[SYCL][CUDA] Port CUDA plugin to Unified Runtime (intel#9512)

This moves the CUDA plugin implementation to Unified Runtime; and
changes the pi_cuda plugin to use pi2ur to implement PI. The changes to
the implementation have been kept to a minimum and should be
functionally the same. Documentation and comments have been moved
verbatim, other than changing PI references to UR.

This PR is based on top of the Level Zero adapter (intel#8744) so will only
be ready when that is merged.

---------

Co-authored-by: Petr Vesely <petr.vesely@codeplay.com>
Co-authored-by: Omar Ahmed <omar.ahmed@codeplay.com>
Co-authored-by: Martin Morrison-Grant <martin.morrisongrant@codeplay.com>
Co-authored-by: Aaron Greig <aaron.greig@codeplay.com>

Author: 5 people

sycl/plugins/cuda/CMakeLists.txt

@@ -48,18 +48,51 @@ endif()
 
 add_sycl_plugin(cuda
   SOURCES
+    # Some code is shared with the UR adapter
+    "../unified_runtime/pi2ur.hpp"
+    "../unified_runtime/pi2ur.cpp"
+    "../unified_runtime/ur/ur.hpp"
+    "../unified_runtime/ur/ur.cpp"
+    "../unified_runtime/ur/usm_allocator.cpp"
+    "../unified_runtime/ur/usm_allocator.hpp"
+    "../unified_runtime/ur/adapters/cuda/common.cpp"
+    "../unified_runtime/ur/adapters/cuda/common.hpp"
+    "../unified_runtime/ur/adapters/cuda/context.cpp"
+    "../unified_runtime/ur/adapters/cuda/context.hpp"
+    "../unified_runtime/ur/adapters/cuda/device.cpp"
+    "../unified_runtime/ur/adapters/cuda/device.hpp"
+    "../unified_runtime/ur/adapters/cuda/enqueue.cpp"
+    "../unified_runtime/ur/adapters/cuda/event.cpp"
+    "../unified_runtime/ur/adapters/cuda/event.hpp"
+    "../unified_runtime/ur/adapters/cuda/kernel.cpp"
+    "../unified_runtime/ur/adapters/cuda/kernel.hpp"
+    "../unified_runtime/ur/adapters/cuda/memory.cpp"
+    "../unified_runtime/ur/adapters/cuda/memory.hpp"
+    "../unified_runtime/ur/adapters/cuda/platform.cpp"
+    "../unified_runtime/ur/adapters/cuda/platform.hpp"
+    "../unified_runtime/ur/adapters/cuda/program.cpp"
+    "../unified_runtime/ur/adapters/cuda/program.hpp"
+    "../unified_runtime/ur/adapters/cuda/queue.cpp"
+    "../unified_runtime/ur/adapters/cuda/queue.hpp"
+    "../unified_runtime/ur/adapters/cuda/sampler.cpp"
+    "../unified_runtime/ur/adapters/cuda/sampler.hpp"
+    "../unified_runtime/ur/adapters/cuda/tracing.cpp"
+    "../unified_runtime/ur/adapters/cuda/ur_interface_loader.cpp"
+    "../unified_runtime/ur/adapters/cuda/usm.cpp"
+    # --- 
     "${sycl_inc_dir}/sycl/detail/pi.h"
     "${sycl_inc_dir}/sycl/detail/pi.hpp"
     "pi_cuda.hpp"
     "pi_cuda.cpp"
-    "tracing.cpp"
     ${XPTI_PROXY_SRC}
   INCLUDE_DIRS
     ${sycl_inc_dir}
     ${XPTI_INCLUDE}
+    ${CMAKE_CURRENT_SOURCE_DIR}/../unified_runtime
   LIBRARIES
     cudadrv
     ${XPTI_LIBS}
+    UnifiedRuntime-Headers
   HEADER "${CMAKE_CURRENT_SOURCE_DIR}/include/features.hpp"
 )