forked from bartvdbraak/blender
c9f1ed1e4c
This adds support for CUDA Texture objects (also known as Bindless textures) for Kepler GPUs (Geforce 6xx and above). This is used for all 2D/3D textures, data still uses arrays as before. User benefits: * No more limits of image textures on Kepler. We had 5 float4 and 145 byte4 slots there before, now we have 1024 float4 and 1024 byte4. This can be extended further if we need to (just change the define). * Single channel textures slots (byte and float) are now supported on Kepler as well (1024 slots for each type). ToDo / Issues: * 3D textures don't work yet, at least don't show up during render. I have no idea whats wrong yet. * Dynamically allocate bindless_mapping array? I hope Fermi still works fine, but that should be tested on a Fermi card before pushing to master. Part of my GSoC 2016. Reviewers: sergey, #cycles, brecht Subscribers: swerner, jtheninja, brecht, sergey Differential Revision: https://developer.blender.org/D1999
71 lines
2.3 KiB
C
71 lines
2.3 KiB
C
/*
|
|
* Copyright 2011-2015 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.
|
|
*/
|
|
|
|
CCL_NAMESPACE_BEGIN
|
|
|
|
/* TODO(sergey): Think of making it more generic volume-type attribute
|
|
* sampler.
|
|
*/
|
|
ccl_device void svm_node_tex_voxel(KernelGlobals *kg,
|
|
ShaderData *sd,
|
|
float *stack,
|
|
uint4 node,
|
|
int *offset)
|
|
{
|
|
uint co_offset, density_out_offset, color_out_offset, space;
|
|
decode_node_uchar4(node.z, &co_offset, &density_out_offset, &color_out_offset, &space);
|
|
#ifdef __VOLUME__
|
|
int id = node.y;
|
|
float3 co = stack_load_float3(stack, co_offset);
|
|
if(space == NODE_TEX_VOXEL_SPACE_OBJECT) {
|
|
co = volume_normalized_position(kg, sd, co);
|
|
}
|
|
else {
|
|
kernel_assert(space == NODE_TEX_VOXEL_SPACE_WORLD);
|
|
Transform tfm;
|
|
tfm.x = read_node_float(kg, offset);
|
|
tfm.y = read_node_float(kg, offset);
|
|
tfm.z = read_node_float(kg, offset);
|
|
tfm.w = read_node_float(kg, offset);
|
|
co = transform_point(&tfm, co);
|
|
}
|
|
float4 r;
|
|
# if defined(__KERNEL_GPU__)
|
|
# if __CUDA_ARCH__ >= 300
|
|
CUtexObject tex = kernel_tex_fetch(__bindless_mapping, id);
|
|
if(id < 2048) /* TODO(dingto): Make this a variable */
|
|
r = kernel_tex_image_interp_3d_float4(tex, co.x, co.y, co.z);
|
|
else {
|
|
float f = kernel_tex_image_interp_3d_float(tex, co.x, co.y, co.z);
|
|
r = make_float4(f, f, f, 1.0);
|
|
}
|
|
# else /* __CUDA_ARCH__ >= 300 */
|
|
r = volume_image_texture_3d(id, co.x, co.y, co.z);
|
|
# endif
|
|
# else /* __KERNEL_GPU__ */
|
|
r = kernel_tex_image_interp_3d(id, co.x, co.y, co.z);
|
|
# endif
|
|
#else
|
|
float4 r = make_float4(0.0f, 0.0f, 0.0f, 0.0f);
|
|
#endif
|
|
if(stack_valid(density_out_offset))
|
|
stack_store_float(stack, density_out_offset, r.w);
|
|
if(stack_valid(color_out_offset))
|
|
stack_store_float3(stack, color_out_offset, make_float3(r.x, r.y, r.z));
|
|
}
|
|
|
|
CCL_NAMESPACE_END
|