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>

1 files changed, 50 insertions, 0 deletions

diff --git a/intern/cycles/kernel/device/oneapi/dll_interface_template.h b/intern/cycles/kernel/device/oneapi/dll_interface_template.h
new file mode 100644
index 00000000000..2d740b4c64a
--- /dev/null
+++ b/intern/cycles/kernel/device/oneapi/dll_interface_template.h
@@ -0,0 +1,50 @@
+/* device_capabilities() returns a C string that must be free'd with oneapi_free(). */
+DLL_INTERFACE_CALL(oneapi_device_capabilities, char *)
+DLL_INTERFACE_CALL(oneapi_free, void, void *)
+DLL_INTERFACE_CALL(oneapi_get_memcapacity, size_t, SyclQueue *queue)
+
+DLL_INTERFACE_CALL(oneapi_get_compute_units_amount, size_t, SyclQueue *queue)
+DLL_INTERFACE_CALL(oneapi_iterate_devices, void, OneAPIDeviceIteratorCallback cb, void *user_ptr)
+DLL_INTERFACE_CALL(oneapi_set_error_cb, void, OneAPIErrorCallback, void *user_ptr)
+
+DLL_INTERFACE_CALL(oneapi_create_queue, bool, SyclQueue *&external_queue, int device_index)
+DLL_INTERFACE_CALL(oneapi_free_queue, void, SyclQueue *queue)
+DLL_INTERFACE_CALL(
+    oneapi_usm_aligned_alloc_host, void *, SyclQueue *queue, size_t memory_size, size_t alignment)
+DLL_INTERFACE_CALL(oneapi_usm_alloc_device, void *, SyclQueue *queue, size_t memory_size)
+DLL_INTERFACE_CALL(oneapi_usm_free, void, SyclQueue *queue, void *usm_ptr)
+
+DLL_INTERFACE_CALL(
+    oneapi_usm_memcpy, bool, SyclQueue *queue, void *dest, void *src, size_t num_bytes)
+DLL_INTERFACE_CALL(oneapi_queue_synchronize, bool, SyclQueue *queue)
+DLL_INTERFACE_CALL(oneapi_usm_memset,
+                   bool,
+                   SyclQueue *queue,
+                   void *usm_ptr,
+                   unsigned char value,
+                   size_t num_bytes)
+
+DLL_INTERFACE_CALL(oneapi_run_test_kernel, bool, SyclQueue *queue)
+
+/* Operation with Kernel globals structure - map of global/constant allocation - filled before
+ * render/kernel execution As we don't know in cycles sizeof this - Cycles will manage just as
+ * pointer. */
+DLL_INTERFACE_CALL(oneapi_kernel_globals_size, bool, SyclQueue *queue, size_t &kernel_global_size)
+DLL_INTERFACE_CALL(oneapi_set_global_memory,
+                   void,
+                   SyclQueue *queue,
+                   void *kernel_globals,
+                   const char *memory_name,
+                   void *memory_device_pointer)
+
+DLL_INTERFACE_CALL(oneapi_kernel_preferred_local_size,
+                   size_t,
+                   SyclQueue *queue,
+                   const DeviceKernel kernel,
+                   const size_t kernel_global_size)
+DLL_INTERFACE_CALL(oneapi_enqueue_kernel,
+                   bool,
+                   KernelContext *context,
+                   int kernel,
+                   size_t global_size,
+                   void **args)