; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature --check-attributes --check-globals
; RUN: opt -attributor -enable-new-pm=0 -attributor-manifest-internal -attributor-max-iterations-verify -attributor-annotate-decl-cs -attributor-max-iterations=3 -S < %s | FileCheck %s --check-prefixes=CHECK,NOT_CGSCC_NPM,NOT_CGSCC_OPM,NOT_TUNIT_NPM,IS__TUNIT____,IS________OPM,IS__TUNIT_OPM
; RUN: opt -aa-pipeline=basic-aa -passes=attributor -attributor-manifest-internal -attributor-max-iterations-verify -attributor-annotate-decl-cs -attributor-max-iterations=3 -S < %s | FileCheck %s --check-prefixes=CHECK,NOT_CGSCC_OPM,NOT_CGSCC_NPM,NOT_TUNIT_OPM,IS__TUNIT____,IS________NPM,IS__TUNIT_NPM
; RUN: opt -attributor-cgscc -enable-new-pm=0 -attributor-manifest-internal -attributor-annotate-decl-cs -S < %s | FileCheck %s --check-prefixes=CHECK,NOT_TUNIT_NPM,NOT_TUNIT_OPM,NOT_CGSCC_NPM,IS__CGSCC____,IS________OPM,IS__CGSCC_OPM
; RUN: opt -aa-pipeline=basic-aa -passes=attributor-cgscc -attributor-manifest-internal -attributor-annotate-decl-cs -S < %s | FileCheck %s --check-prefixes=CHECK,NOT_TUNIT_NPM,NOT_TUNIT_OPM,NOT_CGSCC_OPM,IS__CGSCC____,IS________NPM,IS__CGSCC_NPM
; Test that we only promote arguments when the caller/callee have compatible
; function attrubtes.
target triple = "x86_64-unknown-linux-gnu"
; This should promote
define internal fastcc void @callee_avx512_legal512_prefer512_call_avx512_legal512_prefer512(<8 x i64>* %arg, <8 x i64>* readonly %arg1) #0 {
;
; IS________OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS________OPM-LABEL: define {{[^@]+}}@callee_avx512_legal512_prefer512_call_avx512_legal512_prefer512
; IS________OPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[ARG:%.*]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[ARG1:%.*]]) #[[ATTR0:[0-9]+]] {
; IS________OPM-NEXT: bb:
; IS________OPM-NEXT: [[TMP:%.*]] = load <8 x i64>, <8 x i64>* [[ARG1]], align 64
; IS________OPM-NEXT: store <8 x i64> [[TMP]], <8 x i64>* [[ARG]], align 64
; IS________OPM-NEXT: ret void
;
; IS________NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS________NPM-LABEL: define {{[^@]+}}@callee_avx512_legal512_prefer512_call_avx512_legal512_prefer512
; IS________NPM-SAME: (<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[ARG:%.*]], <8 x i64> [[TMP0:%.*]]) #[[ATTR0:[0-9]+]] {
; IS________NPM-NEXT: bb:
; IS________NPM-NEXT: [[ARG1_PRIV:%.*]] = alloca <8 x i64>, align 64
; IS________NPM-NEXT: store <8 x i64> [[TMP0]], <8 x i64>* [[ARG1_PRIV]], align 64
; IS________NPM-NEXT: [[TMP:%.*]] = load <8 x i64>, <8 x i64>* [[ARG1_PRIV]], align 64
; IS________NPM-NEXT: store <8 x i64> [[TMP]], <8 x i64>* [[ARG]], align 64
; IS________NPM-NEXT: ret void
;
bb:
%tmp = load <8 x i64>, <8 x i64>* %arg1
store <8 x i64> %tmp, <8 x i64>* %arg
ret void
}
define void @avx512_legal512_prefer512_call_avx512_legal512_prefer512(<8 x i64>* %arg) #0 {
;
; IS__TUNIT_OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__TUNIT_OPM-LABEL: define {{[^@]+}}@avx512_legal512_prefer512_call_avx512_legal512_prefer512
; IS__TUNIT_OPM-SAME: (<8 x i64>* nocapture nofree writeonly [[ARG:%.*]]) #[[ATTR0]] {
; IS__TUNIT_OPM-NEXT: bb:
; IS__TUNIT_OPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_OPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_OPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__TUNIT_OPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR6:[0-9]+]]
; IS__TUNIT_OPM-NEXT: call fastcc void @callee_avx512_legal512_prefer512_call_avx512_legal512_prefer512(<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[TMP]]) #[[ATTR7:[0-9]+]]
; IS__TUNIT_OPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__TUNIT_OPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__TUNIT_OPM-NEXT: ret void
;
; IS__TUNIT_NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__TUNIT_NPM-LABEL: define {{[^@]+}}@avx512_legal512_prefer512_call_avx512_legal512_prefer512
; IS__TUNIT_NPM-SAME: (<8 x i64>* nocapture nofree writeonly [[ARG:%.*]]) #[[ATTR0]] {
; IS__TUNIT_NPM-NEXT: bb:
; IS__TUNIT_NPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_NPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_NPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__TUNIT_NPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR5:[0-9]+]]
; IS__TUNIT_NPM-NEXT: [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 64
; IS__TUNIT_NPM-NEXT: call fastcc void @callee_avx512_legal512_prefer512_call_avx512_legal512_prefer512(<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64> [[TMP0]]) #[[ATTR6:[0-9]+]]
; IS__TUNIT_NPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__TUNIT_NPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__TUNIT_NPM-NEXT: ret void
;
; IS__CGSCC_OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__CGSCC_OPM-LABEL: define {{[^@]+}}@avx512_legal512_prefer512_call_avx512_legal512_prefer512
; IS__CGSCC_OPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 2 dereferenceable(64) [[ARG:%.*]]) #[[ATTR0]] {
; IS__CGSCC_OPM-NEXT: bb:
; IS__CGSCC_OPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_OPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_OPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__CGSCC_OPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR6:[0-9]+]]
; IS__CGSCC_OPM-NEXT: call fastcc void @callee_avx512_legal512_prefer512_call_avx512_legal512_prefer512(<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[TMP]]) #[[ATTR7:[0-9]+]]
; IS__CGSCC_OPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__CGSCC_OPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__CGSCC_OPM-NEXT: ret void
;
; IS__CGSCC_NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__CGSCC_NPM-LABEL: define {{[^@]+}}@avx512_legal512_prefer512_call_avx512_legal512_prefer512
; IS__CGSCC_NPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 2 dereferenceable(64) [[ARG:%.*]]) #[[ATTR0]] {
; IS__CGSCC_NPM-NEXT: bb:
; IS__CGSCC_NPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_NPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_NPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__CGSCC_NPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR5:[0-9]+]]
; IS__CGSCC_NPM-NEXT: [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 64
; IS__CGSCC_NPM-NEXT: call fastcc void @callee_avx512_legal512_prefer512_call_avx512_legal512_prefer512(<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64> [[TMP0]]) #[[ATTR6:[0-9]+]]
; IS__CGSCC_NPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__CGSCC_NPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__CGSCC_NPM-NEXT: ret void
;
bb:
%tmp = alloca <8 x i64>, align 32
%tmp2 = alloca <8 x i64>, align 32
%tmp3 = bitcast <8 x i64>* %tmp to i8*
call void @llvm.memset.p0i8.i64(i8* align 32 %tmp3, i8 0, i64 32, i1 false)
call fastcc void @callee_avx512_legal512_prefer512_call_avx512_legal512_prefer512(<8 x i64>* %tmp2, <8 x i64>* %tmp)
%tmp4 = load <8 x i64>, <8 x i64>* %tmp2, align 32
store <8 x i64> %tmp4, <8 x i64>* %arg, align 2
ret void
}
; This should promote
define internal fastcc void @callee_avx512_legal512_prefer256_call_avx512_legal512_prefer256(<8 x i64>* %arg, <8 x i64>* readonly %arg1) #1 {
;
; IS________OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS________OPM-LABEL: define {{[^@]+}}@callee_avx512_legal512_prefer256_call_avx512_legal512_prefer256
; IS________OPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[ARG:%.*]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[ARG1:%.*]]) #[[ATTR1:[0-9]+]] {
; IS________OPM-NEXT: bb:
; IS________OPM-NEXT: [[TMP:%.*]] = load <8 x i64>, <8 x i64>* [[ARG1]], align 64
; IS________OPM-NEXT: store <8 x i64> [[TMP]], <8 x i64>* [[ARG]], align 64
; IS________OPM-NEXT: ret void
;
; IS________NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS________NPM-LABEL: define {{[^@]+}}@callee_avx512_legal512_prefer256_call_avx512_legal512_prefer256
; IS________NPM-SAME: (<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[ARG:%.*]], <8 x i64> [[TMP0:%.*]]) #[[ATTR1:[0-9]+]] {
; IS________NPM-NEXT: bb:
; IS________NPM-NEXT: [[ARG1_PRIV:%.*]] = alloca <8 x i64>, align 64
; IS________NPM-NEXT: store <8 x i64> [[TMP0]], <8 x i64>* [[ARG1_PRIV]], align 64
; IS________NPM-NEXT: [[TMP:%.*]] = load <8 x i64>, <8 x i64>* [[ARG1_PRIV]], align 64
; IS________NPM-NEXT: store <8 x i64> [[TMP]], <8 x i64>* [[ARG]], align 64
; IS________NPM-NEXT: ret void
;
bb:
%tmp = load <8 x i64>, <8 x i64>* %arg1
store <8 x i64> %tmp, <8 x i64>* %arg
ret void
}
define void @avx512_legal512_prefer256_call_avx512_legal512_prefer256(<8 x i64>* %arg) #1 {
;
; IS__TUNIT_OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__TUNIT_OPM-LABEL: define {{[^@]+}}@avx512_legal512_prefer256_call_avx512_legal512_prefer256
; IS__TUNIT_OPM-SAME: (<8 x i64>* nocapture nofree writeonly [[ARG:%.*]]) #[[ATTR1]] {
; IS__TUNIT_OPM-NEXT: bb:
; IS__TUNIT_OPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_OPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_OPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__TUNIT_OPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR6]]
; IS__TUNIT_OPM-NEXT: call fastcc void @callee_avx512_legal512_prefer256_call_avx512_legal512_prefer256(<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[TMP]]) #[[ATTR7]]
; IS__TUNIT_OPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__TUNIT_OPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__TUNIT_OPM-NEXT: ret void
;
; IS__TUNIT_NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__TUNIT_NPM-LABEL: define {{[^@]+}}@avx512_legal512_prefer256_call_avx512_legal512_prefer256
; IS__TUNIT_NPM-SAME: (<8 x i64>* nocapture nofree writeonly [[ARG:%.*]]) #[[ATTR1]] {
; IS__TUNIT_NPM-NEXT: bb:
; IS__TUNIT_NPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_NPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_NPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__TUNIT_NPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR5]]
; IS__TUNIT_NPM-NEXT: [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 64
; IS__TUNIT_NPM-NEXT: call fastcc void @callee_avx512_legal512_prefer256_call_avx512_legal512_prefer256(<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64> [[TMP0]]) #[[ATTR6]]
; IS__TUNIT_NPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__TUNIT_NPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__TUNIT_NPM-NEXT: ret void
;
; IS__CGSCC_OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__CGSCC_OPM-LABEL: define {{[^@]+}}@avx512_legal512_prefer256_call_avx512_legal512_prefer256
; IS__CGSCC_OPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 2 dereferenceable(64) [[ARG:%.*]]) #[[ATTR1]] {
; IS__CGSCC_OPM-NEXT: bb:
; IS__CGSCC_OPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_OPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_OPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__CGSCC_OPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR6]]
; IS__CGSCC_OPM-NEXT: call fastcc void @callee_avx512_legal512_prefer256_call_avx512_legal512_prefer256(<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[TMP]]) #[[ATTR7]]
; IS__CGSCC_OPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__CGSCC_OPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__CGSCC_OPM-NEXT: ret void
;
; IS__CGSCC_NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__CGSCC_NPM-LABEL: define {{[^@]+}}@avx512_legal512_prefer256_call_avx512_legal512_prefer256
; IS__CGSCC_NPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 2 dereferenceable(64) [[ARG:%.*]]) #[[ATTR1]] {
; IS__CGSCC_NPM-NEXT: bb:
; IS__CGSCC_NPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_NPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_NPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__CGSCC_NPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR5]]
; IS__CGSCC_NPM-NEXT: [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 64
; IS__CGSCC_NPM-NEXT: call fastcc void @callee_avx512_legal512_prefer256_call_avx512_legal512_prefer256(<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64> [[TMP0]]) #[[ATTR6]]
; IS__CGSCC_NPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__CGSCC_NPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__CGSCC_NPM-NEXT: ret void
;
bb:
%tmp = alloca <8 x i64>, align 32
%tmp2 = alloca <8 x i64>, align 32
%tmp3 = bitcast <8 x i64>* %tmp to i8*
call void @llvm.memset.p0i8.i64(i8* align 32 %tmp3, i8 0, i64 32, i1 false)
call fastcc void @callee_avx512_legal512_prefer256_call_avx512_legal512_prefer256(<8 x i64>* %tmp2, <8 x i64>* %tmp)
%tmp4 = load <8 x i64>, <8 x i64>* %tmp2, align 32
store <8 x i64> %tmp4, <8 x i64>* %arg, align 2
ret void
}
; This should promote
define internal fastcc void @callee_avx512_legal512_prefer512_call_avx512_legal512_prefer256(<8 x i64>* %arg, <8 x i64>* readonly %arg1) #1 {
;
; IS________OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS________OPM-LABEL: define {{[^@]+}}@callee_avx512_legal512_prefer512_call_avx512_legal512_prefer256
; IS________OPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[ARG:%.*]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[ARG1:%.*]]) #[[ATTR1]] {
; IS________OPM-NEXT: bb:
; IS________OPM-NEXT: [[TMP:%.*]] = load <8 x i64>, <8 x i64>* [[ARG1]], align 64
; IS________OPM-NEXT: store <8 x i64> [[TMP]], <8 x i64>* [[ARG]], align 64
; IS________OPM-NEXT: ret void
;
; IS________NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS________NPM-LABEL: define {{[^@]+}}@callee_avx512_legal512_prefer512_call_avx512_legal512_prefer256
; IS________NPM-SAME: (<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[ARG:%.*]], <8 x i64> [[TMP0:%.*]]) #[[ATTR1]] {
; IS________NPM-NEXT: bb:
; IS________NPM-NEXT: [[ARG1_PRIV:%.*]] = alloca <8 x i64>, align 64
; IS________NPM-NEXT: store <8 x i64> [[TMP0]], <8 x i64>* [[ARG1_PRIV]], align 64
; IS________NPM-NEXT: [[TMP:%.*]] = load <8 x i64>, <8 x i64>* [[ARG1_PRIV]], align 64
; IS________NPM-NEXT: store <8 x i64> [[TMP]], <8 x i64>* [[ARG]], align 64
; IS________NPM-NEXT: ret void
;
bb:
%tmp = load <8 x i64>, <8 x i64>* %arg1
store <8 x i64> %tmp, <8 x i64>* %arg
ret void
}
define void @avx512_legal512_prefer512_call_avx512_legal512_prefer256(<8 x i64>* %arg) #0 {
;
; IS__TUNIT_OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__TUNIT_OPM-LABEL: define {{[^@]+}}@avx512_legal512_prefer512_call_avx512_legal512_prefer256
; IS__TUNIT_OPM-SAME: (<8 x i64>* nocapture nofree writeonly [[ARG:%.*]]) #[[ATTR0]] {
; IS__TUNIT_OPM-NEXT: bb:
; IS__TUNIT_OPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_OPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_OPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__TUNIT_OPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR6]]
; IS__TUNIT_OPM-NEXT: call fastcc void @callee_avx512_legal512_prefer512_call_avx512_legal512_prefer256(<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[TMP]]) #[[ATTR7]]
; IS__TUNIT_OPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__TUNIT_OPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__TUNIT_OPM-NEXT: ret void
;
; IS__TUNIT_NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__TUNIT_NPM-LABEL: define {{[^@]+}}@avx512_legal512_prefer512_call_avx512_legal512_prefer256
; IS__TUNIT_NPM-SAME: (<8 x i64>* nocapture nofree writeonly [[ARG:%.*]]) #[[ATTR0]] {
; IS__TUNIT_NPM-NEXT: bb:
; IS__TUNIT_NPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_NPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_NPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__TUNIT_NPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR5]]
; IS__TUNIT_NPM-NEXT: [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 64
; IS__TUNIT_NPM-NEXT: call fastcc void @callee_avx512_legal512_prefer512_call_avx512_legal512_prefer256(<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64> [[TMP0]]) #[[ATTR6]]
; IS__TUNIT_NPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__TUNIT_NPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__TUNIT_NPM-NEXT: ret void
;
; IS__CGSCC_OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__CGSCC_OPM-LABEL: define {{[^@]+}}@avx512_legal512_prefer512_call_avx512_legal512_prefer256
; IS__CGSCC_OPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 2 dereferenceable(64) [[ARG:%.*]]) #[[ATTR0]] {
; IS__CGSCC_OPM-NEXT: bb:
; IS__CGSCC_OPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_OPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_OPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__CGSCC_OPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR6]]
; IS__CGSCC_OPM-NEXT: call fastcc void @callee_avx512_legal512_prefer512_call_avx512_legal512_prefer256(<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[TMP]]) #[[ATTR7]]
; IS__CGSCC_OPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__CGSCC_OPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__CGSCC_OPM-NEXT: ret void
;
; IS__CGSCC_NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__CGSCC_NPM-LABEL: define {{[^@]+}}@avx512_legal512_prefer512_call_avx512_legal512_prefer256
; IS__CGSCC_NPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 2 dereferenceable(64) [[ARG:%.*]]) #[[ATTR0]] {
; IS__CGSCC_NPM-NEXT: bb:
; IS__CGSCC_NPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_NPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_NPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__CGSCC_NPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR5]]
; IS__CGSCC_NPM-NEXT: [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 64
; IS__CGSCC_NPM-NEXT: call fastcc void @callee_avx512_legal512_prefer512_call_avx512_legal512_prefer256(<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64> [[TMP0]]) #[[ATTR6]]
; IS__CGSCC_NPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__CGSCC_NPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__CGSCC_NPM-NEXT: ret void
;
bb:
%tmp = alloca <8 x i64>, align 32
%tmp2 = alloca <8 x i64>, align 32
%tmp3 = bitcast <8 x i64>* %tmp to i8*
call void @llvm.memset.p0i8.i64(i8* align 32 %tmp3, i8 0, i64 32, i1 false)
call fastcc void @callee_avx512_legal512_prefer512_call_avx512_legal512_prefer256(<8 x i64>* %tmp2, <8 x i64>* %tmp)
%tmp4 = load <8 x i64>, <8 x i64>* %tmp2, align 32
store <8 x i64> %tmp4, <8 x i64>* %arg, align 2
ret void
}
; This should promote
define internal fastcc void @callee_avx512_legal512_prefer256_call_avx512_legal512_prefer512(<8 x i64>* %arg, <8 x i64>* readonly %arg1) #0 {
;
; IS________OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS________OPM-LABEL: define {{[^@]+}}@callee_avx512_legal512_prefer256_call_avx512_legal512_prefer512
; IS________OPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[ARG:%.*]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[ARG1:%.*]]) #[[ATTR0]] {
; IS________OPM-NEXT: bb:
; IS________OPM-NEXT: [[TMP:%.*]] = load <8 x i64>, <8 x i64>* [[ARG1]], align 64
; IS________OPM-NEXT: store <8 x i64> [[TMP]], <8 x i64>* [[ARG]], align 64
; IS________OPM-NEXT: ret void
;
; IS________NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS________NPM-LABEL: define {{[^@]+}}@callee_avx512_legal512_prefer256_call_avx512_legal512_prefer512
; IS________NPM-SAME: (<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[ARG:%.*]], <8 x i64> [[TMP0:%.*]]) #[[ATTR0]] {
; IS________NPM-NEXT: bb:
; IS________NPM-NEXT: [[ARG1_PRIV:%.*]] = alloca <8 x i64>, align 64
; IS________NPM-NEXT: store <8 x i64> [[TMP0]], <8 x i64>* [[ARG1_PRIV]], align 64
; IS________NPM-NEXT: [[TMP:%.*]] = load <8 x i64>, <8 x i64>* [[ARG1_PRIV]], align 64
; IS________NPM-NEXT: store <8 x i64> [[TMP]], <8 x i64>* [[ARG]], align 64
; IS________NPM-NEXT: ret void
;
bb:
%tmp = load <8 x i64>, <8 x i64>* %arg1
store <8 x i64> %tmp, <8 x i64>* %arg
ret void
}
define void @avx512_legal512_prefer256_call_avx512_legal512_prefer512(<8 x i64>* %arg) #1 {
;
; IS__TUNIT_OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__TUNIT_OPM-LABEL: define {{[^@]+}}@avx512_legal512_prefer256_call_avx512_legal512_prefer512
; IS__TUNIT_OPM-SAME: (<8 x i64>* nocapture nofree writeonly [[ARG:%.*]]) #[[ATTR1]] {
; IS__TUNIT_OPM-NEXT: bb:
; IS__TUNIT_OPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_OPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_OPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__TUNIT_OPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR6]]
; IS__TUNIT_OPM-NEXT: call fastcc void @callee_avx512_legal512_prefer256_call_avx512_legal512_prefer512(<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[TMP]]) #[[ATTR7]]
; IS__TUNIT_OPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__TUNIT_OPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__TUNIT_OPM-NEXT: ret void
;
; IS__TUNIT_NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__TUNIT_NPM-LABEL: define {{[^@]+}}@avx512_legal512_prefer256_call_avx512_legal512_prefer512
; IS__TUNIT_NPM-SAME: (<8 x i64>* nocapture nofree writeonly [[ARG:%.*]]) #[[ATTR1]] {
; IS__TUNIT_NPM-NEXT: bb:
; IS__TUNIT_NPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_NPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_NPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__TUNIT_NPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR5]]
; IS__TUNIT_NPM-NEXT: [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 64
; IS__TUNIT_NPM-NEXT: call fastcc void @callee_avx512_legal512_prefer256_call_avx512_legal512_prefer512(<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64> [[TMP0]]) #[[ATTR6]]
; IS__TUNIT_NPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__TUNIT_NPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__TUNIT_NPM-NEXT: ret void
;
; IS__CGSCC_OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__CGSCC_OPM-LABEL: define {{[^@]+}}@avx512_legal512_prefer256_call_avx512_legal512_prefer512
; IS__CGSCC_OPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 2 dereferenceable(64) [[ARG:%.*]]) #[[ATTR1]] {
; IS__CGSCC_OPM-NEXT: bb:
; IS__CGSCC_OPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_OPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_OPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__CGSCC_OPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR6]]
; IS__CGSCC_OPM-NEXT: call fastcc void @callee_avx512_legal512_prefer256_call_avx512_legal512_prefer512(<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[TMP]]) #[[ATTR7]]
; IS__CGSCC_OPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__CGSCC_OPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__CGSCC_OPM-NEXT: ret void
;
; IS__CGSCC_NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__CGSCC_NPM-LABEL: define {{[^@]+}}@avx512_legal512_prefer256_call_avx512_legal512_prefer512
; IS__CGSCC_NPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 2 dereferenceable(64) [[ARG:%.*]]) #[[ATTR1]] {
; IS__CGSCC_NPM-NEXT: bb:
; IS__CGSCC_NPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_NPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_NPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__CGSCC_NPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR5]]
; IS__CGSCC_NPM-NEXT: [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 64
; IS__CGSCC_NPM-NEXT: call fastcc void @callee_avx512_legal512_prefer256_call_avx512_legal512_prefer512(<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64> [[TMP0]]) #[[ATTR6]]
; IS__CGSCC_NPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__CGSCC_NPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__CGSCC_NPM-NEXT: ret void
;
bb:
%tmp = alloca <8 x i64>, align 32
%tmp2 = alloca <8 x i64>, align 32
%tmp3 = bitcast <8 x i64>* %tmp to i8*
call void @llvm.memset.p0i8.i64(i8* align 32 %tmp3, i8 0, i64 32, i1 false)
call fastcc void @callee_avx512_legal512_prefer256_call_avx512_legal512_prefer512(<8 x i64>* %tmp2, <8 x i64>* %tmp)
%tmp4 = load <8 x i64>, <8 x i64>* %tmp2, align 32
store <8 x i64> %tmp4, <8 x i64>* %arg, align 2
ret void
}
; This should not promote
define internal fastcc void @callee_avx512_legal256_prefer256_call_avx512_legal512_prefer256(<8 x i64>* %arg, <8 x i64>* readonly %arg1) #1 {
;
; IS________OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS________OPM-LABEL: define {{[^@]+}}@callee_avx512_legal256_prefer256_call_avx512_legal512_prefer256
; IS________OPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[ARG:%.*]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[ARG1:%.*]]) #[[ATTR1]] {
; IS________OPM-NEXT: bb:
; IS________OPM-NEXT: [[TMP:%.*]] = load <8 x i64>, <8 x i64>* [[ARG1]], align 64
; IS________OPM-NEXT: store <8 x i64> [[TMP]], <8 x i64>* [[ARG]], align 64
; IS________OPM-NEXT: ret void
;
; IS________NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS________NPM-LABEL: define {{[^@]+}}@callee_avx512_legal256_prefer256_call_avx512_legal512_prefer256
; IS________NPM-SAME: (<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[ARG:%.*]], <8 x i64>* noalias nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[ARG1:%.*]]) #[[ATTR1]] {
; IS________NPM-NEXT: bb:
; IS________NPM-NEXT: [[TMP:%.*]] = load <8 x i64>, <8 x i64>* [[ARG1]], align 64
; IS________NPM-NEXT: store <8 x i64> [[TMP]], <8 x i64>* [[ARG]], align 64
; IS________NPM-NEXT: ret void
;
bb:
%tmp = load <8 x i64>, <8 x i64>* %arg1
store <8 x i64> %tmp, <8 x i64>* %arg
ret void
}
define void @avx512_legal256_prefer256_call_avx512_legal512_prefer256(<8 x i64>* %arg) #2 {
;
; IS__TUNIT_OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__TUNIT_OPM-LABEL: define {{[^@]+}}@avx512_legal256_prefer256_call_avx512_legal512_prefer256
; IS__TUNIT_OPM-SAME: (<8 x i64>* nocapture nofree writeonly [[ARG:%.*]]) #[[ATTR2:[0-9]+]] {
; IS__TUNIT_OPM-NEXT: bb:
; IS__TUNIT_OPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_OPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_OPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__TUNIT_OPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR6]]
; IS__TUNIT_OPM-NEXT: call fastcc void @callee_avx512_legal256_prefer256_call_avx512_legal512_prefer256(<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[TMP]]) #[[ATTR7]]
; IS__TUNIT_OPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__TUNIT_OPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__TUNIT_OPM-NEXT: ret void
;
; IS__TUNIT_NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__TUNIT_NPM-LABEL: define {{[^@]+}}@avx512_legal256_prefer256_call_avx512_legal512_prefer256
; IS__TUNIT_NPM-SAME: (<8 x i64>* nocapture nofree writeonly [[ARG:%.*]]) #[[ATTR2:[0-9]+]] {
; IS__TUNIT_NPM-NEXT: bb:
; IS__TUNIT_NPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_NPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_NPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__TUNIT_NPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR5]]
; IS__TUNIT_NPM-NEXT: call fastcc void @callee_avx512_legal256_prefer256_call_avx512_legal512_prefer256(<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64>* noalias nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[TMP]]) #[[ATTR6]]
; IS__TUNIT_NPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__TUNIT_NPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__TUNIT_NPM-NEXT: ret void
;
; IS__CGSCC_OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__CGSCC_OPM-LABEL: define {{[^@]+}}@avx512_legal256_prefer256_call_avx512_legal512_prefer256
; IS__CGSCC_OPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 2 dereferenceable(64) [[ARG:%.*]]) #[[ATTR2:[0-9]+]] {
; IS__CGSCC_OPM-NEXT: bb:
; IS__CGSCC_OPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_OPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_OPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__CGSCC_OPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR6]]
; IS__CGSCC_OPM-NEXT: call fastcc void @callee_avx512_legal256_prefer256_call_avx512_legal512_prefer256(<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[TMP]]) #[[ATTR7]]
; IS__CGSCC_OPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__CGSCC_OPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__CGSCC_OPM-NEXT: ret void
;
; IS__CGSCC_NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__CGSCC_NPM-LABEL: define {{[^@]+}}@avx512_legal256_prefer256_call_avx512_legal512_prefer256
; IS__CGSCC_NPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 2 dereferenceable(64) [[ARG:%.*]]) #[[ATTR2:[0-9]+]] {
; IS__CGSCC_NPM-NEXT: bb:
; IS__CGSCC_NPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_NPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_NPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__CGSCC_NPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR5]]
; IS__CGSCC_NPM-NEXT: call fastcc void @callee_avx512_legal256_prefer256_call_avx512_legal512_prefer256(<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64>* noalias nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[TMP]]) #[[ATTR6]]
; IS__CGSCC_NPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__CGSCC_NPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__CGSCC_NPM-NEXT: ret void
;
bb:
%tmp = alloca <8 x i64>, align 32
%tmp2 = alloca <8 x i64>, align 32
%tmp3 = bitcast <8 x i64>* %tmp to i8*
call void @llvm.memset.p0i8.i64(i8* align 32 %tmp3, i8 0, i64 32, i1 false)
call fastcc void @callee_avx512_legal256_prefer256_call_avx512_legal512_prefer256(<8 x i64>* %tmp2, <8 x i64>* %tmp)
%tmp4 = load <8 x i64>, <8 x i64>* %tmp2, align 32
store <8 x i64> %tmp4, <8 x i64>* %arg, align 2
ret void
}
; This should not promote
define internal fastcc void @callee_avx512_legal512_prefer256_call_avx512_legal256_prefer256(<8 x i64>* %arg, <8 x i64>* readonly %arg1) #2 {
;
; IS________OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS________OPM-LABEL: define {{[^@]+}}@callee_avx512_legal512_prefer256_call_avx512_legal256_prefer256
; IS________OPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[ARG:%.*]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[ARG1:%.*]]) #[[ATTR2:[0-9]+]] {
; IS________OPM-NEXT: bb:
; IS________OPM-NEXT: [[TMP:%.*]] = load <8 x i64>, <8 x i64>* [[ARG1]], align 64
; IS________OPM-NEXT: store <8 x i64> [[TMP]], <8 x i64>* [[ARG]], align 64
; IS________OPM-NEXT: ret void
;
; IS________NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS________NPM-LABEL: define {{[^@]+}}@callee_avx512_legal512_prefer256_call_avx512_legal256_prefer256
; IS________NPM-SAME: (<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[ARG:%.*]], <8 x i64>* noalias nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[ARG1:%.*]]) #[[ATTR2:[0-9]+]] {
; IS________NPM-NEXT: bb:
; IS________NPM-NEXT: [[TMP:%.*]] = load <8 x i64>, <8 x i64>* [[ARG1]], align 64
; IS________NPM-NEXT: store <8 x i64> [[TMP]], <8 x i64>* [[ARG]], align 64
; IS________NPM-NEXT: ret void
;
bb:
%tmp = load <8 x i64>, <8 x i64>* %arg1
store <8 x i64> %tmp, <8 x i64>* %arg
ret void
}
define void @avx512_legal512_prefer256_call_avx512_legal256_prefer256(<8 x i64>* %arg) #1 {
;
; IS__TUNIT_OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__TUNIT_OPM-LABEL: define {{[^@]+}}@avx512_legal512_prefer256_call_avx512_legal256_prefer256
; IS__TUNIT_OPM-SAME: (<8 x i64>* nocapture nofree writeonly [[ARG:%.*]]) #[[ATTR1]] {
; IS__TUNIT_OPM-NEXT: bb:
; IS__TUNIT_OPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_OPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_OPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__TUNIT_OPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR6]]
; IS__TUNIT_OPM-NEXT: call fastcc void @callee_avx512_legal512_prefer256_call_avx512_legal256_prefer256(<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[TMP]]) #[[ATTR7]]
; IS__TUNIT_OPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__TUNIT_OPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__TUNIT_OPM-NEXT: ret void
;
; IS__TUNIT_NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__TUNIT_NPM-LABEL: define {{[^@]+}}@avx512_legal512_prefer256_call_avx512_legal256_prefer256
; IS__TUNIT_NPM-SAME: (<8 x i64>* nocapture nofree writeonly [[ARG:%.*]]) #[[ATTR1]] {
; IS__TUNIT_NPM-NEXT: bb:
; IS__TUNIT_NPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_NPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_NPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__TUNIT_NPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR5]]
; IS__TUNIT_NPM-NEXT: call fastcc void @callee_avx512_legal512_prefer256_call_avx512_legal256_prefer256(<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64>* noalias nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[TMP]]) #[[ATTR6]]
; IS__TUNIT_NPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__TUNIT_NPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__TUNIT_NPM-NEXT: ret void
;
; IS__CGSCC_OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__CGSCC_OPM-LABEL: define {{[^@]+}}@avx512_legal512_prefer256_call_avx512_legal256_prefer256
; IS__CGSCC_OPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 2 dereferenceable(64) [[ARG:%.*]]) #[[ATTR1]] {
; IS__CGSCC_OPM-NEXT: bb:
; IS__CGSCC_OPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_OPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_OPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__CGSCC_OPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR6]]
; IS__CGSCC_OPM-NEXT: call fastcc void @callee_avx512_legal512_prefer256_call_avx512_legal256_prefer256(<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[TMP]]) #[[ATTR7]]
; IS__CGSCC_OPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__CGSCC_OPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__CGSCC_OPM-NEXT: ret void
;
; IS__CGSCC_NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__CGSCC_NPM-LABEL: define {{[^@]+}}@avx512_legal512_prefer256_call_avx512_legal256_prefer256
; IS__CGSCC_NPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 2 dereferenceable(64) [[ARG:%.*]]) #[[ATTR1]] {
; IS__CGSCC_NPM-NEXT: bb:
; IS__CGSCC_NPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_NPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_NPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__CGSCC_NPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR5]]
; IS__CGSCC_NPM-NEXT: call fastcc void @callee_avx512_legal512_prefer256_call_avx512_legal256_prefer256(<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64>* noalias nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[TMP]]) #[[ATTR6]]
; IS__CGSCC_NPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__CGSCC_NPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__CGSCC_NPM-NEXT: ret void
;
bb:
%tmp = alloca <8 x i64>, align 32
%tmp2 = alloca <8 x i64>, align 32
%tmp3 = bitcast <8 x i64>* %tmp to i8*
call void @llvm.memset.p0i8.i64(i8* align 32 %tmp3, i8 0, i64 32, i1 false)
call fastcc void @callee_avx512_legal512_prefer256_call_avx512_legal256_prefer256(<8 x i64>* %tmp2, <8 x i64>* %tmp)
%tmp4 = load <8 x i64>, <8 x i64>* %tmp2, align 32
store <8 x i64> %tmp4, <8 x i64>* %arg, align 2
ret void
}
; This should promote
define internal fastcc void @callee_avx2_legal256_prefer256_call_avx2_legal512_prefer256(<8 x i64>* %arg, <8 x i64>* readonly %arg1) #3 {
;
; IS________OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS________OPM-LABEL: define {{[^@]+}}@callee_avx2_legal256_prefer256_call_avx2_legal512_prefer256
; IS________OPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[ARG:%.*]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[ARG1:%.*]]) #[[ATTR3:[0-9]+]] {
; IS________OPM-NEXT: bb:
; IS________OPM-NEXT: [[TMP:%.*]] = load <8 x i64>, <8 x i64>* [[ARG1]], align 64
; IS________OPM-NEXT: store <8 x i64> [[TMP]], <8 x i64>* [[ARG]], align 64
; IS________OPM-NEXT: ret void
;
; IS________NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS________NPM-LABEL: define {{[^@]+}}@callee_avx2_legal256_prefer256_call_avx2_legal512_prefer256
; IS________NPM-SAME: (<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[ARG:%.*]], <8 x i64> [[TMP0:%.*]]) #[[ATTR3:[0-9]+]] {
; IS________NPM-NEXT: bb:
; IS________NPM-NEXT: [[ARG1_PRIV:%.*]] = alloca <8 x i64>, align 64
; IS________NPM-NEXT: store <8 x i64> [[TMP0]], <8 x i64>* [[ARG1_PRIV]], align 64
; IS________NPM-NEXT: [[TMP:%.*]] = load <8 x i64>, <8 x i64>* [[ARG1_PRIV]], align 64
; IS________NPM-NEXT: store <8 x i64> [[TMP]], <8 x i64>* [[ARG]], align 64
; IS________NPM-NEXT: ret void
;
bb:
%tmp = load <8 x i64>, <8 x i64>* %arg1
store <8 x i64> %tmp, <8 x i64>* %arg
ret void
}
define void @avx2_legal256_prefer256_call_avx2_legal512_prefer256(<8 x i64>* %arg) #4 {
;
; IS__TUNIT_OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__TUNIT_OPM-LABEL: define {{[^@]+}}@avx2_legal256_prefer256_call_avx2_legal512_prefer256
; IS__TUNIT_OPM-SAME: (<8 x i64>* nocapture nofree writeonly [[ARG:%.*]]) #[[ATTR4:[0-9]+]] {
; IS__TUNIT_OPM-NEXT: bb:
; IS__TUNIT_OPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_OPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_OPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__TUNIT_OPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR6]]
; IS__TUNIT_OPM-NEXT: call fastcc void @callee_avx2_legal256_prefer256_call_avx2_legal512_prefer256(<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[TMP]]) #[[ATTR7]]
; IS__TUNIT_OPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__TUNIT_OPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__TUNIT_OPM-NEXT: ret void
;
; IS__TUNIT_NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__TUNIT_NPM-LABEL: define {{[^@]+}}@avx2_legal256_prefer256_call_avx2_legal512_prefer256
; IS__TUNIT_NPM-SAME: (<8 x i64>* nocapture nofree writeonly [[ARG:%.*]]) #[[ATTR3]] {
; IS__TUNIT_NPM-NEXT: bb:
; IS__TUNIT_NPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_NPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_NPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__TUNIT_NPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR5]]
; IS__TUNIT_NPM-NEXT: [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 64
; IS__TUNIT_NPM-NEXT: call fastcc void @callee_avx2_legal256_prefer256_call_avx2_legal512_prefer256(<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64> [[TMP0]]) #[[ATTR6]]
; IS__TUNIT_NPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__TUNIT_NPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__TUNIT_NPM-NEXT: ret void
;
; IS__CGSCC_OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__CGSCC_OPM-LABEL: define {{[^@]+}}@avx2_legal256_prefer256_call_avx2_legal512_prefer256
; IS__CGSCC_OPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 2 dereferenceable(64) [[ARG:%.*]]) #[[ATTR4:[0-9]+]] {
; IS__CGSCC_OPM-NEXT: bb:
; IS__CGSCC_OPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_OPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_OPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__CGSCC_OPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR6]]
; IS__CGSCC_OPM-NEXT: call fastcc void @callee_avx2_legal256_prefer256_call_avx2_legal512_prefer256(<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[TMP]]) #[[ATTR7]]
; IS__CGSCC_OPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__CGSCC_OPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__CGSCC_OPM-NEXT: ret void
;
; IS__CGSCC_NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__CGSCC_NPM-LABEL: define {{[^@]+}}@avx2_legal256_prefer256_call_avx2_legal512_prefer256
; IS__CGSCC_NPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 2 dereferenceable(64) [[ARG:%.*]]) #[[ATTR3]] {
; IS__CGSCC_NPM-NEXT: bb:
; IS__CGSCC_NPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_NPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_NPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__CGSCC_NPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR5]]
; IS__CGSCC_NPM-NEXT: [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 64
; IS__CGSCC_NPM-NEXT: call fastcc void @callee_avx2_legal256_prefer256_call_avx2_legal512_prefer256(<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64> [[TMP0]]) #[[ATTR6]]
; IS__CGSCC_NPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__CGSCC_NPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__CGSCC_NPM-NEXT: ret void
;
bb:
%tmp = alloca <8 x i64>, align 32
%tmp2 = alloca <8 x i64>, align 32
%tmp3 = bitcast <8 x i64>* %tmp to i8*
call void @llvm.memset.p0i8.i64(i8* align 32 %tmp3, i8 0, i64 32, i1 false)
call fastcc void @callee_avx2_legal256_prefer256_call_avx2_legal512_prefer256(<8 x i64>* %tmp2, <8 x i64>* %tmp)
%tmp4 = load <8 x i64>, <8 x i64>* %tmp2, align 32
store <8 x i64> %tmp4, <8 x i64>* %arg, align 2
ret void
}
; This should promote
define internal fastcc void @callee_avx2_legal512_prefer256_call_avx2_legal256_prefer256(<8 x i64>* %arg, <8 x i64>* readonly %arg1) #4 {
;
; IS________OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS________OPM-LABEL: define {{[^@]+}}@callee_avx2_legal512_prefer256_call_avx2_legal256_prefer256
; IS________OPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[ARG:%.*]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[ARG1:%.*]]) #[[ATTR4:[0-9]+]] {
; IS________OPM-NEXT: bb:
; IS________OPM-NEXT: [[TMP:%.*]] = load <8 x i64>, <8 x i64>* [[ARG1]], align 64
; IS________OPM-NEXT: store <8 x i64> [[TMP]], <8 x i64>* [[ARG]], align 64
; IS________OPM-NEXT: ret void
;
; IS________NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS________NPM-LABEL: define {{[^@]+}}@callee_avx2_legal512_prefer256_call_avx2_legal256_prefer256
; IS________NPM-SAME: (<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[ARG:%.*]], <8 x i64> [[TMP0:%.*]]) #[[ATTR3]] {
; IS________NPM-NEXT: bb:
; IS________NPM-NEXT: [[ARG1_PRIV:%.*]] = alloca <8 x i64>, align 64
; IS________NPM-NEXT: store <8 x i64> [[TMP0]], <8 x i64>* [[ARG1_PRIV]], align 64
; IS________NPM-NEXT: [[TMP:%.*]] = load <8 x i64>, <8 x i64>* [[ARG1_PRIV]], align 64
; IS________NPM-NEXT: store <8 x i64> [[TMP]], <8 x i64>* [[ARG]], align 64
; IS________NPM-NEXT: ret void
;
bb:
%tmp = load <8 x i64>, <8 x i64>* %arg1
store <8 x i64> %tmp, <8 x i64>* %arg
ret void
}
define void @avx2_legal512_prefer256_call_avx2_legal256_prefer256(<8 x i64>* %arg) #3 {
;
; IS__TUNIT_OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__TUNIT_OPM-LABEL: define {{[^@]+}}@avx2_legal512_prefer256_call_avx2_legal256_prefer256
; IS__TUNIT_OPM-SAME: (<8 x i64>* nocapture nofree writeonly [[ARG:%.*]]) #[[ATTR3]] {
; IS__TUNIT_OPM-NEXT: bb:
; IS__TUNIT_OPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_OPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_OPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__TUNIT_OPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR6]]
; IS__TUNIT_OPM-NEXT: call fastcc void @callee_avx2_legal512_prefer256_call_avx2_legal256_prefer256(<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[TMP]]) #[[ATTR7]]
; IS__TUNIT_OPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__TUNIT_OPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__TUNIT_OPM-NEXT: ret void
;
; IS__TUNIT_NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__TUNIT_NPM-LABEL: define {{[^@]+}}@avx2_legal512_prefer256_call_avx2_legal256_prefer256
; IS__TUNIT_NPM-SAME: (<8 x i64>* nocapture nofree writeonly [[ARG:%.*]]) #[[ATTR3]] {
; IS__TUNIT_NPM-NEXT: bb:
; IS__TUNIT_NPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_NPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__TUNIT_NPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__TUNIT_NPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR5]]
; IS__TUNIT_NPM-NEXT: [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 64
; IS__TUNIT_NPM-NEXT: call fastcc void @callee_avx2_legal512_prefer256_call_avx2_legal256_prefer256(<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64> [[TMP0]]) #[[ATTR6]]
; IS__TUNIT_NPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__TUNIT_NPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__TUNIT_NPM-NEXT: ret void
;
; IS__CGSCC_OPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__CGSCC_OPM-LABEL: define {{[^@]+}}@avx2_legal512_prefer256_call_avx2_legal256_prefer256
; IS__CGSCC_OPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 2 dereferenceable(64) [[ARG:%.*]]) #[[ATTR3]] {
; IS__CGSCC_OPM-NEXT: bb:
; IS__CGSCC_OPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_OPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_OPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__CGSCC_OPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR6]]
; IS__CGSCC_OPM-NEXT: call fastcc void @callee_avx2_legal512_prefer256_call_avx2_legal256_prefer256(<8 x i64>* nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64>* nocapture nofree noundef nonnull readonly align 64 dereferenceable(64) [[TMP]]) #[[ATTR7]]
; IS__CGSCC_OPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__CGSCC_OPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__CGSCC_OPM-NEXT: ret void
;
; IS__CGSCC_NPM: Function Attrs: argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable
; IS__CGSCC_NPM-LABEL: define {{[^@]+}}@avx2_legal512_prefer256_call_avx2_legal256_prefer256
; IS__CGSCC_NPM-SAME: (<8 x i64>* nocapture nofree noundef nonnull writeonly align 2 dereferenceable(64) [[ARG:%.*]]) #[[ATTR3]] {
; IS__CGSCC_NPM-NEXT: bb:
; IS__CGSCC_NPM-NEXT: [[TMP:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_NPM-NEXT: [[TMP2:%.*]] = alloca <8 x i64>, align 32
; IS__CGSCC_NPM-NEXT: [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
; IS__CGSCC_NPM-NEXT: call void @llvm.memset.p0i8.i64(i8* nocapture nofree noundef nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 noundef 0, i64 noundef 32, i1 noundef false) #[[ATTR5]]
; IS__CGSCC_NPM-NEXT: [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 64
; IS__CGSCC_NPM-NEXT: call fastcc void @callee_avx2_legal512_prefer256_call_avx2_legal256_prefer256(<8 x i64>* noalias nocapture nofree noundef nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64> [[TMP0]]) #[[ATTR6]]
; IS__CGSCC_NPM-NEXT: [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
; IS__CGSCC_NPM-NEXT: store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
; IS__CGSCC_NPM-NEXT: ret void
;
bb:
%tmp = alloca <8 x i64>, align 32
%tmp2 = alloca <8 x i64>, align 32
%tmp3 = bitcast <8 x i64>* %tmp to i8*
call void @llvm.memset.p0i8.i64(i8* align 32 %tmp3, i8 0, i64 32, i1 false)
call fastcc void @callee_avx2_legal512_prefer256_call_avx2_legal256_prefer256(<8 x i64>* %tmp2, <8 x i64>* %tmp)
%tmp4 = load <8 x i64>, <8 x i64>* %tmp2, align 32
store <8 x i64> %tmp4, <8 x i64>* %arg, align 2
ret void
}
; Function Attrs: argmemonly nounwind
declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i1) #5
attributes #0 = { inlinehint norecurse nounwind uwtable "target-features"="+avx512vl" "min-legal-vector-width"="512" "prefer-vector-width"="512" }
attributes #1 = { inlinehint norecurse nounwind uwtable "target-features"="+avx512vl" "min-legal-vector-width"="512" "prefer-vector-width"="256" }
attributes #2 = { inlinehint norecurse nounwind uwtable "target-features"="+avx512vl" "min-legal-vector-width"="256" "prefer-vector-width"="256" }
attributes #3 = { inlinehint norecurse nounwind uwtable "target-features"="+avx2" "min-legal-vector-width"="512" "prefer-vector-width"="256" }
attributes #4 = { inlinehint norecurse nounwind uwtable "target-features"="+avx2" "min-legal-vector-width"="256" "prefer-vector-width"="256" }
attributes #5 = { argmemonly nounwind }
;.
; IS__TUNIT_OPM: attributes #[[ATTR0]] = { argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable "min-legal-vector-width"="512" "prefer-vector-width"="512" "target-features"="+avx512vl" }
; IS__TUNIT_OPM: attributes #[[ATTR1]] = { argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable "min-legal-vector-width"="512" "prefer-vector-width"="256" "target-features"="+avx512vl" }
; IS__TUNIT_OPM: attributes #[[ATTR2]] = { argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable "min-legal-vector-width"="256" "prefer-vector-width"="256" "target-features"="+avx512vl" }
; IS__TUNIT_OPM: attributes #[[ATTR3]] = { argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable "min-legal-vector-width"="512" "prefer-vector-width"="256" "target-features"="+avx2" }
; IS__TUNIT_OPM: attributes #[[ATTR4]] = { argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable "min-legal-vector-width"="256" "prefer-vector-width"="256" "target-features"="+avx2" }
; IS__TUNIT_OPM: attributes #[[ATTR5:[0-9]+]] = { argmemonly nocallback nofree nounwind willreturn writeonly }
; IS__TUNIT_OPM: attributes #[[ATTR6]] = { willreturn writeonly }
; IS__TUNIT_OPM: attributes #[[ATTR7]] = { nofree nosync nounwind willreturn }
;.
; IS__TUNIT_NPM: attributes #[[ATTR0]] = { argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable "min-legal-vector-width"="512" "prefer-vector-width"="512" "target-features"="+avx512vl" }
; IS__TUNIT_NPM: attributes #[[ATTR1]] = { argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable "min-legal-vector-width"="512" "prefer-vector-width"="256" "target-features"="+avx512vl" }
; IS__TUNIT_NPM: attributes #[[ATTR2]] = { argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable "min-legal-vector-width"="256" "prefer-vector-width"="256" "target-features"="+avx512vl" }
; IS__TUNIT_NPM: attributes #[[ATTR3]] = { argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable "min-legal-vector-width"="512" "prefer-vector-width"="256" "target-features"="+avx2" }
; IS__TUNIT_NPM: attributes #[[ATTR4:[0-9]+]] = { argmemonly nocallback nofree nounwind willreturn writeonly }
; IS__TUNIT_NPM: attributes #[[ATTR5]] = { willreturn writeonly }
; IS__TUNIT_NPM: attributes #[[ATTR6]] = { nofree nosync nounwind willreturn }
;.
; IS__CGSCC_OPM: attributes #[[ATTR0]] = { argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable "min-legal-vector-width"="512" "prefer-vector-width"="512" "target-features"="+avx512vl" }
; IS__CGSCC_OPM: attributes #[[ATTR1]] = { argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable "min-legal-vector-width"="512" "prefer-vector-width"="256" "target-features"="+avx512vl" }
; IS__CGSCC_OPM: attributes #[[ATTR2]] = { argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable "min-legal-vector-width"="256" "prefer-vector-width"="256" "target-features"="+avx512vl" }
; IS__CGSCC_OPM: attributes #[[ATTR3]] = { argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable "min-legal-vector-width"="512" "prefer-vector-width"="256" "target-features"="+avx2" }
; IS__CGSCC_OPM: attributes #[[ATTR4]] = { argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable "min-legal-vector-width"="256" "prefer-vector-width"="256" "target-features"="+avx2" }
; IS__CGSCC_OPM: attributes #[[ATTR5:[0-9]+]] = { argmemonly nocallback nofree nounwind willreturn writeonly }
; IS__CGSCC_OPM: attributes #[[ATTR6]] = { willreturn writeonly }
; IS__CGSCC_OPM: attributes #[[ATTR7]] = { nounwind willreturn }
;.
; IS__CGSCC_NPM: attributes #[[ATTR0]] = { argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable "min-legal-vector-width"="512" "prefer-vector-width"="512" "target-features"="+avx512vl" }
; IS__CGSCC_NPM: attributes #[[ATTR1]] = { argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable "min-legal-vector-width"="512" "prefer-vector-width"="256" "target-features"="+avx512vl" }
; IS__CGSCC_NPM: attributes #[[ATTR2]] = { argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable "min-legal-vector-width"="256" "prefer-vector-width"="256" "target-features"="+avx512vl" }
; IS__CGSCC_NPM: attributes #[[ATTR3]] = { argmemonly inlinehint nofree norecurse nosync nounwind willreturn uwtable "min-legal-vector-width"="512" "prefer-vector-width"="256" "target-features"="+avx2" }
; IS__CGSCC_NPM: attributes #[[ATTR4:[0-9]+]] = { argmemonly nocallback nofree nounwind willreturn writeonly }
; IS__CGSCC_NPM: attributes #[[ATTR5]] = { willreturn writeonly }
; IS__CGSCC_NPM: attributes #[[ATTR6]] = { nounwind willreturn }
;.