Put cached perfetto traces as default one (#2138)

* Put cached perfetto traces as default one

* Improve cached data and perfetto traces in order to be more aligned with E2E tests

* Addressing PR comments and findings

* Force early instrumentation bundle instantiation

* Sync-up insturumented containers with thread growth data

* Revert ompvv number of host threads to default 8

* Fixed counter track namings for amd-smi

* AIPROFSYST-34 [rocprof-sys] Update documentation describing newly introduced changes to default tracing mechanism
This commit is contained in:
marantic-amd
2025-12-22 12:47:35 +01:00
committed by GitHub
parent 7da3275b42
commit ba1380a75d
36 changed files with 557 additions and 183 deletions
@@ -26,7 +26,10 @@
#
# -------------------------------------------------------------------------------------- #
# Use legacy trace mode for AMD SMI counters - cached mode doesn't support real-time counter tracking
set(_gpu_connect_environment
"ROCPROFSYS_TRACE_CACHED=OFF"
"ROCPROFSYS_TRACE_LEGACY=ON"
"ROCPROFSYS_ROCM_DOMAINS=hip_runtime_api"
"ROCPROFSYS_AMD_SMI_METRICS=busy,temp,power,xgmi,pcie"
"ROCPROFSYS_SAMPLING_CPUS=none"