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

SWDEV-465322: Adding support for Perfcounter SIMD Mask in ATT (#910)

Browse Source 
* SWDEV-465322: Adding support for r Perfcounter SIMD Mask in ATT

* Apply suggestions from code review

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Benjamin Welton <bewelton@amd.com>

* Adding unit tests

* Adding counters check for gfx9 and SQ block only

* Addressing review comments

* changing the struct size

* fixing header includes

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Benjamin Welton <bewelton@amd.com>

[ROCm/rocprofiler-sdk commit: c49719649b]
This commit is contained in:
Manjunath P Jakaraddi
2024-06-12 16:25:06 -07:00
committed by GitHub
parent f61d91057a
commit 0f51b3b55e
12 changed files with 227 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files
projects/rocprofiler-sdk/source/include/rocprofiler-sdk/amd_detail/thread_trace.h
+12 -1
View File
@@ -26,6 +26,7 @@
#include <rocprofiler-sdk/defines.h>
#include <rocprofiler-sdk/fwd.h>
#include <rocprofiler-sdk/hsa.h>
#include <cstdint>
ROCPROFILER_EXTERN_C_INIT
@@ -43,13 +44,23 @@ typedef enum
ROCPROFILER_ATT_PARAMETER_BUFFER_SIZE, ///< Size of combined GPU buffer for ATT
ROCPROFILER_ATT_PARAMETER_SIMD_SELECT, ///< Bitmask (GFX9) or ID (Navi) of SIMDs
ROCPROFILER_ATT_PARAMETER_CODE_OBJECT_TRACE_ENABLE, ///< Enables Codeobj Markers IDs into ATT
ROCPROFILER_ATT_PARAMETER_PERFCOUNTER, ///< Enables Perfcounter with simd mask (GFX9 only)
ROCPROFILER_ATT_PARAMETER_PERFCOUNTERS_CTRL, ///< Defines the update period (GFX9 only)
ROCPROFILER_ATT_PARAMETER_LAST
} rocprofiler_att_parameter_type_t;
typedef struct
{
rocprofiler_att_parameter_type_t type;
uint64_t value;
union
{
uint64_t value;
struct
{
rocprofiler_counter_id_t counter_id;
uint64_t simd_mask : 4;
};
};
} rocprofiler_att_parameter_t;
typedef enum