Shared Library Constructor (rocprofv3 deadlock fix) (#599)

* Moved tests/apps to tests/bin

* Renamed cmake project in tests/bin

* Update samples

- Use ROCPROFILER_DEFAULT_FAIL_REGEX
- tweaks to stdout messages

* Update tests

- Use ROCPROFILER_DEFAULT_FAIL_REGEX

* Add tests/lib

- libraries with HIP code

* Update PTL submodule

- remove atexit delete of thread_id_map

* Update cmake/rocprofiler_options.cmake

- Set ROCPROFILER_DEFAULT_FAIL_REGEX

* Update common lib: env + logging

- improved customization of logging settings
- default to disabling logging to files
- install failure handler for rocprofv3
- set_env support in environment.*

* Add lib/rocprofiler-sdk/shared_library.cpp

- shared library constructor

* Update lib/rocprofiler-sdk-tool/tool.cpp

- destructor thread safety
- convert callback_name_info and buffered_name_info to pointers
- install failure handler for logging

* Add tests/bin/hip-in-libraries

- hip-in-libraries is an exe which uses two shared libraries where each shared library contains HIP kernels
  - used for testing deadlocking within __hipRegisterFatBinary

* Update bin/rocprofv3

- reorganized the env variables
- use exec to launch command
- set ROCPROFILER_LIBRARY_CTOR=1

* Add tests/rocprofv3/tracing-hip-in-libraries

- uses hip-in-libraries exe for exe which uses shared libraries to launch HIP kernels

* Update bin/rocprofv3

- fix counter collection (no exec)

* Update lib/rocprofiler-sdk-tool/tool.cpp

- replace "Kernel-Name" with "Kernel_Name"

* Update lib/rocprofiler-sdk/registration.cpp

Use RTLD_LOCAL instead of RTLD_GLOBAL for env libraries

* Update tests/rocprofv3

- replace "Kernel-Name" with "Kernel_Name"

* Update tests

- vector-ops (bin) stream syncs + runs with 4 queues per device
- improve counter-collection/input1 validation
- rocprofv3/tracing-hip-in-libraries does not do sys-trace
- improved validation script for tracing-hip-in-libraries
- updated dispatch_callback in json-tool.cpp following reworking of prototypes for counter collection

* Update samples/counter_collection

- updated dispatch_callback(s) and record_callback(s) following reworking of prototypes

* Update bin/rocprofv3

- reorganized help menu
- added options for sub-HSA tables
- added --hip-runtime-trace
- changed --hip-trace to include --hip-compiler-trace

* Update lib/rocprofiler-sdk-tool

- improved kernel filtering
- removed arch_vgpr, accum_vgpr, sgpr code (in rocprofiler-sdk)
- fixed issue with counter-collection w/o tracing
- added support for fine grained HSA API tracing
- removed directly linking to HSA-runtime

* Update lib/rocprofiler-sdk/agent.cpp

- rocp_agents != hsa_agents is non-fatal when ROCPROFILER_BUILD_CI=OFF (CMake option)

* GPR (vector and scalar) info in kernel symbol data

- rocprofiler_callback_tracing_code_object_kernel_symbol_register_data_t contains general purpose register info

* Header include order fix

- Include repo headers first
- Third party library headers next
- standard library headers last

* Update dispatch profiling public API

- introduce rocprofiler_profile_counting_dispatch_data_t
- change signature of rocprofiler_profile_counting_dispatch_callback_t and rocprofiler_profile_counting_record_callback_t
- provide rocprofiler_user_data_t pointer in dispatch callback
- provide rocprofiler_user_data_t value (from dispatch cb) in record callback

* Update tests/bin/CMakeLists.txt

- fix add_subdirectory(hip-in-libraries) order

* Update VERSION

- bump to 0.2.0 in prep for AFAR

[ROCm/rocprofiler-sdk commit: 7b6d3c70bd]

projects/rocprofiler-sdk/source/include/rocprofiler-sdk/callback_tracing.h

@@ -30,6 +30,8 @@
 
 #include <hsa/hsa_ven_amd_loader.h>
 
+#include <stdint.h>
+
 ROCPROFILER_EXTERN_C_INIT
 
 /**
@@ -141,9 +143,14 @@ typedef struct
     uint32_t kernarg_segment_alignment;  ///< Alignment (in bytes) of the buffer used to pass
                                          ///< arguments to the kernel
     uint32_t group_segment_size;    ///< Size of static group segment memory required by the kernel
-                                    ///< (per work-group), in bytes
+                                    ///< (per work-group), in bytes. AKA: LDS size
     uint32_t private_segment_size;  ///< Size of static private, spill, and arg segment memory
-                                    ///< required by this kernel (per work-item), in bytes.
+                                    ///< required by this kernel (per work-item), in bytes. AKA:
+                                    ///< scratch size
+    uint32_t sgpr_count;            ///< Scalar general purpose register count
+    uint32_t arch_vgpr_count;       ///< Architecture vector general purpose register count
+    uint32_t accum_vgpr_count;      ///< Accum vector general purpose register count
+
 } rocprofiler_callback_tracing_code_object_kernel_symbol_register_data_t;
 
 /**

projects/rocprofiler-sdk/source/include/rocprofiler-sdk/dispatch_profile.h

@@ -37,6 +37,23 @@ ROCPROFILER_EXTERN_C_INIT
  * @{
  */
 
+/**
+ * @brief Kernel dispatch data for profile counting callbacks
+ *
+ */
+typedef struct rocprofiler_profile_counting_dispatch_data_t
+{
+    uint64_t                     size;            ///< Size of this struct
+    rocprofiler_kernel_id_t      kernel_id;       ///< Kernel identifier
+    rocprofiler_agent_id_t       agent_id;        ///< Agent ID where kernel is launched
+    rocprofiler_queue_id_t       queue_id;        ///< Queue ID where kernel packet is enqueued
+    rocprofiler_correlation_id_t correlation_id;  ///< Correlation ID for this dispatch
+    uint32_t                     private_segment_size;  /// runtime private memory segment size
+    uint32_t                     group_segment_size;    /// runtime group memory segment size
+    rocprofiler_dim3_t           workgroup_size;        /// runtime workgroup size (grid * threads)
+    rocprofiler_dim3_t           grid_size;             /// runtime grid size
+} rocprofiler_profile_counting_dispatch_data_t;
+
 /**
  * @brief Kernel Dispatch Callback. This is a callback that is invoked before the kernel
  *        is enqueued into the HSA queue. What counters to collect for a kernel are set
@@ -44,22 +61,35 @@ ROCPROFILER_EXTERN_C_INIT
  *        will be collected and emplaced in the buffer with @ref rocprofiler_buffer_id_t used when
  *        setting up this callback.
  *
- * @param [in] queue_id        Queue the kernel dispatch packet is being enqueued onto
- * @param [in] agent           Agent of this queue
- * @param [in] correlation_id  Correlation ID for this dispatch
- * @param [in] dispatch_packet Kernel dispatch packet about to be enqueued into HSA
- * @param [in] kernel_id Kernel identifier
+ * @param [in] dispatch_data      @see ::rocprofiler_profile_counting_dispatch_data_t
+ * @param [out] config            Profile config detailing the counters to collect for this kernel
+ * @param [out] user_data         User data unique to this dispatch. Returned in record callback
  * @param [in] callback_data_args Callback supplied via buffered_dispatch_profile_counting_service
- * @param [out] config         Profile config detailing the counters to collect for this kernel
  */
 typedef void (*rocprofiler_profile_counting_dispatch_callback_t)(
-    rocprofiler_queue_id_t              queue_id,
-    const rocprofiler_agent_t*          agent,
-    rocprofiler_correlation_id_t        correlation_id,
-    const hsa_kernel_dispatch_packet_t* dispatch_packet,
-    uint64_t                            kernel_id,
-    void*                               callback_data_args,
-    rocprofiler_profile_config_id_t*    config);
+    rocprofiler_profile_counting_dispatch_data_t dispatch_data,
+    rocprofiler_profile_config_id_t*             config,
+    rocprofiler_user_data_t*                     user_data,
+    void*                                        callback_data_args);
+
+/**
+ * @brief Counting record callback. This is a callback is invoked when the kernel
+ *        execution is complete and contains the counter profile data requested in
+ *        @ref rocprofiler_profile_counting_dispatch_callback_t. Only used with
+ *        @ref rocprofiler_configure_callback_dispatch_profile_counting_service.
+ *
+ * @param [in] dispatch_data      @see ::rocprofiler_profile_counting_dispatch_data_t
+ * @param [in] record_data        Counter record data.
+ * @param [in] record_count       Number of counter records.
+ * @param [in] user_data          User data instance from dispatch callback
+ * @param [in] callback_data_args Callback supplied via buffered_dispatch_profile_counting_service
+ */
+typedef void (*rocprofiler_profile_counting_record_callback_t)(
+    rocprofiler_profile_counting_dispatch_data_t dispatch_data,
+    rocprofiler_record_counter_t*                record_data,
+    size_t                                       record_count,
+    rocprofiler_user_data_t                      user_data,
+    void*                                        callback_data_args);
 
 /**
  * @brief Configure buffered dispatch profile Counting Service.
@@ -95,29 +125,6 @@ rocprofiler_configure_buffered_dispatch_profile_counting_service(
     rocprofiler_profile_counting_dispatch_callback_t callback,
     void*                                            callback_data_args);
 
-/**
- * @brief Counting record callback. This is a callback is invoked when the kernel
- *        execution is complete and contains the counter profile data requested in
- *        @ref rocprofiler_profile_counting_dispatch_callback_t. Only used with
- *        @ref rocprofiler_configure_callback_dispatch_profile_counting_service.
- *
- * @param [in] queue_id           Queue the kernel dispatch packet is being enqueued onto
- * @param [in] agent              Agent of this queue
- * @param [in] correlation_id     Correlation ID for this dispatch
- * @param [in] kernel_id          Kernel identifier
- * @param [in] callback_data_args Callback supplied via buffered_dispatch_profile_counting_service
- * @param [in] record_count       Number of counter records.
- * @param [in] record_data        Counter record data.
- */
-typedef void (*rocprofiler_profile_counting_record_callback_t)(
-    rocprofiler_queue_id_t        queue_id,
-    rocprofiler_agent_id_t        agent,
-    rocprofiler_correlation_id_t  correlation_id,
-    uint64_t                      kernel_id,
-    void*                         callback_data_args,
-    size_t                        record_count,
-    rocprofiler_record_counter_t* record_data);
-
 /**
  * @brief Configure buffered dispatch profile Counting Service.
  *        Collects the counters in dispatch packets and calls a callback

projects/rocprofiler-sdk/source/include/rocprofiler-sdk/fwd.h

@@ -261,26 +261,16 @@ typedef enum
     ROCPROFILER_TABLE_LAST           = ROCPROFILER_MARKER_NAME_TABLE,
 } rocprofiler_intercept_table_t;
 
-/**
- * @brief Enumeration for specifying the data type contained within the union.
- */
-typedef enum
-{
-    ROCPROFILER_UNION_TYPE_NONE = 0,  ///< No union type
-    ROCPROFILER_UNION_TYPE_STRING,    ///< String Type set
-    ROCPROFILER_UNION_TYPE_INT,       ///< Integer Type Set
-    ROCPROFILER_UNION_TYPE_LAST,
-} rocprofiler_union_type_t;
-
 /**
  * @brief Enumeration for specifying the counter info struct version you want.
  */
 typedef enum
 {
     ROCPROFILER_COUNTER_INFO_VERSION_NONE,
-    ROCPROFILER_COUNTER_INFO_VERSION_0,  ///< @see rocprofiler_counter_info_v0_t
+    ROCPROFILER_COUNTER_INFO_VERSION_0,  ///< @see ::rocprofiler_counter_info_v0_t
     ROCPROFILER_COUNTER_INFO_VERSION_LAST,
 } rocprofiler_counter_info_version_id_t;
+
 //--------------------------------------------------------------------------------------//
 //
 //                                      ALIASES