32 0, i64 0
%tmp3 = getelementptr inbounds %struct.ham, %struct.ham* %arg, i64 0,i32 1, i64 2
%tmp4 = getelementptr inbounds %struct.ham, %struct.ham* %arg, i64 0, i32 1, i64 1
%tmp5 = getelementptr inbounds %struct.ham, %struct.ham* %arg, i64 0, i32 1, i32 0
%tmp6 = bitcast double* %tmp2 to i8*
call void @llvm.memset.p0i8.i64(i8* nonnull align 8 dereferenceable(48) %tmp6, i8 0, i64 48, i1 false)
br i1 %cond, label %bb7, label %bb8
bb7: ; preds = %bb
br label %bb9
bb8: ; preds = %bb
br label %bb9
bb9: ; preds = %bb8, %bb7
store double 1.0, double* %tmp2, align 8
store double 2.0, double* %tmp1, align 8
store double 3.0, double* %tmp, align 8
store double 4.0, double* %tmp5, align 8
store double 5.0, double* %tmp4, align 8
store double 6.0, double* %tmp3, align 8
ret void
}
define void @overlap2(%struct.ham* %arg, i1 %cond) {
; CHECK-LABEL: @overlap2(
; CHECK-NEXT: bb:
; CHECK-NEXT: [[TMP:%.*]] = getelementptr inbounds [[STRUCT_HAM:%.*]], %struct.ham* [[ARG:%.*]], i64 0, i32 0, i64 2
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 0, i64 1
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 0, i64 0
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 1, i64 2
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 1, i64 1
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 1, i32 0
; CHECK-NEXT: [[TMP6:%.*]] = bitcast double* [[TMP2]] to i8*
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* nonnull align 8 dereferenceable(48) [[TMP6]], i8 0, i64 48, i1 false)
; CHECK-NEXT: br i1 [[COND:%.*]], label [[BB7:%.*]], label [[BB8:%.*]]
; CHECK: bb7:
; CHECK-NEXT: call void @may_throw()
; CHECK-NEXT: br label [[BB9:%.*]]
; CHECK: bb8:
; CHECK-NEXT: br label [[BB9]]
; CHECK: bb9:
; CHECK-NEXT: store double 1.000000e+00, double* [[TMP2]], align 8
; CHECK-NEXT: store double 2.000000e+00, double* [[TMP1]], align 8
; CHECK-NEXT: store double 3.000000e+00, double* [[TMP]], align 8
; CHECK-NEXT: store double 4.000000e+00, double* [[TMP5]], align 8
; CHECK-NEXT: store double 5.000000e+00, double* [[TMP4]], align 8
; CHECK-NEXT: store double 6.000000e+00, double* [[TMP3]], align 8
; CHECK-NEXT: ret void
;
bb:
%tmp = getelementptr inbounds %struct.ham, %struct.ham* %arg, i64 0, i32 0, i64 2
%tmp1 = getelementptr inbounds %struct.ham, %struct.ham* %arg, i64 0, i32 0, i64 1
%tmp2 = getelementptr inbounds %struct.ham, %struct.ham* %arg, i64 0, i32 0, i64 0
%tmp3 = getelementptr inbounds %struct.ham, %struct.ham* %arg, i64 0,i32 1, i64 2
%tmp4 = getelementptr inbounds %struct.ham, %struct.ham* %arg, i64 0, i32 1, i64 1
%tmp5 = getelementptr inbounds %struct.ham, %struct.ham* %arg, i64 0, i32 1, i32 0
%tmp6 = bitcast double* %tmp2 to i8*
call void @llvm.memset.p0i8.i64(i8* nonnull align 8 dereferenceable(48) %tmp6, i8 0, i64 48, i1 false)
br i1 %cond, label %bb7, label %bb8
bb7: ; preds = %bb
call void @may_throw()
br label %bb9
bb8: ; preds = %bb
br label %bb9
bb9: ; preds = %bb8, %bb7
store double 1.0, double* %tmp2, align 8
store double 2.0, double* %tmp1, align 8
store double 3.0, double* %tmp, align 8
store double 4.0, double* %tmp5, align 8
store double 5.0, double* %tmp4, align 8
store double 6.0, double* %tmp3, align 8
ret void
}
; Test case from PR46513. Make sure we do not crash.
; TODO: we should be able to shorten store i32 844283136, i32* %cast.i32 to a
; store of i16.
define void @overlap_no_dominance([4 x i8]* %arg, i1 %c) {
; CHECK-LABEL: @overlap_no_dominance(
; CHECK-NEXT: bb:
; CHECK-NEXT: br i1 [[C:%.*]], label [[BB13:%.*]], label [[BB9:%.*]]
; CHECK: bb9:
; CHECK-NEXT: [[CAST_I32:%.*]] = bitcast [4 x i8]* [[ARG:%.*]] to i32*
; CHECK-NEXT: store i32 844283136, i32* [[CAST_I32]], align 4
; CHECK-NEXT: br label [[BB13]]
; CHECK: bb13:
; CHECK-NEXT: [[CAST_I16:%.*]] = bitcast [4 x i8]* [[ARG]] to i16*
; CHECK-NEXT: store i16 0, i16* [[CAST_I16]], align 4
; CHECK-NEXT: ret void
;
bb:
br i1 %c, label %bb13, label %bb9
bb9: ; preds = %bb
%cast.i32 = bitcast [4 x i8]* %arg to i32*
store i32 844283136, i32* %cast.i32, align 4
br label %bb13
bb13: ; preds = %bb9, %bb
%cast.i16 = bitcast [4 x i8]* %arg to i16*
store i16 0, i16* %cast.i16, align 4
ret void
}