Index: llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp =================================================================== --- llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp +++ llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp @@ -7227,12 +7227,11 @@ SDValue ExtLoad = DAG.getExtLoad(ISD::SEXTLOAD, DL, VT, LN0->getChain(), LN0->getBasePtr(), N0.getValueType(), LN0->getMemOperand()); - CombineTo(N, ExtLoad); SDValue Trunc = DAG.getNode(ISD::TRUNCATE, SDLoc(N0), N0.getValueType(), ExtLoad); - CombineTo(N0.getNode(), Trunc, ExtLoad.getValue(1)); ExtendSetCCUses(SetCCs, Trunc, ExtLoad, DL, ISD::SIGN_EXTEND); - return SDValue(N, 0); // Return N so it doesn't get rechecked! + CombineTo(N0.getNode(), Trunc, ExtLoad.getValue(1)); + return CombineTo(N, ExtLoad); // Return N so it doesn't get rechecked! } } @@ -7288,10 +7287,9 @@ SDValue Trunc = DAG.getNode(ISD::TRUNCATE, SDLoc(N0.getOperand(0)), N0.getOperand(0).getValueType(), ExtLoad); - CombineTo(N, And); - CombineTo(N0.getOperand(0).getNode(), Trunc, ExtLoad.getValue(1)); ExtendSetCCUses(SetCCs, Trunc, ExtLoad, DL, ISD::SIGN_EXTEND); - return SDValue(N, 0); // Return N so it doesn't get rechecked! + CombineTo(N0.getOperand(0).getNode(), Trunc, ExtLoad.getValue(1)); + return CombineTo(N, And); // Return N so it doesn't get rechecked! } } } @@ -7530,12 +7528,9 @@ SDValue Trunc = DAG.getNode(ISD::TRUNCATE, SDLoc(N0), N0.getValueType(), ExtLoad); + ExtendSetCCUses(SetCCs, Trunc, ExtLoad, SDLoc(N), ISD::ZERO_EXTEND); CombineTo(N0.getNode(), Trunc, ExtLoad.getValue(1)); - - ExtendSetCCUses(SetCCs, Trunc, ExtLoad, SDLoc(N), - ISD::ZERO_EXTEND); - CombineTo(N, ExtLoad); - return SDValue(N, 0); // Return N so it doesn't get rechecked! + return CombineTo(N, ExtLoad); // Return N so it doesn't get rechecked! } } @@ -7585,11 +7580,9 @@ SDValue Trunc = DAG.getNode(ISD::TRUNCATE, SDLoc(N0.getOperand(0)), N0.getOperand(0).getValueType(), ExtLoad); - CombineTo(N, And); + ExtendSetCCUses(SetCCs, Trunc, ExtLoad, DL, ISD::ZERO_EXTEND); CombineTo(N0.getOperand(0).getNode(), Trunc, ExtLoad.getValue(1)); - ExtendSetCCUses(SetCCs, Trunc, ExtLoad, DL, - ISD::ZERO_EXTEND); - return SDValue(N, 0); // Return N so it doesn't get rechecked! + return CombineTo(N, And); // Return N so it doesn't get rechecked! } } } Index: llvm/trunk/test/CodeGen/X86/pr32284.ll =================================================================== --- llvm/trunk/test/CodeGen/X86/pr32284.ll +++ llvm/trunk/test/CodeGen/X86/pr32284.ll @@ -1,81 +1,17 @@ -; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py -; RUN: llc < %s -mtriple=i686-unknown -mcpu=skx | FileCheck %s --check-prefix=X86 -; RUN: llc < %s -mtriple=i686-unknown -mcpu=skx -O0 | FileCheck %s --check-prefix=X86-O0 -; RUN: llc < %s -mtriple=x86_64-unknown -mcpu=skx | FileCheck %s --check-prefix=X64 -; RUN: llc < %s -mtriple=x86_64-unknown -mcpu=skx -O0 | FileCheck %s --check-prefix=X64-O0 +; RUN: llc -O0 -mtriple=x86_64-unknown -mcpu=skx -o - %s | FileCheck %s --check-prefixes=CHECK,X64 +; RUN: llc -mtriple=x86_64-unknown -mcpu=skx -o - %s | FileCheck %s --check-prefixes=CHECK,X64 +; RUN: llc -O0 -mtriple=i686-unknown -mcpu=skx -o - %s | FileCheck %s --check-prefixes=CHECK,686 +; RUN: llc -mtriple=i686-unknown -mcpu=skx -o - %s | FileCheck %s --check-prefixes=CHECK,686 +; REQUIRES: asserts @c = external constant i8, align 1 define void @foo() { -; X86-LABEL: foo: -; X86: # BB#0: # %entry -; X86-NEXT: subl $8, %esp -; X86-NEXT: .Lcfi0: -; X86-NEXT: .cfi_def_cfa_offset 12 -; X86-NEXT: movzbl c, %eax -; X86-NEXT: xorl %ecx, %ecx -; X86-NEXT: testl %eax, %eax -; X86-NEXT: setne %cl -; X86-NEXT: testb %al, %al -; X86-NEXT: setne {{[0-9]+}}(%esp) -; X86-NEXT: xorl %edx, %edx -; X86-NEXT: cmpl %eax, %ecx -; X86-NEXT: setle %dl -; X86-NEXT: movl %edx, {{[0-9]+}}(%esp) -; X86-NEXT: addl $8, %esp -; X86-NEXT: retl -; -; X86-O0-LABEL: foo: -; X86-O0: # BB#0: # %entry -; X86-O0-NEXT: subl $12, %esp -; X86-O0-NEXT: .Lcfi0: -; X86-O0-NEXT: .cfi_def_cfa_offset 16 -; X86-O0-NEXT: movb c, %al -; X86-O0-NEXT: testb %al, %al -; X86-O0-NEXT: setne {{[0-9]+}}(%esp) -; X86-O0-NEXT: movzbl c, %ecx -; X86-O0-NEXT: testl %ecx, %ecx -; X86-O0-NEXT: setne %al -; X86-O0-NEXT: movzbl %al, %edx -; X86-O0-NEXT: subl %ecx, %edx -; X86-O0-NEXT: setle %al -; X86-O0-NEXT: andb $1, %al -; X86-O0-NEXT: movzbl %al, %ecx -; X86-O0-NEXT: movl %ecx, {{[0-9]+}}(%esp) -; X86-O0-NEXT: movl %edx, (%esp) # 4-byte Spill -; X86-O0-NEXT: addl $12, %esp -; X86-O0-NEXT: retl -; -; X64-LABEL: foo: -; X64: # BB#0: # %entry -; X64-NEXT: movzbl {{.*}}(%rip), %eax -; X64-NEXT: testb %al, %al -; X64-NEXT: setne -{{[0-9]+}}(%rsp) -; X64-NEXT: xorl %ecx, %ecx -; X64-NEXT: testl %eax, %eax -; X64-NEXT: setne %cl -; X64-NEXT: xorl %edx, %edx -; X64-NEXT: cmpl %eax, %ecx -; X64-NEXT: setle %dl -; X64-NEXT: movl %edx, -{{[0-9]+}}(%rsp) -; X64-NEXT: retq -; -; X64-O0-LABEL: foo: -; X64-O0: # BB#0: # %entry -; X64-O0-NEXT: movb {{.*}}(%rip), %al -; X64-O0-NEXT: testb %al, %al -; X64-O0-NEXT: setne -{{[0-9]+}}(%rsp) -; X64-O0-NEXT: movzbl {{.*}}(%rip), %ecx -; X64-O0-NEXT: testl %ecx, %ecx -; X64-O0-NEXT: setne %al -; X64-O0-NEXT: movzbl %al, %edx -; X64-O0-NEXT: subl %ecx, %edx -; X64-O0-NEXT: setle %al -; X64-O0-NEXT: andb $1, %al -; X64-O0-NEXT: movzbl %al, %ecx -; X64-O0-NEXT: movl %ecx, -{{[0-9]+}}(%rsp) -; X64-O0-NEXT: movl %edx, -{{[0-9]+}}(%rsp) # 4-byte Spill -; X64-O0-NEXT: retq +; CHECK-LABEL: foo: +; CHECK: # BB#0: # %entry +; CHECK-DAG: setne +; CHECK-DAG: setle +; CHECK: ret entry: %a = alloca i8, align 1 %b = alloca i32, align 4 @@ -100,3 +36,125 @@ store i32 %conv8, i32* %b, align 4 ret void } + +@var_5 = external global i32, align 4 +@var_57 = external global i64, align 8 +@_ZN8struct_210member_2_0E = external global i64, align 8 + +define void @f1() { +; CHECK-LABEL: f1: +; CHECK: # BB#0: # %entry +; CHECK: sete +; X64: addq $7093, {{.*}} +; 686: addl $7093, {{.*}} +; CHECK: ret +entry: + %a = alloca i8, align 1 + %0 = load i32, i32* @var_5, align 4 + %conv = sext i32 %0 to i64 + %add = add nsw i64 %conv, 8381627093 + %tobool = icmp ne i64 %add, 0 + %frombool = zext i1 %tobool to i8 + store i8 %frombool, i8* %a, align 1 + %1 = load i32, i32* @var_5, align 4 + %neg = xor i32 %1, -1 + %tobool1 = icmp ne i32 %neg, 0 + %lnot = xor i1 %tobool1, true + %conv2 = zext i1 %lnot to i64 + %2 = load i32, i32* @var_5, align 4 + %conv3 = sext i32 %2 to i64 + %add4 = add nsw i64 %conv3, 7093 + %cmp = icmp sgt i64 %conv2, %add4 + %conv5 = zext i1 %cmp to i64 + store i64 %conv5, i64* @var_57, align 8 + %3 = load i32, i32* @var_5, align 4 + %neg6 = xor i32 %3, -1 + %tobool7 = icmp ne i32 %neg6, 0 + %lnot8 = xor i1 %tobool7, true + %conv9 = zext i1 %lnot8 to i64 + store i64 %conv9, i64* @_ZN8struct_210member_2_0E, align 8 + ret void +} + + +@var_7 = external global i8, align 1 + +define void @f2() { +; CHECK-LABEL: f2: +; CHECK: # BB#0: # %entry +; X64: movzbl {{.*}}(%rip), %[[R:[a-z]*]] +; 686: movzbl {{.*}}, %[[R:[a-z]*]] +; CHECK: test{{[qlwb]}} %[[R]], %[[R]] +; CHECK: sete {{.*}} +; CHECK: ret +entry: + %a = alloca i16, align 2 + %0 = load i8, i8* @var_7, align 1 + %conv = zext i8 %0 to i32 + %1 = load i8, i8* @var_7, align 1 + %tobool = icmp ne i8 %1, 0 + %lnot = xor i1 %tobool, true + %conv1 = zext i1 %lnot to i32 + %xor = xor i32 %conv, %conv1 + %conv2 = trunc i32 %xor to i16 + store i16 %conv2, i16* %a, align 2 + %2 = load i8, i8* @var_7, align 1 + %conv3 = zext i8 %2 to i16 + %tobool4 = icmp ne i16 %conv3, 0 + %lnot5 = xor i1 %tobool4, true + %conv6 = zext i1 %lnot5 to i32 + %3 = load i8, i8* @var_7, align 1 + %conv7 = zext i8 %3 to i32 + %cmp = icmp eq i32 %conv6, %conv7 + %conv8 = zext i1 %cmp to i32 + %conv9 = trunc i32 %conv8 to i16 + store i16 %conv9, i16* undef, align 2 + ret void +} + + +@var_13 = external global i32, align 4 +@var_16 = external global i32, align 4 +@var_46 = external global i32, align 4 + +define void @f3() #0 { +; CHECK-LABEL: f3: +; X64-DAG: movl var_13(%rip), {{.*}} +; X64-DAG: movl var_16(%rip), {{.*}} +; X64-DAG: movl {{.*}},{{.*}}var_46{{.*}} +; X64: retq +; 686-DAG: movl var_13, {{.*}} +; 686-DAG: movl var_16, {{.*}} +; 686-DAG: movl {{.*}},{{.*}}var_46{{.*}} +; 686: retl +entry: + %a = alloca i64, align 8 + %0 = load i32, i32* @var_13, align 4 + %neg = xor i32 %0, -1 + %conv = zext i32 %neg to i64 + %1 = load i32, i32* @var_13, align 4 + %tobool = icmp ne i32 %1, 0 + %lnot = xor i1 %tobool, true + %conv1 = zext i1 %lnot to i64 + %2 = load i32, i32* @var_13, align 4 + %neg2 = xor i32 %2, -1 + %3 = load i32, i32* @var_16, align 4 + %xor = xor i32 %neg2, %3 + %conv3 = zext i32 %xor to i64 + %and = and i64 %conv1, %conv3 + %or = or i64 %conv, %and + store i64 %or, i64* %a, align 8 + %4 = load i32, i32* @var_13, align 4 + %neg4 = xor i32 %4, -1 + %conv5 = zext i32 %neg4 to i64 + %5 = load i32, i32* @var_13, align 4 + %tobool6 = icmp ne i32 %5, 0 + %lnot7 = xor i1 %tobool6, true + %conv8 = zext i1 %lnot7 to i64 + %and9 = and i64 %conv8, 0 + %or10 = or i64 %conv5, %and9 + %conv11 = trunc i64 %or10 to i32 + store i32 %conv11, i32* @var_46, align 4 + ret void +} +