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>
2024-04-08 16:43:02 -03:00
Commit 69b8a43dc6
@@ -21,14 +21,22 @@
 // THE SOFTWARE.

 #include "lib/rocprofiler-sdk/hsa/aql_packet.hpp"
-
 #include <cstdlib>
+#include <iostream>
+#include <string>
+
+#define CHECK_HSA(fn, message)                                                                     \
+    if((fn) != HSA_STATUS_SUCCESS)                                                                 \
+    {                                                                                              \
+        std::cerr << __FILE__ << ':' << __LINE__ << ' ' << message;                                \
+        exit(1);                                                                                   \
+    }

 namespace rocprofiler
 {
 namespace hsa
 {
-AQLPacket::~AQLPacket()
+CounterAQLPacket::~CounterAQLPacket()
 {
    if(!profile.command_buffer.ptr)
    {
@@ -36,7 +44,7 @@ AQLPacket::~AQLPacket()
    }
    else if(!command_buf_mallocd)
    {
-        free_func(profile.command_buffer.ptr);
+        CHECK_HSA(free_func(profile.command_buffer.ptr), "freeing memory");
    }
    else
    {
@@ -49,12 +57,61 @@ AQLPacket::~AQLPacket()
    }
    else if(!output_buffer_malloced)
    {
-        free_func(profile.output_buffer.ptr);
+        CHECK_HSA(free_func(profile.output_buffer.ptr), "freeing memory");
    }
    else
    {
        ::free(profile.output_buffer.ptr);
    }
 }
+
+TraceAQLPacket::~TraceAQLPacket() = default;
+/*
+TraceAQLPacket::~TraceAQLPacket()
+{
+    aqlprofile_att_delete_packets(this->handle);
+}
+*/
+
+hsa_status_t
+TraceAQLPacket::Alloc(void** ptr, size_t size, aqlprofile_buffer_desc_flags_t flags, void* data)
+{
+    if(!data) return HSA_STATUS_ERROR;
+    if(!reinterpret_cast<TraceAQLPacket*>(data)->tracepool) return HSA_STATUS_ERROR;
+
+    auto& pool = *reinterpret_cast<TraceAQLPacket*>(data)->tracepool;
+
+    if(!pool.allocate_fn || !pool.free_fn || !pool.allow_access_fn) return HSA_STATUS_ERROR;
+
+    if(flags.host_access)
+    {
+        hsa_status_t status = pool.allocate_fn(pool.cpu_pool_, size, 0, ptr);
+        if(!flags.device_access || status != HSA_STATUS_SUCCESS) return status;
+        return pool.allow_access_fn(1, &pool.gpu_agent, nullptr, *ptr);
+    }
+    return pool.allocate_fn(pool.gpu_pool_, size, 0, ptr);
+}
+
+void
+TraceAQLPacket::Free(void* ptr, void* data)
+{
+    auto* pool = reinterpret_cast<TraceAQLPacket*>(data)->tracepool.get();
+    if(!pool || !pool->free_fn) return;
+
+    pool->free_fn(ptr);
+}
+
+hsa_status_t
+TraceAQLPacket::Copy(void* dst, const void* src, size_t size, void* data)
+{
+    auto* pool = reinterpret_cast<TraceAQLPacket*>(data)->tracepool.get();
+    if(!pool || !pool->api_copy_fn) return HSA_STATUS_ERROR;
+
+    return pool->api_copy_fn(dst, src, size);
+}
+
+TraceAQLPacket::TraceAQLPacket(std::shared_ptr<TraceMemoryPool>& _tracepool)
+: tracepool(_tracepool){};
+
 }  // namespace hsa
 }  // namespace rocprofiler