mirror of
https://github.com/PixarAnimationStudios/OpenSubdiv
synced 2024-11-27 05:50:05 +00:00
541aeddd3a
Add EvalStencils and EvalPatches API for most of CPU and GPU evaluators. with this change, Eval API in the osd layer consists of following parts: - Evaluators (Cpu, Omp, Tbb, Cuda, CL, GLXFB, GLCompute, D3D11Compute) implements EvalStencils and EvalPatches(*). Both supports derivatives (not fully implemented though) - Interop vertex buffer classes (optional, same as before) Note that these classes are not necessary to use Evaluators. All evaluators have EvalStencils/Patches which take device-specific buffer objects. For example, GLXFBEvaluator can take GLuint directly for both stencil tables and input primvars. Although using these interop classes makes it easy to integrate osd into relatively simple applications. - device-dependent StencilTable and PatchTable (optional) These are also optional, but can be used simply a substitute of Far::StencilTable and Far::PatchTable for osd evaluators. - PatchArray, PatchCoord, PatchParam They are tiny structs used for GPU based patch evaluation. (*) TODO and known issues: - CLEvaluator and D3D11Evaluator's EvalPatches() have not been implemented. - GPU Gregory patch evaluation has not been implemented in EvalPatches(). - CudaEvaluator::EvalPatches() is very unstable. - All patch evaluation kernels have not been well optimized. - Currently GLXFB kernel doesn't support derivative evaluation. There's a technical difficulty for the multi-stream output.
104 lines
3.4 KiB
C++
104 lines
3.4 KiB
C++
//
|
|
// Copyright 2015 Pixar
|
|
//
|
|
// Licensed under the Apache License, Version 2.0 (the "Apache License")
|
|
// with the following modification; you may not use this file except in
|
|
// compliance with the Apache License and the following modification to it:
|
|
// Section 6. Trademarks. is deleted and replaced with:
|
|
//
|
|
// 6. Trademarks. This License does not grant permission to use the trade
|
|
// names, trademarks, service marks, or product names of the Licensor
|
|
// and its affiliates, except as required to comply with Section 4(c) of
|
|
// the License and to reproduce the content of the NOTICE file.
|
|
//
|
|
// You may obtain a copy of the Apache License at
|
|
//
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
//
|
|
// Unless required by applicable law or agreed to in writing, software
|
|
// distributed under the Apache License with the above modification is
|
|
// distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
|
// KIND, either express or implied. See the Apache License for the specific
|
|
// language governing permissions and limitations under the Apache License.
|
|
//
|
|
|
|
#include "../osd/cudaPatchTable.h"
|
|
|
|
#include <cuda_runtime.h>
|
|
|
|
#include "../far/patchTable.h"
|
|
#include "../osd/cpuPatchTable.h"
|
|
|
|
namespace OpenSubdiv {
|
|
namespace OPENSUBDIV_VERSION {
|
|
|
|
namespace Osd {
|
|
|
|
CudaPatchTable::CudaPatchTable() :
|
|
_patchArrays(NULL), _indexBuffer(NULL), _patchParamBuffer(NULL) {
|
|
}
|
|
|
|
CudaPatchTable::~CudaPatchTable() {
|
|
if (_patchArrays) cudaFree(_patchArrays);
|
|
if (_indexBuffer) cudaFree(_indexBuffer);
|
|
if (_patchParamBuffer) cudaFree(_patchParamBuffer);
|
|
}
|
|
|
|
CudaPatchTable *
|
|
CudaPatchTable::Create(Far::PatchTable const *farPatchTable,
|
|
void * /*deviceContext*/) {
|
|
CudaPatchTable *instance = new CudaPatchTable();
|
|
if (instance->allocate(farPatchTable)) return instance;
|
|
delete instance;
|
|
return 0;
|
|
}
|
|
|
|
bool
|
|
CudaPatchTable::allocate(Far::PatchTable const *farPatchTable) {
|
|
CpuPatchTable patchTable(farPatchTable);
|
|
|
|
size_t numPatchArrays = patchTable.GetNumPatchArrays();
|
|
size_t indexSize = patchTable.GetPatchIndexSize();
|
|
size_t patchParamSize = patchTable.GetPatchParamSize();
|
|
|
|
cudaError_t err;
|
|
err = cudaMalloc(&_patchArrays, numPatchArrays * sizeof(Osd::PatchArray));
|
|
if (err != cudaSuccess) return false;
|
|
|
|
err = cudaMalloc(&_indexBuffer, indexSize * sizeof(int));
|
|
if (err != cudaSuccess) return false;
|
|
|
|
err = cudaMalloc(&_patchParamBuffer, patchParamSize * sizeof(Osd::PatchParam));
|
|
if (err != cudaSuccess) return false;
|
|
|
|
// copy patch array
|
|
err = cudaMemcpy(_patchArrays,
|
|
patchTable.GetPatchArrayBuffer(),
|
|
numPatchArrays * sizeof(Osd::PatchArray),
|
|
cudaMemcpyHostToDevice);
|
|
if (err != cudaSuccess) return false;
|
|
|
|
// copy index buffer
|
|
err = cudaMemcpy(_indexBuffer,
|
|
patchTable.GetPatchIndexBuffer(),
|
|
indexSize * sizeof(int),
|
|
cudaMemcpyHostToDevice);
|
|
if (err != cudaSuccess) return false;
|
|
|
|
// patch param buffer
|
|
err = cudaMemcpy(_patchParamBuffer,
|
|
patchTable.GetPatchParamBuffer(),
|
|
patchParamSize * sizeof(Osd::PatchParam),
|
|
cudaMemcpyHostToDevice);
|
|
if (err != cudaSuccess) return false;
|
|
|
|
return true;
|
|
}
|
|
|
|
|
|
} // end namespace Osd
|
|
|
|
} // end namespace OPENSUBDIV_VERSION
|
|
} // end namespace OpenSubdiv
|
|
|