[rocprofv3] MultiKernelDispatch ATT support (#774)

* Initial consecutive kernel WIP

* Updated logic after discussion, create context only when needed, change set of captured ids to dispatch_id_t type

* Updated to fix concurrency issues and revert kernel_iterations

* Add captured id in first lock capture

* Updated code to use wlock, added comments, removed some unecessary atomic

* Cleaned up, need to add test

* Add test to check that generated stats csv file is not empty

* Updated test to check if vector-ops kernels are being used

* Fix phase bug

* Updated for comments

* Flattened ATT logic a bit

* Fix incorrect if-statement

* Fix merge conflict

projects/rocprofiler-sdk/source/bin/rocprofv3.py

@@ -794,6 +794,13 @@ For attachment profiling of running processes:
         type=str,
     )
 
+    att_options.add_argument(
+        "--att-consecutive-kernels",
+        help="Consecutive kernels to profile with ATT. Default 0",
+        default=None,
+        type=str,
+    )
+
     att_options.add_argument(
         "--att-buffer-size",
         help="Thread trace buffer size. Default 256MB",
@@ -1627,6 +1634,12 @@ def run(app_args, args, **kwargs):
                 int_auto(args.att_simd_select),
                 overwrite=True,
             )
+        if args.att_consecutive_kernels:
+            update_env(
+                "ROCPROF_ATT_CONSECUTIVE_KERNELS",
+                int_auto(args.att_consecutive_kernels),
+                overwrite=True,
+            )
         if args.att_serialize_all:
             update_env(
                 "ROCPROF_ATT_PARAM_SERIALIZE_ALL",