Skip to content

Greedy: Move physreg check when trying to recolor vregs (NFC) #160484

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
merged 3 commits into from
Oct 2, 2025
Merged

Greedy: Move physreg check when trying to recolor vregs (NFC) #160484

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a529dba
RegAllocGreedy: Check if copied lanes are live in trySplitAroundHintReg
arsenm Sep 23, 2025
661b22d
simplify boolean expression
arsenm Oct 2, 2025
9c6c1a9
Greedy: Move physreg check when trying to recolor vregs (NFC)
arsenm Sep 24, 2025
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
27 changes: 20 additions & 7 deletions llvm/lib/CodeGen/RegAllocGreedy.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1406,8 +1406,24 @@ bool RAGreedy::trySplitAroundHintReg(MCPhysReg Hint,
continue;

// Check if VirtReg interferes with OtherReg after this COPY instruction.
if (!IsDef && VirtReg.liveAt(LIS->getInstructionIndex(Instr).getRegSlot()))
continue;
if (Opnd.readsReg()) {
SlotIndex Index = LIS->getInstructionIndex(Instr).getRegSlot();

if (SubReg) {
LaneBitmask Mask = TRI->getSubRegIndexLaneMask(SubReg);
if (IsDef)
Mask = ~Mask;

if (any_of(VirtReg.subranges(), [=](const LiveInterval::SubRange &S) {
return (S.LaneMask & Mask).any() && S.liveAt(Index);
})) {
continue;
}
} else {
if (VirtReg.liveAt(Index))
continue;
}
}

MCRegister OtherPhysReg =
OtherReg.isPhysical() ? OtherReg.asMCReg() : VRM->getPhys(OtherReg);
Expand Down Expand Up @@ -2482,10 +2498,6 @@ void RAGreedy::tryHintRecoloring(const LiveInterval &VirtReg) {
do {
Reg = RecoloringCandidates.pop_back_val();

// We cannot recolor physical register.
if (Reg.isPhysical())
continue;

// This may be a skipped register.
if (!VRM->hasPhys(Reg)) {
assert(!shouldAllocateRegister(Reg) &&
Expand Down Expand Up @@ -2533,7 +2545,8 @@ void RAGreedy::tryHintRecoloring(const LiveInterval &VirtReg) {
// Push all copy-related live-ranges to keep reconciling the broken
// hints.
for (const HintInfo &HI : Info) {
if (Visited.insert(HI.Reg).second)
// We cannot recolor physical register.
if (HI.Reg.isVirtual() && Visited.insert(HI.Reg).second)
RecoloringCandidates.push_back(HI.Reg);
}
} while (!RecoloringCandidates.empty());
Expand Down
4 changes: 2 additions & 2 deletions llvm/test/CodeGen/SystemZ/fp-cmp-04.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -235,7 +235,7 @@ define half @f12_half(half %dummy, half %val, ptr %dest) {
; CHECK-NEXT: blah %f0
; CHECK-NEXT: #NO_APP
; CHECK-NEXT: brasl %r14, __extendhfsf2@PLT
; CHECK-NEXT: ltebr %f0, %f0
; CHECK-NEXT: ltebr %f1, %f0
; CHECK-NEXT: jl .LBB11_2
; CHECK-NEXT:# %bb.1:
; CHECK-NEXT: lgdr %r0, %f8
Expand Down Expand Up @@ -344,7 +344,7 @@ define half @f15_half(half %val, half %dummy, ptr %dest) {
; CHECK-NEXT: blah %f2
; CHECK-NEXT: #NO_APP
; CHECK-NEXT: brasl %r14, __extendhfsf2@PLT
; CHECK-NEXT: ltebr %f0, %f0
; CHECK-NEXT: ltebr %f1, %f0
; CHECK-NEXT: jl .LBB15_2
; CHECK-NEXT:# %bb.1:
; CHECK-NEXT: lgdr %r0, %f8
Expand Down
81 changes: 40 additions & 41 deletions llvm/test/CodeGen/X86/fshl.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -335,84 +335,83 @@ define i128 @var_shift_i128(i128 %x, i128 %y, i128 %z) nounwind {
; X86-SLOW-NEXT: pushl %esi
; X86-SLOW-NEXT: andl $-16, %esp
; X86-SLOW-NEXT: subl $32, %esp
; X86-SLOW-NEXT: movl 24(%ebp), %esi
; X86-SLOW-NEXT: movl 24(%ebp), %edi
; X86-SLOW-NEXT: movl 28(%ebp), %eax
; X86-SLOW-NEXT: movl 48(%ebp), %edx
; X86-SLOW-NEXT: movl 56(%ebp), %ecx
; X86-SLOW-NEXT: testb $64, %cl
; X86-SLOW-NEXT: movl 52(%ebp), %edi
; X86-SLOW-NEXT: movl 52(%ebp), %ebx
; X86-SLOW-NEXT: jne .LBB6_1
; X86-SLOW-NEXT: # %bb.2:
; X86-SLOW-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: movl %esi, %edx
; X86-SLOW-NEXT: movl 32(%ebp), %esi
; X86-SLOW-NEXT: movl %edi, %ecx
; X86-SLOW-NEXT: movl %eax, %edi
; X86-SLOW-NEXT: movl %edi, %edx
; X86-SLOW-NEXT: movl 32(%ebp), %edi
; X86-SLOW-NEXT: movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: movl %eax, %ebx
; X86-SLOW-NEXT: movl 36(%ebp), %eax
; X86-SLOW-NEXT: jmp .LBB6_3
; X86-SLOW-NEXT: .LBB6_1:
; X86-SLOW-NEXT: movl 40(%ebp), %ecx
; X86-SLOW-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: movl 44(%ebp), %ecx
; X86-SLOW-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: .LBB6_3:
; X86-SLOW-NEXT: movl 56(%ebp), %ebx
; X86-SLOW-NEXT: testb $32, %bl
; X86-SLOW-NEXT: movl 56(%ebp), %ecx
; X86-SLOW-NEXT: testb $32, %cl
; X86-SLOW-NEXT: jne .LBB6_4
; X86-SLOW-NEXT: # %bb.5:
; X86-SLOW-NEXT: movl %ecx, %ebx
; X86-SLOW-NEXT: movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: movl %edx, %edi
; X86-SLOW-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
; X86-SLOW-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: jmp .LBB6_6
; X86-SLOW-NEXT: .LBB6_4:
; X86-SLOW-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: movl %ecx, %edx
; X86-SLOW-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
; X86-SLOW-NEXT: movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: movl %edx, %ebx
; X86-SLOW-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
; X86-SLOW-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
; X86-SLOW-NEXT: .LBB6_6:
; X86-SLOW-NEXT: movl %edx, %esi
; X86-SLOW-NEXT: movl %edi, %eax
; X86-SLOW-NEXT: shll %cl, %eax
; X86-SLOW-NEXT: shrl %esi
; X86-SLOW-NEXT: movl %ecx, %edx
; X86-SLOW-NEXT: notb %dl
; X86-SLOW-NEXT: movl %edx, %ecx
; X86-SLOW-NEXT: shrl %cl, %esi
; X86-SLOW-NEXT: orl %eax, %esi
; X86-SLOW-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: movl %ebx, %eax
; X86-SLOW-NEXT: movl 56(%ebp), %ecx
; X86-SLOW-NEXT: shll %cl, %esi
; X86-SLOW-NEXT: movl %ebx, %edi
; X86-SLOW-NEXT: # kill: def $cl killed $cl killed $ecx
; X86-SLOW-NEXT: shll %cl, %eax
; X86-SLOW-NEXT: shrl %edi
; X86-SLOW-NEXT: movl %ecx, %ebx
; X86-SLOW-NEXT: notb %bl
; X86-SLOW-NEXT: movl %ebx, %ecx
; X86-SLOW-NEXT: movb %bl, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
; X86-SLOW-NEXT: movl %edx, %ecx
; X86-SLOW-NEXT: shrl %cl, %edi
; X86-SLOW-NEXT: orl %esi, %edi
; X86-SLOW-NEXT: orl %eax, %edi
; X86-SLOW-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
; X86-SLOW-NEXT: movl %esi, %eax
; X86-SLOW-NEXT: movl 56(%ebp), %ecx
; X86-SLOW-NEXT: # kill: def $cl killed $cl killed $ecx
; X86-SLOW-NEXT: shll %cl, %eax
; X86-SLOW-NEXT: shrl %edx
; X86-SLOW-NEXT: movl %ebx, %ecx
; X86-SLOW-NEXT: shrl %cl, %edx
; X86-SLOW-NEXT: orl %eax, %edx
; X86-SLOW-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
; X86-SLOW-NEXT: movl %ebx, %eax
; X86-SLOW-NEXT: shrl %ebx
; X86-SLOW-NEXT: movl %edx, %ecx
; X86-SLOW-NEXT: shrl %cl, %ebx
; X86-SLOW-NEXT: orl %eax, %ebx
; X86-SLOW-NEXT: movl 56(%ebp), %ecx
; X86-SLOW-NEXT: # kill: def $cl killed $cl killed $ecx
; X86-SLOW-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
; X86-SLOW-NEXT: shll %cl, %eax
; X86-SLOW-NEXT: shrl %esi
; X86-SLOW-NEXT: movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
; X86-SLOW-NEXT: movl %edx, %ecx
; X86-SLOW-NEXT: shrl %cl, %esi
; X86-SLOW-NEXT: orl %eax, %esi
; X86-SLOW-NEXT: movl 56(%ebp), %ecx
; X86-SLOW-NEXT: # kill: def $cl killed $cl killed $ecx
; X86-SLOW-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
; X86-SLOW-NEXT: shll %cl, %eax
; X86-SLOW-NEXT: shrl %ebx
; X86-SLOW-NEXT: movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
; X86-SLOW-NEXT: shrl %cl, %ebx
; X86-SLOW-NEXT: orl %eax, %ebx
; X86-SLOW-NEXT: movl 8(%ebp), %eax
; X86-SLOW-NEXT: movl %ebx, 12(%eax)
; X86-SLOW-NEXT: movl %esi, 8(%eax)
; X86-SLOW-NEXT: movl %edx, 4(%eax)
; X86-SLOW-NEXT: movl %edi, (%eax)
; X86-SLOW-NEXT: movl %esi, 12(%eax)
; X86-SLOW-NEXT: movl %ebx, 8(%eax)
; X86-SLOW-NEXT: movl %edi, 4(%eax)
; X86-SLOW-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
; X86-SLOW-NEXT: movl %ecx, (%eax)
; X86-SLOW-NEXT: leal -12(%ebp), %esp
; X86-SLOW-NEXT: popl %esi
; X86-SLOW-NEXT: popl %edi
Expand Down
90 changes: 45 additions & 45 deletions llvm/test/CodeGen/X86/fshr.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -322,79 +322,79 @@ define i128 @var_shift_i128(i128 %x, i128 %y, i128 %z) nounwind {
; X86-SLOW-NEXT: subl $16, %esp
; X86-SLOW-NEXT: movl 24(%ebp), %edx
; X86-SLOW-NEXT: movl 28(%ebp), %esi
; X86-SLOW-NEXT: movl 48(%ebp), %ebx
; X86-SLOW-NEXT: movl 48(%ebp), %edi
; X86-SLOW-NEXT: movl 56(%ebp), %eax
; X86-SLOW-NEXT: testb $64, %al
; X86-SLOW-NEXT: movl 52(%ebp), %edi
; X86-SLOW-NEXT: movl 52(%ebp), %eax
; X86-SLOW-NEXT: je .LBB6_1
; X86-SLOW-NEXT: # %bb.2:
; X86-SLOW-NEXT: movl %ebx, (%esp) # 4-byte Spill
; X86-SLOW-NEXT: movl %edx, %ebx
; X86-SLOW-NEXT: movl %edi, (%esp) # 4-byte Spill
; X86-SLOW-NEXT: movl %edx, %edi
; X86-SLOW-NEXT: movl 32(%ebp), %edx
; X86-SLOW-NEXT: movl %edi, %eax
; X86-SLOW-NEXT: movl %esi, %edi
; X86-SLOW-NEXT: movl %eax, %ecx
; X86-SLOW-NEXT: movl %esi, %eax
; X86-SLOW-NEXT: movl 36(%ebp), %esi
; X86-SLOW-NEXT: jmp .LBB6_3
; X86-SLOW-NEXT: .LBB6_1:
; X86-SLOW-NEXT: movl 40(%ebp), %eax
; X86-SLOW-NEXT: movl %eax, (%esp) # 4-byte Spill
; X86-SLOW-NEXT: movl 44(%ebp), %eax
; X86-SLOW-NEXT: movl 40(%ebp), %ecx
; X86-SLOW-NEXT: movl %ecx, (%esp) # 4-byte Spill
; X86-SLOW-NEXT: movl 44(%ebp), %ecx
; X86-SLOW-NEXT: .LBB6_3:
; X86-SLOW-NEXT: movl 56(%ebp), %ecx
; X86-SLOW-NEXT: testb $32, %cl
; X86-SLOW-NEXT: movl 56(%ebp), %ebx
; X86-SLOW-NEXT: testb $32, %bl
; X86-SLOW-NEXT: je .LBB6_4
; X86-SLOW-NEXT: # %bb.5:
; X86-SLOW-NEXT: movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: movl %ecx, %ebx
; X86-SLOW-NEXT: jmp .LBB6_6
; X86-SLOW-NEXT: .LBB6_4:
; X86-SLOW-NEXT: movl %edx, %esi
; X86-SLOW-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: movl %eax, %ebx
; X86-SLOW-NEXT: movl (%esp), %eax # 4-byte Reload
; X86-SLOW-NEXT: movl %ecx, %edi
; X86-SLOW-NEXT: movl (%esp), %ebx # 4-byte Reload
; X86-SLOW-NEXT: .LBB6_6:
; X86-SLOW-NEXT: shrl %cl, %eax
; X86-SLOW-NEXT: movl %eax, %edx
; X86-SLOW-NEXT: movl %ecx, %eax
; X86-SLOW-NEXT: notb %al
; X86-SLOW-NEXT: movl %ebx, %edi
; X86-SLOW-NEXT: addl %ebx, %ebx
; X86-SLOW-NEXT: movl %eax, %ecx
; X86-SLOW-NEXT: shll %cl, %ebx
; X86-SLOW-NEXT: orl %edx, %ebx
; X86-SLOW-NEXT: movl %ebx, (%esp) # 4-byte Spill
; X86-SLOW-NEXT: movl 56(%ebp), %ecx
; X86-SLOW-NEXT: # kill: def $cl killed $cl killed $ecx
; X86-SLOW-NEXT: shrl %cl, %edi
; X86-SLOW-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
; X86-SLOW-NEXT: leal (%ebx,%ebx), %edx
; X86-SLOW-NEXT: movl %eax, %ecx
; X86-SLOW-NEXT: shll %cl, %edx
; X86-SLOW-NEXT: orl %edi, %edx
; X86-SLOW-NEXT: shrl %cl, %ebx
; X86-SLOW-NEXT: movl %ecx, %edx
; X86-SLOW-NEXT: notb %dl
; X86-SLOW-NEXT: movl %edi, %eax
; X86-SLOW-NEXT: addl %edi, %edi
; X86-SLOW-NEXT: movl %edx, %ecx
; X86-SLOW-NEXT: shll %cl, %edi
; X86-SLOW-NEXT: orl %ebx, %edi
; X86-SLOW-NEXT: movl %edi, (%esp) # 4-byte Spill
; X86-SLOW-NEXT: movl 56(%ebp), %ecx
; X86-SLOW-NEXT: # kill: def $cl killed $cl killed $ecx
; X86-SLOW-NEXT: shrl %cl, %ebx
; X86-SLOW-NEXT: movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: shrl %cl, %eax
; X86-SLOW-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
; X86-SLOW-NEXT: leal (%edi,%edi), %ebx
; X86-SLOW-NEXT: movl %eax, %ecx
; X86-SLOW-NEXT: movl %edx, %ecx
; X86-SLOW-NEXT: shll %cl, %ebx
; X86-SLOW-NEXT: orl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
; X86-SLOW-NEXT: orl %eax, %ebx
; X86-SLOW-NEXT: movl 56(%ebp), %ecx
; X86-SLOW-NEXT: # kill: def $cl killed $cl killed $ecx
; X86-SLOW-NEXT: shrl %cl, %edi
; X86-SLOW-NEXT: movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
; X86-SLOW-NEXT: leal (%eax,%eax), %edi
; X86-SLOW-NEXT: movl %edx, %ecx
; X86-SLOW-NEXT: shll %cl, %edi
; X86-SLOW-NEXT: orl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
; X86-SLOW-NEXT: movl 56(%ebp), %ecx
; X86-SLOW-NEXT: # kill: def $cl killed $cl killed $ecx
; X86-SLOW-NEXT: shrl %cl, %eax
; X86-SLOW-NEXT: addl %esi, %esi
; X86-SLOW-NEXT: movl %eax, %ecx
; X86-SLOW-NEXT: movl %edx, %ecx
; X86-SLOW-NEXT: shll %cl, %esi
; X86-SLOW-NEXT: orl %edi, %esi
; X86-SLOW-NEXT: movl 8(%ebp), %ecx
; X86-SLOW-NEXT: movl %esi, 12(%ecx)
; X86-SLOW-NEXT: movl %ebx, 8(%ecx)
; X86-SLOW-NEXT: movl %edx, 4(%ecx)
; X86-SLOW-NEXT: movl (%esp), %eax # 4-byte Reload
; X86-SLOW-NEXT: movl %eax, (%ecx)
; X86-SLOW-NEXT: movl %ecx, %eax
; X86-SLOW-NEXT: orl %eax, %esi
; X86-SLOW-NEXT: movl 8(%ebp), %eax
; X86-SLOW-NEXT: movl %esi, 12(%eax)
; X86-SLOW-NEXT: movl %edi, 8(%eax)
; X86-SLOW-NEXT: movl %ebx, 4(%eax)
; X86-SLOW-NEXT: movl (%esp), %ecx # 4-byte Reload
; X86-SLOW-NEXT: movl %ecx, (%eax)
; X86-SLOW-NEXT: leal -12(%ebp), %esp
; X86-SLOW-NEXT: popl %esi
; X86-SLOW-NEXT: popl %edi
Expand Down
Loading