maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Efficient lowering of vector sdiv when the divisor is a splatted power of two constant. 

PR 14848. The lowered sequence is based on the existing sequence the target-independent
DAG Combiner creates for the scalar case.

Patch by Zvi Rackover.

llvm-svn: 171953
This commit is contained in:
Nadav Rotem 2013-01-09 05:14:33 +00:00
parent 69dce49c76
commit 977e0be4a0
3 changed files with 123 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -1047,6 +1047,8 @@ X86TargetLowering::X86TargetLowering(X86TargetMachine &TM)
setOperationAction(ISD::SRA, MVT::v4i32, Custom);
}
setOperationAction(ISD::SDIV, MVT::v8i16, Custom);
setOperationAction(ISD::SDIV, MVT::v4i32, Custom);
}
if (!TM.Options.UseSoftFloat && Subtarget->hasFp256()) {
@ -1111,6 +1113,8 @@ X86TargetLowering::X86TargetLowering(X86TargetMachine &TM)
setOperationAction(ISD::SRA, MVT::v16i16, Custom);
setOperationAction(ISD::SRA, MVT::v32i8, Custom);
setOperationAction(ISD::SDIV, MVT::v16i16, Custom);
setOperationAction(ISD::SETCC, MVT::v32i8, Custom);
setOperationAction(ISD::SETCC, MVT::v16i16, Custom);
setOperationAction(ISD::SETCC, MVT::v8i32, Custom);
@ -1166,6 +1170,8 @@ X86TargetLowering::X86TargetLowering(X86TargetMachine &TM)
setOperationAction(ISD::SHL, MVT::v8i32, Legal);
setOperationAction(ISD::SRA, MVT::v8i32, Legal);
setOperationAction(ISD::SDIV, MVT::v8i32, Custom);
} else {
setOperationAction(ISD::ADD, MVT::v4i64, Custom);
setOperationAction(ISD::ADD, MVT::v8i32, Custom);
@ -11377,6 +11383,49 @@ static SDValue LowerMUL(SDValue Op, const X86Subtarget *Subtarget,
return DAG.getNode(ISD::ADD, dl, VT, Res, AhiBlo);
}
SDValue X86TargetLowering::LowerSDIV(SDValue Op, SelectionDAG &DAG) const {
EVT VT = Op.getValueType();
EVT EltTy = VT.getVectorElementType();
unsigned NumElts = VT.getVectorNumElements();
SDValue N0 = Op.getOperand(0);
DebugLoc dl = Op.getDebugLoc();
// Lower sdiv X, pow2-const.
BuildVectorSDNode *C = dyn_cast<BuildVectorSDNode>(Op.getOperand(1));
if (!C)
return SDValue();
APInt SplatValue, SplatUndef;
unsigned MinSplatBits;
bool HasAnyUndefs;
if (!C->isConstantSplat(SplatValue, SplatUndef, MinSplatBits, HasAnyUndefs))
return SDValue();
if ((SplatValue != 0) &&
(SplatValue.isPowerOf2() || (-SplatValue).isPowerOf2())) {
unsigned lg2 = SplatValue.countTrailingZeros();
// Splat the sign bit.
SDValue Sz = DAG.getConstant(EltTy.getSizeInBits()-1, MVT::i32);
SDValue SGN = getTargetVShiftNode(X86ISD::VSRAI, dl, VT, N0, Sz, DAG);
// Add (N0 < 0) ? abs2 - 1 : 0;
SDValue Amt = DAG.getConstant(EltTy.getSizeInBits() - lg2, MVT::i32);
SDValue SRL = getTargetVShiftNode(X86ISD::VSRLI, dl, VT, SGN, Amt, DAG);
SDValue ADD = DAG.getNode(ISD::ADD, dl, VT, N0, SRL);
SDValue Lg2Amt = DAG.getConstant(lg2, MVT::i32);
SDValue SRA = getTargetVShiftNode(X86ISD::VSRAI, dl, VT, ADD, Lg2Amt, DAG);
// If we're dividing by a positive value, we're done. Otherwise, we must
// negate the result.
if (SplatValue.isNonNegative())
return SRA;
SmallVector<SDValue, 16> V(NumElts, DAG.getConstant(0, EltTy));
SDValue Zero = DAG.getNode(ISD::BUILD_VECTOR, dl, VT, &V[0], NumElts);
return DAG.getNode(ISD::SUB, dl, VT, Zero, SRA);
}
return SDValue();
}
SDValue X86TargetLowering::LowerShift(SDValue Op, SelectionDAG &DAG) const {
EVT VT = Op.getValueType();
@ -12033,6 +12082,7 @@ SDValue X86TargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const {
case ISD::SUBE: return LowerADDC_ADDE_SUBC_SUBE(Op, DAG);
case ISD::ADD: return LowerADD(Op, DAG);
case ISD::SUB: return LowerSUB(Op, DAG);
case ISD::SDIV: return LowerSDIV(Op, DAG);
}
}

1
llvm/lib/Target/X86/X86ISelLowering.h
View File

@ -841,6 +841,7 @@ namespace llvm {
SDValue LowerINIT_TRAMPOLINE(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFLT_ROUNDS_(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerShift(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerSDIV(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerSIGN_EXTEND_INREG(SDValue Op, SelectionDAG &DAG) const;

72
llvm/test/CodeGen/X86/vec_sdiv_to_shift.ll Normal file
View File

@ -0,0 +1,72 @@
; RUN: llc < %s -mcpu=penryn -mattr=+avx2 | FileCheck %s
define <8 x i16> @sdiv_vec8x16(<8 x i16> %var) {
entry:
; CHECK: sdiv_vec8x16
; CHECK: psraw $15
; CHECK: vpsrlw $11
; CHECK: vpaddw
; CHECK: vpsraw $5
; CHECK: ret
%0 = sdiv <8 x i16> %var, <i16 32, i16 32, i16 32, i16 32, i16 32, i16 32, i16 32, i16 32>
ret <8 x i16> %0
}
define <4 x i32> @sdiv_zero(<4 x i32> %var) {
entry:
; CHECK: sdiv_zero
; CHECK-NOT sra
; CHECK: ret
%0 = sdiv <4 x i32> %var, <i32 0, i32 0, i32 0, i32 0>
ret <4 x i32> %0
}
define <4 x i32> @sdiv_vec4x32(<4 x i32> %var) {
entry:
; CHECK: sdiv_vec4x32
; CHECK: vpsrad $31
; CHECK: vpsrld $28
; CHECK: vpaddd
; CHECK: vpsrad $4
; CHECK: ret
%0 = sdiv <4 x i32> %var, <i32 16, i32 16, i32 16, i32 16>
ret <4 x i32> %0
}
define <4 x i32> @sdiv_negative(<4 x i32> %var) {
entry:
; CHECK: sdiv_negative
; CHECK: vpsrad $31
; CHECK: vpsrld $28
; CHECK: vpaddd
; CHECK: vpsrad $4
; CHECK: vpsubd
; CHECK: ret
%0 = sdiv <4 x i32> %var, <i32 -16, i32 -16, i32 -16, i32 -16>
ret <4 x i32> %0
}
define <8 x i32> @sdiv8x32(<8 x i32> %var) {
entry:
; CHECK: sdiv8x32
; CHECK: vpsrad $31
; CHECK: vpsrld $26
; CHECK: vpaddd
; CHECK: vpsrad $6
; CHECK: ret
%0 = sdiv <8 x i32> %var, <i32 64, i32 64, i32 64, i32 64, i32 64, i32 64, i32 64, i32 64>
ret <8 x i32> %0
}
define <16 x i16> @sdiv16x16(<16 x i16> %var) {
entry:
; CHECK: sdiv16x16
; CHECK: vpsraw $15
; CHECK: vpsrlw $14
; CHECK: vpaddw
; CHECK: vpsraw $2
; CHECK: ret
%a0 = sdiv <16 x i16> %var, <i16 4, i16 4, i16 4, i16 4, i16 4, i16 4, i16 4, i16 4, i16 4, i16 4, i16 4, i16 4, i16 4, i16 4, i16 4, i16 4>
ret <16 x i16> %a0
}