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

[DAGCombiner] Add support for FCEIL, FFLOOR and FTRUNC vector constant folding 

Differential Revision: http://reviews.llvm.org/D8715

llvm-svn: 234179
This commit is contained in:
Simon Pilgrim 2015-04-06 17:15:41 +00:00
parent b23c24c2a8
commit 07e063e44c
3 changed files with 53 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

@ -8194,11 +8194,10 @@ SDValue DAGCombiner::visitFP_EXTEND(SDNode *N) {
SDValue DAGCombiner::visitFCEIL(SDNode *N) { SDValue DAGCombiner::visitFCEIL(SDNode *N) {
SDValue N0 = N->getOperand(0); SDValue N0 = N->getOperand(0);
ConstantFPSDNode *N0CFP = dyn_cast<ConstantFPSDNode>(N0);
EVT VT = N->getValueType(0); EVT VT = N->getValueType(0);
// fold (fceil c1) -> fceil(c1) // fold (fceil c1) -> fceil(c1)
if (N0CFP) if (isConstantFPBuildVectorOrConstantFP(N0))
return DAG.getNode(ISD::FCEIL, SDLoc(N), VT, N0); return DAG.getNode(ISD::FCEIL, SDLoc(N), VT, N0);
return SDValue(); return SDValue();
@ -8206,11 +8205,10 @@ SDValue DAGCombiner::visitFCEIL(SDNode *N) {
SDValue DAGCombiner::visitFTRUNC(SDNode *N) { SDValue DAGCombiner::visitFTRUNC(SDNode *N) {
SDValue N0 = N->getOperand(0); SDValue N0 = N->getOperand(0);
ConstantFPSDNode *N0CFP = dyn_cast<ConstantFPSDNode>(N0);
EVT VT = N->getValueType(0); EVT VT = N->getValueType(0);
// fold (ftrunc c1) -> ftrunc(c1) // fold (ftrunc c1) -> ftrunc(c1)
if (N0CFP) if (isConstantFPBuildVectorOrConstantFP(N0))
return DAG.getNode(ISD::FTRUNC, SDLoc(N), VT, N0); return DAG.getNode(ISD::FTRUNC, SDLoc(N), VT, N0);
return SDValue(); return SDValue();
@ -8218,11 +8216,10 @@ SDValue DAGCombiner::visitFTRUNC(SDNode *N) {
SDValue DAGCombiner::visitFFLOOR(SDNode *N) { SDValue DAGCombiner::visitFFLOOR(SDNode *N) {
SDValue N0 = N->getOperand(0); SDValue N0 = N->getOperand(0);
ConstantFPSDNode *N0CFP = dyn_cast<ConstantFPSDNode>(N0);
EVT VT = N->getValueType(0); EVT VT = N->getValueType(0);
// fold (ffloor c1) -> ffloor(c1) // fold (ffloor c1) -> ffloor(c1)
if (N0CFP) if (isConstantFPBuildVectorOrConstantFP(N0))
return DAG.getNode(ISD::FFLOOR, SDLoc(N), VT, N0); return DAG.getNode(ISD::FFLOOR, SDLoc(N), VT, N0);
return SDValue(); return SDValue();

4
llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
View File

@ -2853,6 +2853,9 @@ SDValue SelectionDAG::getNode(unsigned Opcode, SDLoc DL,
break; break;
case ISD::FNEG: case ISD::FNEG:
case ISD::FABS: case ISD::FABS:
case ISD::FCEIL:
case ISD::FTRUNC:
case ISD::FFLOOR:
case ISD::FP_EXTEND: case ISD::FP_EXTEND:
case ISD::TRUNCATE: case ISD::TRUNCATE:
case ISD::UINT_TO_FP: case ISD::UINT_TO_FP:
@ -2870,6 +2873,7 @@ SDValue SelectionDAG::getNode(unsigned Opcode, SDLoc DL,
} }
if (Ops.size() == VT.getVectorNumElements()) if (Ops.size() == VT.getVectorNumElements())
return getNode(ISD::BUILD_VECTOR, DL, VT, Ops); return getNode(ISD::BUILD_VECTOR, DL, VT, Ops);
break;
} }
} }
} }

46
llvm/test/CodeGen/X86/vec_floor.ll
View File

@ -180,3 +180,49 @@ define <8 x float> @nearbyint_v8f32(<8 x float> %p)
ret <8 x float> %t ret <8 x float> %t
} }
declare <8 x float> @llvm.nearbyint.v8f32(<8 x float> %p) declare <8 x float> @llvm.nearbyint.v8f32(<8 x float> %p)
;
; Constant Folding
;
define <2 x double> @const_floor_v2f64() {
; CHECK: const_floor_v2f64
; CHECK: movaps {{.*#+}} xmm0 = [-2.000000e+00,2.000000e+00]
%t = call <2 x double> @llvm.floor.v2f64(<2 x double> <double -1.5, double 2.5>)
ret <2 x double> %t
}
define <4 x float> @const_floor_v4f32() {
; CHECK: const_floor_v4f32
; CHECK: movaps {{.*#+}} xmm0 = [-4.000000e+00,6.000000e+00,-9.000000e+00,2.000000e+00]
%t = call <4 x float> @llvm.floor.v4f32(<4 x float> <float -3.5, float 6.0, float -9.0, float 2.5>)
ret <4 x float> %t
}
define <2 x double> @const_ceil_v2f64() {
; CHECK: const_ceil_v2f64
; CHECK: movaps {{.*#+}} xmm0 = [-1.000000e+00,3.000000e+00]
%t = call <2 x double> @llvm.ceil.v2f64(<2 x double> <double -1.5, double 2.5>)
ret <2 x double> %t
}
define <4 x float> @const_ceil_v4f32() {
; CHECK: const_ceil_v4f32
; CHECK: movaps {{.*#+}} xmm0 = [-3.000000e+00,6.000000e+00,-9.000000e+00,3.000000e+00]
%t = call <4 x float> @llvm.ceil.v4f32(<4 x float> <float -3.5, float 6.0, float -9.0, float 2.5>)
ret <4 x float> %t
}
define <2 x double> @const_trunc_v2f64() {
; CHECK: const_trunc_v2f64
; CHECK: movaps {{.*#+}} xmm0 = [-1.000000e+00,2.000000e+00]
%t = call <2 x double> @llvm.trunc.v2f64(<2 x double> <double -1.5, double 2.5>)
ret <2 x double> %t
}
define <4 x float> @const_trunc_v4f32() {
; CHECK: const_trunc_v4f32
; CHECK: movaps {{.*#+}} xmm0 = [-3.000000e+00,6.000000e+00,-9.000000e+00,2.000000e+00]
%t = call <4 x float> @llvm.trunc.v4f32(<4 x float> <float -3.5, float 6.0, float -9.0, float 2.5>)
ret <4 x float> %t
}