diff options
author | Thomas Dinges <blender@dingto.org> | 2016-05-19 13:47:41 +0300 |
---|---|---|
committer | Thomas Dinges <blender@dingto.org> | 2016-05-19 14:14:37 +0300 |
commit | c9f1ed1e4c22728b1f711656ab4de56c11c65e35 (patch) | |
tree | d64b736497f386827ef327d8b35fd5d9ce91588a /intern/cycles/kernel/geom | |
parent | 03f846ea12ba38d4686edfeef01a571329bd9385 (diff) |
Cycles: Add support for bindless textures.
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
Diffstat (limited to 'intern/cycles/kernel/geom')
-rw-r--r-- | intern/cycles/kernel/geom/geom_volume.h | 13 |
1 files changed, 12 insertions, 1 deletions
diff --git a/intern/cycles/kernel/geom/geom_volume.h b/intern/cycles/kernel/geom/geom_volume.h index ef02c01dec6..2044aafc877 100644 --- a/intern/cycles/kernel/geom/geom_volume.h +++ b/intern/cycles/kernel/geom/geom_volume.h @@ -29,7 +29,7 @@ CCL_NAMESPACE_BEGIN /* Return position normalized to 0..1 in mesh bounds */ -#ifdef __KERNEL_GPU__ +#if defined(__KERNEL_GPU__) && __CUDA_ARCH__ < 300 ccl_device float4 volume_image_texture_3d(int id, float x, float y, float z) { float4 r; @@ -65,7 +65,13 @@ ccl_device float volume_attribute_float(KernelGlobals *kg, const ShaderData *sd, { float3 P = volume_normalized_position(kg, sd, sd->P); #ifdef __KERNEL_GPU__ +# if __CUDA_ARCH__ >= 300 + CUtexObject tex = kernel_tex_fetch(__bindless_mapping, id); + float f = kernel_tex_image_interp_3d_float(tex, P.x, P.y, P.z); + float4 r = make_float4(f, f, f, 1.0); +# else float4 r = volume_image_texture_3d(id, P.x, P.y, P.z); +# endif #else float4 r; if(sd->flag & SD_VOLUME_CUBIC) @@ -84,7 +90,12 @@ ccl_device float3 volume_attribute_float3(KernelGlobals *kg, const ShaderData *s { float3 P = volume_normalized_position(kg, sd, sd->P); #ifdef __KERNEL_GPU__ +# if __CUDA_ARCH__ >= 300 + CUtexObject tex = kernel_tex_fetch(__bindless_mapping, id); + float4 r = kernel_tex_image_interp_3d_float4(tex, P.x, P.y, P.z); +# else float4 r = volume_image_texture_3d(id, P.x, P.y, P.z); +# endif #else float4 r; if(sd->flag & SD_VOLUME_CUBIC) |