Index: lib/Transforms/InstCombine/InstCombineAndOrXor.cpp =================================================================== --- lib/Transforms/InstCombine/InstCombineAndOrXor.cpp +++ lib/Transforms/InstCombine/InstCombineAndOrXor.cpp @@ -1209,8 +1209,7 @@ Value *Cast1Src = Cast1->getOperand(0); // fold logic(cast(A), cast(B)) -> cast(logic(A, B)) - if ((!isa(Cast0Src) || !isa(Cast1Src)) && - shouldOptimizeCast(Cast0) && shouldOptimizeCast(Cast1)) { + if (shouldOptimizeCast(Cast0) && shouldOptimizeCast(Cast1)) { Value *NewOp = Builder->CreateBinOp(LogicOpc, Cast0Src, Cast1Src, I.getName()); return CastInst::Create(CastOpcode, NewOp, DestTy); Index: lib/Transforms/InstCombine/InstCombineCasts.cpp =================================================================== --- lib/Transforms/InstCombine/InstCombineCasts.cpp +++ lib/Transforms/InstCombine/InstCombineCasts.cpp @@ -623,7 +623,9 @@ if (CI.getType() == In->getType()) return replaceInstUsesWith(CI, In); - return CastInst::CreateIntegerCast(In, CI.getType(), false/*ZExt*/); + + Value *IntCast = Builder->CreateIntCast(In, CI.getType(), false); + return replaceInstUsesWith(CI, IntCast); } } } @@ -890,16 +892,27 @@ BinaryOperator *SrcI = dyn_cast(Src); if (SrcI && SrcI->getOpcode() == Instruction::Or) { - // zext (or icmp, icmp) --> or (zext icmp), (zext icmp) if at least one - // of the (zext icmp) will be transformed. + // zext (or icmp, icmp) -> or (zext icmp), (zext icmp) if at least one + // of the (zext icmp) can be eliminated. If so, immediately perform the + // according elimination. ICmpInst *LHS = dyn_cast(SrcI->getOperand(0)); ICmpInst *RHS = dyn_cast(SrcI->getOperand(1)); if (LHS && RHS && LHS->hasOneUse() && RHS->hasOneUse() && (transformZExtICmp(LHS, CI, false) || transformZExtICmp(RHS, CI, false))) { - Value *LCast = Builder->CreateZExt(LHS, CI.getType(), LHS->getName()); - Value *RCast = Builder->CreateZExt(RHS, CI.getType(), RHS->getName()); - return BinaryOperator::Create(Instruction::Or, LCast, RCast); + // zext (or icmp, icmp) -> or (zext icmp), (zext icmp) + auto *LCast = cast( + Builder->CreateZExt(LHS, CI.getType(), LHS->getName())); + auto *RCast = cast( + Builder->CreateZExt(RHS, CI.getType(), RHS->getName())); + BinaryOperator *Or = + BinaryOperator::Create(Instruction::Or, LCast, RCast); + + // Perform the elimination. + transformZExtICmp(LHS, *LCast); + transformZExtICmp(RHS, *LCast); + + return Or; } } Index: test/Transforms/InstCombine/zext-or-icmp.ll =================================================================== --- test/Transforms/InstCombine/zext-or-icmp.ll +++ test/Transforms/InstCombine/zext-or-icmp.ll @@ -13,8 +13,8 @@ ; CHECK-LABEL: zext_or_icmp_icmp( ; CHECK-NEXT: %mask = and i8 %a, 1 ; CHECK-NEXT: %toBool2 = icmp eq i8 %b, 0 -; CHECK-NEXT: %1 = xor i8 %mask, 1 ; CHECK-NEXT: %toBool22 = zext i1 %toBool2 to i8 +; CHECK-NEXT: %1 = xor i8 %mask, 1 ; CHECK-NEXT: %zext = or i8 %1, %toBool22 ; CHECK-NEXT: ret i8 %zext } Index: test/Transforms/InstCombine/zext.ll =================================================================== --- test/Transforms/InstCombine/zext.ll +++ test/Transforms/InstCombine/zext.ll @@ -70,3 +70,72 @@ ret <2 x i64> %zext2 } +; Assert that zexts in and(zext(icmp), zext(icmp)) can be folded. +; CHECK-LABEL: @fold_and_zext_icmp( +; CHECK-NEXT: [[ICMP1:%.*]] = icmp sgt i64 %a, %b +; CHECK-NEXT: [[ICMP2:%.*]] = icmp slt i64 %a, %c +; CHECK-NEXT: [[AND:%.*]] = and i1 [[ICMP1]], [[ICMP2]] +; CHECK-NEXT: [[ZEXT:%.*]] = zext i1 [[AND]] to i8 +; CHECK-NEXT: ret i8 [[ZEXT]] +define i8 @fold_and_zext_icmp(i64 %a, i64 %b, i64 %c) { + %1 = icmp sgt i64 %a, %b + %2 = zext i1 %1 to i8 + %3 = icmp slt i64 %a, %c + %4 = zext i1 %3 to i8 + %5 = and i8 %2, %4 + ret i8 %5 +} + +; Assert that zexts in or(zext(icmp), zext(icmp)) can be folded. +; CHECK-LABEL: @fold_or_zext_icmp( +; CHECK-NEXT: [[ICMP1:%.*]] = icmp sgt i64 %a, %b +; CHECK-NEXT: [[ICMP2:%.*]] = icmp slt i64 %a, %c +; CHECK-NEXT: [[OR:%.*]] = or i1 [[ICMP1]], [[ICMP2]] +; CHECK-NEXT: [[ZEXT:%.*]] = zext i1 [[OR]] to i8 +; CHECK-NEXT: ret i8 [[ZEXT]] +define i8 @fold_or_zext_icmp(i64 %a, i64 %b, i64 %c) { + %1 = icmp sgt i64 %a, %b + %2 = zext i1 %1 to i8 + %3 = icmp slt i64 %a, %c + %4 = zext i1 %3 to i8 + %5 = or i8 %2, %4 + ret i8 %5 +} + +; Assert that zexts in xor(zext(icmp), zext(icmp)) can be folded. +; CHECK-LABEL: @fold_xor_zext_icmp( +; CHECK-NEXT: [[ICMP1:%.*]] = icmp sgt i64 %a, %b +; CHECK-NEXT: [[ICMP2:%.*]] = icmp slt i64 %a, %c +; CHECK-NEXT: [[XOR:%.*]] = xor i1 [[ICMP1]], [[ICMP2]] +; CHECK-NEXT: [[ZEXT:%.*]] = zext i1 [[XOR]] to i8 +; CHECK-NEXT: ret i8 [[ZEXT]] +define i8 @fold_xor_zext_icmp(i64 %a, i64 %b, i64 %c) { + %1 = icmp sgt i64 %a, %b + %2 = zext i1 %1 to i8 + %3 = icmp slt i64 %a, %c + %4 = zext i1 %3 to i8 + %5 = xor i8 %2, %4 + ret i8 %5 +} + +; Assert that zexts in logic(zext(icmp), zext(icmp)) are also folded accross +; nested logical operators. +; CHECK-LABEL: @fold_nested_logic_zext_icmp( +; CHECK-NEXT: [[ICMP1:%.*]] = icmp sgt i64 %a, %b +; CHECK-NEXT: [[ICMP2:%.*]] = icmp slt i64 %a, %c +; CHECK-NEXT: [[AND:%.*]] = and i1 [[ICMP1]], [[ICMP2]] +; CHECK-NEXT: [[ICMP3:%.*]] = icmp eq i64 %a, %d +; CHECK-NEXT: [[OR:%.*]] = or i1 [[AND]], [[ICMP3]] +; CHECK-NEXT: [[ZEXT:%.*]] = zext i1 [[OR]] to i8 +; CHECK-NEXT: ret i8 [[ZEXT]] +define i8 @fold_nested_logic_zext_icmp(i64 %a, i64 %b, i64 %c, i64 %d) { + %1 = icmp sgt i64 %a, %b + %2 = zext i1 %1 to i8 + %3 = icmp slt i64 %a, %c + %4 = zext i1 %3 to i8 + %5 = and i8 %2, %4 + %6 = icmp eq i64 %a, %d + %7 = zext i1 %6 to i8 + %8 = or i8 %5, %7 + ret i8 %8 +}