Cycles: Add support for rendering on Intel GPUs using oneAPI

This patch adds a new Cycles device with similar functionality to the
existing GPU devices.  Kernel compilation and runtime interaction happen
via oneAPI DPC++ compiler and SYCL API.

This implementation is primarly focusing on Intel® Arc™ GPUs and other
future Intel GPUs.  The first supported drivers are 101.1660 on Windows
and 22.10.22597 on Linux.

The necessary tools for compilation are:
- A SYCL compiler such as oneAPI DPC++ compiler or
  https://github.com/intel/llvm
- Intel® oneAPI Level Zero which is used for low level device queries:
  https://github.com/oneapi-src/level-zero
- To optionally generate prebuilt graphics binaries: Intel® Graphics
  Compiler All are included in Linux precompiled libraries on svn:
  https://svn.blender.org/svnroot/bf-blender/trunk/lib The same goes for
  Windows precompiled binaries but for the graphics compiler, available
  as "Intel® Graphics Offline Compiler for OpenCL™ Code" from
  https://www.intel.com/content/www/us/en/developer/articles/tool/oneapi-standalone-components.html,
  for which path can be set as OCLOC_INSTALL_DIR.

Being based on the open SYCL standard, this implementation could also be
extended to run on other compatible non-Intel hardware in the future.

Reviewed By: sergey, brecht

Differential Revision: https://developer.blender.org/D15254

Co-authored-by: Nikita Sirgienko <nikita.sirgienko@intel.com>
Co-authored-by: Stefan Werner <stefan.werner@intel.com>
This commit is contained in:
2022-06-29 12:58:04 +02:00
parent 302b04a5a3
commit a02992f131
81 changed files with 4185 additions and 76 deletions

View File

@@ -871,18 +871,20 @@ static PyObject *enable_print_stats_func(PyObject * /*self*/, PyObject * /*args*
static PyObject *get_device_types_func(PyObject * /*self*/, PyObject * /*args*/)
{
vector<DeviceType> device_types = Device::available_types();
bool has_cuda = false, has_optix = false, has_hip = false, has_metal = false;
bool has_cuda = false, has_optix = false, has_hip = false, has_metal = false, has_oneapi = false;
foreach (DeviceType device_type, device_types) {
has_cuda |= (device_type == DEVICE_CUDA);
has_optix |= (device_type == DEVICE_OPTIX);
has_hip |= (device_type == DEVICE_HIP);
has_metal |= (device_type == DEVICE_METAL);
has_oneapi |= (device_type == DEVICE_ONEAPI);
}
PyObject *list = PyTuple_New(4);
PyObject *list = PyTuple_New(5);
PyTuple_SET_ITEM(list, 0, PyBool_FromLong(has_cuda));
PyTuple_SET_ITEM(list, 1, PyBool_FromLong(has_optix));
PyTuple_SET_ITEM(list, 2, PyBool_FromLong(has_hip));
PyTuple_SET_ITEM(list, 3, PyBool_FromLong(has_metal));
PyTuple_SET_ITEM(list, 4, PyBool_FromLong(has_oneapi));
return list;
}
@@ -914,6 +916,9 @@ static PyObject *set_device_override_func(PyObject * /*self*/, PyObject *arg)
else if (override == "METAL") {
BlenderSession::device_override = DEVICE_MASK_METAL;
}
else if (override == "ONEAPI") {
BlenderSession::device_override = DEVICE_MASK_ONEAPI;
}
else {
printf("\nError: %s is not a valid Cycles device.\n", override.c_str());
Py_RETURN_FALSE;