Cycles: Support multithreaded compilation of kernels
This patch implements a workaround to get the multithreaded compilation from D2231 working.
So far, it only works for Blender, not for Cycles Standalone. Also, I have only tested the Linux codepath in the helper function.
Depends on D2231.
Patch by lukasstockner97, jbakker, brecht
job | scene_name | compilation_time
----------+-----------------+------------------
Baseline | empty | 22.73
D2264 | empty | 13.94
Baseline | bmw | 56.44
D2264 | bmw | 41.32
Baseline | fishycat | 59.50
D2264 | fishycat | 45.19
Baseline | barbershop | 212.28
D2264 | barbershop | 169.81
Baseline | victor | 67.51
D2264 | victor | 53.60
Baseline | classroom | 51.46
D2264 | classroom | 39.02
Baseline | koro | 62.48
D2264 | koro | 49.03
Baseline | pavillion | 54.37
D2264 | pavillion | 38.82
Baseline | splash279 | 47.43
D2264 | splash279 | 37.94
Baseline | volume_emission | 145.22
D2264 | volume_emission | 121.10
This patch reduced compilation time as the split kernels and base
kernels are compiled in parallel. In cycles debug mode (256) you can set
unmark the opencl single program file, what reduces the compilation time
even further (bmw 17 seconds, barbershop 53 seconds).
Reviewers: brecht, dingto, sergey, juicyfruit, lukasstockner97
Reviewed By: brecht
Subscribers: Loner, jbakker, candreacchio, 3dLuver, LazyDodo, bliblubli
Differential Revision: https://developer.blender.org/D2264
This commit is contained in:
@@ -40,6 +40,10 @@
|
||||
#include <OSL/oslconfig.h>
|
||||
#endif
|
||||
|
||||
#ifdef WITH_OPENCL
|
||||
#include "device/device_intern.h"
|
||||
#endif
|
||||
|
||||
CCL_NAMESPACE_BEGIN
|
||||
|
||||
namespace {
|
||||
@@ -624,6 +628,31 @@ static PyObject *opencl_disable_func(PyObject * /*self*/, PyObject * /*value*/)
|
||||
DebugFlags().opencl.device_type = DebugFlags::OpenCL::DEVICE_NONE;
|
||||
Py_RETURN_NONE;
|
||||
}
|
||||
|
||||
static PyObject *opencl_compile_func(PyObject * /*self*/, PyObject *args)
|
||||
{
|
||||
PyObject *sequence = PySequence_Fast(args, "Arguments must be a sequence");
|
||||
if(sequence == NULL) {
|
||||
Py_RETURN_FALSE;
|
||||
}
|
||||
|
||||
vector<string> parameters;
|
||||
for(Py_ssize_t i = 0; i < PySequence_Fast_GET_SIZE(sequence); i++) {
|
||||
PyObject *item = PySequence_Fast_GET_ITEM(sequence, i);
|
||||
PyObject *item_as_string = PyObject_Str(item);
|
||||
const char *parameter_string = PyUnicode_AsUTF8(item_as_string);
|
||||
parameters.push_back(parameter_string);
|
||||
Py_DECREF(item_as_string);
|
||||
}
|
||||
Py_DECREF(sequence);
|
||||
|
||||
if (device_opencl_compile_kernel(parameters)) {
|
||||
Py_RETURN_TRUE;
|
||||
}
|
||||
else {
|
||||
Py_RETURN_FALSE;
|
||||
}
|
||||
}
|
||||
#endif
|
||||
|
||||
static bool denoise_parse_filepaths(PyObject *pyfilepaths, vector<string>& filepaths)
|
||||
@@ -899,6 +928,7 @@ static PyMethodDef methods[] = {
|
||||
{"system_info", system_info_func, METH_NOARGS, ""},
|
||||
#ifdef WITH_OPENCL
|
||||
{"opencl_disable", opencl_disable_func, METH_NOARGS, ""},
|
||||
{"opencl_compile", opencl_compile_func, METH_VARARGS, ""},
|
||||
#endif
|
||||
|
||||
/* Standalone denoising */
|
||||
|
||||
Reference in New Issue
Block a user