3 Коммитов

Автор SHA1 Сообщение Дата
Kian Cossettini 698ac6b8bc [rocprofiler-systems] Add build option for "examples" to specify gfx-arch (#2626)
## Motivation
 - Added `check_rocminfo` function that returns true if the provided regex was found, false otherwise. Can also use `GET_OUTPUT` to get the raw output filtered with or without a regex.
 - Moved `rocprofiler_systems_get_gfx_archs()` to `MacroUtilities.cmake` 
 - Added `rocprofiler_systems_lookup_gfx()`, which detects whether a given `gfx` is from the `instinct`, `radeon` or `apu` family.
 - Added `ROCPROFSYS_GFX_TARGETS` as a build argument. Used to specify the offloading architectures that GPU examples should compile for. If empty, defaults to whatever your system has.
 - GPU examples now check if the given `gfx` targets (from `ROCPROFSYS_GFX_TARGETS`) are supported.
 - OMPVV offload tests now only compile if `amdflang` version is `>= 20`
 - Improve link time by reducing the number of GFX targets that binaries need to support.
   - RCCL is now passed a `GPU_TARGETS` var specifying the architectures to build/link against.
2026-01-20 12:13:21 -05:00
Kian Cossettini 9f014db6a4 [rocprofiler-systems] Update install path for examples (#2625)
* Update install path for examples to `share/rocprofiler-systems/examples`

----

Co-authored-by: Kian Cossettini <Kian.Cossettini@amd.com>
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
2026-01-15 21:51:16 -05:00
Sajina PK 09b8342e22 [Rocprofiler-systems] : Add XGMI and PCIe metrics to the profiling data (#1628)
* Add XGMI and PCIe metrics to the profiling data

Add support for AMD XGMI (GPU-to-GPU interconnect) and PCIe
metrics:
  * XGMI link width in bits
  * XGMI link speed in GT/s
  * Per-link read bandwidth (KB)
  * Per-link write bandwidth (KB)

- Add new categories for PCIe metrics:
  * PCIe link width
  * PCIe link speed in GT/s
  * Accumulated bandwidth (MB)
  * Instantaneous bandwidth (MB/s)

* Fix VCN/JPEG insert logic

* Modify the gpu_metrics struct to accomodate XCP structure

* Add ctest automation for gpu interconnect metrics

* Refactor to move gpu_metrics struct and serialization to another file

* Possible fix for timeout in CI

Fix redundant skip check in ctest
Add xgmi and pcie option in rocprof-sys-avail.

* Change2: Address review comments

Change ctest sampling to avoid timeout
Change variable name and code structuring

* Add option in ctest to run rocprof-sys-run without rewrite

Run transferbench with rocprof-sys-run without sampling

* Change3: Fix sample insert bug and address review comments

xgmi and pci support check
renaming variables
additional hip_api validation in rocpd

* Reduce the load from the trnasferBench sample

The CI builds were timing out when flushing a big temporary file to the
DB: (2720824.23 KB / 2720.82 MB / 2.72 GB)...
2025-11-14 19:42:33 -05:00