* SWDEV-555347 - Remove lock contention in async events loop
* SWDEV-555347 - Introduce Pool of AsyncEventItems
* create generic mempool for AsyncEventItem
* Use BaseShared allocate and free for async event pool
---------
Co-authored-by: Rahul Manocha <rmanocha@amd.com>
* Check emulator mode at runtime
* Reduce emu mode function call to one time and use result
* Move function to main.cc
* Address feedback
* EmuMode check improvement; convert to AoS
* replace g_isEmuMode with func call
* Add mode check func for every sample
1. Create a set of mini numa interface.
In Linux, the interface is based on system call rather than libnuma.
In Windows, the interface can also work, but the policy class is dummy.
Different from Linux, Windows doesn't provide numactl tool or numa lib to setup numa policy, thus
the default policy is followed in Windows, that is, using the closest host numa node to allocate
pinned host memory in hipHostMalloc().
To get the closest host numa node of a GPU device, you need query the new attribute
hipDeviceAttributeHostNumaId. Then you can create a thread with CPU affinity on the numa node.
For example, reference the test in hip-tests/catch/perftests/memory/hipPerfHostNumaAllocWin.cc.
2. Remove pfnSetThreadGroupAffinity and pfnGetNumaNodeProcessorMaskEx as the functions have been exposed since Win7 and Win server 2008.
3. Other minor fixes.
* SyncAll test case would run Sync
* Despecialized name for argument reader
* Rename sync-test to team-sync-test as it uses teams
* Another stab at probing NUM_GPUS
[ROCm/rocshmem commit: 054bc33dc4]
* SyncAll test case would run Sync
* Despecialized name for argument reader
* Rename sync-test to team-sync-test as it uses teams
* Another stab at probing NUM_GPUS
Changes:
- Fix `rocm-smi --setsclk [0 .. n]` for multiple devices to continue on fail when
in a partitioned configuration (ex. in DPX/QPX/CPX/etc).
- Partitioned configurations or devices which do not support changing
sclk/mclk/pcie clks will now continue on failure. Will report a "not
supported" or other (rocm-smi) error codes for these devices.
- Updates impact other clock settings such as `--setmclk` and
`--setpcie`.
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
* initial commit
* add csv support extraction for non kernel selection mode
* add --kernel-trace for rocprofiler-sdk mode
* make non kernel selective mode runnable
* make kernel selection work with -k
* remove upper case of arg hint
* update documentation
* display same kernel name at only one place and merge instruction id with same obj id as well as offset
* remove kernel name's display for single kernel selection
* change log added
---------
Co-authored-by: Fei Zheng <44449748+feizheng10@users.noreply.github.com>
* SWDEV-554608 - Add hipHostRegisterIoMemory for hipHostRegister
* SWDEV-554608 - Add hipHostRegisterIoMemory for hipHostRegister
* SWDEV-554174 Added hipHostRegisterIoMemory flag in test cases
* SWDEV-554174 : Did formatting corrections
* SWDEV-554608 - set HSA_AMD_MEMORY_POOL_UNCACHED_FLAG if IoMemory is set
* SWDEV-554608 - set HSA_AMD_MEMORY_POOL_UNCACHED_FLAG if IoMemory is set
* SWDEV-554608 - Add hipHostRegisterIoMemory for hipHostRegister
---------
Co-authored-by: Anavena Venkatesh <Anavena.Venkatesh@amd.com>
Co-authored-by: Rambabu Swargam <rambabu.swargam@amd.com>
* [SWDEV-542718] Correct socket_affinity
Updated Socket affinity to show bitmask and expanded cpu list.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
* Update per-device local_cpulist for socket_affinity
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
* Added amdsmi_get_cpu_affinity_from_local_cpulist API.
Updated the wrapper.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
* Revert "Added amdsmi_get_cpu_affinity_from_local_cpulist API."
This reverts commit 9a2ef934b1787f8aa09d3e4efe02f897b4295215.
* Moved the changes to C API.
In case of SOCKET_SCOPE, use local_cpulist first.
If it is unavailable or not readable, fallback to
numa.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
* Addressed review comments
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
---------
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
* [SWDEV-542718] Correct socket_affinity
Updated Socket affinity to show bitmask and expanded cpu list.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
* Update per-device local_cpulist for socket_affinity
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
* Added amdsmi_get_cpu_affinity_from_local_cpulist API.
Updated the wrapper.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
* Revert "Added amdsmi_get_cpu_affinity_from_local_cpulist API."
This reverts commit 9a2ef934b1787f8aa09d3e4efe02f897b4295215.
* Moved the changes to C API.
In case of SOCKET_SCOPE, use local_cpulist first.
If it is unavailable or not readable, fallback to
numa.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
* Addressed review comments
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
---------
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
[ROCm/amdsmi commit: 09a97f02ed]
- Remove unimplemented older API functions
- Remove mentions of reattach API
- Remove details on implementing a process attachment library
- This will return later as a theory of operation
* add gfx1100 support
Add support for Radeon 7900 GPUs (RX and PRO), and 7800 PRO.
I was contemplating to add gfx1101 and gfx1102 GPUs as well, but those are the lower end models that are more unlikely to be used for compute intensive jobs. In addition, I do not have access to them to test the support.
* update WF_SIZe for different options
Radeon systems use a WarpSize of 32, unlike current Instinct systems,
which use a warp size of 64. For the device side, a gfx specific ifdef
is sufficient. For the host side, we need to query the device
properties.
* adjust functional tests to wf_size of 32
* update unit tests to handle wf_size of 32
* address reviewer comments
[ROCm/rocshmem commit: d0c2845031]
* add gfx1100 support
Add support for Radeon 7900 GPUs (RX and PRO), and 7800 PRO.
I was contemplating to add gfx1101 and gfx1102 GPUs as well, but those are the lower end models that are more unlikely to be used for compute intensive jobs. In addition, I do not have access to them to test the support.
* update WF_SIZe for different options
Radeon systems use a WarpSize of 32, unlike current Instinct systems,
which use a warp size of 64. For the device side, a gfx specific ifdef
is sufficient. For the host side, we need to query the device
properties.
* adjust functional tests to wf_size of 32
* update unit tests to handle wf_size of 32
* address reviewer comments
* Add `ROCSHMEM_CTX_INVALID` for invalid context handling
- Define `ROCSHMEM_CTX_INVALID` as {nullptr, nullptr}
- Add == and != operators to rocshmem_ctx_t
- Use `ROCSHMEM_CTX_INVALID` on failed context creation
- Skip ctx destroy if context is invalid
* Update docs for context create and destroy APIs usage and behavior
[ROCm/rocshmem commit: 955c22aeed]
* Add `ROCSHMEM_CTX_INVALID` for invalid context handling
- Define `ROCSHMEM_CTX_INVALID` as {nullptr, nullptr}
- Add == and != operators to rocshmem_ctx_t
- Use `ROCSHMEM_CTX_INVALID` on failed context creation
- Skip ctx destroy if context is invalid
* Update docs for context create and destroy APIs usage and behavior
* Check if test exists before adding validation
* Adjust validation parameters for rocpd_string
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
---------
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
Rahul Manocha
marandje
pghoshamd
systems-assistant[bot]
Jatin Chaudhary
abchoudh-amd
SaleelK
MachineTom
Ioannis Assiouras
Julia Jiang
amd-hsivasun
nunnikri
Yiltan
Pengda Xie
Kian Cossettini
Aurelien Bouteiller
Venkateshwar Reddy Kandula
Kapil S. Pawar
Charis Poag Jones
Edgar Gabriel
vedithal-amd
ywang103-amd
Gopesh Bhardwaj
amd-srinivas1
Gerardo Hernandez
Aryan Salmanpour
Jimbo
Kanangot Balakrishnan, Bindhiya
Mark Meserve
Todd tiantuo Li
Joseph Macaranas
xuchen-amd
Avinash Kethineedi
David Galiffi
Swati Rawat
pcritchl-amd