Set affinity to the closest node of the current GPU. This reduces
the latency to fetch kernel args since device would query the CPU cache
of core which did the dispatch. This behavior is controlled with
AMD_CPU_AFFINITY env var(disabled by default)
Change-Id: I65afba62cb818ea25a311b88d1c0dd5c51330292
- Create hash values for binaries
- Add the binaries into RGP trace
- Add corresponding hash value for every dispatch
Change-Id: I2c3ce004d69f37d0d46bc4744e12f24273517f5e
Just signal check will still submit the marker and then later
runtime will have a timeout, but the barrier packet is still
generated. Hence early timeout will allow to skip the marker.
Change-Id: Ieb7d89becbcff43a4f4c46715354ca65ab4a80b9
The optimization is controlled with ROCR_SKIP_KERNEL_ARG_COPY.
This is initial check-in for experiments. Extra changes are
necessary for full support:
- handle graph capture with the original sysmem alloc
- avoid memobject references, otherwise there is a race condition with
reusage of the arg buffer
- Remove arg setup from hip
Change-Id: Ib0af710f93e79834711fa4049a7c66093711e68b
The kernel arg pool will be divided into 8 chunks to avoid long stalls,
when the pool will be reused.
Change-Id: I228e6ca1c09e428c1775f1e5b685220a9a5d71af
If we don't create the __amd_rocclr_gwsInit kernel, we still want
to create the rest of the image related blit kernels.
Change-Id: I8bc4645f9f9116eeecbb8b22e981ac4d520f3121
Change the scope of hostcall buffer access lock during destruction.
Make sure wait() returns the signal value after timeout. That
matches ROCr behaviour for HSA signal wait.
Change-Id: I3df34207e0c2e21972ec8052777e5742bda1dca0
The queue can be destroyed at the time the app will request
the event status. Hence just get the active state from the device.
Change-Id: I887ecb0cfe414c2119247228b0d1255b8308da1e
When unsetting runtime should use HSA_AMD_SVM_ATTRIB_AGENT_ACCESSIBLE
for the agent and not HSA_AMD_SVM_ATTRIB_AGENT_ACCESSIBLE_IN_PLACE
Change-Id: I3814802d1fb3b72c54e7566defafafed6b0d5cee
The original logic left only one slot for HW processing in the queue.
For some reason there is a race condition on CPU overwrite of the slot
before the current active. The workaround is to avoid the previous to
the current active slot for possible unfinished HW processing.
Change-Id: I565495a8feeaedffc9fc8a505edbee5ff5816975
For the fillBuffer shader, if there are two 32bit writes to a MMIO
register, it can get dropped. It has to be a single 64bit write.
Add optimization to fillBuffer to write 64bit and 16bit writes.
Change-Id: I3aa78e027898f8ae01e9c8f09004615673720c2b
Add a env var ROC_USE_FGS_KERNARG to toggle kernel arg placement
By default its in Fine Grain Kernel arg segment for supported asics.
Change-Id: I3d57ed69a1a4db2b392b0438ead499f3ddca4716
PCMark10 counts the time spent in clCreateKernel as part of execution
time, so as workaround for the PAL path, move code object loading
back to clBuildProgram.
Change-Id: I3b9cf1879ece08ab59f447ec165b0525bc8593a4
Pass the device agent specified by the user to the ROCr api instead of passing the device agent attached to the specified stream
Change-Id: I86c98935b9dc404eaa6d47ccdd082a8c3678fb36
Fixes Seg fault caused when the attribute hipMemRangeAttributeAccessedBy
is queried using hipMemRangeGetAttribute
Change-Id: I2ceb2267d89bfc31a55d9eae2685610c7ad89b1f
kjayapra-amd
Saleel Kudchadker
German Andryeyev
pghafari
Julia Jiang
Alex Xie
Sarbojit Sarkar
Bing Ma
Jason Tang
Tao Sang
Sourabh
Jatin Chaudhary
Satyanvesh Dittakavi