summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorTaewook Oh <twoh@fb.com>2017-03-02 21:58:35 +0000
committerTaewook Oh <twoh@fb.com>2017-03-02 21:58:35 +0000
commit96c641569717745f58b78091b34d7bb7311b0d3a (patch)
tree3e2e356fc6a484961e749efd6b40b83a0291c65b
parent7884dcb788f58390172b330a7269a8deff851c7f (diff)
downloadbcm5719-llvm-96c641569717745f58b78091b34d7bb7311b0d3a.tar.gz
bcm5719-llvm-96c641569717745f58b78091b34d7bb7311b0d3a.zip
[DAGCombiner] Fix DebugLoc propagation when folding !(x cc y) -> (x !cc y)
Summary: Currently, when 't1: i1 = setcc t2, t3, cc' followed by 't4: i1 = xor t1, Constant:i1<-1>' is folded into 't5: i1 = setcc t2, t3 !cc', SDLoc of newly created SDValue 't5' follows SDLoc of 't4', not 't1'. However, as the opcode of newly created SDValue is 'setcc', it make more sense to take DebugLoc from 't1' than 't4'. For the code below ``` extern int bar(); extern int baz(); int foo(int x, int y) { if (x != y) return bar(); else return baz(); } ``` , following is the bitcode representation of 'foo' at the end of llvm-ir level optimization: ``` define i32 @foo(i32 %x, i32 %y) !dbg !4 { entry: tail call void @llvm.dbg.value(metadata i32 %x, i64 0, metadata !9, metadata !11), !dbg !12 tail call void @llvm.dbg.value(metadata i32 %y, i64 0, metadata !10, metadata !11), !dbg !13 %cmp = icmp ne i32 %x, %y, !dbg !14 br i1 %cmp, label %if.then, label %if.else, !dbg !16 if.then: ; preds = %entry %call = tail call i32 (...) @bar() #3, !dbg !17 br label %return, !dbg !18 if.else: ; preds = %entry %call1 = tail call i32 (...) @baz() #3, !dbg !19 br label %return, !dbg !20 return: ; preds = %if.else, %if.then %retval.0 = phi i32 [ %call, %if.then ], [ %call1, %if.else ] ret i32 %retval.0, !dbg !21 } !14 = !DILocation(line: 5, column: 9, scope: !15) !16 = !DILocation(line: 5, column: 7, scope: !4) ``` As you can see, in 'entry' block, 'icmp' instruction and 'br' instruction have different debug locations. However, with current implementation, there's no distinction between debug locations of these two when they are lowered to asm instructions. This is because 'icmp' and 'br' become 'setcc' 'xor' and 'brcond' in SelectionDAG, where SDLoc of 'setcc' follows the debug location of 'icmp' but SDLOC of 'xor' and 'brcond' follows the debug location of 'br' instruction, and SDLoc of 'xor' overwrites SDLoc of 'setcc' when they are folded. This patch addresses this issue. Reviewers: atrick, bogner, andreadb, craig.topper, aprantl Reviewed By: andreadb Subscribers: jlebar, mkuper, jholewinski, andreadb, llvm-commits Differential Revision: https://reviews.llvm.org/D29813 llvm-svn: 296825
-rw-r--r--llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp4
-rw-r--r--llvm/test/CodeGen/NVPTX/lower-aggr-copies.ll4
-rw-r--r--llvm/test/CodeGen/X86/and-sink.ll20
-rw-r--r--llvm/test/CodeGen/X86/avx512-fsel.ll16
-rw-r--r--llvm/test/CodeGen/X86/fp128-i128.ll4
-rw-r--r--llvm/test/CodeGen/X86/xor-combine-debugloc.ll69
6 files changed, 93 insertions, 24 deletions
diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 2f6a26d319f..921b1f4284a 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -4856,9 +4856,9 @@ SDValue DAGCombiner::visitXOR(SDNode *N) {
default:
llvm_unreachable("Unhandled SetCC Equivalent!");
case ISD::SETCC:
- return DAG.getSetCC(SDLoc(N), VT, LHS, RHS, NotCC);
+ return DAG.getSetCC(SDLoc(N0), VT, LHS, RHS, NotCC);
case ISD::SELECT_CC:
- return DAG.getSelectCC(SDLoc(N), LHS, RHS, N0.getOperand(2),
+ return DAG.getSelectCC(SDLoc(N0), LHS, RHS, N0.getOperand(2),
N0.getOperand(3), NotCC);
}
}
diff --git a/llvm/test/CodeGen/NVPTX/lower-aggr-copies.ll b/llvm/test/CodeGen/NVPTX/lower-aggr-copies.ll
index f593969f2a4..192d4becb05 100644
--- a/llvm/test/CodeGen/NVPTX/lower-aggr-copies.ll
+++ b/llvm/test/CodeGen/NVPTX/lower-aggr-copies.ll
@@ -114,8 +114,8 @@ entry:
; PTX-LABEL: .visible .func (.param .b64 func_retval0) memmove_caller(
; PTX: ld.param.u64 %rd[[N:[0-9]+]]
-; PTX: setp.eq.s64 %p[[NEQ0:[0-9]+]], %rd[[N]], 0
-; PTX: setp.ge.u64 %p[[SRC_GT_THAN_DST:[0-9]+]], %rd{{[0-9]+}}, %rd{{[0-9]+}}
+; PTX-DAG: setp.eq.s64 %p[[NEQ0:[0-9]+]], %rd[[N]], 0
+; PTX-DAG: setp.ge.u64 %p[[SRC_GT_THAN_DST:[0-9]+]], %rd{{[0-9]+}}, %rd{{[0-9]+}}
; PTX-NEXT: @%p[[SRC_GT_THAN_DST]] bra LBB[[FORWARD_BB:[0-9_]+]]
; -- this is the backwards copying BB
; PTX: @%p[[NEQ0]] bra LBB[[EXIT:[0-9_]+]]
diff --git a/llvm/test/CodeGen/X86/and-sink.ll b/llvm/test/CodeGen/X86/and-sink.ll
index 18120d7f786..46e50f2a6a7 100644
--- a/llvm/test/CodeGen/X86/and-sink.ll
+++ b/llvm/test/CodeGen/X86/and-sink.ll
@@ -80,8 +80,8 @@ define i32 @and_sink3(i1 %c, i32* %p) {
; CHECK: testb $1,
; CHECK: je
; CHECK: movzbl
-; CHECK: movl $0, A
-; CHECK: testl %
+; CHECK-DAG: movl $0, A
+; CHECK-DAG: testl %
; CHECK: je
; CHECK-CGP-LABEL: @and_sink3(
@@ -109,11 +109,11 @@ define i32 @and_sink4(i32 %a, i32 %b, i1 %c) {
; CHECK: testb $1,
; CHECK: je
; CHECK-NOT: andl
-; CHECK: movl $0, A
-; CHECK: testl [[REG1:%[a-z0-9]+]], [[REG2:%[a-z0-9]+]]
+; CHECK-DAG: movl $0, A
+; CHECK-DAG: testl [[REG1:%[a-z0-9]+]], [[REG2:%[a-z0-9]+]]
; CHECK: jne
-; CHECK: movl {{%[a-z0-9]+}}, B
-; CHECK: testl [[REG1]], [[REG2]]
+; CHECK-DAG: movl {{%[a-z0-9]+}}, B
+; CHECK-DAG: testl [[REG1]], [[REG2]]
; CHECK: je
; CHECK-CGP-LABEL: @and_sink4(
@@ -148,11 +148,11 @@ define i32 @and_sink5(i32 %a, i32 %b, i32 %a2, i32 %b2, i1 %c) {
; CHECK-LABEL: and_sink5:
; CHECK: testb $1,
; CHECK: je
-; CHECK: andl {{[0-9]+\(%[a-z0-9]+\)}}, [[REG:%[a-z0-9]+]]
-; CHECK: movl $0, A
+; CHECK-DAG: andl {{[0-9]+\(%[a-z0-9]+\)}}, [[REG:%[a-z0-9]+]]
+; CHECK-DAG: movl $0, A
; CHECK: jne
-; CHECK: movl {{%[a-z0-9]+}}, B
-; CHECK: testl [[REG]], [[REG]]
+; CHECK-DAG: movl {{%[a-z0-9]+}}, B
+; CHECK-DAG: testl [[REG]], [[REG]]
; CHECK: je
; CHECK-CGP-LABEL: @and_sink5(
diff --git a/llvm/test/CodeGen/X86/avx512-fsel.ll b/llvm/test/CodeGen/X86/avx512-fsel.ll
index c6f2da6ff60..2f52ecd23e9 100644
--- a/llvm/test/CodeGen/X86/avx512-fsel.ll
+++ b/llvm/test/CodeGen/X86/avx512-fsel.ll
@@ -12,18 +12,18 @@ define i32 @test(float %a, float %b) {
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: movb $1, %al
; CHECK-NEXT: vucomiss %xmm1, %xmm0
-; CHECK-NEXT: setnp %cl
-; CHECK-NEXT: sete %dl
-; CHECK-NEXT: setp %sil
-; CHECK-NEXT: setne %dil
-; CHECK-NEXT: andb %cl, %dl
+; CHECK-NEXT: setp %cl
+; CHECK-NEXT: setne %dl
+; CHECK-NEXT: setnp %sil
+; CHECK-NEXT: sete %dil
+; CHECK-NEXT: andb %sil, %dil
; CHECK-NEXT: ## implicit-def: %R8D
-; CHECK-NEXT: movb %dl, %r8b
+; CHECK-NEXT: movb %dil, %r8b
; CHECK-NEXT: andl $1, %r8d
; CHECK-NEXT: kmovw %r8d, %k0
-; CHECK-NEXT: orb %sil, %dil
+; CHECK-NEXT: orb %cl, %dl
; CHECK-NEXT: ## implicit-def: %R8D
-; CHECK-NEXT: movb %dil, %r8b
+; CHECK-NEXT: movb %dl, %r8b
; CHECK-NEXT: andl $1, %r8d
; CHECK-NEXT: kmovw %r8d, %k1
; CHECK-NEXT: kmovw %k1, %ecx
diff --git a/llvm/test/CodeGen/X86/fp128-i128.ll b/llvm/test/CodeGen/X86/fp128-i128.ll
index 77160674ab2..4e987d7b925 100644
--- a/llvm/test/CodeGen/X86/fp128-i128.ll
+++ b/llvm/test/CodeGen/X86/fp128-i128.ll
@@ -306,10 +306,10 @@ cleanup: ; preds = %entry, %if.then
ret void
; CHECK-LABEL: TestCopySign
; CHECK-NOT: call
-; CHECK: callq __subtf3
-; CHECK-NOT: call
; CHECK: callq __gttf2
; CHECK-NOT: call
+; CHECK: callq __subtf3
+; CHECK-NOT: call
; CHECK: andps {{.*}}, %xmm0
; CHECK: retq
}
diff --git a/llvm/test/CodeGen/X86/xor-combine-debugloc.ll b/llvm/test/CodeGen/X86/xor-combine-debugloc.ll
new file mode 100644
index 00000000000..21777c1c572
--- /dev/null
+++ b/llvm/test/CodeGen/X86/xor-combine-debugloc.ll
@@ -0,0 +1,69 @@
+; RUN: llc -stop-after=expand-isel-pseudos < %s | FileCheck %s
+;
+; Make sure that when the entry block of IR below is lowered, an instruction
+; that implictly defines %eflags has a same debug location with the icmp
+; instruction, and the branch instructions have a same debug location with the
+; br instruction.
+;
+; CHECK: [[DLOC1:![0-9]+]] = !DILocation(line: 5, column: 9, scope: !{{[0-9]+}})
+; CHECK: [[DLOC2:![0-9]+]] = !DILocation(line: 5, column: 7, scope: !{{[0-9]+}})
+; CHECK-DAG: [[VREG1:%[^ ]+]] = COPY %esi
+; CHECK-DAG: [[VREG2:%[^ ]+]] = COPY %edi
+; CHECK: SUB32rr [[VREG2]], [[VREG1]], implicit-def %eflags, debug-location [[DLOC1]]
+; CHECK-NEXT: JE_1{{.*}} implicit %eflags, debug-location [[DLOC2]]
+; CHECK-NEXT: JMP_1{{.*}} debug-location [[DLOC2]]
+
+target triple = "x86_64-unknown-linux-gnu"
+
+; Function Attrs: nounwind uwtable
+define i32 @foo(i32 %x, i32 %y) !dbg !4 {
+entry:
+ tail call void @llvm.dbg.value(metadata i32 %x, i64 0, metadata !9, metadata !11), !dbg !12
+ tail call void @llvm.dbg.value(metadata i32 %y, i64 0, metadata !10, metadata !11), !dbg !13
+ %cmp = icmp ne i32 %x, %y, !dbg !14
+ br i1 %cmp, label %if.then, label %if.else, !dbg !16
+
+if.then: ; preds = %entry
+ %call = tail call i32 (...) @bar() #3, !dbg !17
+ br label %return, !dbg !18
+
+if.else: ; preds = %entry
+ %call1 = tail call i32 (...) @baz() #3, !dbg !19
+ br label %return, !dbg !20
+
+return: ; preds = %if.else, %if.then
+ %retval.0 = phi i32 [ %call, %if.then ], [ %call1, %if.else ]
+ ret i32 %retval.0, !dbg !21
+}
+
+declare i32 @bar(...)
+declare i32 @baz(...)
+
+; Function Attrs: nounwind readnone
+declare void @llvm.dbg.value(metadata, i64, metadata, metadata)
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!2, !3}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, emissionKind: FullDebug)
+!1 = !DIFile(filename: "foo.c", directory: "b/")
+!2 = !{i32 2, !"Dwarf Version", i32 4}
+!3 = !{i32 2, !"Debug Info Version", i32 3}
+!4 = distinct !DISubprogram(name: "foo", scope: !1, file: !1, line: 4, type: !5, isLocal: false, isDefinition: true, scopeLine: 4, flags: DIFlagPrototyped, isOptimized: true, unit: !0, variables: !8)
+!5 = !DISubroutineType(types: !6)
+!6 = !{!7, !7, !7}
+!7 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
+!8 = !{!9, !10}
+!9 = !DILocalVariable(name: "x", arg: 1, scope: !4, file: !1, line: 4, type: !7)
+!10 = !DILocalVariable(name: "y", arg: 2, scope: !4, file: !1, line: 4, type: !7)
+!11 = !DIExpression()
+!12 = !DILocation(line: 4, column: 13, scope: !4)
+!13 = !DILocation(line: 4, column: 20, scope: !4)
+!14 = !DILocation(line: 5, column: 9, scope: !15)
+!15 = distinct !DILexicalBlock(scope: !4, file: !1, line: 5, column: 7)
+!16 = !DILocation(line: 5, column: 7, scope: !4)
+!17 = !DILocation(line: 6, column: 12, scope: !15)
+!18 = !DILocation(line: 6, column: 5, scope: !15)
+!19 = !DILocation(line: 8, column: 12, scope: !15)
+!20 = !DILocation(line: 8, column: 5, scope: !15)
+!21 = !DILocation(line: 9, column: 1, scope: !4)
OpenPOWER on IntegriCloud