Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Arm64EC] Improve alignment mangling in arm64ec thunks. #90115

Merged
merged 1 commit into from
Apr 26, 2024
Merged

[Arm64EC] Improve alignment mangling in arm64ec thunks. #90115

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 4 additions & 3 deletions llvm/lib/Target/AArch64/AArch64Arm64ECCallLowering.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -178,13 +178,14 @@ void AArch64Arm64ECCallLowering::getThunkArgTypes(
}

for (unsigned E = FT->getNumParams(); I != E; ++I) {
Align ParamAlign = AttrList.getParamAlignment(I).valueOrOne();
#if 0
// FIXME: Need more information about argument size; see
// https://reviews.llvm.org/D132926
uint64_t ArgSizeBytes = AttrList.getParamArm64ECArgSizeBytes(I);
Align ParamAlign = AttrList.getParamAlignment(I).valueOrOne();
#else
uint64_t ArgSizeBytes = 0;
Align ParamAlign = Align();
#endif
Type *Arm64Ty, *X64Ty;
canonicalizeThunkType(FT->getParamType(I), ParamAlign,
Expand Down Expand Up @@ -294,7 +295,7 @@ void AArch64Arm64ECCallLowering::canonicalizeThunkType(
uint64_t TotalSizeBytes = ElementCnt * ElementSizePerBytes;
if (ElementTy->isFloatTy() || ElementTy->isDoubleTy()) {
Out << (ElementTy->isFloatTy() ? "F" : "D") << TotalSizeBytes;
if (Alignment.value() >= 8 && !T->isPointerTy())
if (Alignment.value() >= 16 && !Ret)
Out << "a" << Alignment.value();
Arm64Ty = T;
if (TotalSizeBytes <= 8) {
Expand Down Expand Up @@ -325,7 +326,7 @@ void AArch64Arm64ECCallLowering::canonicalizeThunkType(
Out << "m";
if (TypeSize != 4)
Out << TypeSize;
if (Alignment.value() >= 8 && !T->isPointerTy())
if (Alignment.value() >= 16 && !Ret)
Out << "a" << Alignment.value();
// FIXME: Try to canonicalize Arm64Ty more thoroughly?
Arm64Ty = T;
Expand Down
6 changes: 3 additions & 3 deletions llvm/test/CodeGen/AArch64/arm64ec-entry-thunks.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -223,8 +223,8 @@ define i8 @matches_has_sret() nounwind {

%TSRet = type { i64, i64 }
define void @has_aligned_sret(ptr align 32 sret(%TSRet)) nounwind {
; CHECK-LABEL: .def $ientry_thunk$cdecl$m16a32$v;
; CHECK: .section .wowthk$aa,"xr",discard,$ientry_thunk$cdecl$m16a32$v
; CHECK-LABEL: .def $ientry_thunk$cdecl$m16$v;
; CHECK: .section .wowthk$aa,"xr",discard,$ientry_thunk$cdecl$m16$v
; CHECK: // %bb.0:
; CHECK-NEXT: stp q6, q7, [sp, #-176]! // 32-byte Folded Spill
; CHECK-NEXT: .seh_save_any_reg_px q6, 176
Expand Down Expand Up @@ -457,7 +457,7 @@ define %T2 @simple_struct(%T1 %0, %T2 %1, %T3, %T4) nounwind {
; CHECK-NEXT: .symidx $ientry_thunk$cdecl$i8$v
; CHECK-NEXT: .word 1
; CHECK-NEXT: .symidx "#has_aligned_sret"
; CHECK-NEXT: .symidx $ientry_thunk$cdecl$m16a32$v
; CHECK-NEXT: .symidx $ientry_thunk$cdecl$m16$v
; CHECK-NEXT: .word 1
; CHECK-NEXT: .symidx "#small_array"
; CHECK-NEXT: .symidx $ientry_thunk$cdecl$m2$m2F8
Expand Down
10 changes: 5 additions & 5 deletions llvm/test/CodeGen/AArch64/arm64ec-exit-thunks.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -236,8 +236,8 @@ declare void @has_sret(ptr sret([100 x i8])) nounwind;

%TSRet = type { i64, i64 }
declare void @has_aligned_sret(ptr align 32 sret(%TSRet)) nounwind;
; CHECK-LABEL: .def $iexit_thunk$cdecl$m16a32$v;
; CHECK: .section .wowthk$aa,"xr",discard,$iexit_thunk$cdecl$m16a32$v
; CHECK-LABEL: .def $iexit_thunk$cdecl$m16$v;
; CHECK: .section .wowthk$aa,"xr",discard,$iexit_thunk$cdecl$m16$v
; CHECK: // %bb.0:
; CHECK-NEXT: sub sp, sp, #48
; CHECK-NEXT: .seh_stackalloc 48
Expand Down Expand Up @@ -271,8 +271,8 @@ declare void @has_aligned_sret(ptr align 32 sret(%TSRet)) nounwind;
; CHECK: adrp x11, has_aligned_sret
; CHECK: add x11, x11, :lo12:has_aligned_sret
; CHECK: ldr x9, [x9, :lo12:__os_arm64x_check_icall]
; CHECK: adrp x10, ($iexit_thunk$cdecl$m16a32$v)
; CHECK: add x10, x10, :lo12:($iexit_thunk$cdecl$m16a32$v)
; CHECK: adrp x10, ($iexit_thunk$cdecl$m16$v)
; CHECK: add x10, x10, :lo12:($iexit_thunk$cdecl$m16$v)
; CHECK: blr x9
; CHECK: .seh_startepilogue
; CHECK: ldr x30, [sp], #16 // 8-byte Folded Reload
Expand Down Expand Up @@ -492,7 +492,7 @@ declare %T2 @simple_struct(%T1, %T2, %T3, %T4) nounwind;
; CHECK-NEXT: .symidx has_sret
; CHECK-NEXT: .word 0
; CHECK-NEXT: .symidx has_aligned_sret
; CHECK-NEXT: .symidx $iexit_thunk$cdecl$m16a32$v
; CHECK-NEXT: .symidx $iexit_thunk$cdecl$m16$v
; CHECK-NEXT: .word 4
; CHECK-NEXT: .symidx "#has_aligned_sret$exit_thunk"
; CHECK-NEXT: .symidx has_aligned_sret
Expand Down
Loading