[X86] Avoid SFB - Fix inconsistent codegen with/without debug info

Fixes https://bugs.llvm.org/show_bug.cgi?id=40969

The functions findPotentiallyBlockedCopies and buildCopy are currently not
accounting for the presence of debug instructions. In the former this results
in the optimization not being trigerred, and in the latter results in
inconsistent codegen.

This patch enables the optimization to be performed in a debug build and
ensures the codegen is consistent with non-debug builds.

Patch by Chris Dawson.

Differential Revision: https://reviews.llvm.org/D61680

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@360436 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86AvoidStoreForwardingBlocks.cpp b/lib/Target/X86/X86AvoidStoreForwardingBlocks.cpp
index 3ac0b1ae5143d7aaaec5b7275698cd113b53ab4e..11a3ff1bd57e26bb08eeedc7b0981e49b8060fa4 100644 (file)
--- a/lib/Target/X86/X86AvoidStoreForwardingBlocks.cpp
+++ b/lib/Target/X86/X86AvoidStoreForwardingBlocks.cpp
@@ -406,7 +406,9 @@ void X86AvoidSFBPass::buildCopy(MachineInstr *LoadInst, unsigned NLoadOpcode,
   // If the load and store are consecutive, use the loadInst location to
   // reduce register pressure.
   MachineInstr *StInst = StoreInst;
-  if (StoreInst->getPrevNode() == LoadInst)
+  auto PrevInstrIt = skipDebugInstructionsBackward(
+      std::prev(MachineBasicBlock::instr_iterator(StoreInst)), MBB->instr_begin());
+  if (PrevInstrIt.getNodePtr() == LoadInst)
     StInst = LoadInst;
   MachineInstr *NewStore =
       BuildMI(*MBB, StInst, StInst->getDebugLoc(), TII->get(NStoreOpcode))
@@ -530,7 +532,7 @@ void X86AvoidSFBPass::findPotentiallylBlockedCopies(MachineFunction &MF) {
       if (!isPotentialBlockedMemCpyLd(MI.getOpcode()))
         continue;
       int DefVR = MI.getOperand(0).getReg();
-      if (!MRI->hasOneUse(DefVR))
+      if (!MRI->hasOneNonDBGUse(DefVR))
         continue;
       for (auto UI = MRI->use_nodbg_begin(DefVR), UE = MRI->use_nodbg_end();
            UI != UE;) {

diff --git a/test/CodeGen/X86/avoid-sfb-g-no-change.mir b/test/CodeGen/X86/avoid-sfb-g-no-change.mir
new file mode 100644 (file)
index 0000000..b78bb4c
--- /dev/null
+++ b/test/CodeGen/X86/avoid-sfb-g-no-change.mir
@@ -0,0 +1,248 @@
+# RUN: llc %s -run-pass x86-avoid-SFB -mtriple=x86_64-unknown-linux-gnu -o - | FileCheck %s -check-prefixes DEBUG-LABEL,CHECK
+# RUN: llc %s -run-pass x86-avoid-SFB -mtriple=x86_64-unknown-linux-gnu -o - | FileCheck %s -check-prefixes NODEBUG-LABEL,CHECK
+#
+# This was generated from:
+#
+# using alpha = float __attribute__((ext_vector_type(4)));
+#
+# void bravo(alpha charlie) {
+#   unsigned char *delta = (unsigned char *)&charlie;
+#   delta[0] = 0;
+#   volatile alpha echo = charlie;
+# }
+#
+# Using the command line:
+# clang -g -c 1.cpp -O2 -S -emit-llvm -fno-strict-aliasing --target=x86_64-unknown-unknown -o test.ll
+
+--- |
+  ; ModuleID = 'test.ll'
+  source_filename = "1.cpp"
+  target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+  target triple = "x86_64-unknown-unknown"
+
+  ; Function Attrs: nounwind uwtable
+  define dso_local void @debug(<4 x float> %charlie) local_unnamed_addr #0 !dbg !10 {
+  entry:
+    %charlie.addr = alloca <4 x float>, align 16
+    %echo = alloca <4 x float>, align 16
+    call void @llvm.dbg.value(metadata <4 x float> %charlie, metadata !19, metadata !DIExpression()), !dbg !23
+    store <4 x float> %charlie, <4 x float>* %charlie.addr, align 16
+    call void @llvm.dbg.value(metadata i8* undef, metadata !20, metadata !DIExpression()), !dbg !24
+    %charlie.addr.0.charlie.addr.0.arrayidx.sroa_cast = bitcast <4 x float>* %charlie.addr to i8*, !dbg !25
+    store i8 0, i8* %charlie.addr.0.charlie.addr.0.arrayidx.sroa_cast, align 16, !dbg !25
+    %echo.0.echo.0..sroa_cast = bitcast <4 x float>* %echo to i8*, !dbg !26
+    call void @llvm.lifetime.start.p0i8(i64 16, i8* nonnull %echo.0.echo.0..sroa_cast), !dbg !26
+    call void @llvm.dbg.declare(metadata <4 x float>* %echo, metadata !21, metadata !DIExpression()), !dbg !27
+    %charlie.addr.0.charlie.addr.0. = load <4 x float>, <4 x float>* %charlie.addr, align 16, !dbg !28
+    call void @llvm.dbg.value(metadata <4 x float> %charlie.addr.0.charlie.addr.0., metadata !19, metadata !DIExpression()), !dbg !23
+    store volatile <4 x float> %charlie.addr.0.charlie.addr.0., <4 x float>* %echo, align 16, !dbg !27
+    call void @llvm.lifetime.end.p0i8(i64 16, i8* nonnull %echo.0.echo.0..sroa_cast), !dbg !29
+    ret void, !dbg !29
+  }
+
+  ; Function Attrs: nounwind uwtable
+  define dso_local void @nodebug(<4 x float> %charlie) local_unnamed_addr #0 {
+  entry:
+    %charlie.addr = alloca <4 x float>, align 16
+    %echo = alloca <4 x float>, align 16
+    store <4 x float> %charlie, <4 x float>* %charlie.addr, align 16
+    %charlie.addr.0.charlie.addr.0.arrayidx.sroa_cast = bitcast <4 x float>* %charlie.addr to i8*
+    store i8 0, i8* %charlie.addr.0.charlie.addr.0.arrayidx.sroa_cast, align 16
+    %echo.0.echo.0..sroa_cast = bitcast <4 x float>* %echo to i8*
+    call void @llvm.lifetime.start.p0i8(i64 16, i8* nonnull %echo.0.echo.0..sroa_cast)
+    %charlie.addr.0.charlie.addr.0. = load <4 x float>, <4 x float>* %charlie.addr, align 16
+    store volatile <4 x float> %charlie.addr.0.charlie.addr.0., <4 x float>* %echo, align 16
+    call void @llvm.lifetime.end.p0i8(i64 16, i8* nonnull %echo.0.echo.0..sroa_cast)
+    ret void
+  }
+
+  ; Function Attrs: nounwind readnone speculatable
+  declare void @llvm.dbg.declare(metadata, metadata, metadata) #1
+
+  ; Function Attrs: argmemonly nounwind
+  declare void @llvm.lifetime.start.p0i8(i64 immarg, i8* nocapture) #2
+
+  ; Function Attrs: argmemonly nounwind
+  declare void @llvm.lifetime.end.p0i8(i64 immarg, i8* nocapture) #2
+
+  ; Function Attrs: nounwind readnone speculatable
+  declare void @llvm.dbg.value(metadata, metadata, metadata) #1
+
+  ; Function Attrs: nounwind
+  declare void @llvm.stackprotector(i8*, i8**) #3
+
+  attributes #0 = { nounwind uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="128" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" }
+  attributes #1 = { nounwind readnone speculatable }
+  attributes #2 = { argmemonly nounwind }
+  attributes #3 = { nounwind }
+
+  !llvm.dbg.cu = !{!0}
+  !llvm.module.flags = !{!6, !7, !8}
+  !llvm.ident = !{!9}
+
+  !0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1, producer: "clang version 9.0.0 (https://github.com/llvm/llvm-project.git dfaba1587d4c17409f28c4be46b184fb77237e8e)", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, enums: !2, retainedTypes: !3, nameTableKind: None)
+  !1 = !DIFile(filename: "1.cpp", directory: "C:\5CUsers\5Cgbdawsoc\5CDocuments\5Cllvm\5Cbg40969")
+  !2 = !{}
+  !3 = !{!4}
+  !4 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !5, size: 64)
+  !5 = !DIBasicType(name: "unsigned char", size: 8, encoding: DW_ATE_unsigned_char)
+  !6 = !{i32 2, !"Dwarf Version", i32 4}
+  !7 = !{i32 2, !"Debug Info Version", i32 3}
+  !8 = !{i32 1, !"wchar_size", i32 4}
+  !9 = !{!"clang version 9.0.0 (https://github.com/llvm/llvm-project.git dfaba1587d4c17409f28c4be46b184fb77237e8e)"}
+  !10 = distinct !DISubprogram(name: "bravo", linkageName: "_Z5bravoDv4_f", scope: !1, file: !1, line: 3, type: !11, scopeLine: 3, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !0, retainedNodes: !18)
+  !11 = !DISubroutineType(types: !12)
+  !12 = !{null, !13}
+  !13 = !DIDerivedType(tag: DW_TAG_typedef, name: "alpha", file: !1, line: 1, baseType: !14)
+  !14 = !DICompositeType(tag: DW_TAG_array_type, baseType: !15, size: 128, flags: DIFlagVector, elements: !16)
+  !15 = !DIBasicType(name: "float", size: 32, encoding: DW_ATE_float)
+  !16 = !{!17}
+  !17 = !DISubrange(count: 4)
+  !18 = !{!19, !20, !21}
+  !19 = !DILocalVariable(name: "charlie", arg: 1, scope: !10, file: !1, line: 3, type: !13)
+  !20 = !DILocalVariable(name: "delta", scope: !10, file: !1, line: 4, type: !4)
+  !21 = !DILocalVariable(name: "echo", scope: !10, file: !1, line: 6, type: !22)
+  !22 = !DIDerivedType(tag: DW_TAG_volatile_type, baseType: !13)
+  !23 = !DILocation(line: 3, column: 18, scope: !10)
+  !24 = !DILocation(line: 4, column: 18, scope: !10)
+  !25 = !DILocation(line: 5, column: 12, scope: !10)
+  !26 = !DILocation(line: 6, column: 3, scope: !10)
+  !27 = !DILocation(line: 6, column: 18, scope: !10)
+  !28 = !DILocation(line: 6, column: 25, scope: !10)
+  !29 = !DILocation(line: 7, column: 1, scope: !10)
+
+...
+---
+name:            debug
+alignment:       4
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+failedISel:      false
+tracksRegLiveness: true
+hasWinCFI:       false
+registers:
+  - { id: 0, class: vr128, preferred-register: '' }
+  - { id: 1, class: vr128, preferred-register: '' }
+liveins:
+  - { reg: '$xmm0', virtual-reg: '%0' }
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       0
+  offsetAdjustment: 0
+  maxAlignment:    16
+  adjustsStack:    false
+  hasCalls:        false
+  stackProtector:  ''
+  maxCallFrameSize: 4294967295
+  cvBytesOfCalleeSavedRegisters: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+  localFrameSize:  0
+  savePoint:       ''
+  restorePoint:    ''
+fixedStack:      []
+stack:
+  - { id: 0, name: charlie.addr, type: default, offset: 0, size: 16, alignment: 16,
+      stack-id: 0, callee-saved-register: '', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+  - { id: 1, name: echo, type: default, offset: 0, size: 16, alignment: 16,
+      stack-id: 0, callee-saved-register: '', callee-saved-restored: true,
+      debug-info-variable: '!21', debug-info-expression: '!DIExpression()',
+      debug-info-location: '!27' }
+constants:       []
+machineFunctionInfo: {}
+body:             |
+  bb.0.entry:
+    liveins: $xmm0
+
+    DBG_VALUE $xmm0, $noreg, !19, !DIExpression(), debug-location !23
+    %0:vr128 = COPY $xmm0
+    DBG_VALUE %0, $noreg, !19, !DIExpression(), debug-location !23
+    MOVAPSmr %stack.0.charlie.addr, 1, $noreg, 0, $noreg, %0 :: (store 16 into %ir.charlie.addr)
+    DBG_VALUE $noreg, $noreg, !20, !DIExpression(), debug-location !24
+    MOV8mi %stack.0.charlie.addr, 1, $noreg, 0, $noreg, 0, debug-location !25 :: (store 1 into %ir.charlie.addr.0.charlie.addr.0.arrayidx.sroa_cast, align 16)
+    %1:vr128 = MOVAPSrm %stack.0.charlie.addr, 1, $noreg, 0, $noreg, debug-location !28 :: (dereferenceable load 16 from %ir.charlie.addr)
+    DBG_VALUE %1, $noreg, !19, !DIExpression(), debug-location !23
+    MOVAPSmr %stack.1.echo, 1, $noreg, 0, $noreg, killed %1, debug-location !27 :: (volatile store 16 into %ir.echo)
+    RET 0, debug-location !29
+
+...
+---
+name:            nodebug
+alignment:       4
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+failedISel:      false
+tracksRegLiveness: true
+hasWinCFI:       false
+registers:
+  - { id: 0, class: vr128, preferred-register: '' }
+  - { id: 1, class: vr128, preferred-register: '' }
+liveins:
+  - { reg: '$xmm0', virtual-reg: '%0' }
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       0
+  offsetAdjustment: 0
+  maxAlignment:    16
+  adjustsStack:    false
+  hasCalls:        false
+  stackProtector:  ''
+  maxCallFrameSize: 4294967295
+  cvBytesOfCalleeSavedRegisters: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+  localFrameSize:  0
+  savePoint:       ''
+  restorePoint:    ''
+fixedStack:      []
+stack:
+  - { id: 0, name: charlie.addr, type: default, offset: 0, size: 16, alignment: 16,
+      stack-id: 0, callee-saved-register: '', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+  - { id: 1, name: echo, type: default, offset: 0, size: 16, alignment: 16,
+      stack-id: 0, callee-saved-register: '', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+constants:       []
+machineFunctionInfo: {}
+body:             |
+  bb.0.entry:
+    liveins: $xmm0
+
+    %0:vr128 = COPY $xmm0
+    MOVAPSmr %stack.0.charlie.addr, 1, $noreg, 0, $noreg, %0 :: (store 16 into %ir.charlie.addr)
+    MOV8mi %stack.0.charlie.addr, 1, $noreg, 0, $noreg, 0 :: (store 1 into %ir.charlie.addr.0.charlie.addr.0.arrayidx.sroa_cast, align 16)
+    %1:vr128 = MOVAPSrm %stack.0.charlie.addr, 1, $noreg, 0, $noreg :: (dereferenceable load 16 from %ir.charlie.addr)
+    MOVAPSmr %stack.1.echo, 1, $noreg, 0, $noreg, killed %1 :: (volatile store 16 into %ir.echo)
+    RET 0
+
+    ; DEBUG-LABEL: name: debug
+    ; NODEBUG-LABEL: name: nodebug
+    ; CHECK: %0:vr128 = COPY $xmm0
+    ; CHECK: MOVAPSmr
+    ; CHECK: MOV8mi
+    ; ChECK: %2:gr8 = MOV8rm
+    ; CHECK: MOV8mr
+    ; CHECK: %3:gr64 = MOV64rm
+    ; CHECK: MOV64mr
+    ; CHECK: %4:gr32 = MOV32rm
+    ; CHECK: MOV32mr
+    ; CHECK: %5:gr16 = MOV16rm
+    ; CHECK: MOV16mr
+    ; CHECK: %6:gr8 = MOV8rm
+    ; CHECK: MOV8mr
+    ; CHECK: RET 0
+    ; DEBUG-LABEL: name: nodebug
+...