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, 47 insertions, 0 deletions

diff --git a/intern/cycles/kernel/device/oneapi/globals.h b/intern/cycles/kernel/device/oneapi/globals.h
new file mode 100644
index 00000000000..d60f4f135ba
--- /dev/null
+++ b/intern/cycles/kernel/device/oneapi/globals.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: Apache-2.0
+ * Copyright 2021-2022 Intel Corporation */
+
+#pragma once
+
+#include "kernel/integrator/state.h"
+#include "kernel/types.h"
+#include "kernel/util/profiling.h"
+
+CCL_NAMESPACE_BEGIN
+
+/* NOTE(@nsirgien): With SYCL we can't declare __constant__ global variable, which will be
+ * accessible from device code, like it has been done for Cycles CUDA backend. So, the backend will
+ * allocate this "constant" memory regions and store pointers to them in oneAPI context class */
+
+struct IntegratorStateGPU;
+struct IntegratorQueueCounter;
+
+typedef struct KernelGlobalsGPU {
+
+#define KERNEL_DATA_ARRAY(type, name) const type *__##name = nullptr;
+#include "kernel/data_arrays.h"
+#undef KERNEL_DATA_ARRAY
+  IntegratorStateGPU *integrator_state;
+  const KernelData *__data;
+#ifdef WITH_ONEAPI_SYCL_HOST_ENABLED
+  size_t nd_item_local_id_0;
+  size_t nd_item_local_range_0;
+  size_t nd_item_group_0;
+  size_t nd_item_group_range_0;
+
+  size_t nd_item_global_id_0;
+  size_t nd_item_global_range_0;
+#endif
+} KernelGlobalsGPU;
+
+typedef ccl_global KernelGlobalsGPU *ccl_restrict KernelGlobals;
+
+#define kernel_data (*(__data))
+#define kernel_integrator_state (*(integrator_state))
+
+/* data lookup defines */
+
+#define kernel_data_fetch(name, index) __##name[index]
+#define kernel_data_array(name) __##name
+
+CCL_NAMESPACE_END