Commit Graph

14 Commits

Author SHA1 Message Date
Xavier Hallade
d8e8e8eb9a Cycles: oneAPI: fix device compilation with latest MSVC
<algorithm> header include is missing from some sycl headers, this will
be fixed upstream with https://github.com/intel/llvm/pull/10424,
meanwhile, we work around it by including it directly.
2023-10-02 09:17:17 +02:00
Nikita Sirgienko
abab47a805 Cycles: oneAPI: Refactoring of local size choice logic 2023-08-22 19:04:16 +02:00
Campbell Barton
c12994612b License headers: use SPDX-FileCopyrightText in intern/cycles 2023-06-14 16:53:23 +10:00
Nikita Sirgienko
bafd82c9c1 Cycles: oneAPI: use local memory for faster shader sorting
Co-authored-by: Stefan Werner <stefan.werner@intel.com>

Pull Request: https://projects.blender.org/blender/blender/pulls/107994
2023-05-17 11:07:57 +02:00
Xavier Hallade
4382a0b350 Cleanup: avoid warnings from gcc in oneAPI device compilation
When building using GCC and with Embree without GPU support, there were
a few unused variables and a non-defined macro.
2023-04-18 22:40:40 +02:00
Xavier Hallade
70892e82ac Cycles: oneAPI: use specialization constant to compile with/without Embree on GPU 2023-04-18 22:09:42 +02:00
Xavier Hallade
9821a2d397 Cycles: pass kernel features to get_bvh_layout_mask
This allows to selectively disable Hardware Raytracing in oneAPI
backend, depending on features used.
2023-04-18 22:09:42 +02:00
Nikita Sirgienko
3f8c995109 Cycles: add hardware raytracing support to oneAPI device
Updated Embree 4 library with GPU support is required for it to be
compiled - compatiblity with Embree 3 and Embree 4 without GPU support
is maintained.
Enabling hardware raytracing is an opt-in user setting for now.

Pull Request: https://projects.blender.org/blender/blender/pulls/106266
2023-04-18 22:09:42 +02:00
Xavier Hallade
2943997d2a Cycles: oneAPI: include sycl/sycl.hpp instead of CL/sycl.hpp
Since SYCL 2020 API, sycl/sycl.hpp is the way.
2022-10-19 16:42:10 +02:00
Werner, Stefan
c32a455605 Cleanup: Fixed some warnings
Some unused parameters were left after changing the oneAPI device code
to be a direclty linked shared library.
2022-10-13 09:45:53 +02:00
Xavier Hallade
7eeeaec6da Cycles: use direct linking for oneAPI backend
This is a minimal set of changes, allowing a lot of cleanup that can
happen afterward as it allows sycl method and objects to be used outside
of kernel.cpp.

Reviewed By: brecht, sergey

Differential Revision: https://developer.blender.org/D15397
2022-10-07 09:50:05 +02:00
Nikita Sirgienko
8b11ed392c Cycles: Fix crashes in oneAPI backend for scenes not fitting in dGPU memory
Differential Revision: https://developer.blender.org/D15889
2022-09-06 15:38:15 +02:00
Xavier Hallade
d706d0460c Cycles oneAPI: simplify num_concurrent_states selection
The number of Execution Units and resident "threads" (simd width * threads
per EUs) are now exposed and used to select the number of states using
a simplified heuristic.
2022-07-27 09:45:33 +02:00
Xavier Hallade
a02992f131 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>
2022-06-29 12:58:04 +02:00