Use barrier packets for every profile marker that gets submitted
and use the completion signal to get GPU ts. This gives most accurate
dispatch time. Club cache flushes with profile marker if there is a
pending dispatch that needs cache flush. This optimization saves on
extra barrier and helps wall time
Change-Id: Ib62d6d7aabf4743827b561be6c9c5afa813203da
[ROCm/clr commit: 59c6cb0268]
- As `long`/`ulong` on Windows has different bit sizes from Linux
platforms, even compiled in 64-bit mode. Need to use portable data
type `int64_t`/`uint64_t` as possible or use `long long` ones to
match the prototype in LLVM IR.
Change-Id: I62fe16a2e53aa0f2f2b4069b8a1596b8db7050c9
[ROCm/clr commit: f3b63c004a]
1. Negative Test Cases
2. API functionality tests for hopcount and linktype using rocm-smi library.
3. API functionality test for hopcount when devices are reversed.
4. Disabling test case 7.
5. Implemented External Review Comments.
6. Created a new header file hipP2pLinkTypeAndHopFunc.h.
7. Removed test case 0x7 from directed test.
8. Put testMaskedDevice() under __linux__, placed TODO in line 404 (comments) and replaced '&=' with '='.
SWDEV-238517 for enhancing hip unit tests
Change-Id: I1ae256ecfd637d6c25bca293c1724b026be20eca
[ROCm/clr commit: 4b16d3896d]
- Test d2d transfer after doing copy from pinned host buffer
- Test d2d transfer after doing copy from unpinned host buffer
SWDEV-238517 for enhancing hip unit tests
Change-Id: Ib262185ce2692036e11c0f95ccb850eb3bce1c81
[ROCm/clr commit: 50524ae60c]
1. Negative Test Cases
2. API functionality test using multiple streams.
3. API functionality validation using multiple GPUs.
4. Setting hipTexRefSetFlags() with HIP_TRSF_READ_AS_INTEGER flag instead of 0 as suggested in SWDEV-256096.
5. Enabling test cases 0x03 (short) and 0x04 (char).
6. Implemented external code review comments.
SWDEV-238517 for enhancing hip unit tests
Change-Id: If42796047ec1cf2e3695dc2b7f40a2d9dd50f5bd
[ROCm/clr commit: 4f039d1bf5]
SWDEV-262064 - compilation fails when hipLaunchCooperativeKernel C++ routine is invoked
on nvcc path.
Change-Id: Icde35dd1a7008b406401bb3996c06d7acfb27d8d
[ROCm/clr commit: 80cb172fef]
[PAL to KFD/ROCr][ROCr_Runtime][Vega10] OCLSeparateCompile subtest of
oclcompiler from ocltst test package is encountering clLinkProgram()
failed (chksum 0x00000001) error
If runtime does not provide a file name as dump file to ELF library,
ELF library use a temp file in current folder.
The current folder can be not writable for several reasons:
1. The application current folder might be system folder, the user
does not have write permission.
2. The current folder is under a readonly file system. This happens for
embedded customers.
Tested in VEGA10. Issue was fixed.
Change-Id: Ic0e9f040b7c7583914301673cce237ab28b0c0cb
[ROCm/clr commit: 6327dbc4cc]
Change-Id: I043caa89b2a43dace7f18c739f30d2a7bfa644ca
Fixes the issue when memcpy DtoH is performed on device 0 where the device buffer
is allocated on device1 and the destination pinned buffer is allocated from device 0.
[ROCm/clr commit: 60ec2a3e46]
PAL doesn't perform chunking for system memory allocations, hence we
should fall back to using pinned memory for mapping large buffers.
Change-Id: I1b472616b72d12ed0105fb65532acacdb98ac7b3
[ROCm/clr commit: b4e212a0f9]
If deferred allocation is disabled, then make sure the image view
is created without a delay. Also reset the allocation state, since
create() method isn't called for a view creation.
Change-Id: I7aa22a62bff18289ade83e56b5d3305ba68c715b
[ROCm/clr commit: 089a5cc4ad]
Saleel Kudchadker
agodavar
Sarbojit Sarkar
Chauncey Hui
Jason Tang
Sourabh Betigeri
Yaxun (Sam) Liu
German Andryeyev
Michael LIAO
Siu Chi Chan
Rupam Chetia
Sudheer Kumar
Satyanvesh Dittakavi
Alex Xie
Tony
Aryan Salmanpour
Cole Nelson
jujiang
Vladislav Sytchenko
cjatin
Rahul Garg