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

R600: Implement f64 ftrunc, ffloor and fceil. 

CI has instructions for these, so this fixes them for older hardware.

llvm-svn: 211183
This commit is contained in:
Matt Arsenault 2014-06-18 17:05:30 +00:00
parent e8208ec95b
commit 4601093267
5 changed files with 197 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

107
llvm/lib/Target/R600/AMDGPUISelLowering.cpp
View File

@ -219,7 +219,10 @@ AMDGPUTargetLowering::AMDGPUTargetLowering(TargetMachine &TM) :
setOperationAction(ISD::BR_CC, MVT::i1, Expand);
if (Subtarget->getGeneration() < AMDGPUSubtarget::SEA_ISLANDS) {
setOperationAction(ISD::FCEIL, MVT::f64, Custom);
setOperationAction(ISD::FTRUNC, MVT::f64, Custom);
setOperationAction(ISD::FRINT, MVT::f64, Custom);
setOperationAction(ISD::FFLOOR, MVT::f64, Custom);
}
if (!Subtarget->hasBFI()) {
@ -494,7 +497,10 @@ SDValue AMDGPUTargetLowering::LowerOperation(SDValue Op,
case ISD::SDIV: return LowerSDIV(Op, DAG);
case ISD::SREM: return LowerSREM(Op, DAG);
case ISD::UDIVREM: return LowerUDIVREM(Op, DAG);
case ISD::FCEIL: return LowerFCEIL(Op, DAG);
case ISD::FTRUNC: return LowerFTRUNC(Op, DAG);
case ISD::FRINT: return LowerFRINT(Op, DAG);
case ISD::FFLOOR: return LowerFFLOOR(Op, DAG);
case ISD::UINT_TO_FP: return LowerUINT_TO_FP(Op, DAG);
// AMDIL DAG lowering.
@ -1571,6 +1577,84 @@ SDValue AMDGPUTargetLowering::LowerUDIVREM(SDValue Op,
return DAG.getMergeValues(Ops, DL);
}
SDValue AMDGPUTargetLowering::LowerFCEIL(SDValue Op, SelectionDAG &DAG) const {
SDLoc SL(Op);
SDValue Src = Op.getOperand(0);
// result = trunc(src)
// if (src > 0.0 && src != result)
// result += 1.0
SDValue Trunc = DAG.getNode(ISD::FTRUNC, SL, MVT::f64, Src);
const SDValue Zero = DAG.getConstantFP(0.0, MVT::f64);
const SDValue One = DAG.getConstantFP(1.0, MVT::f64);
EVT SetCCVT = getSetCCResultType(*DAG.getContext(), MVT::f64);
SDValue Lt0 = DAG.getSetCC(SL, SetCCVT, Src, Zero, ISD::SETOGT);
SDValue NeTrunc = DAG.getSetCC(SL, SetCCVT, Src, Trunc, ISD::SETONE);
SDValue And = DAG.getNode(ISD::AND, SL, SetCCVT, Lt0, NeTrunc);
SDValue Add = DAG.getNode(ISD::SELECT, SL, MVT::f64, And, One, Zero);
return DAG.getNode(ISD::FADD, SL, MVT::f64, Trunc, Add);
}
SDValue AMDGPUTargetLowering::LowerFTRUNC(SDValue Op, SelectionDAG &DAG) const {
SDLoc SL(Op);
SDValue Src = Op.getOperand(0);
assert(Op.getValueType() == MVT::f64);
const SDValue Zero = DAG.getConstant(0, MVT::i32);
const SDValue One = DAG.getConstant(1, MVT::i32);
SDValue VecSrc = DAG.getNode(ISD::BITCAST, SL, MVT::v2i32, Src);
// Extract the upper half, since this is where we will find the sign and
// exponent.
SDValue Hi = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, SL, MVT::i32, VecSrc, One);
const unsigned FractBits = 52;
const unsigned ExpBits = 11;
// Extract the exponent.
SDValue ExpPart = DAG.getNode(AMDGPUISD::BFE_I32, SL, MVT::i32,
Hi,
DAG.getConstant(FractBits - 32, MVT::i32),
DAG.getConstant(ExpBits, MVT::i32));
SDValue Exp = DAG.getNode(ISD::SUB, SL, MVT::i32, ExpPart,
DAG.getConstant(1023, MVT::i32));
// Extract the sign bit.
const SDValue SignBitMask = DAG.getConstant(1ul << 31, MVT::i32);
SDValue SignBit = DAG.getNode(ISD::AND, SL, MVT::i32, Hi, SignBitMask);
// Extend back to to 64-bits.
SDValue SignBit64 = DAG.getNode(ISD::BUILD_VECTOR, SL, MVT::v2i32,
Zero, SignBit);
SignBit64 = DAG.getNode(ISD::BITCAST, SL, MVT::i64, SignBit64);
SDValue BcInt = DAG.getNode(ISD::BITCAST, SL, MVT::i64, Src);
const SDValue FractMask = DAG.getConstant((1L << FractBits) - 1, MVT::i64);
SDValue Shr = DAG.getNode(ISD::SRA, SL, MVT::i64, FractMask, Exp);
SDValue Not = DAG.getNOT(SL, Shr, MVT::i64);
SDValue Tmp0 = DAG.getNode(ISD::AND, SL, MVT::i64, BcInt, Not);
EVT SetCCVT = getSetCCResultType(*DAG.getContext(), MVT::i32);
const SDValue FiftyOne = DAG.getConstant(FractBits - 1, MVT::i32);
SDValue ExpLt0 = DAG.getSetCC(SL, SetCCVT, Exp, Zero, ISD::SETLT);
SDValue ExpGt51 = DAG.getSetCC(SL, SetCCVT, Exp, FiftyOne, ISD::SETGT);
SDValue Tmp1 = DAG.getNode(ISD::SELECT, SL, MVT::i64, ExpLt0, SignBit64, Tmp0);
SDValue Tmp2 = DAG.getNode(ISD::SELECT, SL, MVT::i64, ExpGt51, BcInt, Tmp1);
return DAG.getNode(ISD::BITCAST, SL, MVT::f64, Tmp2);
}
SDValue AMDGPUTargetLowering::LowerFRINT(SDValue Op, SelectionDAG &DAG) const {
SDLoc SL(Op);
SDValue Src = Op.getOperand(0);
@ -1592,6 +1676,29 @@ SDValue AMDGPUTargetLowering::LowerFRINT(SDValue Op, SelectionDAG &DAG) const {
return DAG.getSelect(SL, MVT::f64, Cond, Src, Tmp2);
}
SDValue AMDGPUTargetLowering::LowerFFLOOR(SDValue Op, SelectionDAG &DAG) const {
SDLoc SL(Op);
SDValue Src = Op.getOperand(0);
// result = trunc(src);
// if (src < 0.0 && src != result)
// result += -1.0.
SDValue Trunc = DAG.getNode(ISD::FTRUNC, SL, MVT::f64, Src);
const SDValue Zero = DAG.getConstantFP(0.0, MVT::f64);
const SDValue NegOne = DAG.getConstantFP(-1.0, MVT::f64);
EVT SetCCVT = getSetCCResultType(*DAG.getContext(), MVT::f64);
SDValue Lt0 = DAG.getSetCC(SL, SetCCVT, Src, Zero, ISD::SETOLT);
SDValue NeTrunc = DAG.getSetCC(SL, SetCCVT, Src, Trunc, ISD::SETONE);
SDValue And = DAG.getNode(ISD::AND, SL, SetCCVT, Lt0, NeTrunc);
SDValue Add = DAG.getNode(ISD::SELECT, SL, MVT::f64, And, NegOne, Zero);
return DAG.getNode(ISD::FADD, SL, MVT::f64, Trunc, Add);
}
SDValue AMDGPUTargetLowering::LowerUINT_TO_FP(SDValue Op,
SelectionDAG &DAG) const {
SDValue S0 = Op.getOperand(0);

4
llvm/lib/Target/R600/AMDGPUISelLowering.h
View File

@ -51,7 +51,11 @@ private:
SDValue LowerSREM32(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerSREM64(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerUDIVREM(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFCEIL(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFTRUNC(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFRINT(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFFLOOR(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerUINT_TO_FP(SDValue Op, SelectionDAG &DAG) const;
SDValue ExpandSIGN_EXTEND_INREG(SDValue Op,

33
llvm/test/CodeGen/R600/fceil.ll
View File

@ -1,4 +1,5 @@
; RUN: llc -march=r600 -mcpu=bonaire < %s | FileCheck -check-prefix=CI %s
; RUN: llc -march=r600 -mcpu=bonaire < %s | FileCheck -check-prefix=CI -check-prefix=FUNC %s
; RUN: llc -march=r600 -mcpu=SI < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
declare double @llvm.ceil.f64(double) nounwind readnone
declare <2 x double> @llvm.ceil.v2f64(<2 x double>) nounwind readnone
@ -7,15 +8,33 @@ declare <4 x double> @llvm.ceil.v4f64(<4 x double>) nounwind readnone
declare <8 x double> @llvm.ceil.v8f64(<8 x double>) nounwind readnone
declare <16 x double> @llvm.ceil.v16f64(<16 x double>) nounwind readnone
; CI-LABEL: @fceil_f64:
; FUNC-LABEL: @fceil_f64:
; CI: V_CEIL_F64_e32
; SI: S_BFE_I32 [[SEXP:s[0-9]+]], {{s[0-9]+}}, 0xb0014
; SI: S_ADD_I32 s{{[0-9]+}}, [[SEXP]], 0xfffffc01
; SI: S_LSHR_B64
; SI: S_NOT_B64
; SI: S_AND_B64
; SI: S_AND_B32 s{{[0-9]+}}, s{{[0-9]+}}, 0x80000000
; SI: CMP_LT_I32
; SI: CNDMASK_B32
; SI: CNDMASK_B32
; SI: CMP_GT_I32
; SI: CNDMASK_B32
; SI: CNDMASK_B32
; SI: CMP_GT_F64
; SI: CNDMASK_B32
; SI: CMP_NE_I32
; SI: CNDMASK_B32
; SI: CNDMASK_B32
; SI: V_ADD_F64
define void @fceil_f64(double addrspace(1)* %out, double %x) {
%y = call double @llvm.ceil.f64(double %x) nounwind readnone
store double %y, double addrspace(1)* %out
ret void
}
; CI-LABEL: @fceil_v2f64:
; FUNC-LABEL: @fceil_v2f64:
; CI: V_CEIL_F64_e32
; CI: V_CEIL_F64_e32
define void @fceil_v2f64(<2 x double> addrspace(1)* %out, <2 x double> %x) {
@ -24,7 +43,7 @@ define void @fceil_v2f64(<2 x double> addrspace(1)* %out, <2 x double> %x) {
ret void
}
; FIXME-CI-LABEL: @fceil_v3f64:
; FIXME-FUNC-LABEL: @fceil_v3f64:
; FIXME-CI: V_CEIL_F64_e32
; FIXME-CI: V_CEIL_F64_e32
; FIXME-CI: V_CEIL_F64_e32
@ -34,7 +53,7 @@ define void @fceil_v2f64(<2 x double> addrspace(1)* %out, <2 x double> %x) {
; ret void
; }
; CI-LABEL: @fceil_v4f64:
; FUNC-LABEL: @fceil_v4f64:
; CI: V_CEIL_F64_e32
; CI: V_CEIL_F64_e32
; CI: V_CEIL_F64_e32
@ -45,7 +64,7 @@ define void @fceil_v4f64(<4 x double> addrspace(1)* %out, <4 x double> %x) {
ret void
}
; CI-LABEL: @fceil_v8f64:
; FUNC-LABEL: @fceil_v8f64:
; CI: V_CEIL_F64_e32
; CI: V_CEIL_F64_e32
; CI: V_CEIL_F64_e32
@ -60,7 +79,7 @@ define void @fceil_v8f64(<8 x double> addrspace(1)* %out, <8 x double> %x) {
ret void
}
; CI-LABEL: @fceil_v16f64:
; FUNC-LABEL: @fceil_v16f64:
; CI: V_CEIL_F64_e32
; CI: V_CEIL_F64_e32
; CI: V_CEIL_F64_e32

34
llvm/test/CodeGen/R600/ffloor.ll
View File

@ -1,4 +1,5 @@
; RUN: llc -march=r600 -mcpu=bonaire < %s | FileCheck -check-prefix=CI %s
; RUN: llc -march=r600 -mcpu=bonaire < %s | FileCheck -check-prefix=CI -check-prefix=FUNC %s
; RUN: llc -march=r600 -mcpu=SI < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
declare double @llvm.floor.f64(double) nounwind readnone
declare <2 x double> @llvm.floor.v2f64(<2 x double>) nounwind readnone
@ -7,15 +8,34 @@ declare <4 x double> @llvm.floor.v4f64(<4 x double>) nounwind readnone
declare <8 x double> @llvm.floor.v8f64(<8 x double>) nounwind readnone
declare <16 x double> @llvm.floor.v16f64(<16 x double>) nounwind readnone
; CI-LABEL: @ffloor_f64:
; FUNC-LABEL: @ffloor_f64:
; CI: V_FLOOR_F64_e32
; SI: S_BFE_I32 [[SEXP:s[0-9]+]], {{s[0-9]+}}, 0xb0014
; SI: S_ADD_I32 s{{[0-9]+}}, [[SEXP]], 0xfffffc01
; SI: S_LSHR_B64
; SI: S_NOT_B64
; SI: S_AND_B64
; SI: S_AND_B32 s{{[0-9]+}}, s{{[0-9]+}}, 0x80000000
; SI: CMP_LT_I32
; SI: CNDMASK_B32
; SI: CNDMASK_B32
; SI: CMP_GT_I32
; SI: CNDMASK_B32
; SI: CNDMASK_B32
; SI: CMP_LT_F64
; SI: CNDMASK_B32
; SI: CMP_NE_I32
; SI: CNDMASK_B32
; SI: CNDMASK_B32
; SI: V_ADD_F64
define void @ffloor_f64(double addrspace(1)* %out, double %x) {
%y = call double @llvm.floor.f64(double %x) nounwind readnone
store double %y, double addrspace(1)* %out
ret void
}
; CI-LABEL: @ffloor_v2f64:
; FUNC-LABEL: @ffloor_v2f64:
; CI: V_FLOOR_F64_e32
; CI: V_FLOOR_F64_e32
define void @ffloor_v2f64(<2 x double> addrspace(1)* %out, <2 x double> %x) {
@ -24,7 +44,7 @@ define void @ffloor_v2f64(<2 x double> addrspace(1)* %out, <2 x double> %x) {
ret void
}
; FIXME-CI-LABEL: @ffloor_v3f64:
; FIXME-FUNC-LABEL: @ffloor_v3f64:
; FIXME-CI: V_FLOOR_F64_e32
; FIXME-CI: V_FLOOR_F64_e32
; FIXME-CI: V_FLOOR_F64_e32
@ -34,7 +54,7 @@ define void @ffloor_v2f64(<2 x double> addrspace(1)* %out, <2 x double> %x) {
; ret void
; }
; CI-LABEL: @ffloor_v4f64:
; FUNC-LABEL: @ffloor_v4f64:
; CI: V_FLOOR_F64_e32
; CI: V_FLOOR_F64_e32
; CI: V_FLOOR_F64_e32
@ -45,7 +65,7 @@ define void @ffloor_v4f64(<4 x double> addrspace(1)* %out, <4 x double> %x) {
ret void
}
; CI-LABEL: @ffloor_v8f64:
; FUNC-LABEL: @ffloor_v8f64:
; CI: V_FLOOR_F64_e32
; CI: V_FLOOR_F64_e32
; CI: V_FLOOR_F64_e32
@ -60,7 +80,7 @@ define void @ffloor_v8f64(<8 x double> addrspace(1)* %out, <8 x double> %x) {
ret void
}
; CI-LABEL: @ffloor_v16f64:
; FUNC-LABEL: @ffloor_v16f64:
; CI: V_FLOOR_F64_e32
; CI: V_FLOOR_F64_e32
; CI: V_FLOOR_F64_e32

40
llvm/test/CodeGen/R600/ftrunc.ll
View File

@ -1,4 +1,5 @@
; RUN: llc -march=r600 -mcpu=bonaire < %s | FileCheck -check-prefix=CI %s
; RUN: llc -march=r600 -mcpu=bonaire < %s | FileCheck -check-prefix=CI -check-prefix=FUNC %s
; RUN: llc -march=r600 -mcpu=SI < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
declare double @llvm.trunc.f64(double) nounwind readnone
declare <2 x double> @llvm.trunc.v2f64(<2 x double>) nounwind readnone
@ -7,15 +8,40 @@ declare <4 x double> @llvm.trunc.v4f64(<4 x double>) nounwind readnone
declare <8 x double> @llvm.trunc.v8f64(<8 x double>) nounwind readnone
declare <16 x double> @llvm.trunc.v16f64(<16 x double>) nounwind readnone
; CI-LABEL: @ftrunc_f64:
; FUNC-LABEL: @v_ftrunc_f64:
; CI: V_TRUNC_F64_e32
; SI: V_BFE_I32 {{v[0-9]+}}, {{v[0-9]+}}, 20, 11
; SI: S_ENDPGM
define void @v_ftrunc_f64(double addrspace(1)* %out, double addrspace(1)* %in) {
%x = load double addrspace(1)* %in, align 8
%y = call double @llvm.trunc.f64(double %x) nounwind readnone
store double %y, double addrspace(1)* %out, align 8
ret void
}
; FUNC-LABEL: @ftrunc_f64:
; CI: V_TRUNC_F64_e32
; SI: S_BFE_I32 [[SEXP:s[0-9]+]], {{s[0-9]+}}, 0xb0014
; SI: S_ADD_I32 s{{[0-9]+}}, [[SEXP]], 0xfffffc01
; SI: S_LSHR_B64
; SI: S_NOT_B64
; SI: S_AND_B64
; SI: S_AND_B32 s{{[0-9]+}}, s{{[0-9]+}}, 0x80000000
; SI: CMP_LT_I32
; SI: CNDMASK_B32
; SI: CNDMASK_B32
; SI: CMP_GT_I32
; SI: CNDMASK_B32
; SI: CNDMASK_B32
; SI: S_ENDPGM
define void @ftrunc_f64(double addrspace(1)* %out, double %x) {
%y = call double @llvm.trunc.f64(double %x) nounwind readnone
store double %y, double addrspace(1)* %out
ret void
}
; CI-LABEL: @ftrunc_v2f64:
; FUNC-LABEL: @ftrunc_v2f64:
; CI: V_TRUNC_F64_e32
; CI: V_TRUNC_F64_e32
define void @ftrunc_v2f64(<2 x double> addrspace(1)* %out, <2 x double> %x) {
@ -24,7 +50,7 @@ define void @ftrunc_v2f64(<2 x double> addrspace(1)* %out, <2 x double> %x) {
ret void
}
; FIXME-CI-LABEL: @ftrunc_v3f64:
; FIXME-FUNC-LABEL: @ftrunc_v3f64:
; FIXME-CI: V_TRUNC_F64_e32
; FIXME-CI: V_TRUNC_F64_e32
; FIXME-CI: V_TRUNC_F64_e32
@ -34,7 +60,7 @@ define void @ftrunc_v2f64(<2 x double> addrspace(1)* %out, <2 x double> %x) {
; ret void
; }
; CI-LABEL: @ftrunc_v4f64:
; FUNC-LABEL: @ftrunc_v4f64:
; CI: V_TRUNC_F64_e32
; CI: V_TRUNC_F64_e32
; CI: V_TRUNC_F64_e32
@ -45,7 +71,7 @@ define void @ftrunc_v4f64(<4 x double> addrspace(1)* %out, <4 x double> %x) {
ret void
}
; CI-LABEL: @ftrunc_v8f64:
; FUNC-LABEL: @ftrunc_v8f64:
; CI: V_TRUNC_F64_e32
; CI: V_TRUNC_F64_e32
; CI: V_TRUNC_F64_e32
@ -60,7 +86,7 @@ define void @ftrunc_v8f64(<8 x double> addrspace(1)* %out, <8 x double> %x) {
ret void
}
; CI-LABEL: @ftrunc_v16f64:
; FUNC-LABEL: @ftrunc_v16f64:
; CI: V_TRUNC_F64_e32
; CI: V_TRUNC_F64_e32
; CI: V_TRUNC_F64_e32