addressed review comments

Author: t4c1

sycl/doc/extensions/experimental/sycl_ext_oneapi_cuda_async_barrier.asciidoc

@@ -73,14 +73,18 @@ value to determine which of the extension's APIs the implementation supports.
 
 [%header,cols="1,5"]
 |===
-|Value |Description
-|1     |Initial extension version.  Base features are supported.
+|Value
+|Description
+
+|1
+|The APIs of this experimental extension are not versioned, so the
+ feature-test macro always has this value.
 |===
 
 === Overview
 
 This extension introduces asynchronous barrier for CUDA devices. This extends 
-`group_barrier` by splitting it into into two calls - arrive and wait. The 
+`group_barrier` by splitting it into two calls - arrive and wait. The 
 wait call blocks until the predetermined number of work items in the same work 
 group call arrive. This is also very similar to 
 https://en.cppreference.com/w/cpp/thread/barrier[`std::barrier`] introduced 

sycl/include/CL/sycl.hpp

@@ -60,7 +60,7 @@
 #if SYCL_EXT_ONEAPI_BACKEND_LEVEL_ZERO
 #include <sycl/ext/oneapi/backend/level_zero.hpp>
 #endif
-#include <sycl/ext/oneapi/barrier.hpp>
+#include <sycl/ext/oneapi/experimental/cuda/barrier.hpp>
 #include <sycl/ext/oneapi/bf16_storage_builtins.hpp>
 #include <sycl/ext/oneapi/device_global/properties.hpp>
 #include <sycl/ext/oneapi/experimental/builtins.hpp>

sycl/include/CL/sycl/detail/pi.h

@@ -316,7 +316,7 @@ typedef enum {
   PI_EXT_ONEAPI_DEVICE_INFO_MAX_WORK_GROUPS_1D = 0x20001,
   PI_EXT_ONEAPI_DEVICE_INFO_MAX_WORK_GROUPS_2D = 0x20002,
   PI_EXT_ONEAPI_DEVICE_INFO_MAX_WORK_GROUPS_3D = 0x20003,
-  PI_EXT_ONEAPI_DEVICE_INFO_CUDA_ASYNC_BARRIER = 0x30000,
+  PI_EXT_ONEAPI_DEVICE_INFO_CUDA_ASYNC_BARRIER = 0x20004,
 } _pi_device_info;
 
 typedef enum {