diff --git a/llvm/lib/Target/X86/X86InstrCompiler.td b/llvm/lib/Target/X86/X86InstrCompiler.td index a1cef5be81f4..2e935db9f5a1 100644 --- a/llvm/lib/Target/X86/X86InstrCompiler.td +++ b/llvm/lib/Target/X86/X86InstrCompiler.td @@ -1036,34 +1036,21 @@ def ADD32rr_DB : I<0, Pseudo, (outs GR32:$dst), (ins GR32:$src1, GR32:$src2), def ADD64rr_DB : I<0, Pseudo, (outs GR64:$dst), (ins GR64:$src1, GR64:$src2), "", // orq/addq REG, REG [(set GR64:$dst, (or_is_add GR64:$src1, GR64:$src2))]>; - - -def ADD16ri_DB : I<0, Pseudo, (outs GR16:$dst), (ins GR16:$src1, i16imm:$src2), - "", // orw/addw REG, imm - [(set GR16:$dst, (or_is_add GR16:$src1, imm:$src2))]>; -def ADD32ri_DB : I<0, Pseudo, (outs GR32:$dst), (ins GR32:$src1, i32imm:$src2), - "", // orl/addl REG, imm - [(set GR32:$dst, (or_is_add GR32:$src1, imm:$src2))]>; -def ADD64ri32_DB : I<0, Pseudo, - (outs GR64:$dst), (ins GR64:$src1, i64i32imm:$src2), - "", // orq/addq REG, imm - [(set GR64:$dst, (or_is_add GR64:$src1, - i64immSExt32:$src2))]>; - -def ADD16ri8_DB : I<0, Pseudo, - (outs GR16:$dst), (ins GR16:$src1, i16i8imm:$src2), - "", // orw/addw REG, imm8 - [(set GR16:$dst,(or_is_add GR16:$src1,i16immSExt8:$src2))]>; -def ADD32ri8_DB : I<0, Pseudo, - (outs GR32:$dst), (ins GR32:$src1, i32i8imm:$src2), - "", // orl/addl REG, imm8 - [(set GR32:$dst,(or_is_add GR32:$src1,i32immSExt8:$src2))]>; -def ADD64ri8_DB : I<0, Pseudo, - (outs GR64:$dst), (ins GR64:$src1, i64i8imm:$src2), - "", // orq/addq REG, imm8 - [(set GR64:$dst, (or_is_add GR64:$src1, - i64immSExt8:$src2))]>; } + +def : Pat<(or_is_add GR16:$src1, imm:$src2), + (ADD16ri GR16:$src1, imm:$src2)>; +def : Pat<(or_is_add GR32:$src1, imm:$src2), + (ADD32ri GR32:$src1, imm:$src2)>; +def : Pat<(or_is_add GR64:$src1, i64immSExt32:$src2), + (ADD64ri32 GR64:$src1, i64immSExt32:$src2)>; + +def : Pat<(or_is_add GR16:$src1, i16immSExt8:$src2), + (ADD16ri8 GR16:$src1, i16immSExt8:$src2)>; +def : Pat<(or_is_add GR32:$src1, i32immSExt8:$src2), + (ADD32ri8 GR32:$src1, i32immSExt8:$src2)>; +def : Pat<(or_is_add GR64:$src1, i64immSExt8:$src2), + (ADD64ri8 GR64:$src1, i64immSExt8:$src2)>; } // AddedComplexity diff --git a/llvm/lib/Target/X86/X86InstrInfo.cpp b/llvm/lib/Target/X86/X86InstrInfo.cpp index 204a187dc5d7..5e16a2093dde 100644 --- a/llvm/lib/Target/X86/X86InstrInfo.cpp +++ b/llvm/lib/Target/X86/X86InstrInfo.cpp @@ -68,20 +68,14 @@ X86InstrInfo::X86InstrInfo(X86TargetMachine &tm) { X86::ADC64rr, X86::ADC64mr }, { X86::ADD16ri, X86::ADD16mi }, { X86::ADD16ri8, X86::ADD16mi8 }, - { X86::ADD16ri_DB, X86::ADD16mi | TB_NOT_REVERSABLE }, - { X86::ADD16ri8_DB, X86::ADD16mi8 | TB_NOT_REVERSABLE }, { X86::ADD16rr, X86::ADD16mr }, { X86::ADD16rr_DB, X86::ADD16mr | TB_NOT_REVERSABLE }, { X86::ADD32ri, X86::ADD32mi }, { X86::ADD32ri8, X86::ADD32mi8 }, - { X86::ADD32ri_DB, X86::ADD32mi | TB_NOT_REVERSABLE }, - { X86::ADD32ri8_DB, X86::ADD32mi8 | TB_NOT_REVERSABLE }, { X86::ADD32rr, X86::ADD32mr }, { X86::ADD32rr_DB, X86::ADD32mr | TB_NOT_REVERSABLE }, { X86::ADD64ri32, X86::ADD64mi32 }, { X86::ADD64ri8, X86::ADD64mi8 }, - { X86::ADD64ri32_DB,X86::ADD64mi32 | TB_NOT_REVERSABLE }, - { X86::ADD64ri8_DB, X86::ADD64mi8 | TB_NOT_REVERSABLE }, { X86::ADD64rr, X86::ADD64mr }, { X86::ADD64rr_DB, X86::ADD64mr | TB_NOT_REVERSABLE }, { X86::ADD8ri, X86::ADD8mi }, @@ -1166,8 +1160,6 @@ X86InstrInfo::convertToThreeAddressWithLEA(unsigned MIOpc, break; case X86::ADD16ri: case X86::ADD16ri8: - case X86::ADD16ri_DB: - case X86::ADD16ri8_DB: addRegOffset(MIB, leaInReg, true, MI->getOperand(2).getImm()); break; case X86::ADD16rr: @@ -1432,8 +1424,6 @@ X86InstrInfo::convertToThreeAddress(MachineFunction::iterator &MFI, } case X86::ADD64ri32: case X86::ADD64ri8: - case X86::ADD64ri32_DB: - case X86::ADD64ri8_DB: assert(MI->getNumOperands() >= 3 && "Unknown add instruction!"); NewMI = addRegOffset(BuildMI(MF, MI->getDebugLoc(), get(X86::LEA64r)) .addReg(Dest, RegState::Define | @@ -1441,9 +1431,7 @@ X86InstrInfo::convertToThreeAddress(MachineFunction::iterator &MFI, Src, isKill, MI->getOperand(2).getImm()); break; case X86::ADD32ri: - case X86::ADD32ri8: - case X86::ADD32ri_DB: - case X86::ADD32ri8_DB: { + case X86::ADD32ri8: { assert(MI->getNumOperands() >= 3 && "Unknown add instruction!"); unsigned Opc = is64Bit ? X86::LEA64_32r : X86::LEA32r; NewMI = addRegOffset(BuildMI(MF, MI->getDebugLoc(), get(Opc)) @@ -1454,8 +1442,6 @@ X86InstrInfo::convertToThreeAddress(MachineFunction::iterator &MFI, } case X86::ADD16ri: case X86::ADD16ri8: - case X86::ADD16ri_DB: - case X86::ADD16ri8_DB: if (DisableLEA16) return is64Bit ? convertToThreeAddressWithLEA(MIOpc, MFI, MBBI, LV) : 0; assert(MI->getNumOperands() >= 3 && "Unknown add instruction!"); diff --git a/llvm/lib/Target/X86/X86MCInstLower.cpp b/llvm/lib/Target/X86/X86MCInstLower.cpp index 8f90d8728291..662717bae713 100644 --- a/llvm/lib/Target/X86/X86MCInstLower.cpp +++ b/llvm/lib/Target/X86/X86MCInstLower.cpp @@ -437,15 +437,9 @@ ReSimplify: // These are pseudo-ops for OR to help with the OR->ADD transformation. We do // this with an ugly goto in case the resultant OR uses EAX and needs the // short form. - case X86::ADD16rr_DB: OutMI.setOpcode(X86::OR16rr); goto ReSimplify; - case X86::ADD32rr_DB: OutMI.setOpcode(X86::OR32rr); goto ReSimplify; - case X86::ADD64rr_DB: OutMI.setOpcode(X86::OR64rr); goto ReSimplify; - case X86::ADD16ri_DB: OutMI.setOpcode(X86::OR16ri); goto ReSimplify; - case X86::ADD32ri_DB: OutMI.setOpcode(X86::OR32ri); goto ReSimplify; - case X86::ADD64ri32_DB: OutMI.setOpcode(X86::OR64ri32); goto ReSimplify; - case X86::ADD16ri8_DB: OutMI.setOpcode(X86::OR16ri8); goto ReSimplify; - case X86::ADD32ri8_DB: OutMI.setOpcode(X86::OR32ri8); goto ReSimplify; - case X86::ADD64ri8_DB: OutMI.setOpcode(X86::OR64ri8); goto ReSimplify; + case X86::ADD16rr_DB: OutMI.setOpcode(X86::OR16rr); goto ReSimplify; + case X86::ADD32rr_DB: OutMI.setOpcode(X86::OR32rr); goto ReSimplify; + case X86::ADD64rr_DB: OutMI.setOpcode(X86::OR64rr); goto ReSimplify; // The assembler backend wants to see branches in their small form and relax // them to their large form. The JIT can only handle the large form because diff --git a/llvm/test/CodeGen/X86/3addr-or.ll b/llvm/test/CodeGen/X86/3addr-or.ll index 912bdc215474..30a1f36850de 100644 --- a/llvm/test/CodeGen/X86/3addr-or.ll +++ b/llvm/test/CodeGen/X86/3addr-or.ll @@ -1,9 +1,9 @@ ; RUN: llc < %s -mtriple=x86_64-apple-darwin | FileCheck %s ; rdar://7527734 -define i32 @test1(i32 %x) nounwind readnone ssp { +define i32 @test(i32 %x) nounwind readnone ssp { entry: -; CHECK: test1: +; CHECK: test: ; CHECK: leal 3(%rdi), %eax %0 = shl i32 %x, 5 ; [#uses=1] %1 = or i32 %0, 3 ; [#uses=1] @@ -25,37 +25,3 @@ define i64 @test2(i8 %A, i8 %B) nounwind { %H = or i64 %G, %E ; [#uses=1] ret i64 %H } - -;; Test that OR is only emitted as LEA, not as ADD. - -define void @test3(i32 %x, i32* %P) nounwind readnone ssp { -entry: -; No reason to emit an add here, should be an or. -; CHECK: test3: -; CHECK: orl $3, %edi - %0 = shl i32 %x, 5 - %1 = or i32 %0, 3 - store i32 %1, i32* %P - ret void -} - -define i32 @test4(i32 %a, i32 %b) nounwind readnone ssp { -entry: - %and = and i32 %a, 6 - %and2 = and i32 %b, 16 - %or = or i32 %and2, %and - ret i32 %or -; CHECK: test4: -; CHECK: leal (%rsi,%rdi), %eax -} - -define void @test5(i32 %a, i32 %b, i32* nocapture %P) nounwind ssp { -entry: - %and = and i32 %a, 6 - %and2 = and i32 %b, 16 - %or = or i32 %and2, %and - store i32 %or, i32* %P, align 4 - ret void -; CHECK: test5: -; CHECK: orl -}