Skip to content

[PowerPC] Utilize getReservedRegs to find asm clobberable registers. #107863

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

Merged
diggerlin merged 4 commits into from
Nov 4, 2024
Merged

[PowerPC] Utilize getReservedRegs to find asm clobberable registers. #107863

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
153d1d9
Implement isAsmClobberable() and make r2 allocatable on AIX64 for som…
diggerlin Sep 13, 2024
c2bd364
add comment
diggerlin Oct 16, 2024
ee1ce9d
address comment
diggerlin Oct 31, 2024
a359c27
Merge branch 'main' into digger/r2_aix
diggerlin Nov 4, 2024
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
8 changes: 8 additions & 0 deletions llvm/lib/Target/PowerPC/PPCFrameLowering.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2771,6 +2771,14 @@ void PPCFrameLowering::updateCalleeSaves(const MachineFunction &MF,
MCPhysReg Cand = CSRegs[i];
if (!SavedRegs.test(Cand))
continue;
// When R2/X2 is a CSR and not used for passing arguments, it is allocated
// earlier than other volatile registers. R2/X2 is not contiguous with
// R13/X13 to R31/X31.
if (Cand == PPC::X2 || Cand == PPC::R2) {
SavedRegs.set(Cand);
continue;
}

if (PPC::GPRCRegClass.contains(Cand) && Cand < LowestGPR)
LowestGPR = Cand;
else if (PPC::G8RCRegClass.contains(Cand) && Cand < LowestG8R)
Expand Down
4 changes: 4 additions & 0 deletions llvm/lib/Target/PowerPC/PPCISelLowering.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3437,6 +3437,10 @@ SDValue PPCTargetLowering::LowerGlobalTLSAddressAIX(SDValue Op,
if (Subtarget.hasAIXShLibTLSModelOpt())
updateForAIXShLibTLSModelOpt(Model, DAG, getTargetMachine());

// TLS variables are accessed through TOC entries.
// To support this, set the DAG to use the TOC base pointer.
setUsesTOCBasePtr(DAG);

bool IsTLSLocalExecModel = Model == TLSModel::LocalExec;

if (IsTLSLocalExecModel || Model == TLSModel::InitialExec) {
Expand Down
32 changes: 14 additions & 18 deletions llvm/lib/Target/PowerPC/PPCRegisterInfo.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -380,23 +380,21 @@ BitVector PPCRegisterInfo::getReservedRegs(const MachineFunction &MF) const {

markSuperRegs(Reserved, PPC::VRSAVE);

const PPCFunctionInfo *FuncInfo = MF.getInfo<PPCFunctionInfo>();
bool UsesTOCBasePtr = FuncInfo->usesTOCBasePtr();
// The SVR4 ABI reserves r2 and r13
if (Subtarget.isSVR4ABI()) {
if (Subtarget.isSVR4ABI() || Subtarget.isAIXABI()) {
// We only reserve r2 if we need to use the TOC pointer. If we have no
// explicit uses of the TOC pointer (meaning we're a leaf function with
// no constant-pool loads, etc.) and we have no potential uses inside an
// inline asm block, then we can treat r2 has an ordinary callee-saved
// register.
const PPCFunctionInfo *FuncInfo = MF.getInfo<PPCFunctionInfo>();
if (!TM.isPPC64() || FuncInfo->usesTOCBasePtr() || MF.hasInlineAsm())
markSuperRegs(Reserved, PPC::R2); // System-reserved register
markSuperRegs(Reserved, PPC::R13); // Small Data Area pointer register
}
if (!TM.isPPC64() || UsesTOCBasePtr || MF.hasInlineAsm())
markSuperRegs(Reserved, PPC::R2); // System-reserved register.

// Always reserve r2 on AIX for now.
// TODO: Make r2 allocatable on AIX/XCOFF for some leaf functions.
if (Subtarget.isAIXABI())
markSuperRegs(Reserved, PPC::R2); // System-reserved register
if (Subtarget.isSVR4ABI())
markSuperRegs(Reserved, PPC::R13); // Small Data Area pointer register.
}

// On PPC64, r13 is the thread pointer. Never allocate this register.
if (TM.isPPC64())
Expand Down Expand Up @@ -441,14 +439,12 @@ BitVector PPCRegisterInfo::getReservedRegs(const MachineFunction &MF) const {

bool PPCRegisterInfo::isAsmClobberable(const MachineFunction &MF,
MCRegister PhysReg) const {
// We cannot use getReservedRegs() to find the registers that are not asm
// clobberable because there are some reserved registers which can be
// clobbered by inline asm. For example, when LR is clobbered, the register is
// saved and restored. We will hardcode the registers that are not asm
// cloberable in this function.

// The stack pointer (R1/X1) is not clobberable by inline asm
return PhysReg != PPC::R1 && PhysReg != PPC::X1;
// CTR and LR registers are always reserved, but they are asm clobberable.
if (PhysReg == PPC::CTR || PhysReg == PPC::CTR8 || PhysReg == PPC::LR ||
PhysReg == PPC::LR8)
return true;

return !getReservedRegs(MF).test(PhysReg);
}

bool PPCRegisterInfo::requiresFrameIndexScavenging(const MachineFunction &MF) const {
Expand Down
14 changes: 7 additions & 7 deletions llvm/test/CodeGen/PowerPC/aix-cc-abi-mir.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1146,11 +1146,11 @@ define i64 @test_ints_stack(i32 %i1, i32 %i2, i32 %i3, i32 %i4, i32 %i5, i32 %i6
; 64BIT-NEXT: renamable $r11 = LWZ 0, %fixed-stack.1, implicit-def $x11 :: (load (s32) from %fixed-stack.1)
; 64BIT-NEXT: renamable $x12 = LWZ8 0, %fixed-stack.4 :: (load (s32) from %fixed-stack.4)
; 64BIT-NEXT: renamable $x0 = LWA 0, %fixed-stack.0 :: (load (s32) from %fixed-stack.0)
; 64BIT-NEXT: renamable $x31 = LD 0, %fixed-stack.2 :: (load (s64) from %fixed-stack.2)
; 64BIT-NEXT: renamable $x30 = LWA 0, %fixed-stack.3 :: (load (s32) from %fixed-stack.3)
; 64BIT-NEXT: renamable $r29 = LWZ 0, %fixed-stack.5, implicit-def $x29 :: (load (s32) from %fixed-stack.5)
; 64BIT-NEXT: renamable $x28 = LWA 0, %fixed-stack.6 :: (load (s32) from %fixed-stack.6)
; 64BIT-NEXT: renamable $x27 = LD 0, %fixed-stack.7 :: (load (s64) from %fixed-stack.7, align 16)
; 64BIT-NEXT: renamable $x2 = LD 0, %fixed-stack.2 :: (load (s64) from %fixed-stack.2)
; 64BIT-NEXT: renamable $x31 = LWA 0, %fixed-stack.3 :: (load (s32) from %fixed-stack.3)
; 64BIT-NEXT: renamable $r30 = LWZ 0, %fixed-stack.5, implicit-def $x30 :: (load (s32) from %fixed-stack.5)
; 64BIT-NEXT: renamable $x29 = LWA 0, %fixed-stack.6 :: (load (s32) from %fixed-stack.6)
; 64BIT-NEXT: renamable $x28 = LD 0, %fixed-stack.7 :: (load (s64) from %fixed-stack.7, align 16)
; 64BIT-NEXT: renamable $r3 = nsw ADD4 renamable $r3, renamable $r4, implicit killed $x4, implicit killed $x3
; 64BIT-NEXT: renamable $r3 = nsw ADD4 killed renamable $r3, renamable $r5, implicit killed $x5
; 64BIT-NEXT: renamable $r3 = nsw ADD4 killed renamable $r3, renamable $r6, implicit killed $x6
Expand All @@ -1159,12 +1159,12 @@ define i64 @test_ints_stack(i32 %i1, i32 %i2, i32 %i3, i32 %i4, i32 %i5, i32 %i6
; 64BIT-NEXT: renamable $r3 = nsw ADD4 killed renamable $r3, renamable $r9, implicit killed $x9
; 64BIT-NEXT: renamable $r3 = nsw ADD4 killed renamable $r3, renamable $r10, implicit killed $x10
; 64BIT-NEXT: renamable $x3 = EXTSW_32_64 killed renamable $r3
; 64BIT-NEXT: renamable $x3 = nsw ADD8 killed renamable $x3, killed renamable $x27
; 64BIT-NEXT: renamable $x3 = nsw ADD8 killed renamable $x3, killed renamable $x28
; 64BIT-NEXT: renamable $x3 = nsw ADD8 killed renamable $x3, killed renamable $x29
; 64BIT-NEXT: renamable $x3 = nsw ADD8 killed renamable $x3, killed renamable $x12
; 64BIT-NEXT: renamable $x3 = nsw ADD8 killed renamable $x3, killed renamable $x30
; 64BIT-NEXT: renamable $x3 = nsw ADD8 killed renamable $x3, killed renamable $x12
; 64BIT-NEXT: renamable $x3 = nsw ADD8 killed renamable $x3, killed renamable $x31
; 64BIT-NEXT: renamable $x3 = nsw ADD8 killed renamable $x3, killed renamable $x2
; 64BIT-NEXT: renamable $x3 = nsw ADD8 killed renamable $x3, killed renamable $x11
; 64BIT-NEXT: renamable $x3 = nsw ADD8 killed renamable $x3, killed renamable $x0
; 64BIT-NEXT: BLR8 implicit $lr8, implicit $rm, implicit $x3
Expand Down
8 changes: 4 additions & 4 deletions llvm/test/CodeGen/PowerPC/aix-cc-abi.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1240,19 +1240,19 @@ define i64 @test_ints_stack(i32 %i1, i32 %i2, i32 %i3, i32 %i4, i32 %i5, i32 %i6
; ASM64PWR4-NEXT: lwz 5, 132(1)
; ASM64PWR4-NEXT: add 3, 3, 4
; ASM64PWR4-NEXT: add 3, 3, 12
; ASM64PWR4-NEXT: std 31, -8(1) # 8-byte Folded Spill
; ASM64PWR4-NEXT: std 2, -8(1) # 8-byte Folded Spill
; ASM64PWR4-NEXT: add 3, 3, 5
; ASM64PWR4-NEXT: lwz 31, 140(1)
; ASM64PWR4-NEXT: lwz 2, 140(1)
; ASM64PWR4-NEXT: lwa 11, 148(1)
; ASM64PWR4-NEXT: add 3, 3, 31
; ASM64PWR4-NEXT: add 3, 3, 2
; ASM64PWR4-NEXT: add 3, 3, 11
; ASM64PWR4-NEXT: ld 4, 152(1)
; ASM64PWR4-NEXT: lwz 0, 164(1)
; ASM64PWR4-NEXT: add 3, 3, 4
; ASM64PWR4-NEXT: lwa 5, 172(1)
; ASM64PWR4-NEXT: add 3, 3, 0
; ASM64PWR4-NEXT: add 3, 3, 5
; ASM64PWR4-NEXT: ld 31, -8(1) # 8-byte Folded Reload
; ASM64PWR4-NEXT: ld 2, -8(1) # 8-byte Folded Reload
; ASM64PWR4-NEXT: blr
entry:
%add = add nsw i32 %i1, %i2
Expand Down
15 changes: 15 additions & 0 deletions llvm/test/CodeGen/PowerPC/aix-inline-asm-clobber-warning.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
; RUN: llc < %s -mtriple=powerpc-unknown-aix-xcoff -verify-machineinstrs \
Copy link
Contributor

@amy-kwan amy-kwan Oct 29, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should we add a 64-bit run line, too?

; RUN: -mcpu=pwr7 -mattr=+altivec -O0 2>&1 | FileCheck %s
; RUN: llc < %s -mtriple=powerpc64-unknown-aix-xcoff -verify-machineinstrs \
; RUN: -mcpu=pwr7 -mattr=+altivec -O0 2>&1 | FileCheck %s

; CHECK: warning: inline asm clobber list contains reserved registers: R2
; CHECK-NEXT: note: Reserved registers on the clobber list may not be preserved across the asm statement, and clobbering them may lead to undefined behaviour.

@a = external global i32, align 4

define void @bar() {
store i32 0, ptr @a, align 4
call void asm sideeffect "li 2, 1", "~{r2}"()
ret void
}
3 changes: 1 addition & 2 deletions llvm/test/CodeGen/PowerPC/aix64-csr-alloc.mir
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,5 @@ body: |
BLR8 implicit $lr8, implicit undef $rm, implicit $x3, implicit $f1
...
# CHECK-DAG: AllocationOrder(VFRC) = [ $vf2 $vf3 $vf4 $vf5 $vf0 $vf1 $vf6 $vf7 $vf8 $vf9 $vf10 $vf11 $vf12 $vf13 $vf14 $vf15 $vf16 $vf17 $vf18 $vf19 $vf31 $vf30 $vf29 $vf28 $vf27 $vf26 $vf25 $vf24 $vf23 $vf22 $vf21 $vf20 ]
# CHECK-DAG: AllocationOrder(G8RC_and_G8RC_NOX0) = [ $x3 $x4 $x5 $x6 $x7 $x8 $x9 $x10 $x11 $x12 $x31 $x30 $x29 $x28 $x27 $x26 $x25 $x24 $x23 $x22 $x21 $x20 $x19 $x18 $x17 $x16 $x15 $x1
# CHECK-DAG: 4 ]
# CHECK-DAG: AllocationOrder(G8RC_and_G8RC_NOX0) = [ $x3 $x4 $x5 $x6 $x7 $x8 $x9 $x10 $x11 $x12 $x2 $x31 $x30 $x29 $x28 $x27 $x26 $x25 $x24 $x23 $x22 $x21 $x20 $x19 $x18 $x17 $x16 $x15 $x14 ]
# CHECK-DAG: AllocationOrder(F8RC) = [ $f0 $f1 $f2 $f3 $f4 $f5 $f6 $f7 $f8 $f9 $f10 $f11 $f12 $f13 $f31 $f30 $f29 $f28 $f27 $f26 $f25 $f24 $f23 $f22 $f21 $f20 $f19 $f18 $f17 $f16 $f15 $f14 ]
126 changes: 63 additions & 63 deletions llvm/test/CodeGen/PowerPC/inc-of-add.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -166,81 +166,81 @@ define <16 x i8> @vector_i128_i8(<16 x i8> %x, <16 x i8> %y) nounwind {
;
; AIX-PPC64-LABEL: vector_i128_i8:
; AIX-PPC64: # %bb.0:
; AIX-PPC64-NEXT: std 22, -80(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: lbz 22, 207(1)
; AIX-PPC64-NEXT: std 23, -72(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: lbz 23, 207(1)
; AIX-PPC64-NEXT: std 24, -64(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: std 26, -48(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: std 25, -56(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: std 27, -40(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: std 26, -48(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: std 30, -16(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: std 29, -24(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: std 28, -32(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: std 27, -40(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: std 2, -80(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: std 31, -8(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: std 30, -16(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: lbz 23, 199(1)
; AIX-PPC64-NEXT: lbz 24, 191(1)
; AIX-PPC64-NEXT: add 6, 22, 6
; AIX-PPC64-NEXT: lbz 22, 231(1)
; AIX-PPC64-NEXT: add 5, 23, 5
; AIX-PPC64-NEXT: lbz 23, 223(1)
; AIX-PPC64-NEXT: add 4, 24, 4
; AIX-PPC64-NEXT: lbz 24, 215(1)
; AIX-PPC64-NEXT: add 9, 22, 9
; AIX-PPC64-NEXT: lbz 26, 127(1)
; AIX-PPC64-NEXT: add 8, 23, 8
; AIX-PPC64-NEXT: lbz 22, 255(1)
; AIX-PPC64-NEXT: add 7, 24, 7
; AIX-PPC64-NEXT: lbz 25, 119(1)
; AIX-PPC64-NEXT: lbz 24, 199(1)
; AIX-PPC64-NEXT: lbz 25, 191(1)
; AIX-PPC64-NEXT: add 6, 23, 6
; AIX-PPC64-NEXT: lbz 23, 231(1)
; AIX-PPC64-NEXT: add 5, 24, 5
; AIX-PPC64-NEXT: lbz 24, 223(1)
; AIX-PPC64-NEXT: add 4, 25, 4
; AIX-PPC64-NEXT: lbz 25, 215(1)
; AIX-PPC64-NEXT: add 9, 23, 9
; AIX-PPC64-NEXT: lbz 27, 127(1)
; AIX-PPC64-NEXT: add 8, 24, 8
; AIX-PPC64-NEXT: lbz 23, 255(1)
; AIX-PPC64-NEXT: add 7, 25, 7
; AIX-PPC64-NEXT: lbz 26, 119(1)
; AIX-PPC64-NEXT: addi 9, 9, 1
; AIX-PPC64-NEXT: lbz 23, 247(1)
; AIX-PPC64-NEXT: add 26, 22, 26
; AIX-PPC64-NEXT: lbz 24, 239(1)
; AIX-PPC64-NEXT: lbz 24, 247(1)
; AIX-PPC64-NEXT: add 27, 23, 27
; AIX-PPC64-NEXT: lbz 25, 239(1)
; AIX-PPC64-NEXT: addi 8, 8, 1
; AIX-PPC64-NEXT: lbz 29, 151(1)
; AIX-PPC64-NEXT: add 25, 23, 25
; AIX-PPC64-NEXT: lbz 22, 279(1)
; AIX-PPC64-NEXT: add 10, 24, 10
; AIX-PPC64-NEXT: lbz 28, 143(1)
; AIX-PPC64-NEXT: lbz 30, 151(1)
; AIX-PPC64-NEXT: add 26, 24, 26
; AIX-PPC64-NEXT: lbz 23, 279(1)
; AIX-PPC64-NEXT: add 10, 25, 10
; AIX-PPC64-NEXT: lbz 29, 143(1)
; AIX-PPC64-NEXT: addi 10, 10, 1
; AIX-PPC64-NEXT: lbz 23, 271(1)
; AIX-PPC64-NEXT: add 29, 22, 29
; AIX-PPC64-NEXT: lbz 27, 135(1)
; AIX-PPC64-NEXT: lbz 24, 271(1)
; AIX-PPC64-NEXT: add 30, 23, 30
; AIX-PPC64-NEXT: lbz 28, 135(1)
; AIX-PPC64-NEXT: addi 7, 7, 1
; AIX-PPC64-NEXT: lbz 24, 263(1)
; AIX-PPC64-NEXT: add 28, 23, 28
; AIX-PPC64-NEXT: lbz 25, 263(1)
; AIX-PPC64-NEXT: add 29, 24, 29
; AIX-PPC64-NEXT: lbz 11, 183(1)
; AIX-PPC64-NEXT: addi 6, 6, 1
; AIX-PPC64-NEXT: lbz 22, 311(1)
; AIX-PPC64-NEXT: add 27, 24, 27
; AIX-PPC64-NEXT: lbz 23, 311(1)
; AIX-PPC64-NEXT: add 28, 25, 28
; AIX-PPC64-NEXT: lbz 12, 175(1)
; AIX-PPC64-NEXT: addi 5, 5, 1
; AIX-PPC64-NEXT: lbz 0, 303(1)
; AIX-PPC64-NEXT: add 11, 22, 11
; AIX-PPC64-NEXT: lbz 31, 167(1)
; AIX-PPC64-NEXT: add 11, 23, 11
; AIX-PPC64-NEXT: lbz 2, 167(1)
; AIX-PPC64-NEXT: addi 11, 11, 1
; AIX-PPC64-NEXT: lbz 23, 295(1)
; AIX-PPC64-NEXT: lbz 24, 295(1)
; AIX-PPC64-NEXT: add 12, 0, 12
; AIX-PPC64-NEXT: lbz 30, 159(1)
; AIX-PPC64-NEXT: lbz 31, 159(1)
; AIX-PPC64-NEXT: addi 4, 4, 1
; AIX-PPC64-NEXT: lbz 24, 287(1)
; AIX-PPC64-NEXT: add 31, 23, 31
; AIX-PPC64-NEXT: lbz 25, 287(1)
; AIX-PPC64-NEXT: add 2, 24, 2
; AIX-PPC64-NEXT: stb 11, 15(3)
; AIX-PPC64-NEXT: addi 11, 12, 1
; AIX-PPC64-NEXT: add 30, 24, 30
; AIX-PPC64-NEXT: add 31, 25, 31
; AIX-PPC64-NEXT: stb 11, 14(3)
; AIX-PPC64-NEXT: addi 11, 31, 1
; AIX-PPC64-NEXT: addi 11, 2, 1
; AIX-PPC64-NEXT: stb 11, 13(3)
; AIX-PPC64-NEXT: addi 11, 30, 1
; AIX-PPC64-NEXT: addi 11, 31, 1
; AIX-PPC64-NEXT: stb 11, 12(3)
; AIX-PPC64-NEXT: addi 11, 29, 1
; AIX-PPC64-NEXT: addi 11, 30, 1
; AIX-PPC64-NEXT: stb 11, 11(3)
; AIX-PPC64-NEXT: addi 11, 28, 1
; AIX-PPC64-NEXT: addi 11, 29, 1
; AIX-PPC64-NEXT: stb 11, 10(3)
; AIX-PPC64-NEXT: addi 11, 27, 1
; AIX-PPC64-NEXT: addi 11, 28, 1
; AIX-PPC64-NEXT: stb 11, 9(3)
; AIX-PPC64-NEXT: addi 11, 26, 1
; AIX-PPC64-NEXT: addi 11, 27, 1
; AIX-PPC64-NEXT: stb 11, 8(3)
; AIX-PPC64-NEXT: addi 11, 25, 1
; AIX-PPC64-NEXT: addi 11, 26, 1
; AIX-PPC64-NEXT: stb 11, 7(3)
; AIX-PPC64-NEXT: stb 10, 6(3)
; AIX-PPC64-NEXT: stb 9, 5(3)
Expand All @@ -249,6 +249,7 @@ define <16 x i8> @vector_i128_i8(<16 x i8> %x, <16 x i8> %y) nounwind {
; AIX-PPC64-NEXT: stb 6, 2(3)
; AIX-PPC64-NEXT: stb 5, 1(3)
; AIX-PPC64-NEXT: stb 4, 0(3)
; AIX-PPC64-NEXT: ld 2, -80(1) # 8-byte Folded Reload
; AIX-PPC64-NEXT: ld 31, -8(1) # 8-byte Folded Reload
; AIX-PPC64-NEXT: ld 30, -16(1) # 8-byte Folded Reload
; AIX-PPC64-NEXT: ld 29, -24(1) # 8-byte Folded Reload
Expand All @@ -258,7 +259,6 @@ define <16 x i8> @vector_i128_i8(<16 x i8> %x, <16 x i8> %y) nounwind {
; AIX-PPC64-NEXT: ld 25, -56(1) # 8-byte Folded Reload
; AIX-PPC64-NEXT: ld 24, -64(1) # 8-byte Folded Reload
; AIX-PPC64-NEXT: ld 23, -72(1) # 8-byte Folded Reload
; AIX-PPC64-NEXT: ld 22, -80(1) # 8-byte Folded Reload
; AIX-PPC64-NEXT: blr
;
; PPC64LE-LABEL: vector_i128_i8:
Expand Down Expand Up @@ -314,30 +314,30 @@ define <8 x i16> @vector_i128_i16(<8 x i16> %x, <8 x i16> %y) nounwind {
;
; AIX-PPC64-LABEL: vector_i128_i16:
; AIX-PPC64: # %bb.0:
; AIX-PPC64-NEXT: std 26, -48(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: std 27, -40(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: std 28, -32(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: std 29, -24(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: std 30, -16(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: std 31, -8(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: std 2, -48(1) # 8-byte Folded Spill
; AIX-PPC64-NEXT: lhz 11, 118(1)
; AIX-PPC64-NEXT: lhz 12, 182(1)
; AIX-PPC64-NEXT: lhz 0, 174(1)
; AIX-PPC64-NEXT: lhz 31, 166(1)
; AIX-PPC64-NEXT: lhz 2, 166(1)
; AIX-PPC64-NEXT: add 11, 12, 11
; AIX-PPC64-NEXT: lhz 30, 158(1)
; AIX-PPC64-NEXT: lhz 31, 158(1)
; AIX-PPC64-NEXT: add 10, 0, 10
; AIX-PPC64-NEXT: lhz 29, 142(1)
; AIX-PPC64-NEXT: add 9, 31, 9
; AIX-PPC64-NEXT: lhz 28, 126(1)
; AIX-PPC64-NEXT: add 8, 30, 8
; AIX-PPC64-NEXT: lhz 27, 134(1)
; AIX-PPC64-NEXT: add 6, 29, 6
; AIX-PPC64-NEXT: lhz 26, 150(1)
; AIX-PPC64-NEXT: add 4, 28, 4
; AIX-PPC64-NEXT: add 5, 27, 5
; AIX-PPC64-NEXT: lhz 30, 142(1)
; AIX-PPC64-NEXT: add 9, 2, 9
; AIX-PPC64-NEXT: lhz 29, 126(1)
; AIX-PPC64-NEXT: add 8, 31, 8
; AIX-PPC64-NEXT: lhz 28, 134(1)
; AIX-PPC64-NEXT: add 6, 30, 6
; AIX-PPC64-NEXT: lhz 27, 150(1)
; AIX-PPC64-NEXT: add 4, 29, 4
; AIX-PPC64-NEXT: add 5, 28, 5
; AIX-PPC64-NEXT: addi 11, 11, 1
; AIX-PPC64-NEXT: add 7, 26, 7
; AIX-PPC64-NEXT: add 7, 27, 7
; AIX-PPC64-NEXT: addi 10, 10, 1
; AIX-PPC64-NEXT: addi 9, 9, 1
; AIX-PPC64-NEXT: addi 8, 8, 1
Expand All @@ -353,12 +353,12 @@ define <8 x i16> @vector_i128_i16(<8 x i16> %x, <8 x i16> %y) nounwind {
; AIX-PPC64-NEXT: sth 6, 4(3)
; AIX-PPC64-NEXT: sth 5, 2(3)
; AIX-PPC64-NEXT: sth 4, 0(3)
; AIX-PPC64-NEXT: ld 2, -48(1) # 8-byte Folded Reload
; AIX-PPC64-NEXT: ld 31, -8(1) # 8-byte Folded Reload
; AIX-PPC64-NEXT: ld 30, -16(1) # 8-byte Folded Reload
; AIX-PPC64-NEXT: ld 29, -24(1) # 8-byte Folded Reload
; AIX-PPC64-NEXT: ld 28, -32(1) # 8-byte Folded Reload
; AIX-PPC64-NEXT: ld 27, -40(1) # 8-byte Folded Reload
; AIX-PPC64-NEXT: ld 26, -48(1) # 8-byte Folded Reload
; AIX-PPC64-NEXT: blr
;
; PPC64LE-LABEL: vector_i128_i16:
Expand Down
25 changes: 23 additions & 2 deletions llvm/test/CodeGen/PowerPC/inline-asm-clobber-warning.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
; RUN: llc < %s -verify-machineinstrs -mtriple=powerpc-unknown-unkown \
; RUN: -mcpu=pwr7 2>&1 | FileCheck %s
; RUN: -mcpu=pwr7 -O0 2>&1 | FileCheck %s
; RUN: llc < %s -verify-machineinstrs -mtriple=powerpc64-unknown-unkown \
; RUN: -mcpu=pwr7 2>&1 | FileCheck %s
; RUN: -mcpu=pwr7 -O0 2>&1 | FileCheck %s

define void @test_r1_clobber() {
entry:
Expand All @@ -20,3 +20,24 @@ entry:

; CHECK: warning: inline asm clobber list contains reserved registers: X1
; CHECK-NEXT: note: Reserved registers on the clobber list may not be preserved across the asm statement, and clobbering them may lead to undefined behaviour.

; CHECK: warning: inline asm clobber list contains reserved registers: R31
; CHECK-NEXT: note: Reserved registers on the clobber list may not be preserved across the asm statement, and clobbering them may lead to undefined behaviour.

@a = dso_local global i32 100, align 4
define dso_local signext i32 @main() {
entry:
%retval = alloca i32, align 4
%old = alloca i64, align 8
store i32 0, ptr %retval, align 4
call void asm sideeffect "li 31, 1", "~{r31}"()
call void asm sideeffect "li 30, 1", "~{r30}"()
%0 = call i64 asm sideeffect "mr $0, 31", "=r"()
store i64 %0, ptr %old, align 8
%1 = load i32, ptr @a, align 4
%conv = sext i32 %1 to i64
%2 = alloca i8, i64 %conv, align 16
%3 = load i64, ptr %old, align 8
%conv1 = trunc i64 %3 to i32
ret i32 %conv1
}
Loading
Loading