griefith/test
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Cycles: Fix CUDA split kernel

Browse Source 
Global size y needs to be a multiple of 16.
This commit is contained in:
Sergey Sharybin
2017-05-02 15:03:51 +02:00
parent 4174e533c0
commit 4384a7cf46
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
intern/cycles/device/device_cuda.cpp
View File

@@ -1634,7 +1634,8 @@ int2 CUDASplitKernel::split_kernel_global_size(device_memory& kg, device_memory&
<< string_human_readable_size(free) << ").";
size_t num_elements = max_elements_for_max_buffer_size(kg, data, free / 2);
int2 global_size = make_int2(round_down((int)sqrt(num_elements), 32), (int)sqrt(num_elements));
size_t side = round_down((int)sqrt(num_elements), 32);
int2 global_size = make_int2(side, round_down(num_elements / side, 16));
VLOG(1) << "Global size: " << global_size << ".";
return global_size;
}