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, 5 insertions, 3 deletions

diff --git a/intern/cycles/util/half.h b/intern/cycles/util/half.h
index 434bc12d670..c668638eb02 100644
--- a/intern/cycles/util/half.h
+++ b/intern/cycles/util/half.h
@@ -35,7 +35,7 @@ ccl_device_inline float half_to_float(half h_in)
 #else
 
 /* CUDA has its own half data type, no need to define then */
-#  if !defined(__KERNEL_CUDA__) && !defined(__KERNEL_HIP__)
+#  if !defined(__KERNEL_CUDA__) && !defined(__KERNEL_HIP__) && !defined(__KERNEL_ONEAPI__)
 /* Implementing this as a class rather than a typedef so that the compiler can tell it apart from
  * unsigned shorts. */
 class half {
@@ -73,7 +73,7 @@ struct half4 {
 
 ccl_device_inline half float_to_half_image(float f)
 {
-#if defined(__KERNEL_METAL__)
+#if defined(__KERNEL_METAL__) || defined(__KERNEL_ONEAPI__)
   return half(min(f, 65504.0f));
 #elif defined(__KERNEL_CUDA__) || defined(__KERNEL_HIP__)
   return __float2half(min(f, 65504.0f));
@@ -103,6 +103,8 @@ ccl_device_inline float half_to_float_image(half h)
 {
 #if defined(__KERNEL_METAL__)
   return half_to_float(h);
+#elif defined(__KERNEL_ONEAPI__)
+  return float(h);
 #elif defined(__KERNEL_CUDA__) || defined(__KERNEL_HIP__)
   return __half2float(h);
 #else
@@ -136,7 +138,7 @@ ccl_device_inline float4 half4_to_float4_image(const half4 h)
 
 ccl_device_inline half float_to_half_display(const float f)
 {
-#if defined(__KERNEL_METAL__)
+#if defined(__KERNEL_METAL__) || defined(__KERNEL_ONEAPI__)
   return half(min(f, 65504.0f));
 #elif defined(__KERNEL_CUDA__) || defined(__KERNEL_HIP__)
   return __float2half(min(f, 65504.0f));