Make ocltst -m tests/ocltst/liboclruntime.so -t OCLMemoryInfo
pass in emu where GPU memory is very big.
Cherry pick
https://gerrit-git.amd.com/c/compute/ec/clr/+/1014858
Change-Id: I0228c5e87ce7c366983fd4af71c25e7f8161c2c7
- Header files inside rocclr/utils when included from hipamd or opencl should be included as #include "rocclr/utils/xxx.h" instead of "utils/xxx.h"
Change-Id: Ic0760c33b9d091f5620dec67e5482c9698d22093
Replaced clGetExtensionFunctionAddress calls with
clGetExtensionFunctionAddressForPlatform to ensure
interoperability with distribution ICD loaders.
Change-Id: I560a62459f2ad222750e65e869b98d6b6ec56665
1. Fix LDSSize type to be uint32_t.
2. Prevent clWaitForEvents running on complete events whose
HostQueue have been destructed.
Change-Id: I829e915f56b37db2ba76bb876c9656166534f154
This is the first step to remove rocm-ocl-icd.
We don't build amd icd after this commit.
We still need to remove header files usage in future steps.
Change-Id: Ic4ac5476180f9ef2ce87b62891c08b28d6c9bfd2
Updating field num_mip_levels to better align with OpenCL specification that mip-mapped images can not be created for CL_MEM_OBJECT_IMAGE1D_BUFFER images. Added check for miplevels value used for ClCreateImage call.
Change-Id: I82a25b83ef0637a877409572b7976d9e4413dfac
Remove the redundant copies inside sub folders. This was useful when
these projects were independent but now since they are merged they
should have one single .clang-format file.
Change-Id: I60510d7b78b129c761e84f13403492bd0c5d941a
When CL-GL interop is used, a GL context are used by two or more threads at the same time, which causes race condition.
Solution:
Add lock when accessing GL functions during CL-GL interop.
Change-Id: I3a34da3cbdf74c401111cc4e3a04ad84cc52709e
- Create a vector to allow multiple TS to be stored in Command.
- This would mean we dont wait for entire batch in Accumulate command
to finish when we exhaust signals.
- Reduce the number of signals created at init to 64. This min value
may still need to be tuned but the KFD allows max of 4094 interrupt
signals per device.
- Store kernel names whenever they are available and not just when
profiling. If we dynamically enable profiling like for Torch, a crash
can happen if hipGraphInstantiate wasnt included in Torch profile scope
beacuse we previously entered kernel names only when profiler is
attached.
Change-Id: I34e7881a25bbc763f82fdeb3408a8ea58e1ec006
This reverts commit 5f68a4531a.
Reason for revert: due to windows staging branch using Opencl-icd-loader master
Change-Id: I9cca7564a21de1733665a34da6f0322aa3b886e7
Update cmake minimum requirement on deprecated cmake version (2.8.11) to non-deprecated version (3.5)
Change-Id: Ib76d241babf475a26464e8b12b91d67e48f72b60
This header file is used by ROCclr and might be used by HIP too.
ROCclr folder is a right place for this header file.
Change-Id: Ie2307331f9bd445f3c295d2ccbfc4924b0fa9510
Chaudhary, Jatin Jaikishan
Branislav Brzak
Todd tiantuo Li
Alex Xie
taosang2
Ranjith Ramakrishnan
Marko Arandjelovic
Ioannis Assiouras
Julia Jiang
Jaydeep Patel
Ajay
cadolphe
Gu, Wangfeng
kjayapra-amd
Saleel Kudchadker
Konstantin Zhuravlyov
AravindanC