PC-Sampling doc updates - FW version (#455)
* Initial doc update * addressed review comments * addressed review comments - 2 * accept reviewer suggestions Co-authored-by: Rawat, Swati <Swati.Rawat@amd.com> * accept reviewer suggestions-2 Co-authored-by: Rawat, Swati <Swati.Rawat@amd.com> * accept reviewer suggestions-3 Co-authored-by: Rawat, Swati <Swati.Rawat@amd.com> * accept reviewer suggestions-4 Co-authored-by: Rawat, Swati <Swati.Rawat@amd.com> * Update README.md Co-authored-by: Rawat, Swati <Swati.Rawat@amd.com> * Update CHANGELOG.md as per viewer suggestions Co-authored-by: Rawat, Swati <Swati.Rawat@amd.com> * accept review suggestion Co-authored-by: Indic, Vladimir <Vladimir.Indic@amd.com> * accept reviewer suggestion Co-authored-by: Rawat, Swati <Swati.Rawat@amd.com> * accept reviewer suggestions Co-authored-by: Rawat, Swati <Swati.Rawat@amd.com> --------- Co-authored-by: Rawat, Swati <Swati.Rawat@amd.com> Co-authored-by: Indic, Vladimir <Vladimir.Indic@amd.com> Co-authored-by: Bhardwaj, Gopesh <Gopesh.Bhardwaj@amd.com>
This commit is contained in:
Verma, Saurabh
GitHub
@@ -208,6 +208,8 @@ Full documentation for ROCprofiler-SDK is available at [rocm.docs.amd.com/projec
|
||||
- Fixed potential data race in rocprofiler-sdk double buffering scheme
|
||||
- Usage of std::regex in core rocprofiler-sdk library which causes segfaults/exceptions when used under dual ABI
|
||||
- Fixed perfetto counter collection by introducing per dispatch accumulation.
|
||||
- Fixed queue preemption error and HSA_STATUS_ERROR_INVALID_PACKET_FORMAT error for stochastic PC-sampling for MI300X, leading to more stable runs.
|
||||
- Fixed the system hang issue for host-trap PC-sampling on MI300X.
|
||||
|
||||
### Removed
|
||||
|
||||
|
||||
+4
-1
@@ -97,7 +97,7 @@ Please report issues on GitHub OR send an email to <dl.ROCm-Profiler.support@amd
|
||||
|
||||
- Timestamps in PC sampling records might not be 100% accurate.
|
||||
|
||||
- Using PC sampling on multi-threaded applications might fail with `HSA_STATUS_ERROR_EXCEPTION`.Furthermore, if three or more threads launch operations to the same agent, and if PC sampling is enabled, the `HSA_STATUS_ERROR_EXCEPTION` might appear.
|
||||
- For low PC-sampling frequencies with intervals < 65k cycles, a lot of error samples might be delivered. We're working on optimizing this to allow lower sampling frequencies.
|
||||
|
||||
- gfx10, gfx11 and gfx12 requires a stable power state for counter collection. This includes Radeon 7000 GPUs.
|
||||
```bash
|
||||
@@ -126,5 +126,8 @@ Please report issues on GitHub OR send an email to <dl.ROCm-Profiler.support@amd
|
||||
TARGET_GRAPHICS_VERSION: gfx1102
|
||||
```
|
||||
|
||||
|
||||
|
||||
|
||||
> [!WARNING]
|
||||
> The latest mainline version of AQLprofile can be found at [https://repo.radeon.com/rocm/misc/aqlprofile/](https://repo.radeon.com/rocm/misc/aqlprofile/). However, it's important to note that updates to the public AQLProfile may not occur as frequently as updates to the rocprofiler-sdk. This discrepancy could lead to a potential mismatch between the AQLprofile binary and the rocprofiler-sdk source.
|
||||
|
||||
@@ -49,7 +49,24 @@ The output lists if ``rocprofv3`` supports PC sampling on the GPU and the suppor
|
||||
|
||||
The preceding output shows that the GPU supports PC sampling with the ``ROCPROFILER_PC_SAMPLING_METHOD_HOST_TRAP`` method and the ``ROCPROFILER_PC_SAMPLING_UNIT_TIME`` unit. The minimum and maximum intervals are also displayed.
|
||||
|
||||
Based on the preceding configuration, you can use the following command to profile the application using PC sampling:
|
||||
.. note::
|
||||
Important firmware fixes to host-trap and stochastic PC-sampling for AMD Instinct MI300X have been made in ROCm 7.0.
|
||||
To ensure that you have the latest fixes, check if you have the correct firmware versions installed:
|
||||
|
||||
For host-trap PC-sampling on MI300X: PSP TOS Firmware >= version 00.36.02.59 or 0x00360259
|
||||
For stochastic PC-sampling on MI300X as described in the following section: MEC Firmware feature version: 50, firmware version >= 0x0000001a
|
||||
|
||||
To check the firmware versions, use:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
# To check PSP TOS Firmware:
|
||||
sudo cat /sys/kernel/debug/dri/0/amdgpu_firmware_info | grep SOS
|
||||
|
||||
# To check MEC Firmware:
|
||||
sudo cat /sys/kernel/debug/dri/1/amdgpu_firmware_info | grep MEC
|
||||
|
||||
Based on the available PC-sampling configurations, use the following command to profile the application using PC-sampling:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
|
||||
مرجع در شماره جدید
Block a user