diff options
author | Sergey Sharybin <sergey.vfx@gmail.com> | 2015-04-13 21:05:09 +0300 |
---|---|---|
committer | Sergey Sharybin <sergey.vfx@gmail.com> | 2015-04-20 15:29:51 +0300 |
commit | 828abaf11c3cd5177ae37e5943492a9ec23ce399 (patch) | |
tree | 9f6684d2f03fe544d86f049f3131e9663348002f /intern/cycles/kernel/svm | |
parent | cd44449578faa87c22776a0e8ecb792e18ed9a1b (diff) |
Cycles: Split BVH nodes storage into inner and leaf nodes
This way we can get rid of inefficient memory usage caused by BVH boundbox
part being unused by leaf nodes but still being allocated for them. Doing
such split allows to save 6 of float4 values for QBVH per leaf node and 3
of float4 values for regular BVH per leaf node.
This translates into following memory save using 01.01.01.G rendered
without hair:
Device memory size Device memory peak Global memory peak
Before the patch: 4957 5051 7668
With the patch: 4467 4562 7332
The measurements are done against current master. Still need to run speed tests
and it's hard to predict if it's faster or not: on the one hand leaf nodes are
now much more coherent in cache, on the other hand they're not so much coherent
with regular nodes anymore.
Reviewers: brecht, juicyfruit
Subscribers: venomgfx, eyecandy
Differential Revision: https://developer.blender.org/D1236
Diffstat (limited to 'intern/cycles/kernel/svm')
-rw-r--r-- | intern/cycles/kernel/svm/svm_image.h | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/intern/cycles/kernel/svm/svm_image.h b/intern/cycles/kernel/svm/svm_image.h index e927d46d404..ccc1e3df730 100644 --- a/intern/cycles/kernel/svm/svm_image.h +++ b/intern/cycles/kernel/svm/svm_image.h @@ -251,9 +251,9 @@ ccl_device float4 svm_image_texture(KernelGlobals *kg, int id, float x, float y, case 95: r = kernel_tex_image_interp(__tex_image_095, x, y); break; case 96: r = kernel_tex_image_interp(__tex_image_096, x, y); break; case 97: r = kernel_tex_image_interp(__tex_image_097, x, y); break; - case 98: r = kernel_tex_image_interp(__tex_image_098, x, y); break; #if defined(__CUDA_ARCH__) && (__CUDA_ARCH__ >= 300) + case 98: r = kernel_tex_image_interp(__tex_image_098, x, y); break; case 99: r = kernel_tex_image_interp(__tex_image_099, x, y); break; case 100: r = kernel_tex_image_interp(__tex_image_100, x, y); break; case 101: r = kernel_tex_image_interp(__tex_image_101, x, y); break; |