[llvm] [HEXAGON] Fix corner cases for hwloops pass (PR #135439)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Apr 11 17:42:57 PDT 2025
https://github.com/aankit-quic updated https://github.com/llvm/llvm-project/pull/135439
>From d13e1915c3c73c3bec4e2f908b86917e9d52bd0c Mon Sep 17 00:00:00 2001
From: aankit-quic <aankit at quicinc.com>
Date: Tue, 1 Apr 2025 10:57:14 -0700
Subject: [PATCH 1/2] [HEXAGON] Fix corner cases for hwloops pass
Add check to make sure Dist > 0 or Dist < 0 for appropriate cmp
cases to hexagon hardware loops pass. The change modifies the
HexagonHardwareLoops pass to add runtime checks to make sure that
end_value > initial_value for less than comparisons and
end_value < initial_value for greater than comparisons.
Change-Id: Ie4b3666ecf69b7aebeb6cfaa48535063677f929c
---
.../Target/Hexagon/HexagonHardwareLoops.cpp | 46 ++-
.../CodeGen/Hexagon/hwloop-dist-check.mir | 281 ++++++++++++++++++
llvm/test/CodeGen/Hexagon/swp-phi-start.ll | 5 +-
3 files changed, 329 insertions(+), 3 deletions(-)
create mode 100644 llvm/test/CodeGen/Hexagon/hwloop-dist-check.mir
diff --git a/llvm/lib/Target/Hexagon/HexagonHardwareLoops.cpp b/llvm/lib/Target/Hexagon/HexagonHardwareLoops.cpp
index 743991447ad1f..67fd03f7ba376 100644
--- a/llvm/lib/Target/Hexagon/HexagonHardwareLoops.cpp
+++ b/llvm/lib/Target/Hexagon/HexagonHardwareLoops.cpp
@@ -731,6 +731,11 @@ CountValue *HexagonHardwareLoops::computeCount(MachineLoop *Loop,
Register IVReg,
int64_t IVBump,
Comparison::Kind Cmp) const {
+ LLVM_DEBUG(llvm::dbgs() << "Loop: " << *Loop << "\n");
+ LLVM_DEBUG(llvm::dbgs() << "Initial Value: " << *Start << "\n");
+ LLVM_DEBUG(llvm::dbgs() << "End Value: " << *End << "\n");
+ LLVM_DEBUG(llvm::dbgs() << "Inc/Dec Value: " << IVBump << "\n");
+ LLVM_DEBUG(llvm::dbgs() << "Comparison: " << Cmp << "\n");
// Cannot handle comparison EQ, i.e. while (A == B).
if (Cmp == Comparison::EQ)
return nullptr;
@@ -846,6 +851,7 @@ CountValue *HexagonHardwareLoops::computeCount(MachineLoop *Loop,
if (IVBump < 0) {
std::swap(Start, End);
IVBump = -IVBump;
+ std::swap(CmpLess, CmpGreater);
}
// Cmp may now have a wrong direction, e.g. LEs may now be GEs.
// Signedness, and "including equality" are preserved.
@@ -989,7 +995,45 @@ CountValue *HexagonHardwareLoops::computeCount(MachineLoop *Loop,
CountSR = 0;
}
- return new CountValue(CountValue::CV_Register, CountR, CountSR);
+ const TargetRegisterClass *PredRC = &Hexagon::PredRegsRegClass;
+ Register MuxR = CountR;
+ unsigned MuxSR = CountSR;
+ // For the loop count to be valid unsigned number, CmpLess should imply
+ // Dist >= 0. Similarly, CmpGreater should imply Dist < 0. We can skip the
+ // check if the initial distance is zero and the comparison is LTu || LTEu.
+ if (!(Start->isImm() && StartV == 0 && Comparison::isUnsigned(Cmp) &&
+ CmpLess) &&
+ (CmpLess || CmpGreater)) {
+ // Generate:
+ // DistCheck = CMP_GT DistR, 0 --> CmpLess
+ // DistCheck = CMP_GT DistR, -1 --> CmpGreater
+ Register DistCheckR = MRI->createVirtualRegister(PredRC);
+ const MCInstrDesc &DistCheckD = TII->get(Hexagon::C2_cmpgti);
+ BuildMI(*PH, InsertPos, DL, DistCheckD, DistCheckR)
+ .addReg(DistR, 0, DistSR)
+ .addImm((CmpLess) ? 0 : -1);
+
+ // Generate:
+ // MUXR = MUX DistCheck, CountR, 1 --> CmpLess
+ // MUXR = MUX DistCheck, 1, CountR --> CmpGreater
+ MuxR = MRI->createVirtualRegister(IntRC);
+ if (CmpLess) {
+ const MCInstrDesc &MuxD = TII->get(Hexagon::C2_muxir);
+ BuildMI(*PH, InsertPos, DL, MuxD, MuxR)
+ .addReg(DistCheckR)
+ .addReg(CountR, 0, CountSR)
+ .addImm(1);
+ } else {
+ const MCInstrDesc &MuxD = TII->get(Hexagon::C2_muxri);
+ BuildMI(*PH, InsertPos, DL, MuxD, MuxR)
+ .addReg(DistCheckR)
+ .addImm(1)
+ .addReg(CountR, 0, CountSR);
+ }
+ MuxSR = 0;
+ }
+
+ return new CountValue(CountValue::CV_Register, MuxR, MuxSR);
}
/// Return true if the operation is invalid within hardware loop.
diff --git a/llvm/test/CodeGen/Hexagon/hwloop-dist-check.mir b/llvm/test/CodeGen/Hexagon/hwloop-dist-check.mir
new file mode 100644
index 0000000000000..f5286d6e86fc1
--- /dev/null
+++ b/llvm/test/CodeGen/Hexagon/hwloop-dist-check.mir
@@ -0,0 +1,281 @@
+# RUN: llc -run-pass=hwloops %s -o - | FileCheck %s
+
+# CHECK-LABEL: name: f
+# CHECK: [[R1:%[0-9]+]]:predregs = C2_cmpgti [[R0:%[0-9]+]], 0
+# CHECK: [[R3:%[0-9]+]]:intregs = C2_muxir [[R1:%[0-9]+]], [[R2:%[0-9]+]], 1
+# CHECK-LABEL: name: g
+# CHECK: [[R1:%[0-9]+]]:predregs = C2_cmpgti [[R0:%[0-9]+]], 0
+# CHECK: [[R3:%[0-9]+]]:intregs = C2_muxir [[R1:%[0-9]+]], [[R2:%[0-9]+]], 1
+--- |
+ @a = dso_local global [255 x ptr] zeroinitializer, align 8
+
+ ; Function Attrs: minsize nofree norecurse nosync nounwind optsize memory(write, argmem: none, inaccessiblemem: none)
+ define dso_local void @f(i32 noundef %m) local_unnamed_addr #0 {
+ entry:
+ %cond = tail call i32 @llvm.smax.i32(i32 %m, i32 2)
+ %0 = add nsw i32 %cond, -4
+ %1 = shl i32 %cond, 3
+ %cgep = getelementptr i8, ptr @a, i32 %1
+ %cgep36 = bitcast ptr @a to ptr
+ br label %do.body
+
+ do.body: ; preds = %do.body, %entry
+ %lsr.iv1 = phi ptr [ %cgep4, %do.body ], [ %cgep, %entry ]
+ %lsr.iv = phi i32 [ %lsr.iv.next, %do.body ], [ %0, %entry ]
+ %sh.0 = phi i32 [ 256, %entry ], [ %shr, %do.body ]
+ %shr = lshr i32 %sh.0, 1
+ %cgep5 = getelementptr inbounds [255 x ptr], ptr %cgep36, i32 0, i32 %shr
+ store ptr %lsr.iv1, ptr %cgep5, align 4, !tbaa !5
+ %lsr.iv.next = add nsw i32 %lsr.iv, 4
+ %cmp1 = icmp samesign ult i32 %lsr.iv.next, 1073741836
+ %cgep4 = getelementptr i8, ptr %lsr.iv1, i32 32
+ br i1 %cmp1, label %do.body, label %do.end, !llvm.loop !9
+
+ do.end: ; preds = %do.body
+ ret void
+ }
+
+ ; Function Attrs: minsize nofree norecurse nosync nounwind optsize memory(write, argmem: none, inaccessiblemem: none)
+ define dso_local void @g(i32 noundef %m) local_unnamed_addr #0 {
+ entry:
+ %0 = add i32 %m, -4
+ %1 = shl i32 %m, 3
+ %cgep = getelementptr i8, ptr @a, i32 %1
+ %cgep36 = bitcast ptr @a to ptr
+ br label %do.body
+
+ do.body: ; preds = %do.body, %entry
+ %lsr.iv1 = phi ptr [ %cgep4, %do.body ], [ %cgep, %entry ]
+ %lsr.iv = phi i32 [ %lsr.iv.next, %do.body ], [ %0, %entry ]
+ %sh.0 = phi i32 [ 256, %entry ], [ %shr, %do.body ]
+ %shr = lshr i32 %sh.0, 1
+ %cgep5 = getelementptr inbounds [255 x ptr], ptr %cgep36, i32 0, i32 %shr
+ store ptr %lsr.iv1, ptr %cgep5, align 4, !tbaa !5
+ %lsr.iv.next = add i32 %lsr.iv, 4
+ %cmp = icmp slt i32 %lsr.iv.next, 1073741836
+ %cgep4 = getelementptr i8, ptr %lsr.iv1, i32 32
+ br i1 %cmp, label %do.body, label %do.end, !llvm.loop !11
+
+ do.end: ; preds = %do.body
+ ret void
+ }
+
+ ; Function Attrs: nocallback nofree nosync nounwind speculatable willreturn memory(none)
+ declare i32 @llvm.smax.i32(i32, i32) #1
+
+ attributes #0 = { minsize nofree norecurse nosync nounwind optsize memory(write, argmem: none, inaccessiblemem: none) "frame-pointer"="all" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="hexagonv68" "target-features"="+v68,-long-calls" }
+ attributes #1 = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
+
+ !llvm.module.flags = !{!0, !1, !2, !3}
+
+ !0 = !{i32 1, !"wchar_size", i32 4}
+ !1 = !{i32 8, !"PIC Level", i32 2}
+ !2 = !{i32 7, !"PIE Level", i32 2}
+ !3 = !{i32 7, !"frame-pointer", i32 2}
+ !5 = !{!6, !6, i64 0}
+ !6 = !{!"any pointer", !7, i64 0}
+ !7 = !{!"omnipotent char", !8, i64 0}
+ !8 = !{!"Simple C/C++ TBAA"}
+ !9 = distinct !{!9, !10}
+ !10 = !{!"llvm.loop.mustprogress"}
+ !11 = distinct !{!11, !10}
+
+...
+---
+name: f
+alignment: 4
+exposesReturnsTwice: false
+legalized: false
+regBankSelected: false
+selected: false
+failedISel: false
+tracksRegLiveness: true
+hasWinCFI: false
+noPhis: false
+isSSA: true
+noVRegs: false
+hasFakeUses: false
+callsEHReturn: false
+callsUnwindInit: false
+hasEHScopes: false
+hasEHFunclets: false
+isOutlined: false
+debugInstrRef: false
+failsVerification: false
+tracksDebugUserValues: false
+registers:
+ - { id: 0, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 1, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 2, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 3, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 4, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 5, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 6, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 7, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 8, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 9, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 10, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 11, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 12, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 13, class: predregs, preferred-register: '', flags: [ ] }
+ - { id: 14, class: predregs, preferred-register: '', flags: [ ] }
+ - { id: 15, class: intregs, preferred-register: '', flags: [ ] }
+liveins:
+ - { reg: '$r0', virtual-reg: '%9' }
+frameInfo:
+ isFrameAddressTaken: false
+ isReturnAddressTaken: false
+ hasStackMap: false
+ hasPatchPoint: false
+ stackSize: 0
+ offsetAdjustment: 0
+ maxAlignment: 1
+ adjustsStack: false
+ hasCalls: false
+ stackProtector: ''
+ functionContext: ''
+ maxCallFrameSize: 4294967295
+ cvBytesOfCalleeSavedRegisters: 0
+ hasOpaqueSPAdjustment: false
+ hasVAStart: false
+ hasMustTailInVarArgFunc: false
+ hasTailCall: false
+ isCalleeSavedInfoValid: false
+ localFrameSize: 0
+ savePoint: ''
+ restorePoint: ''
+fixedStack: []
+stack: []
+entry_values: []
+callSites: []
+debugValueSubstitutions: []
+constants: []
+machineFunctionInfo: {}
+body: |
+ bb.0.entry:
+ successors: %bb.1(0x80000000)
+ liveins: $r0
+
+ %9:intregs = COPY $r0
+ %11:intregs = A2_tfrsi 2
+ %12:intregs = A2_max %9, %11
+ %0:intregs = nsw A2_addi %12, -4
+ %1:intregs = S4_addi_asl_ri @a, %12, 3
+ %2:intregs = A2_tfrsi @a
+ %10:intregs = A2_tfrsi 256
+
+ bb.1.do.body:
+ successors: %bb.1(0x7c000000), %bb.2(0x04000000)
+
+ %3:intregs = PHI %1, %bb.0, %8, %bb.1
+ %4:intregs = PHI %0, %bb.0, %7, %bb.1
+ %5:intregs = PHI %10, %bb.0, %15, %bb.1
+ %15:intregs = S2_extractu %5, 8, 1
+ S4_storeri_rr %2, %15, 2, %3 :: (store (s32) into %ir.cgep5, !tbaa !5)
+ %7:intregs = nsw A2_addi %4, 4
+ %13:predregs = C2_cmpgtui %7, 1073741835
+ %8:intregs = A2_addi %3, 32
+ J2_jumpf %13, %bb.1, implicit-def dead $pc
+ J2_jump %bb.2, implicit-def dead $pc
+
+ bb.2.do.end:
+ PS_jmpret $r31, implicit-def dead $pc
+
+...
+---
+name: g
+alignment: 4
+exposesReturnsTwice: false
+legalized: false
+regBankSelected: false
+selected: false
+failedISel: false
+tracksRegLiveness: true
+hasWinCFI: false
+noPhis: false
+isSSA: true
+noVRegs: false
+hasFakeUses: false
+callsEHReturn: false
+callsUnwindInit: false
+hasEHScopes: false
+hasEHFunclets: false
+isOutlined: false
+debugInstrRef: false
+failsVerification: false
+tracksDebugUserValues: false
+registers:
+ - { id: 0, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 1, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 2, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 3, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 4, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 5, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 6, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 7, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 8, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 9, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 10, class: intregs, preferred-register: '', flags: [ ] }
+ - { id: 11, class: predregs, preferred-register: '', flags: [ ] }
+ - { id: 12, class: predregs, preferred-register: '', flags: [ ] }
+ - { id: 13, class: intregs, preferred-register: '', flags: [ ] }
+liveins:
+ - { reg: '$r0', virtual-reg: '%9' }
+frameInfo:
+ isFrameAddressTaken: false
+ isReturnAddressTaken: false
+ hasStackMap: false
+ hasPatchPoint: false
+ stackSize: 0
+ offsetAdjustment: 0
+ maxAlignment: 1
+ adjustsStack: false
+ hasCalls: false
+ stackProtector: ''
+ functionContext: ''
+ maxCallFrameSize: 4294967295
+ cvBytesOfCalleeSavedRegisters: 0
+ hasOpaqueSPAdjustment: false
+ hasVAStart: false
+ hasMustTailInVarArgFunc: false
+ hasTailCall: false
+ isCalleeSavedInfoValid: false
+ localFrameSize: 0
+ savePoint: ''
+ restorePoint: ''
+fixedStack: []
+stack: []
+entry_values: []
+callSites: []
+debugValueSubstitutions: []
+constants: []
+machineFunctionInfo: {}
+body: |
+ bb.0.entry:
+ successors: %bb.1(0x80000000)
+ liveins: $r0
+
+ %9:intregs = COPY $r0
+ %0:intregs = A2_addi %9, -4
+ %1:intregs = S4_addi_asl_ri @a, %9, 3
+ %2:intregs = A2_tfrsi @a
+ %10:intregs = A2_tfrsi 256
+
+ bb.1.do.body:
+ successors: %bb.1(0x7c000000), %bb.2(0x04000000)
+
+ %3:intregs = PHI %1, %bb.0, %8, %bb.1
+ %4:intregs = PHI %0, %bb.0, %7, %bb.1
+ %5:intregs = PHI %10, %bb.0, %13, %bb.1
+ %13:intregs = S2_extractu %5, 8, 1
+ S4_storeri_rr %2, %13, 2, %3 :: (store (s32) into %ir.cgep5, !tbaa !5)
+ %7:intregs = A2_addi %4, 4
+ %11:predregs = C2_cmpgti %7, 1073741835
+ %8:intregs = A2_addi %3, 32
+ J2_jumpf %11, %bb.1, implicit-def dead $pc
+ J2_jump %bb.2, implicit-def dead $pc
+
+ bb.2.do.end:
+ PS_jmpret $r31, implicit-def dead $pc
+
+...
diff --git a/llvm/test/CodeGen/Hexagon/swp-phi-start.ll b/llvm/test/CodeGen/Hexagon/swp-phi-start.ll
index 52c258656ec22..6c2b08d83b1c7 100644
--- a/llvm/test/CodeGen/Hexagon/swp-phi-start.ll
+++ b/llvm/test/CodeGen/Hexagon/swp-phi-start.ll
@@ -5,8 +5,9 @@
; the same stage.
; CHECK-DAG: [[REG3:(r[0-9]+)]] = add([[REG1:(r[0-9]+)]],#-1)
-; CHECK-DAG: [[REG2:(r[0-9]+)]] = add([[REG1]],#-1)
-; CHECK-DAG: loop0(.LBB0_[[LOOP:.]],[[REG3]])
+; CHECK-DAG: [[REG2:(r[0-9]+)]] = add([[REG4:(r[0-9]+)]],#-1)
+; CHECK-DAG: loop0(.LBB0_[[LOOP:.]],[[REG2]])
+; CHECK-NOT: = [[REG3]]
; CHECK-NOT: = [[REG2]]
; CHECK: .LBB0_[[LOOP]]:
; CHECK: }{{[ \t]*}}:endloop
>From f80d13c1c50195c44ecbf0de1c148312f540f406 Mon Sep 17 00:00:00 2001
From: aankit-quic <aankit at quicinc.com>
Date: Fri, 11 Apr 2025 17:42:22 -0700
Subject: [PATCH 2/2] Fix lit test
Change-Id: I2fd135a0086db33ab0fd1520d88d38dbadde884a
---
llvm/test/CodeGen/Hexagon/hwloop-dist-check.mir | 6 +-----
1 file changed, 1 insertion(+), 5 deletions(-)
diff --git a/llvm/test/CodeGen/Hexagon/hwloop-dist-check.mir b/llvm/test/CodeGen/Hexagon/hwloop-dist-check.mir
index f5286d6e86fc1..9f8c14a314309 100644
--- a/llvm/test/CodeGen/Hexagon/hwloop-dist-check.mir
+++ b/llvm/test/CodeGen/Hexagon/hwloop-dist-check.mir
@@ -1,4 +1,4 @@
-# RUN: llc -run-pass=hwloops %s -o - | FileCheck %s
+# RUN: llc --mtriple=hexagon -run-pass=hwloops %s -o - | FileCheck %s
# CHECK-LABEL: name: f
# CHECK: [[R1:%[0-9]+]]:predregs = C2_cmpgti [[R0:%[0-9]+]], 0
@@ -63,11 +63,7 @@
; Function Attrs: nocallback nofree nosync nounwind speculatable willreturn memory(none)
declare i32 @llvm.smax.i32(i32, i32) #1
- attributes #0 = { minsize nofree norecurse nosync nounwind optsize memory(write, argmem: none, inaccessiblemem: none) "frame-pointer"="all" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="hexagonv68" "target-features"="+v68,-long-calls" }
- attributes #1 = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
-
!llvm.module.flags = !{!0, !1, !2, !3}
-
!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{i32 8, !"PIC Level", i32 2}
!2 = !{i32 7, !"PIE Level", i32 2}
More information about the llvm-commits
mailing list