Index: lib/Transforms/InstCombine/InstCombineAndOrXor.cpp =================================================================== --- lib/Transforms/InstCombine/InstCombineAndOrXor.cpp +++ lib/Transforms/InstCombine/InstCombineAndOrXor.cpp @@ -1212,6 +1212,13 @@ isa(CastSrc) && CI->getDestTy()->isVectorTy()) return false; + // Don't optimize the cast if it is a (zext icmp) that can already be + // eliminated. + if (auto *ZExt = dyn_cast(CI)) + if (auto *ICmp = dyn_cast(CastSrc)) + if (transformZExtICmp(ICmp, *ZExt, false)) + return false; + return true; } @@ -1260,8 +1267,7 @@ 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: test/Transforms/InstCombine/zext.ll =================================================================== --- test/Transforms/InstCombine/zext.ll +++ test/Transforms/InstCombine/zext.ll @@ -73,3 +73,41 @@ ret <2 x i64> %zext2 } +; Assert that zexts in logic(zext(icmp), zext(icmp)) can be folded +; CHECK-LABEL: @fold_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: [[ZEXT:%.*]] = zext i1 [[AND]] to i8 +; CHECK-NEXT: ret i8 [[ZEXT]] +define i8 @fold_logic_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 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 +} +