Skip to content

[CodeGen] Register-coalescer remat fix subreg liveness #165662

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 6 commits into from
Nov 5, 2025
Merged

[CodeGen] Register-coalescer remat fix subreg liveness #165662

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
64bbd4b
[CodeGen] Register-coalescer remat fix subreg liveness
VigneshwarJ Oct 30, 2025
54060b3
fix tests
VigneshwarJ Oct 30, 2025
74bdb76
review comments
VigneshwarJ Oct 30, 2025
4df78bb
updated tests
VigneshwarJ Nov 3, 2025
8e64e71
changed to refineSubrange
VigneshwarJ Nov 4, 2025
6ef4f65
added one more test
VigneshwarJ Nov 5, 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
1 change: 1 addition & 0 deletions llvm/lib/CodeGen/RegisterCoalescer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1625,6 +1625,7 @@ bool RegisterCoalescer::reMaterializeDef(const CoalescerPair &CP,
// dead def so that the interferences are properly modeled.
if (!SR.liveAt(DefIndex))
SR.createDeadDef(DefIndex, Alloc);
SR.LaneMask = DstMask & SR.LaneMask;
}
}
if (UpdatedSubRanges)
Expand Down
78 changes: 78 additions & 0 deletions llvm/test/CodeGen/AMDGPU/reg-coalescer-subreg-liveness.mir
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,78 @@
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 6
# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1250 -run-pass=register-coalescer -verify-coalescing -o - %s | FileCheck %s

# This test is to check fix for failure with "Bad machine code: Defining instruction does not modify register" due to corrupt lane mask.

---
name: reg_coalescer_subreg_liveness
tracksRegLiveness: true
liveins:
body: |
; CHECK-LABEL: name: reg_coalescer_subreg_liveness
; CHECK: bb.0:
; CHECK-NEXT: successors: %bb.1(0x80000000)
; CHECK-NEXT: liveins: $sgpr4_sgpr5
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5
; CHECK-NEXT: undef [[S_LOAD_DWORD_IMM:%[0-9]+]].sub1:sgpr_128 = S_LOAD_DWORD_IMM [[COPY]], 0, 0 :: (dereferenceable invariant load (s32), align 16, addrspace 4)
; CHECK-NEXT: undef [[S_MOV_B32_:%[0-9]+]].sub0:sgpr_128 = S_MOV_B32 1
; CHECK-NEXT: undef [[S_MOV_B32_1:%[0-9]+]].sub0:sgpr_256 = S_MOV_B32 0
; CHECK-NEXT: TENSOR_LOAD_TO_LDS_D2 [[S_MOV_B32_]], [[S_MOV_B32_1]], 0, 0, implicit-def dead $tensorcnt, implicit $exec, implicit $tensorcnt
; CHECK-NEXT: [[S_LOAD_DWORD_IMM:%[0-9]+]].sub0:sgpr_128 = S_MOV_B32 1
; CHECK-NEXT: [[S_MOV_B32_:%[0-9]+]].sub1:sgpr_128 = COPY [[S_MOV_B32_]].sub0
; CHECK-NEXT: [[S_LOAD_DWORD_IMM:%[0-9]+]].sub2:sgpr_128 = S_MOV_B32 0
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.1:
; CHECK-NEXT: successors: %bb.1(0x40000000), %bb.2(0x40000000)
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[S_MOV_B32_:%[0-9]+]].sub2:sgpr_128 = COPY [[S_MOV_B32_]].sub0
; CHECK-NEXT: [[S_MOV_B32_:%[0-9]+]].sub3:sgpr_128 = COPY [[S_MOV_B32_]].sub0
; CHECK-NEXT: TENSOR_LOAD_TO_LDS_D2 [[S_MOV_B32_]], [[S_MOV_B32_1]], 0, 0, implicit-def dead $tensorcnt, implicit $exec, implicit $tensorcnt
; CHECK-NEXT: TENSOR_LOAD_TO_LDS_D2 [[S_LOAD_DWORD_IMM]], [[S_MOV_B32_1]], 0, 0, implicit-def dead $tensorcnt, implicit $exec, implicit $tensorcnt
; CHECK-NEXT: $vcc_lo = COPY $exec_lo
; CHECK-NEXT: [[S_MOV_B32_:%[0-9]+]].sub1:sgpr_128 = S_MOV_B32 0
; CHECK-NEXT: [[S_LOAD_DWORD_IMM:%[0-9]+]].sub2:sgpr_128 = S_MOV_B32 1
; CHECK-NEXT: S_CBRANCH_VCCNZ %bb.1, implicit killed $vcc_lo, implicit $vcc_lo, implicit $vcc_lo
; CHECK-NEXT: S_BRANCH %bb.2
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.2:
; CHECK-NEXT: S_ENDPGM 0
bb.0:
successors: %bb.1(0x80000000)
liveins: $sgpr4_sgpr5

%0:sgpr_64 = COPY killed $sgpr4_sgpr5
%1:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM killed %0, 0, 0 :: (dereferenceable invariant load (s32), align 16, addrspace 4)
%2:sreg_32 = S_MOV_B32 1
undef %3.sub0:sgpr_128 = COPY %2
%4:sreg_32 = S_MOV_B32 0
undef %5.sub0:sgpr_256 = COPY %4
TENSOR_LOAD_TO_LDS_D2 %3, %5, 0, 0, implicit-def dead $tensorcnt, implicit $exec, implicit $tensorcnt
%6:sgpr_128 = COPY killed %3
%6.sub1:sgpr_128 = COPY killed %1
%7:sreg_32 = COPY $exec_lo
%8:sreg_32 = COPY %2
%9:sreg_32 = COPY %4

bb.1:
successors: %bb.1(0x40000000), %bb.2(0x40000000)

%10:sreg_32 = COPY killed %8
undef %11.sub0:sgpr_128 = COPY %2
%11.sub1:sgpr_128 = COPY killed %10
%11.sub2:sgpr_128 = COPY %2
%11.sub3:sgpr_128 = COPY %2
TENSOR_LOAD_TO_LDS_D2 killed %11, %5, 0, 0, implicit-def dead $tensorcnt, implicit $exec, implicit $tensorcnt
%12:sreg_32 = COPY killed %9
%13:sgpr_128 = COPY %6
%13.sub2:sgpr_128 = COPY killed %12
TENSOR_LOAD_TO_LDS_D2 killed %13, %5, 0, 0, implicit-def dead $tensorcnt, implicit $exec, implicit $tensorcnt
$vcc_lo = COPY %7
%8:sreg_32 = COPY %4
%9:sreg_32 = COPY %2
S_CBRANCH_VCCNZ %bb.1, implicit killed $vcc_lo, implicit $vcc_lo, implicit $vcc
S_BRANCH %bb.2

bb.2:
S_ENDPGM 0
...
4 changes: 2 additions & 2 deletions llvm/test/CodeGen/SystemZ/regcoal_remat_empty_subrange.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,10 +22,10 @@ define void @main(i16 %in) {
; CHECK-NEXT: locghile %r3, 1
; CHECK-NEXT: o %r0, 0(%r1)
; CHECK-NEXT: larl %r1, g_222
; CHECK-NEXT: lghi %r5, 0
; CHECK-NEXT: dsgfr %r2, %r0
; CHECK-NEXT: lghi %r3, 0
; CHECK-NEXT: stgrl %r2, g_39
; CHECK-NEXT: stc %r5, 19(%r1)
; CHECK-NEXT: stc %r3, 19(%r1)
; CHECK-NEXT: br %r14
%tmp = load i32, ptr @g_151, align 4
%tmp3 = or i32 %tmp, 1
Expand Down
Loading