LiveRangeEdit: Clear all dead flags when rematerializing #73933
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
It's allowed to rematerialize instructions with implicit-defs of the same register as the single explicit def. If this happened, it was only clearing the dead flags on the one main result.
|
@llvm/pr-subscribers-backend-aarch64 @llvm/pr-subscribers-llvm-regalloc Author: Matt Arsenault (arsenm) ChangesIt's allowed to rematerialize instructions with implicit-defs of the same register as the single explicit def. If this happened, it was only clearing the dead flags on the one main result. Full diff: https://github.com/llvm/llvm-project/pull/73933.diff 3 Files Affected:
diff --git a/llvm/lib/CodeGen/LiveRangeEdit.cpp b/llvm/lib/CodeGen/LiveRangeEdit.cpp
index ff49e080090c2bd..0203034b5a01474 100644
--- a/llvm/lib/CodeGen/LiveRangeEdit.cpp
+++ b/llvm/lib/CodeGen/LiveRangeEdit.cpp
@@ -190,7 +190,7 @@ SlotIndex LiveRangeEdit::rematerializeAt(MachineBasicBlock &MBB,
// DestReg of the cloned instruction cannot be Dead. Set isDead of DestReg
// to false anyway in case the isDead flag of RM.OrigMI's dest register
// is true.
- (*--MI).getOperand(0).setIsDead(false);
+ (*--MI).clearRegisterDeads(DestReg);
Rematted.insert(RM.ParentVNI);
++NumReMaterialization;
diff --git a/llvm/test/CodeGen/AArch64/clear-dead-implicit-def-impdef.ll b/llvm/test/CodeGen/AArch64/clear-dead-implicit-def-impdef.ll
new file mode 100644
index 000000000000000..bc26eca6f27ef8e
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/clear-dead-implicit-def-impdef.ll
@@ -0,0 +1,125 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
+; RUN: llc -mtriple=arm64-apple-macosx10.13.0 -mcpu=apple-m1 < %s | FileCheck %s
+
+@.str = external constant [9 x i8]
+
+define void @_ZN38SanitizerCommonInterceptors_Scanf_Test8TestBodyEv(ptr %.str.40, ptr %.str.41, ptr %.str.42, ptr %.str.43, ptr %.str.44, ptr %.str.45, ptr nocapture writeonly %.str.47) nounwind {
+; CHECK-LABEL: _ZN38SanitizerCommonInterceptors_Scanf_Test8TestBodyEv:
+; CHECK: ; %bb.0: ; %entry
+; CHECK-NEXT: sub sp, sp, #128
+; CHECK-NEXT: stp x28, x27, [sp, #32] ; 16-byte Folded Spill
+; CHECK-NEXT: stp x26, x25, [sp, #48] ; 16-byte Folded Spill
+; CHECK-NEXT: stp x24, x23, [sp, #64] ; 16-byte Folded Spill
+; CHECK-NEXT: stp x22, x21, [sp, #80] ; 16-byte Folded Spill
+; CHECK-NEXT: stp x20, x19, [sp, #96] ; 16-byte Folded Spill
+; CHECK-NEXT: stp x29, x30, [sp, #112] ; 16-byte Folded Spill
+; CHECK-NEXT: mov x24, x6
+; CHECK-NEXT: mov x19, x5
+; CHECK-NEXT: mov x20, x4
+; CHECK-NEXT: mov x21, x3
+; CHECK-NEXT: mov x22, x2
+; CHECK-NEXT: mov x23, x1
+; CHECK-NEXT: mov x25, x0
+; CHECK-NEXT: str xzr, [sp]
+; CHECK-NEXT: mov x0, #0 ; =0x0
+; CHECK-NEXT: mov w1, #1 ; =0x1
+; CHECK-NEXT: bl __ZL9testScanfPKcjz
+; CHECK-NEXT: mov w28, #4 ; =0x4
+; CHECK-NEXT: stp x28, x28, [sp, #8]
+; CHECK-NEXT: str x28, [sp]
+; CHECK-NEXT: mov x0, #0 ; =0x0
+; CHECK-NEXT: mov w1, #0 ; =0x0
+; CHECK-NEXT: bl __ZL9testScanfPKcjz
+; CHECK-NEXT: stp x28, xzr, [sp]
+; CHECK-NEXT: mov x0, #0 ; =0x0
+; CHECK-NEXT: mov w1, #0 ; =0x0
+; CHECK-NEXT: bl __ZL9testScanfPKcjz
+; CHECK-NEXT: mov w27, #8 ; =0x8
+; CHECK-NEXT: str x27, [sp]
+; CHECK-NEXT: mov x0, #0 ; =0x0
+; CHECK-NEXT: mov w1, #0 ; =0x0
+; CHECK-NEXT: bl __ZL9testScanfPKcjz
+; CHECK-NEXT: mov w26, #1 ; =0x1
+; CHECK-NEXT: stp xzr, x26, [sp]
+; CHECK-NEXT: mov x0, #0 ; =0x0
+; CHECK-NEXT: mov w1, #0 ; =0x0
+; CHECK-NEXT: bl __ZL9testScanfPKcjz
+; CHECK-NEXT: str x26, [sp]
+; CHECK-NEXT: mov x0, #0 ; =0x0
+; CHECK-NEXT: mov w1, #0 ; =0x0
+; CHECK-NEXT: bl __ZL9testScanfPKcjz
+; CHECK-NEXT: str x28, [sp]
+; CHECK-NEXT: Lloh0:
+; CHECK-NEXT: adrp x26, _.str@GOTPAGE
+; CHECK-NEXT: Lloh1:
+; CHECK-NEXT: ldr x26, [x26, _.str@GOTPAGEOFF]
+; CHECK-NEXT: mov x0, x26
+; CHECK-NEXT: mov w1, #0 ; =0x0
+; CHECK-NEXT: bl __ZL9testScanfPKcjz
+; CHECK-NEXT: str wzr, [x24]
+; CHECK-NEXT: str x27, [sp]
+; CHECK-NEXT: mov x0, x25
+; CHECK-NEXT: mov w1, #0 ; =0x0
+; CHECK-NEXT: bl __ZL20testScanfNoGnuMallocPKcjz
+; CHECK-NEXT: str x28, [sp]
+; CHECK-NEXT: mov x0, x23
+; CHECK-NEXT: mov w1, #0 ; =0x0
+; CHECK-NEXT: bl __ZL20testScanfNoGnuMallocPKcjz
+; CHECK-NEXT: str x28, [sp]
+; CHECK-NEXT: mov x0, x22
+; CHECK-NEXT: mov w1, #0 ; =0x0
+; CHECK-NEXT: bl __ZL20testScanfNoGnuMallocPKcjz
+; CHECK-NEXT: str x28, [sp]
+; CHECK-NEXT: mov x0, x21
+; CHECK-NEXT: mov w1, #0 ; =0x0
+; CHECK-NEXT: bl __ZL20testScanfNoGnuMallocPKcjz
+; CHECK-NEXT: str x28, [sp]
+; CHECK-NEXT: mov x0, x20
+; CHECK-NEXT: mov w1, #0 ; =0x0
+; CHECK-NEXT: bl __ZL20testScanfNoGnuMallocPKcjz
+; CHECK-NEXT: str xzr, [sp]
+; CHECK-NEXT: mov x0, x19
+; CHECK-NEXT: mov w1, #0 ; =0x0
+; CHECK-NEXT: bl __ZL20testScanfNoGnuMallocPKcjz
+; CHECK-NEXT: str xzr, [sp]
+; CHECK-NEXT: mov x0, x26
+; CHECK-NEXT: mov w1, #0 ; =0x0
+; CHECK-NEXT: bl __ZL20testScanfNoGnuMallocPKcjz
+; CHECK-NEXT: mov w8, #1 ; =0x1
+; CHECK-NEXT: stp x8, xzr, [sp, #8]
+; CHECK-NEXT: str xzr, [sp]
+; CHECK-NEXT: mov x0, #0 ; =0x0
+; CHECK-NEXT: mov w1, #0 ; =0x0
+; CHECK-NEXT: bl __ZL20testScanfNoGnuMallocPKcjz
+; CHECK-NEXT: ldp x29, x30, [sp, #112] ; 16-byte Folded Reload
+; CHECK-NEXT: ldp x20, x19, [sp, #96] ; 16-byte Folded Reload
+; CHECK-NEXT: ldp x22, x21, [sp, #80] ; 16-byte Folded Reload
+; CHECK-NEXT: ldp x24, x23, [sp, #64] ; 16-byte Folded Reload
+; CHECK-NEXT: ldp x26, x25, [sp, #48] ; 16-byte Folded Reload
+; CHECK-NEXT: ldp x28, x27, [sp, #32] ; 16-byte Folded Reload
+; CHECK-NEXT: add sp, sp, #128
+; CHECK-NEXT: ret
+; CHECK-NEXT: .loh AdrpLdrGot Lloh0, Lloh1
+entry:
+ tail call void (ptr, i32, ...) @_ZL9testScanfPKcjz(ptr null, i32 1, i32 0)
+ tail call void (ptr, i32, ...) @_ZL9testScanfPKcjz(ptr null, i32 0, i32 4, i32 4, i32 4)
+ tail call void (ptr, i32, ...) @_ZL9testScanfPKcjz(ptr null, i32 0, i32 4, i32 0)
+ tail call void (ptr, i32, ...) @_ZL9testScanfPKcjz(ptr null, i32 0, i32 8)
+ tail call void (ptr, i32, ...) @_ZL9testScanfPKcjz(ptr null, i32 0, i32 0, i32 1)
+ tail call void (ptr, i32, ...) @_ZL9testScanfPKcjz(ptr null, i32 0, i32 1)
+ tail call void (ptr, i32, ...) @_ZL9testScanfPKcjz(ptr nonnull @.str, i32 0, i32 4)
+ store i32 0, ptr %.str.47, align 4
+ tail call void (ptr, i32, ...) @_ZL20testScanfNoGnuMallocPKcjz(ptr %.str.40, i32 0, i32 8)
+ tail call void (ptr, i32, ...) @_ZL20testScanfNoGnuMallocPKcjz(ptr %.str.41, i32 0, i32 4)
+ tail call void (ptr, i32, ...) @_ZL20testScanfNoGnuMallocPKcjz(ptr %.str.42, i32 0, i32 4)
+ tail call void (ptr, i32, ...) @_ZL20testScanfNoGnuMallocPKcjz(ptr %.str.43, i32 0, i32 4)
+ tail call void (ptr, i32, ...) @_ZL20testScanfNoGnuMallocPKcjz(ptr %.str.44, i32 0, i32 4)
+ tail call void (ptr, i32, ...) @_ZL20testScanfNoGnuMallocPKcjz(ptr %.str.45, i32 0, i32 0)
+ tail call void (ptr, i32, ...) @_ZL20testScanfNoGnuMallocPKcjz(ptr nonnull @.str, i32 0, i32 0)
+ tail call void (ptr, i32, ...) @_ZL20testScanfNoGnuMallocPKcjz(ptr null, i32 0, i32 0, i32 1, i32 0)
+ ret void
+}
+
+declare void @_ZL9testScanfPKcjz(ptr, i32, ...) local_unnamed_addr
+
+declare void @_ZL20testScanfNoGnuMallocPKcjz(ptr, i32, ...) local_unnamed_addr
diff --git a/llvm/test/CodeGen/AArch64/clear-dead-implicit-def-impdef.mir b/llvm/test/CodeGen/AArch64/clear-dead-implicit-def-impdef.mir
new file mode 100644
index 000000000000000..9040937d027df48
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/clear-dead-implicit-def-impdef.mir
@@ -0,0 +1,119 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 4
+# RUN: llc -mtriple=arm64-apple-macosx -mcpu=apple-m1 -verify-regalloc -run-pass=greedy -o - %s | FileCheck %s
+---
+name: func
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $x0, $x1, $x2, $x3, $x4, $x5, $x6
+
+ ; CHECK-LABEL: name: func
+ ; CHECK: liveins: $x0, $x1, $x2, $x3, $x4, $x5, $x6
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[DEF:%[0-9]+]]:gpr64sp = IMPLICIT_DEF
+ ; CHECK-NEXT: dead [[DEF1:%[0-9]+]]:gpr32 = IMPLICIT_DEF
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:gpr64common = COPY $x0
+ ; CHECK-NEXT: [[COPY1:%[0-9]+]]:gpr64 = COPY $x1
+ ; CHECK-NEXT: [[COPY2:%[0-9]+]]:gpr64 = COPY $x2
+ ; CHECK-NEXT: [[COPY3:%[0-9]+]]:gpr64 = COPY $x3
+ ; CHECK-NEXT: [[COPY4:%[0-9]+]]:gpr64 = COPY $x4
+ ; CHECK-NEXT: [[COPY5:%[0-9]+]]:gpr64 = COPY $x5
+ ; CHECK-NEXT: [[COPY6:%[0-9]+]]:gpr64 = COPY $x6
+ ; CHECK-NEXT: undef [[MOVi32imm:%[0-9]+]].sub_32:gpr64 = MOVi32imm 4, implicit-def [[MOVi32imm]]
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 8, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: BL 0, csr_darwin_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit-def $sp
+ ; CHECK-NEXT: ADJCALLSTACKUP 8, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 24, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: ADJCALLSTACKUP 24, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 16, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: ADJCALLSTACKUP 16, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 8, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: [[DEF2:%[0-9]+]]:gpr64 = IMPLICIT_DEF
+ ; CHECK-NEXT: ADJCALLSTACKUP 8, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 16, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: undef [[DEF3:%[0-9]+]].sub_32:gpr64 = IMPLICIT_DEF implicit-def [[DEF3]]
+ ; CHECK-NEXT: STRXui [[DEF3]], [[DEF]], 1 :: (store (s64) into stack + 8)
+ ; CHECK-NEXT: BL 0, csr_darwin_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit-def $sp
+ ; CHECK-NEXT: ADJCALLSTACKUP 16, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 8, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: STRXui [[MOVi32imm]], [[DEF]], 0 :: (store (s64) into stack)
+ ; CHECK-NEXT: ADJCALLSTACKUP 8, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: STRWui undef [[MOVi32imm]].sub_32, [[COPY]], 0 :: (store (s32))
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 8, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: STRXui [[DEF2]], undef [[DEF]], 0 :: (store (s64) into stack)
+ ; CHECK-NEXT: $x0 = COPY [[COPY6]]
+ ; CHECK-NEXT: ADJCALLSTACKUP 8, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 8, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: $x0 = COPY [[COPY5]]
+ ; CHECK-NEXT: ADJCALLSTACKUP 8, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 8, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: $x0 = COPY [[COPY4]]
+ ; CHECK-NEXT: ADJCALLSTACKUP 8, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 8, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: $x0 = COPY [[COPY3]]
+ ; CHECK-NEXT: ADJCALLSTACKUP 8, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 8, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: $x0 = COPY [[COPY2]]
+ ; CHECK-NEXT: ADJCALLSTACKUP 8, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 8, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: $x0 = COPY [[COPY1]]
+ ; CHECK-NEXT: ADJCALLSTACKUP 8, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: ADJCALLSTACKDOWN 24, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: undef [[DEF4:%[0-9]+]].sub_32:gpr64 = IMPLICIT_DEF implicit-def [[DEF4]]
+ ; CHECK-NEXT: STRXui [[DEF4]], undef [[DEF]], 1 :: (store (s64) into stack + 8)
+ ; CHECK-NEXT: ADJCALLSTACKUP 24, 0, implicit-def dead $sp, implicit $sp
+ ; CHECK-NEXT: RET_ReallyLR
+ %0:gpr64sp = IMPLICIT_DEF
+ undef %13.sub_32:gpr64 = IMPLICIT_DEF implicit-def %13
+ dead %2:gpr32 = IMPLICIT_DEF
+ %3:gpr64common = COPY $x0
+ %4:gpr64 = COPY $x1
+ %5:gpr64 = COPY $x2
+ %6:gpr64 = COPY $x3
+ %7:gpr64 = COPY $x4
+ %8:gpr64 = COPY $x5
+ %9:gpr64 = COPY $x6
+ undef %11.sub_32:gpr64 = MOVi32imm 4, implicit-def %11
+ ADJCALLSTACKDOWN 8, 0, implicit-def dead $sp, implicit $sp
+ BL 0, csr_darwin_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit-def $sp
+ ADJCALLSTACKUP 8, 0, implicit-def dead $sp, implicit $sp
+ ADJCALLSTACKDOWN 24, 0, implicit-def dead $sp, implicit $sp
+ ADJCALLSTACKUP 24, 0, implicit-def dead $sp, implicit $sp
+ ADJCALLSTACKDOWN 16, 0, implicit-def dead $sp, implicit $sp
+ ADJCALLSTACKUP 16, 0, implicit-def dead $sp, implicit $sp
+ ADJCALLSTACKDOWN 8, 0, implicit-def dead $sp, implicit $sp
+ %12:gpr64 = IMPLICIT_DEF
+ ADJCALLSTACKUP 8, 0, implicit-def dead $sp, implicit $sp
+ ADJCALLSTACKDOWN 16, 0, implicit-def dead $sp, implicit $sp
+ STRXui %13, %0, 1 :: (store (s64) into stack + 8)
+ BL 0, csr_darwin_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit-def $sp
+ ADJCALLSTACKUP 16, 0, implicit-def dead $sp, implicit $sp
+ ADJCALLSTACKDOWN 8, 0, implicit-def dead $sp, implicit $sp
+ STRXui %11, %0, 0 :: (store (s64) into stack)
+ ADJCALLSTACKUP 8, 0, implicit-def dead $sp, implicit $sp
+ STRWui undef %11.sub_32, %3, 0 :: (store (s32))
+ ADJCALLSTACKDOWN 8, 0, implicit-def dead $sp, implicit $sp
+ STRXui %12, undef %0, 0 :: (store (s64) into stack)
+ $x0 = COPY %9
+ ADJCALLSTACKUP 8, 0, implicit-def dead $sp, implicit $sp
+ ADJCALLSTACKDOWN 8, 0, implicit-def dead $sp, implicit $sp
+ $x0 = COPY %8
+ ADJCALLSTACKUP 8, 0, implicit-def dead $sp, implicit $sp
+ ADJCALLSTACKDOWN 8, 0, implicit-def dead $sp, implicit $sp
+ $x0 = COPY %7
+ ADJCALLSTACKUP 8, 0, implicit-def dead $sp, implicit $sp
+ ADJCALLSTACKDOWN 8, 0, implicit-def dead $sp, implicit $sp
+ $x0 = COPY %6
+ ADJCALLSTACKUP 8, 0, implicit-def dead $sp, implicit $sp
+ ADJCALLSTACKDOWN 8, 0, implicit-def dead $sp, implicit $sp
+ $x0 = COPY %5
+ ADJCALLSTACKUP 8, 0, implicit-def dead $sp, implicit $sp
+ ADJCALLSTACKDOWN 8, 0, implicit-def dead $sp, implicit $sp
+ $x0 = COPY %4
+ ADJCALLSTACKUP 8, 0, implicit-def dead $sp, implicit $sp
+ ADJCALLSTACKDOWN 24, 0, implicit-def dead $sp, implicit $sp
+ STRXui %13, undef %0, 1 :: (store (s64) into stack + 8)
+ ADJCALLSTACKUP 24, 0, implicit-def dead $sp, implicit $sp
+ RET_ReallyLR
+
+...
|
kparzysz
approved these changes
Dec 1, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
It's allowed to rematerialize instructions with implicit-defs of the same register as the single explicit def. If this happened, it was only clearing the dead flags on the one main result.