Applications may submit commands withoout waits
for GPU. That causes a growth of SW unreleased commands.
Make sure runtime flushes SW queue, if it grows over some
threshold, controlled by DEBUG_CLR_MAX_BATCH_SIZE.
Change-Id: Ia4d85c24210ef91c394f638ab6b53b14323a0396
[ROCm/clr commit: 8657a77029]
Since we don't distribute icd loader, we need to install distro icd loader.
Change-Id: I1ea86bcf7c642a034c53f71130b15de1fa27e31e
[ROCm/clr commit: df9ae754a4]
- 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]
Changed the validation to occur on the sub-object rather than the parent.
Change-Id: I87bf5ef3526d0db9304099ef9ac1a5494e9a01a9
[ROCm/clr commit: 5da72f9d52]
- Use AMD_LOG_LEVEL_SIZE in MBs to set log file size truncation, by default its 2048 MB
Change-Id: Ia2f87e8c6b94148e30edfb602b279f93630817c3
[ROCm/clr commit: 35e03ea0d0]
PAL supports allocating from system memory once device memory is used up
or allocation is larger than the device memory.
Change-Id: Iccd3377e95a6cc6d23e45d4738a17af8b9ee32d7
[ROCm/clr commit: b07178618c]
* In a scenario where kernel is launched with hipExtLaunchKernelGGL and stop event is used, hipGraphInstantiate leaks. Since stop event is used, profiling is enabled and Timestamp (ReferencedCountedObject) is created, but it doesn't get released.
* The idea behind this solution is that profiling should be disabled when command is captured, hence the timestamp should not be created. Because information about capturing isn't available when kernel command is created, packet capturing state is used to determine whether to create a timestamp or not.
Change-Id: Ia23adac4592ded4fb5e236acf99e12e729f63692
[ROCm/clr commit: da5f1a6146]
Gfx12 has 16 bits for grid dim Y/Z. Detect gfxIp and return error if dim y/z > 16 bits
Change-Id: I43dd14affc9e4073d0b1232e7523967f0180fa31
[ROCm/clr commit: 0a918c8f96]
Although unpinned copies require synchronizations
in HIP, runtime can avoid syncs for H2D copies with
a staging buffer
Change-Id: If2203c6bc0cbd89742823688dc8e89e9acd873b2
[ROCm/clr commit: 29cc678d8d]
This reverts commit 2e7581a69a.
Changing the error code is considered as a breaking change,
so it should be done in major releases only.
The other reason for reverting the commit is that this change itself
is incorrect. Cuda behaves in the same way as hip when
pResDesc or pTexDesc are nullptr.
Change-Id: I3abee6b79279b81ab01c7f8466c7f8e3776c4109
[ROCm/clr commit: cfdc9dfc36]
1) Child Graph nodes need to have parent graph dependencies in waitlist.
2) Marker is placed on base stream with parent graph waitlist
Change-Id: Iec65a0171ea387be05b0733abcc708fb630e4be4
[ROCm/clr commit: 4d1ded9eaf]
This PR adds UberTrace-based tracing support to ROCclr's PAL device class.
Legacy RGP-based tracing is still available and is the default.
If UberTrace support is enabled tool-side, this new code path will activate.
Change-Id: I268b2dcef70e850a50e2caef8355f38bf51d4641
[ROCm/clr commit: e550032d25]
German Andryeyev
Alex Xie
Ajay
Ioannis Assiouras
Todd tiantuo Li
kjayapra-amd
Vladana Stojiljkovic
Jaydeep Patel
Jatin Chaudhary
Julia Jiang
Satyanvesh Dittakavi
Branislav Brzak
Saleel Kudchadker
pghafari
Rahul Manocha
Anusha GodavarthySurya
Jonathan R. Madsen
Maneesh Gupta
Marko Arandjelovic
Daniel Livingston