Merge branch 'sycl' into gmlueck/mv-proposed-extensions

Author: gmlueck

sycl/ReleaseNotes.md

@@ -148,7 +148,7 @@ kernel arguments.  For example, the [SYCL\_ONEAPI\_accessor\_properties][6]
 extension could be redesigned to use compile-time properties.  Such a redesign
 might look like:
 
-[6]: <https://github.com/intel/llvm/blob/sycl/sycl/doc/extensions/accessor_properties/SYCL_ONEAPI_accessor_properties.asciidoc>
+[6]: <extensions/supported/SYCL_EXT_ONEAPI_ACCESSOR_PROPERTIES.asciidoc>
 
 ```
 namespace sycl {

sycl/doc/CompileTimeProperties.md

@@ -20,7 +20,7 @@ compiler and runtime.
 | `SYCL_CACHE_THRESHOLD` | Positive integer | Cache eviction threshold in days (default value is 7 for 1 week). Set to 0 for disabling time-based cache eviction. |
 | `SYCL_CACHE_MIN_DEVICE_IMAGE_SIZE` | Positive integer | Minimum size of device code image in bytes which is reasonable to cache on disk because disk access operation may take more time than do JIT compilation for it. Default value is 0 to cache all images. |
 | `SYCL_CACHE_MAX_DEVICE_IMAGE_SIZE` | Positive integer | Maximum size of device image in bytes which is cached. Too big kernels may overload disk too fast. Default value is 1 GB. |
-| `SYCL_ENABLE_DEFAULT_CONTEXTS` | '1' or '0' | Enable ('1') or disable ('0') creation of default platform contexts in SYCL runtime. The default context for each platform contains all devices in the platform. Refer to [Platform Default Contexts](extensions/PlatformContext/PlatformContext.adoc) extension to learn more. Enabled by default on Linux and disabled on Windows. |
+| `SYCL_ENABLE_DEFAULT_CONTEXTS` | '1' or '0' | Enable ('1') or disable ('0') creation of default platform contexts in SYCL runtime. The default context for each platform contains all devices in the platform. Refer to [Platform Default Contexts](extensions/supported/SYCL_EXT_ONEAPI_DEFAULT_CONTEXT.asciidoc) extension to learn more. Enabled by default on Linux and disabled on Windows. |
 | `SYCL_USM_HOSTPTR_IMPORT` | Integer | Enable by specifying non-zero value. Buffers created with a host pointer will result in host data promotion to USM, improving data transfer performance. To use this feature, also set SYCL_HOST_UNIFIED_MEMORY=1. |
 
 `(*) Note: Any means this environment variable is effective when set to any non-null value.`

sycl/doc/EnvironmentVariables.md

@@ -705,7 +705,7 @@ SYCL_BE=PI_CUDA ./simple-sycl-app-cuda.exe
 
 **NOTE**: DPC++/SYCL developers can specify SYCL device for execution using
 device selectors (e.g. `cl::sycl::cpu_selector`, `cl::sycl::gpu_selector`,
-[Intel FPGA selector(s)](extensions/IntelFPGA/FPGASelector.md)) as
+[Intel FPGA selector(s)](extensions/supported/SYCL_EXT_INTEL_FPGA_DEVICE_SELECTOR.md)) as
 explained in following section [Code the program for a specific
 GPU](#code-the-program-for-a-specific-gpu).
 

sycl/doc/GetStartedGuide.md

@@ -24,7 +24,7 @@ One is using environment variable SYCL_DEVICE_FILTER described in [EnvironmentVa
 $ SYCL_DEVICE_FILTER=level_zero sycl-ls
 [level_zero:0] GPU : Intel(R) Level-Zero 1.1 [1.1.19792]
 ```
-Another way is to use similar SYCL API described in [FilterSelector.md](https://github.com/intel/llvm/blob/sycl/sycl/doc/extensions/FilterSelector/FilterSelector.adoc)
+Another way is to use similar SYCL API described in [SYCL\_EXT\_ONEAPI\_FILTER\_SELECTOR](extensions/supported/SYCL_EXT_ONEAPI_FILTER_SELECTOR.asciidoc)
 E.g. `filter_selector("level_zero")` will only see Level-Zero operated devices.
 
 If there are multiple GPUs in a system then they will be seen as multiple different root-devices.

sycl/doc/MultiTileCardWithLevelZero.md

@@ -48,7 +48,7 @@ Invoking `__devicelib_assert_read` after a kernel doesn't imply the kernel has
 assertion failed.
 
 See also: assert_extension_.
-.. _assert_extension: ../Assert/SYCL_ONEAPI_ASSERT.asciidoc)
+.. _assert_extension: ../supported/SYCL_EXT_ONEAPI_ASSERT.asciidoc)
 
 cl_intel_devicelib_math
 ==========================

sycl/doc/extensions/Bitcast/SYCL_INTEL_bitcast.asciidoc

@@ -168,7 +168,7 @@ enum class event_command_status : int {
 This non-normative section describes the conditions when the DPC++ implementation provides an optimization benefit* for the `discard_events` property.
 
  - The queue must be constructed with the `in_order` property.
- - A kernel submitted to the queue must not use the https://github.com/intel/llvm/blob/sycl/sycl/doc/extensions/Assert/SYCL_ONEAPI_ASSERT.asciidoc[fallback assert feature].
+ - A kernel submitted to the queue must not use the link:../supported/SYCL_EXT_ONEAPI_ASSERT.asciidoc[fallback assert feature].
  - A queue operation submitted to the queue must not use streams or buffer / image accessors. However, local accessors do not inhibit optimization.
  - Any queue operations using Level Zero backend temporarily work without optimization.