In a previous change we started using "MI300" for gpu_model instead of the full
"MI300X_A0" or "MI300X_A1", etc.
The XCD detection code was using gpu_model and expecting the full name, causing
the XCD count = 1. Passing chip_id fixes the issue.
Signed-off-by: benrichard-amd <ben.richard@amd.com>
Remove occupancy metrics and replace with OccupancyPercent
Add OCCUPANCY_PERCENT which uses OccupancyPercent
Add GR_ENGINE_ACTIVE which uses GPU_UTIL/100
Add TENSOR_ACTIVE_PERCENT which uses MfmaUtil
Modify FLOPS_64 to use FP64_ACTIVE
Change-Id: I5f30d77a0c80f5ac78abd1a9e57f8a0a3c6cc00b
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
* Correct the package name of rocprofiler-sdk
ROCM VERSION(for ex: 60300) was missing in the package name.
Added the same
* Use cmake cache string while setting the variable for ROCm Version
* correct the cmake-format
---------
Co-authored-by: Ranjith Ramakrishnan <Ranjith.Ramakrishnan@amd.com>
[ROCm/rocprofiler-sdk commit: 309d53b20b]
* Correct the package name of rocprofiler-sdk
ROCM VERSION(for ex: 60300) was missing in the package name.
Added the same
* Use cmake cache string while setting the variable for ROCm Version
* correct the cmake-format
---------
Co-authored-by: Ranjith Ramakrishnan <Ranjith.Ramakrishnan@amd.com>
The Omnitrace program is being renamed.
Full name: "ROCm Systems Profiler"
Package name: "rocprofiler-systems"
Binary / Library names: "rocprof-sys-*"
---------
Co-authored-by: Xuan Chen <xuchen@amd.com>
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
[ROCm/rocprofiler-systems commit: d07bf508a9]
The Omnitrace program is being renamed.
Full name: "ROCm Systems Profiler"
Package name: "rocprofiler-systems"
Binary / Library names: "rocprof-sys-*"
---------
Co-authored-by: Xuan Chen <xuchen@amd.com>
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
- Don't generate callbacks for HIP events
- Don't process profiling info in the callback for HIP events
- Wait for CPU status update of the submitted commands
every 50 calls. That will allow to drain the commands and
destroy HSA signals.
Change-Id: Ib601a350e7e7c2b6c6209a172385389baccf73a9
[ROCm/clr commit: 364dfb0ed1]
- Don't generate callbacks for HIP events
- Don't process profiling info in the callback for HIP events
- Wait for CPU status update of the submitted commands
every 50 calls. That will allow to drain the commands and
destroy HSA signals.
Change-Id: Ib601a350e7e7c2b6c6209a172385389baccf73a9
Fix VirtMemory_Basic_Test permissions to adjust for previous change to
the hsa_amd_vmem_set_access behavior change that was done with this
patch:
rocr/vmm: Only modify permisions for specified agents
Change-Id: I97230600b9b9144459b08ca3da3a5bfbdbb98231
Fix VirtMemory_Basic_Test permissions to adjust for previous change to
the hsa_amd_vmem_set_access behavior change that was done with this
patch:
rocr/vmm: Only modify permisions for specified agents
Change-Id: I97230600b9b9144459b08ca3da3a5bfbdbb98231
[ROCm/ROCR-Runtime commit: ead3aafcda]
Changed the validation to occur on the sub-object rather than the parent.
Change-Id: I87bf5ef3526d0db9304099ef9ac1a5494e9a01a9
[ROCm/clr commit: 5da72f9d52]
hip-lang package is part of the toolchain and shouldn't have to rely
on the user's settings for CMAKE_PREFIX_PATH in order to find lower
level dependencies. This commit also sets the CMAKE_SIZEOF_VOID_P
variable before searching for hsa and comgr dependencies.
This is a workaround to force cmake to include lib64 directories
in the search.
Change-Id: Ie7d10bd4078929275659aae10ec270816d4a30f5
[ROCm/hip commit: a885727cce]
hip-lang package is part of the toolchain and shouldn't have to rely
on the user's settings for CMAKE_PREFIX_PATH in order to find lower
level dependencies. This commit also sets the CMAKE_SIZEOF_VOID_P
variable before searching for hsa and comgr dependencies.
This is a workaround to force cmake to include lib64 directories
in the search.
Change-Id: Ie7d10bd4078929275659aae10ec270816d4a30f5
Devices older than GFX90a hit a segfault on queue unmap when an
SDMA queue has been assigned a fixed engine. Bypass fixing the
engine for these devices for now.
Change-Id: I7d2f882d2377f004a7bb65f3b397396db07ce6d3
Devices older than GFX90a hit a segfault on queue unmap when an
SDMA queue has been assigned a fixed engine. Bypass fixing the
engine for these devices for now.
Change-Id: I7d2f882d2377f004a7bb65f3b397396db07ce6d3
[ROCm/ROCR-Runtime commit: 1d6ff45673]
This reverts commit f014c03f30.
Reason for revert: <Imapcting driver install to QA due to timeout>
Change-Id: If5d98341e9ac3e803965064e3f5dc435b9310a0b
[ROCm/roctracer commit: f3df78f746]
This reverts commit b42028fcc0.
Reason for revert: <Imapcting driver install to QA due to timeout>
Change-Id: If5d98341e9ac3e803965064e3f5dc435b9310a0b
Ben Richard
itrowbri
Benjamin Welton
Ammar ELWazir
Galantsev, Dmitrii
Jonathan R. Madsen
Daniel Su
David Yat Sin
David Galiffi
sdashmiz
Ajay
Manjunath-Jakaraddi
Giovanni LB
coleramos425
German Andryeyev
gobhardw
Ioannis Assiouras
Todd tiantuo Li
jokim
kjayapra-amd
Pramendra Kumar
Vladana Stojiljkovic