SWDEV-492623: Hip Host Function to Device Symbols Mapping (#18)
* Adding changes to register and read symbols from the hip fat binary * adding json output for host_functions * added error handling * adding json tool support * Adding tests * formatting changes * Adding documentation * refactoring as per amd-staging * Adding intializers and changing macros * Fix page-migration background thread on fork (#31) * Fix page-migration background thread on fork After falling off main in the forked child, all the children try to join on on the parent's monitoring thread. This results in a deadlock. Parent is waiting for the child to exit, but the child is trying to join the parent's thread which is signaled from the parent's static destructors. Even with just one parent and child, due to copy-on-write semantics, a child signalling the background thread to join will still block (thread's updated state is not visible in the child). This fix creates background treads on fork per-child with a pthread_atfork handler, ensuring that each child has its own monitoring thread. * Formatting fixes * Detach page-migration background thread and update test timeout * Attach files with ctest * Update corr-id assert * Tweak on-fork, simplify background thread * Revert thread detach * Adding --collection-period feature in rocprofv3 to match v1/v2 parity (#9) * Adding Trace Period feature to rocprofv3 * Adding feature documentation * Update source/bin/rocprofv3.py Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> * Fixing format * Moving to Collection Period and changing the input params * Format Fixes * Fixing rebasing issues * Removing atomic include from the tool * Adding more options for units, optimizing the code * Fixing rocprofv3.py * Fixing time conv & adding time controlled app * Fixing format * Changing to shared memory testing methodology * use of shmem use * Fix include headers for transpose-time-controlled.cpp * Format upload-image-to-github.py * Removing shmem and using only env var to dump timestamps from the tool * Tool Fixes + Test Config * Adding Tests * Fixing Review comments * Update trace period implementation * Update trace period tests * check between start and stop timestamps * Merge Fix * Update validate.py * Improve safety of rocprofiler_stop_context after finalization * Pass context id to collection_period_cntrl by value * Adding 20 us error margin * Ensure log level for collection-period test is not more than warning --------- Co-authored-by: Ammar ELWazir <aelwazir@amd.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com> * Update lib/rocprofiler-sdk/code_object/hip/code_object.* - move error code check macros to implementation - fix macros which check error code - use constexpr values instead of #define * Update lib/rocprofiler-sdk/code_object/hip/code_object.* - debugging for error that cannot be locally reproduced * Update lib/rocprofiler-sdk/code_object/hip/code_object.* - improve error handling and logging * Update lib/rocprofiler-sdk/code_object/hip/code_object.* - tweak to non-fatal logging messages * Update lib/rocprofiler-sdk/code_object/hip/code_object.* - cleanup of logging messages * Update host kernel symbol register data fields * Update source/lib/rocprofiler-sdk/code_object/hip/code_object.hpp --------- Co-authored-by: Madsen, Jonathan <Jonathan.Madsen@amd.com> Co-authored-by: Kuricheti, Mythreya <Mythreya.Kuricheti@amd.com> Co-authored-by: Elwazir, Ammar <Ammar.Elwazir@amd.com> Co-authored-by: Ammar ELWazir <aelwazir@amd.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Bu işleme şunda yer alıyor:
Jakaraddi, Manjunath
işlemeyi yapan:
GitHub
GitHub
ebeveyn
61ce79c84d
işleme
78d8f4b8ea
@@ -181,6 +181,27 @@ typedef struct
|
||||
uint32_t accum_vgpr_count; ///< Accum vector general purpose register count
|
||||
|
||||
} rocprofiler_callback_tracing_code_object_kernel_symbol_register_data_t;
|
||||
// rename struct
|
||||
|
||||
typedef struct
|
||||
{
|
||||
uint64_t size; ///< size of this struct
|
||||
uint64_t host_function_id; ///< unique host function identifier value
|
||||
uint64_t kernel_id; ///< unique symbol identifier value
|
||||
uint64_t code_object_id; ///< parent unique code object identifier
|
||||
rocprofiler_address_t host_function; ///< kernel host function pointer
|
||||
rocprofiler_address_t modules; ///< reference address where modules will be loaded
|
||||
const char* device_function;
|
||||
uint32_t thread_limit; ///< thread limit
|
||||
rocprofiler_dim3_t thread_ids; ///< thread ids address
|
||||
rocprofiler_dim3_t block_ids; ///< block ids address
|
||||
rocprofiler_dim3_t block_dims; ///< block dimensions address
|
||||
rocprofiler_dim3_t grid_dims; ///< grid dimensions address
|
||||
uint64_t workgroup_size; ///< workgroup size address
|
||||
|
||||
/// @var device_function
|
||||
/// @brief device function name used to map the metadata during kernel launch
|
||||
} rocprofiler_callback_tracing_code_object_host_kernel_symbol_register_data_t;
|
||||
|
||||
/**
|
||||
* @brief ROCProfiler Kernel Dispatch Callback Tracer Record.
|
||||
|
||||
@@ -139,6 +139,13 @@ save(ArchiveT& ar, rocprofiler_dim3_t data)
|
||||
ROCP_SDK_SAVE_DATA_FIELD(z);
|
||||
}
|
||||
|
||||
template <typename ArchiveT>
|
||||
void
|
||||
save(ArchiveT& ar, rocprofiler_address_t data)
|
||||
{
|
||||
ROCP_SDK_SAVE_DATA_FIELD(value);
|
||||
}
|
||||
|
||||
template <typename ArchiveT>
|
||||
void
|
||||
save(ArchiveT& ar, rocprofiler_callback_tracing_code_object_load_data_t data)
|
||||
@@ -181,6 +188,25 @@ save(ArchiveT& ar, rocprofiler_callback_tracing_code_object_kernel_symbol_regist
|
||||
ROCP_SDK_SAVE_DATA_FIELD(accum_vgpr_count);
|
||||
}
|
||||
|
||||
template <typename ArchiveT>
|
||||
void
|
||||
save(ArchiveT& ar, rocprofiler_callback_tracing_code_object_host_kernel_symbol_register_data_t data)
|
||||
{
|
||||
ROCP_SDK_SAVE_DATA_FIELD(size);
|
||||
ROCP_SDK_SAVE_DATA_FIELD(host_function_id);
|
||||
ROCP_SDK_SAVE_DATA_FIELD(kernel_id);
|
||||
ROCP_SDK_SAVE_DATA_FIELD(code_object_id);
|
||||
ROCP_SDK_SAVE_DATA_FIELD(host_function);
|
||||
ROCP_SDK_SAVE_DATA_FIELD(modules);
|
||||
ROCP_SDK_SAVE_DATA_CSTR(device_function);
|
||||
ROCP_SDK_SAVE_DATA_FIELD(thread_limit);
|
||||
ROCP_SDK_SAVE_DATA_FIELD(thread_ids);
|
||||
ROCP_SDK_SAVE_DATA_FIELD(block_ids);
|
||||
ROCP_SDK_SAVE_DATA_FIELD(block_dims);
|
||||
ROCP_SDK_SAVE_DATA_FIELD(grid_dims);
|
||||
ROCP_SDK_SAVE_DATA_FIELD(workgroup_size);
|
||||
}
|
||||
|
||||
template <typename ArchiveT>
|
||||
void
|
||||
save(ArchiveT& ar, rocprofiler_hsa_api_retval_t data)
|
||||
|
||||
@@ -34,21 +34,12 @@ namespace utility
|
||||
{
|
||||
template <typename Tp>
|
||||
auto
|
||||
_as_hex(Tp val, size_t width = 0)
|
||||
as_hex(Tp val, size_t width = 0)
|
||||
{
|
||||
auto ss = std::stringstream{};
|
||||
ss << "0x" << std::hex << std::setw(width) << std::setfill('0') << val;
|
||||
ss << "0x" << std::hex << std::setfill('0') << std::setw(width) << val;
|
||||
return ss.str();
|
||||
}
|
||||
|
||||
#define ROCPROFILER_CXX_DEFINE_AS_HEX(TYPE) \
|
||||
inline auto as_hex(TYPE val, size_t width = 0) \
|
||||
{ \
|
||||
return ::rocprofiler::sdk::utility::_as_hex(val, width); \
|
||||
}
|
||||
|
||||
ROCPROFILER_CXX_DEFINE_AS_HEX(uint64_t)
|
||||
#undef ROCPROFILER_CXX_DEFINE_AS_HEX
|
||||
} // namespace utility
|
||||
} // namespace sdk
|
||||
} // namespace rocprofiler
|
||||
|
||||
@@ -216,7 +216,8 @@ typedef enum // NOLINT(performance-enum-size)
|
||||
{
|
||||
ROCPROFILER_CODE_OBJECT_NONE = 0, ///< Unknown code object operation
|
||||
ROCPROFILER_CODE_OBJECT_LOAD, ///< Code object containing kernel symbols
|
||||
ROCPROFILER_CODE_OBJECT_DEVICE_KERNEL_SYMBOL_REGISTER, ///< Kernel symbols
|
||||
ROCPROFILER_CODE_OBJECT_DEVICE_KERNEL_SYMBOL_REGISTER, ///< Kernel symbols - Device
|
||||
ROCPROFILER_CODE_OBJECT_HOST_KERNEL_SYMBOL_REGISTER, ///< Kernel symbols - Host
|
||||
ROCPROFILER_CODE_OBJECT_LAST,
|
||||
} rocprofiler_code_object_operation_t;
|
||||
|
||||
|
||||
Yeni konuda referans
Bir kullanıcı engelle