29f6616d60
except for curves, that's still missing from the OpenColorIO GLSL shader. The pixels are stored in a half float texture, converterd from full float with native GPU instructions and SIMD on the CPU, so it should be pretty quick. Using a GLSL shader is useful for GPU render because it avoids a copy through CPU memory.
72 lines
2.6 KiB
Plaintext
72 lines
2.6 KiB
Plaintext
/*
|
|
* Copyright 2011-2013 Blender Foundation
|
|
*
|
|
* Licensed under the Apache License, Version 2.0 (the "License");
|
|
* you may not use this file except in compliance with the License.
|
|
* You may obtain a copy of the License at
|
|
*
|
|
* http://www.apache.org/licenses/LICENSE-2.0
|
|
*
|
|
* Unless required by applicable law or agreed to in writing, software
|
|
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
* See the License for the specific language governing permissions and
|
|
* limitations under the License
|
|
*/
|
|
|
|
/* CUDA kernel entry points */
|
|
|
|
#include "kernel_compat_cuda.h"
|
|
#include "kernel_math.h"
|
|
#include "kernel_types.h"
|
|
#include "kernel_globals.h"
|
|
#include "kernel_film.h"
|
|
#include "kernel_path.h"
|
|
#include "kernel_displace.h"
|
|
|
|
extern "C" __global__ void kernel_cuda_path_trace(float *buffer, uint *rng_state, int sample, int sx, int sy, int sw, int sh, int offset, int stride)
|
|
{
|
|
int x = sx + blockDim.x*blockIdx.x + threadIdx.x;
|
|
int y = sy + blockDim.y*blockIdx.y + threadIdx.y;
|
|
|
|
if(x < sx + sw && y < sy + sh)
|
|
kernel_path_trace(NULL, buffer, rng_state, sample, x, y, offset, stride);
|
|
}
|
|
|
|
#ifdef __BRANCHED_PATH__
|
|
extern "C" __global__ void kernel_cuda_branched_path_trace(float *buffer, uint *rng_state, int sample, int sx, int sy, int sw, int sh, int offset, int stride)
|
|
{
|
|
int x = sx + blockDim.x*blockIdx.x + threadIdx.x;
|
|
int y = sy + blockDim.y*blockIdx.y + threadIdx.y;
|
|
|
|
if(x < sx + sw && y < sy + sh)
|
|
kernel_branched_path_trace(NULL, buffer, rng_state, sample, x, y, offset, stride);
|
|
}
|
|
#endif
|
|
|
|
extern "C" __global__ void kernel_cuda_convert_to_byte(uchar4 *rgba, float *buffer, float sample_scale, int sx, int sy, int sw, int sh, int offset, int stride)
|
|
{
|
|
int x = sx + blockDim.x*blockIdx.x + threadIdx.x;
|
|
int y = sy + blockDim.y*blockIdx.y + threadIdx.y;
|
|
|
|
if(x < sx + sw && y < sy + sh)
|
|
kernel_film_convert_to_byte(NULL, rgba, buffer, sample_scale, x, y, offset, stride);
|
|
}
|
|
|
|
extern "C" __global__ void kernel_cuda_convert_to_half_float(uchar4 *rgba, float *buffer, float sample_scale, int sx, int sy, int sw, int sh, int offset, int stride)
|
|
{
|
|
int x = sx + blockDim.x*blockIdx.x + threadIdx.x;
|
|
int y = sy + blockDim.y*blockIdx.y + threadIdx.y;
|
|
|
|
if(x < sx + sw && y < sy + sh)
|
|
kernel_film_convert_to_half_float(NULL, rgba, buffer, sample_scale, x, y, offset, stride);
|
|
}
|
|
|
|
extern "C" __global__ void kernel_cuda_shader(uint4 *input, float4 *output, int type, int sx)
|
|
{
|
|
int x = sx + blockDim.x*blockIdx.x + threadIdx.x;
|
|
|
|
kernel_shader_evaluate(NULL, input, output, (ShaderEvalType)type, x);
|
|
}
|
|
|