[RISCV] With Zbb, fold (sext_inreg (abs X)) -> (max X, (negw X))

With Zbb, abs is expanded to (max X, neg) by default. If X has 33 or
more sign bits, we can expand it a little early using negw instead of
neg to save a sext_inreg. If X started as a 32 bit value, type
legalization would have inserted a sext before the abs so X having
33 sign bits should always be true.

Note: I've used ISD::FREEZE here since we increase the number of uses.
Our default expansion for ABS doesn't do that, but I think that's a bug.

We can't do this with custom type legalization because ISD::FREEZE
doesn't propagate sign bits so later DAG combine won't expand be
able to see optmize it.

Alives2 https://alive2.llvm.org/ce/z/Gx3RNe

Reviewed By: spatel

Differential Revision: https://reviews.llvm.org/D120597
This commit is contained in:
Craig Topper 2022-03-03 14:21:59 -08:00
parent b4c1cbff79
commit 3d4e83f17d
2 changed files with 33 additions and 7 deletions

View File

@ -1041,7 +1041,7 @@ RISCVTargetLowering::RISCVTargetLowering(const TargetMachine &TM,
}
setTargetDAGCombine(ISD::ANY_EXTEND);
setTargetDAGCombine(ISD::INTRINSIC_WO_CHAIN);
if (Subtarget.hasStdExtZfh())
if (Subtarget.hasStdExtZfh() || Subtarget.hasStdExtZbb())
setTargetDAGCombine(ISD::SIGN_EXTEND_INREG);
if (Subtarget.hasStdExtF()) {
setTargetDAGCombine(ISD::ZERO_EXTEND);
@ -7617,15 +7617,43 @@ static SDValue performXORCombine(SDNode *N, SelectionDAG &DAG) {
return combineSelectAndUseCommutative(N, DAG, /*AllOnes*/ false);
}
static SDValue performSIGN_EXTEND_INREG(SDNode *N, SelectionDAG &DAG) {
static SDValue
performSIGN_EXTEND_INREGCombine(SDNode *N, SelectionDAG &DAG,
const RISCVSubtarget &Subtarget) {
SDValue Src = N->getOperand(0);
EVT VT = N->getValueType(0);
// Fold (sext_inreg (fmv_x_anyexth X), i16) -> (fmv_x_signexth X)
if (Src.getOpcode() == RISCVISD::FMV_X_ANYEXTH &&
cast<VTSDNode>(N->getOperand(1))->getVT().bitsGE(MVT::i16))
return DAG.getNode(RISCVISD::FMV_X_SIGNEXTH, SDLoc(N), N->getValueType(0),
return DAG.getNode(RISCVISD::FMV_X_SIGNEXTH, SDLoc(N), VT,
Src.getOperand(0));
// Fold (i64 (sext_inreg (abs X), i32)) ->
// (i64 (smax (sext_inreg (neg X), i32), X)) if X has more than 32 sign bits.
// The (sext_inreg (neg X), i32) will be selected to negw by isel. This
// pattern occurs after type legalization of (i32 (abs X)) on RV64 if the user
// of the (i32 (abs X)) is a sext or setcc or something else that causes type
// legalization to add a sext_inreg after the abs. The (i32 (abs X)) will have
// been type legalized to (i64 (abs (sext_inreg X, i32))), but the sext_inreg
// may get combined into an earlier operation so we need to use
// ComputeNumSignBits.
// NOTE: (i64 (sext_inreg (abs X), i32)) can also be created for
// (i64 (ashr (shl (abs X), 32), 32)) without any type legalization so
// we can't assume that X has 33 sign bits. We must check.
if (Subtarget.hasStdExtZbb() && Subtarget.is64Bit() &&
Src.getOpcode() == ISD::ABS && Src.hasOneUse() && VT == MVT::i64 &&
cast<VTSDNode>(N->getOperand(1))->getVT() == MVT::i32 &&
DAG.ComputeNumSignBits(Src.getOperand(0)) > 32) {
SDLoc DL(N);
SDValue Freeze = DAG.getFreeze(Src.getOperand(0));
SDValue Neg =
DAG.getNode(ISD::SUB, DL, VT, DAG.getConstant(0, DL, MVT::i64), Freeze);
Neg = DAG.getNode(ISD::SIGN_EXTEND_INREG, DL, MVT::i64, Neg,
DAG.getValueType(MVT::i32));
return DAG.getNode(ISD::SMAX, DL, MVT::i64, Freeze, Neg);
}
return SDValue();
}
@ -8244,7 +8272,7 @@ SDValue RISCVTargetLowering::PerformDAGCombine(SDNode *N,
case ISD::XOR:
return performXORCombine(N, DAG);
case ISD::SIGN_EXTEND_INREG:
return performSIGN_EXTEND_INREG(N, DAG);
return performSIGN_EXTEND_INREGCombine(N, DAG, Subtarget);
case ISD::ANY_EXTEND:
return performANY_EXTENDCombine(N, DCI, Subtarget);
case ISD::ZERO_EXTEND:

View File

@ -960,7 +960,6 @@ define i32 @abs_i32(i32 %x) {
ret i32 %abs
}
; FIXME: We can remove the sext.w on RV64ZBB by using negw.
define signext i32 @abs_i32_sext(i32 signext %x) {
; RV64I-LABEL: abs_i32_sext:
; RV64I: # %bb.0:
@ -971,9 +970,8 @@ define signext i32 @abs_i32_sext(i32 signext %x) {
;
; RV64ZBB-LABEL: abs_i32_sext:
; RV64ZBB: # %bb.0:
; RV64ZBB-NEXT: neg a1, a0
; RV64ZBB-NEXT: negw a1, a0
; RV64ZBB-NEXT: max a0, a0, a1
; RV64ZBB-NEXT: sext.w a0, a0
; RV64ZBB-NEXT: ret
%abs = tail call i32 @llvm.abs.i32(i32 %x, i1 true)
ret i32 %abs