Gbaraldi/threadtrace2 (#724)

* Added first ATT API * Finalizing thread trace API * Fixing more rebase conflicts * Added codeobj disassembly sample * Fixing merge issues with rebase [2] * Adding ATT packets * Implemented thread trace intercept * Moved codeobj parser to same repo as rocprofiler * Moved thread trace to new API * Fixing merge conflicts * Fixing more merge conflicts * Adding thread trace packet reuse * Merged aql_profile_v2 headers * Linked ATT sample to aqlprofile * Updated decoder to include non-loaded codeobjs * Implemented ISA decoder into ATT sample * Added marker_id to vaddr * Updating aql_profile_v2 API to memcpy * Updating thread trace API to include 64bit markers. Using the result of ISA matching. * Added instruction type and cycles summary * Updated sample with selection of kernel by kernel_object * Added option to copy from memory kernels * Moved tool_data in thread_trace to dynamic alloc * Restoring hsa.cpp * Fixed ATT sample crash. General improvements. * Moved codeobj library to outside src/ * Updated license header * Moved codeobj_capture to camelcase * Solving some more merge conflicts * Update samples/advanced_thread_trace/CMakeLists.txt Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> * Update samples/advanced_thread_trace/CMakeLists.txt Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> * Update samples/code_object_isa_decode/CMakeLists.txt Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> * Update source/lib/rocprofiler-sdk/thread_trace/CMakeLists.txt * Removing unused parameter check * Adding const to isEmpty * Removing unused warning * Adding libdw-dev to requirements * Running clang-format * Commenting out new aql calls * Clang format * Unused variable fix * Adding codeobj-decoder coverage * Commenting out threadtrace * Update samples/CMakeLists.txt Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> * P * WOverloaded * Addressing clang-tidy * Virtual destructor on ttracer class * Corr id * Fixing code source format * Update CMakeLists.txt * Build fixes * Update source/lib/rocprofiler-sdk-codeobj/code_object_track.cpp Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> * Fix shadowing * Update CMakeLists.txt * Update samples/CMakeLists.txt Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Ammar ELWazir <ammar.elwazir@amd.com> Co-authored-by: Ammar ELWazir <aelwazir@amd.com> Co-authored-by: Benjamin Welton <bewelton@amd.com> [ROCm/rocprofiler-sdk commit: 69b8a43dc6]
2024-04-08 16:43:02 -03:00
@@ -218,7 +218,7 @@ counter_callback_info::setup_profile_config(const hsa::AgentCache&           age
        }
    }

-    profile->pkt_generator = std::make_unique<rocprofiler::aql::AQLPacketConstruct>(
+    profile->pkt_generator = std::make_unique<rocprofiler::aql::CounterPacketConstruct>(
        agent,
        std::vector<counters::Metric>{profile->reqired_hw_counters.begin(),
                                      profile->reqired_hw_counters.end()});
@@ -288,7 +288,7 @@ queue_cb(const context::context*                                         ctx,
    // Packet generated when no instrumentation is performed. May contain serialization
    // packets/barrier packets (and can be empty).
    auto no_instrumentation = [&]() {
-        auto ret_pkt = std::make_unique<rocprofiler::hsa::AQLPacket>(nullptr);
+        auto ret_pkt = std::make_unique<rocprofiler::hsa::CounterAQLPacket>(nullptr);
        // If we have a counter collection context but it is not enabled, we still might need
        // to add barrier packets to transition from serialized -> unserialized execution. This
        // transition is coordinated by the serializer.
@@ -59,7 +59,7 @@ struct profile_config
    std::vector<counters::EvaluateAST> asts{};
    rocprofiler_profile_config_id_t    id{.handle = 0};
    // Packet generator to create AQL packets for insertion
-    std::unique_ptr<rocprofiler::aql::AQLPacketConstruct> pkt_generator{nullptr};
+    std::unique_ptr<rocprofiler::aql::CounterPacketConstruct> pkt_generator{nullptr};
    // A packet cache of AQL packets. This allows reuse of AQL packets (preventing costly
    // allocation of new packets/destruction).
    rocprofiler::common::Synchronized<std::vector<std::unique_ptr<rocprofiler::hsa::AQLPacket>>>
@@ -61,8 +61,8 @@ getBlockDimensions(std::string_view agent, const Metric& metric)
    {
        if(maybe_agent.name() == agent)
        {
-            aql::AQLPacketConstruct pkt_gen(maybe_agent, {metric});
-            const auto&             events = pkt_gen.get_counter_events(metric);
+            aql::CounterPacketConstruct pkt_gen(maybe_agent, {metric});
+            const auto&                 events = pkt_gen.get_counter_events(metric);

            for(const auto& event : events)
            {
@@ -450,16 +450,16 @@ EvaluateAST::read_special_counters(
 }

 std::unordered_map<uint64_t, std::vector<rocprofiler_record_counter_t>>
-EvaluateAST::read_pkt(const aql::AQLPacketConstruct* pkt_gen, hsa::AQLPacket& pkt)
+EvaluateAST::read_pkt(const aql::CounterPacketConstruct* pkt_gen, hsa::AQLPacket& pkt)
 {
    struct it_data
    {
        std::unordered_map<uint64_t, std::vector<rocprofiler_record_counter_t>>* data;
-        const aql::AQLPacketConstruct*                                           pkt_gen;
+        const aql::CounterPacketConstruct*                                       pkt_gen;
    };

    std::unordered_map<uint64_t, std::vector<rocprofiler_record_counter_t>> ret;
-    if(pkt.empty) return ret;
+    if(pkt.isEmpty()) return ret;
    it_data aql_data{.data = &ret, .pkt_gen = pkt_gen};
    ;
    hsa_status_t status = hsa_ven_amd_aqlprofile_iterate_data(
@@ -136,8 +136,8 @@ public:
     *
     */
    static std::unordered_map<uint64_t, std::vector<rocprofiler_record_counter_t>> read_pkt(
-        const aql::AQLPacketConstruct* pkt_gen,
-        hsa::AQLPacket&                pkt);
+        const aql::CounterPacketConstruct* pkt_gen,
+        hsa::AQLPacket&                    pkt);

    /**
     * @brief Insert special counter values, such as constants of the agent (i.e. max waves)
@@ -251,8 +251,8 @@ TEST(dimension, block_dim_test)
            }
            else
            {
-                aql::AQLPacketConstruct pkt_gen(agent, {metric});
-                const auto&             events = pkt_gen.get_counter_events(metric);
+                aql::CounterPacketConstruct pkt_gen(agent, {metric});
+                const auto&                 events = pkt_gen.get_counter_events(metric);
                for(const auto& event : events)
                {
                    std::map<int, uint64_t> dims;