Index: llvm/lib/Target/SystemZ/SystemZISelLowering.h =================================================================== --- llvm/lib/Target/SystemZ/SystemZISelLowering.h +++ llvm/lib/Target/SystemZ/SystemZISelLowering.h @@ -441,11 +441,7 @@ bool isTruncateFree(EVT, EVT) const override; bool shouldFormOverflowOp(unsigned Opcode, EVT VT, - bool MathUsed) const override { - // Using overflow ops for overflow checks only should beneficial on - // SystemZ. - return TargetLowering::shouldFormOverflowOp(Opcode, VT, true); - } + bool MathUsed) const override; const char *getTargetNodeName(unsigned Opcode) const override; std::pair Index: llvm/lib/Target/SystemZ/SystemZISelLowering.cpp =================================================================== --- llvm/lib/Target/SystemZ/SystemZISelLowering.cpp +++ llvm/lib/Target/SystemZ/SystemZISelLowering.cpp @@ -981,6 +981,13 @@ return FromBits > ToBits; } +bool SystemZTargetLowering::shouldFormOverflowOp(unsigned Opcode, EVT VT, + bool MathUsed) const { + // Form add and sub with overflow intrinsics regardless of any extra users + // of the math result. + return VT == MVT::i32 || VT == MVT::i64; +} + //===----------------------------------------------------------------------===// // Inline asm support //===----------------------------------------------------------------------===// Index: llvm/test/CodeGen/SystemZ/codegenprepare-form-OF-ops.ll =================================================================== --- /dev/null +++ llvm/test/CodeGen/SystemZ/codegenprepare-form-OF-ops.ll @@ -0,0 +1,54 @@ +; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z14 -O3 | FileCheck %s +; +; Check that CodeGenPrepare transforms these functions to use +; uadd.with.overflow / usub.with.overflow intrinsics so that the compare +; instruction is eliminated. + +define i32 @uaddo_32(i32 %arg) { +; CHECK-LABEL: uaddo_32: +; CHECK: alhsik %r0, %r2, -1 +; CHECK: locrnle %r2, %r0 +; CHECK: br %r14 + +bb: + %tmp10 = icmp ne i32 %arg, 0 + %tmp11 = add nsw i32 %arg, -1 + %tmp12 = select i1 %tmp10, i32 %tmp11, i32 %arg + ret i32 %tmp12 +} + +define i64 @uaddo_64(i64 %arg) { +; CHECK-LABEL: uaddo_64: +; CHECK: alghsik %r0, %r2, -1 +; CHECK: locgrnle %r2, %r0 +; CHECK: br %r14 +bb: + %tmp10 = icmp ne i64 %arg, 0 + %tmp11 = add nsw i64 %arg, -1 + %tmp12 = select i1 %tmp10, i64 %tmp11, i64 %arg + ret i64 %tmp12 +} + +define i32 @usubo_32(i32 %arg) { +; CHECK-LABEL: usubo_32: +; CHECK: alhsik %r0, %r2, -1 +; CHECK: locrle %r2, %r0 +; CHECK: br %r14 +bb: + %tmp10 = icmp eq i32 %arg, 0 + %tmp11 = sub nsw i32 %arg, 1 + %tmp12 = select i1 %tmp10, i32 %tmp11, i32 %arg + ret i32 %tmp12 +} + +define i64 @usubo_64(i64 %arg) { +; CHECK-LABEL: usubo_64: +; CHECK: alghsik %r0, %r2, -1 +; CHECK: locgrle %r2, %r0 +; CHECK: br %r14 +bb: + %tmp10 = icmp eq i64 %arg, 0 + %tmp11 = sub nsw i64 %arg, 1 + %tmp12 = select i1 %tmp10, i64 %tmp11, i64 %arg + ret i64 %tmp12 +}