[SYCL][UR][OpenCL] Fix profiling tag ordering on OpenCL GPU

[crystarm]

Related to #22229.

submit_profiling_tag returned timestamps in the wrong order on opencl:gpu: the end tag's command_end could be earlier than the completion of work submitted before it, so E2End <= EndTagEnd failed and the e2e tests were masked with UNSUPPORTED: opencl && gpu.

Why

OpenCL devices don't advertise ext_oneapi_queue_profiling_tag (the adapter hard-codes UR_DEVICE_INFO_TIMESTAMP_RECORDING_SUPPORT_EXP to false), so the tag fell back to ext_oneapi_submit_barrier() and read its profiling info straight off the barrier event.

The NEO driver timestamps clEnqueueBarrierWithWaitList / clEnqueueMarkerWithWaitList when the command enters the pipeline, not when the preceding work completes. So the barrier's CL_PROFILING_COMMAND_END can be earlier than the end of a kernel enqueued before it.

I confirmed this with a small pure-OpenCL reproducer on Intel Iris Xe (NEO 26.05.037020): any synchronization-only tag (barrier/marker, empty or explicit wait list) fails 100% of the time, while any real device command (kernel or buffer fill) gives correct timestamps - including a fill into a
dedicated buffer, which is what this PR does.

Changes

• unified-runtime/.../opencl/event.cpp: implement urEnqueueTimestampRecordingExpusingclEnqueueFillBufferon a small internal buffer, whose timestamps do reflect completion of prior work. It needs command profiling, so if the queue isn't profiling-enabled we returnUR_RESULT_ERROR_UNSUPPORTED_FEATURE`.

• unified-runtime/.../opencl/context.hpp: lazily-created, thread-safe 4-byte buffer per context, released with the context. It's never read - only the fill command's timestamps are used.

• sycl/.../scheduler/commands.cpp (CGType::ProfilingTag): issue the recording with call_nocheck and fall back to a barrier on UR_RESULT_ERROR_UNSUPPORTED_FEATURE. Also addresses the existing TODO here.

• sycl/.../experimental/profiling_tag.hpp: when the device lacks the aspect but the queue has profiling enabled, submit a profiling-tag command group (reusing the scheduler's in-order/out-of-order marker+barrier handling) instead of a bare barrier.

The device aspect stays false for OpenCL: the emulation needs queue profiling, but the aspect promises the tag works without it. Enabling the aspect (e.g. via an internal profiling queue) is a possible follow-up.

Level Zero / CUDA / HIP are unaffected - they advertise the aspect and already implement the recording, so they never take the fallback branch. The scheduler change only adds the fallback branch and turns a throwing call into a checked one; the success path is unchanged.

Testing

• Unit tests (sycl/unittests/Extensions/ProfilingTag.cpp): split the old fallback test into two - native recording used on a profiling queue without the aspect, and the barrier fallback when the backend reports the recording unsupported.

• E2E: dropped UNSUPPORTED: opencl && gpu from ProfilingTag/in_order_profiling_queue.cpp and ProfilingTag profiling_queue.cpp.

• The reproducer's dedicated-buffer fill (matching this implementation) passes 200/200 iterations on Intel Iris Xe, vs. the old barrier fallback failing 200/200.

The NEO timestamping behavior is arguably a driver bug worth reporting separately; this is a runtime workaround that doesn't touch the public API or other backends.

P.S. I may have gone a little overboard with the code comments. If anyone else feels the same way, I will clean them up.