AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Gbaraldi/threadtrace2 (#724)

Browse Source 
* 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>
This commit is contained in:
Giovanni Lenzi Baraldi
2024-04-08 16:43:02 -03:00
committed by GitHub
parent d2bad14bf6
commit 69b8a43dc6
48 changed files with 4649 additions and 109 deletions
Download Patch File Download Diff File Expand all files Collapse all files
source/lib/rocprofiler-sdk/aql/tests/aql_test.cpp
+26 -23
View File
@@ -122,7 +122,7 @@ TEST(aql_profile, construct_packets)
LOG(WARNING) << fmt::format("Found Agent: {}", agent.get_hsa_agent().handle);
auto metrics = rocprofiler::findDeviceMetrics(agent, {"SQ_WAVES"});
ASSERT_EQ(metrics.size(), 1);
AQLPacketConstruct(agent, metrics);
CounterPacketConstruct(agent, metrics);
}
hsa_shut_down();
}
@@ -142,7 +142,7 @@ TEST(aql_profile, too_many_counters)
{
try
{
AQLPacketConstruct(agent, metrics);
CounterPacketConstruct(agent, metrics);
} catch(const std::exception& e)
{
EXPECT_NE(e.what(), nullptr) << e.what();
@@ -163,9 +163,9 @@ TEST(aql_profile, packet_generation_single)
ASSERT_GT(agents.size(), 0);
for(const auto& [_, agent] : agents)
{
auto metrics = rocprofiler::findDeviceMetrics(agent, {"SQ_WAVES"});
AQLPacketConstruct pkt(agent, metrics);
auto test_pkt = pkt.construct_packet(rocprofiler::get_ext_table());
auto metrics = rocprofiler::findDeviceMetrics(agent, {"SQ_WAVES"});
CounterPacketConstruct pkt(agent, metrics);
auto test_pkt = pkt.construct_packet(rocprofiler::get_ext_table());
EXPECT_TRUE(test_pkt);
}
@@ -183,14 +183,30 @@ TEST(aql_profile, packet_generation_multi)
{
auto metrics =
rocprofiler::findDeviceMetrics(agent, {"SQ_WAVES", "TA_FLAT_READ_WAVEFRONTS"});
AQLPacketConstruct pkt(agent, metrics);
auto test_pkt = pkt.construct_packet(rocprofiler::get_ext_table());
CounterPacketConstruct pkt(agent, metrics);
auto test_pkt = pkt.construct_packet(rocprofiler::get_ext_table());
EXPECT_TRUE(test_pkt);
}
hsa_shut_down();
}
class TestAqlPacket : public rocprofiler::hsa::CounterAQLPacket
{
public:
TestAqlPacket(bool mallocd)
: rocprofiler::hsa::CounterAQLPacket([](void* x) -> hsa_status_t {
::free(x);
return HSA_STATUS_SUCCESS;
})
{
this->profile.output_buffer.ptr = malloc(sizeof(double));
this->profile.command_buffer.ptr = malloc(sizeof(double));
this->command_buf_mallocd = mallocd;
this->output_buffer_malloced = mallocd;
}
};
TEST(aql_profile, test_aql_packet)
{
auto check_null = [](auto& val) {
@@ -201,25 +217,12 @@ TEST(aql_profile, test_aql_packet)
val.completion_signal.handle == null_val.completion_signal.handle;
};
rocprofiler::hsa::AQLPacket test_pkt([](void* x) -> hsa_status_t {
::free(x);
return HSA_STATUS_SUCCESS;
});
TestAqlPacket test_pkt(true);
EXPECT_TRUE(check_null(test_pkt.start)) << "Start packet not null";
EXPECT_TRUE(check_null(test_pkt.stop)) << "Stop packet not null";
EXPECT_TRUE(check_null(test_pkt.read)) << "Read packet not null";
// If this leaks, then AQLPacket is not freeing data correctly.
test_pkt.profile.output_buffer.ptr = malloc(sizeof(double));
test_pkt.profile.command_buffer.ptr = malloc(sizeof(double));
test_pkt.command_buf_mallocd = true;
test_pkt.output_buffer_malloced = true;
// test custom destructor as well
rocprofiler::hsa::AQLPacket test_pkt2([](void* x) -> hsa_status_t {
::free(x);
return HSA_STATUS_SUCCESS;
});
test_pkt2.profile.output_buffer.ptr = malloc(sizeof(double));
test_pkt2.profile.command_buffer.ptr = malloc(sizeof(double));
// Why is this valid?
TestAqlPacket test_pkt2(false);
}