diff --git a/lib/Target/R600/AMDGPUISelLowering.cpp b/lib/Target/R600/AMDGPUISelLowering.cpp index 4707279ce87..62a33fad64b 100644 --- a/lib/Target/R600/AMDGPUISelLowering.cpp +++ b/lib/Target/R600/AMDGPUISelLowering.cpp @@ -885,9 +885,6 @@ SDValue AMDGPUTargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op, return LowerIntrinsicIABS(Op, DAG); case AMDGPUIntrinsic::AMDGPU_lrp: return LowerIntrinsicLRP(Op, DAG); - case AMDGPUIntrinsic::AMDGPU_fract: - case AMDGPUIntrinsic::AMDIL_fraction: // Legacy name. - return DAG.getNode(AMDGPUISD::FRACT, DL, VT, Op.getOperand(1)); case AMDGPUIntrinsic::AMDGPU_clamp: case AMDGPUIntrinsic::AMDIL_clamp: // Legacy name. diff --git a/lib/Target/R600/R600ISelLowering.cpp b/lib/Target/R600/R600ISelLowering.cpp index d4f3145e6ae..06b72179676 100644 --- a/lib/Target/R600/R600ISelLowering.cpp +++ b/lib/Target/R600/R600ISelLowering.cpp @@ -837,6 +837,10 @@ SDValue R600TargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const case Intrinsic::AMDGPU_rsq: // XXX - I'm assuming SI's RSQ_LEGACY matches R600's behavior. return DAG.getNode(AMDGPUISD::RSQ_LEGACY, DL, VT, Op.getOperand(1)); + + case AMDGPUIntrinsic::AMDGPU_fract: + case AMDGPUIntrinsic::AMDIL_fraction: // Legacy name. + return DAG.getNode(AMDGPUISD::FRACT, DL, VT, Op.getOperand(1)); } // break out of case ISD::INTRINSIC_WO_CHAIN in switch(Op.getOpcode()) break; diff --git a/lib/Target/R600/SIISelLowering.cpp b/lib/Target/R600/SIISelLowering.cpp index 16d67022aa8..01fece2694f 100644 --- a/lib/Target/R600/SIISelLowering.cpp +++ b/lib/Target/R600/SIISelLowering.cpp @@ -928,6 +928,12 @@ SDValue SITargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op, Op.getOperand(1), Op.getOperand(2), Op.getOperand(3)); + + case AMDGPUIntrinsic::AMDGPU_fract: + case AMDGPUIntrinsic::AMDIL_fraction: // Legacy name. + return DAG.getNode(ISD::FSUB, DL, VT, Op.getOperand(1), + DAG.getNode(ISD::FFLOOR, DL, VT, Op.getOperand(1))); + default: return AMDGPUTargetLowering::LowerOperation(Op, DAG); } diff --git a/lib/Target/R600/SIInstructions.td b/lib/Target/R600/SIInstructions.td index 10a7aa30ecc..b06955c8331 100644 --- a/lib/Target/R600/SIInstructions.td +++ b/lib/Target/R600/SIInstructions.td @@ -3316,6 +3316,28 @@ def : Pat < (V_CNDMASK_B32_e64 $src0, $src1, $src2) >; +//===----------------------------------------------------------------------===// +// Fract Patterns +//===----------------------------------------------------------------------===// + +let Predicates = [isCI] in { + +// Convert (x - floor(x)) to fract(x) +def : Pat < + (f32 (fsub (f32 (VOP3Mods f32:$x, i32:$mods)), + (f32 (ffloor (f32 (VOP3Mods f32:$x, i32:$mods)))))), + (V_FRACT_F32_e64 $mods, $x, DSTCLAMP.NONE, DSTOMOD.NONE) +>; + +// Convert (x + (-floor(x))) to fract(x) +def : Pat < + (f64 (fadd (f64 (VOP3Mods f64:$x, i32:$mods)), + (f64 (fneg (f64 (ffloor (f64 (VOP3Mods f64:$x, i32:$mods)))))))), + (V_FRACT_F64_e64 $mods, $x, DSTCLAMP.NONE, DSTOMOD.NONE) +>; + +} // End Predicates = [isCI] + //============================================================================// // Miscellaneous Optimization Patterns //============================================================================// diff --git a/test/CodeGen/R600/llvm.AMDGPU.fract.ll b/test/CodeGen/R600/llvm.AMDGPU.fract.ll index f4cf7fc293d..7501b4b7546 100644 --- a/test/CodeGen/R600/llvm.AMDGPU.fract.ll +++ b/test/CodeGen/R600/llvm.AMDGPU.fract.ll @@ -1,14 +1,19 @@ -; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s -; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s -; RUN: llc -march=r600 -mcpu=cypress -verify-machineinstrs < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s +; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -check-prefix=GCN -check-prefix=SI -check-prefix=FUNC %s +; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -check-prefix=GCN -check-prefix=CI -check-prefix=FUNC %s +; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -check-prefix=GCN -check-prefix=CI -check-prefix=FUNC %s +; RUN: llc -march=r600 -mcpu=cypress -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s +declare float @llvm.fabs.f32(float %Val) declare float @llvm.AMDGPU.fract.f32(float) nounwind readnone ; Legacy name declare float @llvm.AMDIL.fraction.f32(float) nounwind readnone ; FUNC-LABEL: {{^}}fract_f32: -; SI: v_fract_f32 +; CI: v_fract_f32_e32 [[RESULT:v[0-9]+]], [[INPUT:v[0-9]+]] +; SI: v_floor_f32_e32 [[FLR:v[0-9]+]], [[INPUT:v[0-9]+]] +; SI: v_subrev_f32_e32 [[RESULT:v[0-9]+]], [[FLR]], [[INPUT]] +; GCN: buffer_store_dword [[RESULT]] ; EG: FRACT define void @fract_f32(float addrspace(1)* %out, float addrspace(1)* %src) nounwind { %val = load float, float addrspace(1)* %src, align 4 @@ -18,7 +23,10 @@ define void @fract_f32(float addrspace(1)* %out, float addrspace(1)* %src) nounw } ; FUNC-LABEL: {{^}}fract_f32_legacy_amdil: -; SI: v_fract_f32 +; CI: v_fract_f32_e32 [[RESULT:v[0-9]+]], [[INPUT:v[0-9]+]] +; SI: v_floor_f32_e32 [[FLR:v[0-9]+]], [[INPUT:v[0-9]+]] +; SI: v_subrev_f32_e32 [[RESULT:v[0-9]+]], [[FLR]], [[INPUT]] +; GCN: buffer_store_dword [[RESULT]] ; EG: FRACT define void @fract_f32_legacy_amdil(float addrspace(1)* %out, float addrspace(1)* %src) nounwind { %val = load float, float addrspace(1)* %src, align 4 @@ -26,3 +34,32 @@ define void @fract_f32_legacy_amdil(float addrspace(1)* %out, float addrspace(1) store float %fract, float addrspace(1)* %out, align 4 ret void } + +; FUNC-LABEL: {{^}}fract_f32_neg: +; CI: v_fract_f32_e64 [[RESULT:v[0-9]+]], -[[INPUT:v[0-9]+]] +; SI: v_floor_f32_e64 [[FLR:v[0-9]+]], -[[INPUT:v[0-9]+]] +; SI: v_sub_f32_e64 [[RESULT:v[0-9]+]], -[[INPUT]], [[FLR]] +; GCN: buffer_store_dword [[RESULT]] +; EG: FRACT +define void @fract_f32_neg(float addrspace(1)* %out, float addrspace(1)* %src) nounwind { + %val = load float, float addrspace(1)* %src, align 4 + %neg = fsub float 0.0, %val + %fract = call float @llvm.AMDGPU.fract.f32(float %neg) nounwind readnone + store float %fract, float addrspace(1)* %out, align 4 + ret void +} + +; FUNC-LABEL: {{^}}fract_f32_neg_abs: +; CI: v_fract_f32_e64 [[RESULT:v[0-9]+]], -|[[INPUT:v[0-9]+]]| +; SI: v_floor_f32_e64 [[FLR:v[0-9]+]], -|[[INPUT:v[0-9]+]]| +; SI: v_sub_f32_e64 [[RESULT:v[0-9]+]], -|[[INPUT]]|, [[FLR]] +; GCN: buffer_store_dword [[RESULT]] +; EG: FRACT +define void @fract_f32_neg_abs(float addrspace(1)* %out, float addrspace(1)* %src) nounwind { + %val = load float, float addrspace(1)* %src, align 4 + %abs = call float @llvm.fabs.f32(float %val) + %neg = fsub float 0.0, %abs + %fract = call float @llvm.AMDGPU.fract.f32(float %neg) nounwind readnone + store float %fract, float addrspace(1)* %out, align 4 + ret void +}