This issue happens because we getLastQueuedCommand when recording
the event and do end_ - start_ so it takes the ticks for the
completion of the last command before event record. This may not
happen if one records a marker command for hipEventRecord
Change-Id: I1d6b06a5befb3b93f16b67692c59dca25c982e0f
SWDEV-235579
Move the lock before destroying the queue as there's a multithreaded race condition if the queue
is being destroy and right after we set queue_ to nullptr, another thread can call ihipWaitStreams
which will then call create on that same stream because queue is now nullptr.
Moving the lock on streamSet prevents this from happening because we would remove the stream from that
list and therefore ihipWait will not try to call asHostQueue which tries to create the queue if not created yet
since the stream won't be in the list anymore
Change-Id: I3108657ab403d39d4123e83294fcf1f0880e5563
This technique should never be used, and only accessed through
__builtins.
There's currently no builtin for groupstaticsize. I left ds_swizzle
since for some reason it switches to the builtin based on __HCC__ or
not.
Change-Id: If1e1394221dba83ea4add6db5e94d6b715552044
The hipcc script takes arguments and uses this to build up a new
command. Characters which are special to the shell need to be quoted
to prevent them being interpreted.
In particular adding
--Wl,--enable-new-dtags -Wl,--rpath,'$ORIGIN:$ORIGIN/../lib'
to the command should pass quoted dollar signs into the resulting
string so the shell passes them on, rather than substituting the
values.
The arguments are processed in a conventional loop, but can be altered
during the course of the loop, and also by linker response files.
Tested by running
HIPCC_VERBOSE=7 HIP_COMPILER=clang hipcc --cxxflags \
fred.c -Wl,,--rpath,'$ORIGIN:$ORIGIN:/../lib'
and observing "-Wl,--rpath,\$ORIGIN\:\$ORIGIN\:..\/lib" in the
displayed hipcc-cmd output (and ignoring the errors due to rocm not
being installed)
Change-Id: I26b62f09ff3518cceeb85fa8823bb12a95c1c78e
Signed-off-by: Icarus Sparry <icarus.sparry@amd.com>
Before setting the HIP_RUNTIME and HIP_COMPILER variables, first check the environment if these are set. We should prioritize the environment settings. For windows, it will be set, and also explicitly call perl when invoking hipconfig.
Change-Id: I89ad267285239e6d8a897dc681c4af5906e7b9d8
Support performance tests while direct tests commands keep unchanged.
To build performance tests, run "make build_perf".
To run all performance testis, run "make perf".
To run specific tests, for example, run
/usr/bin/ctest -C performance -R performance_tests/perfDispatch --verbose
To run individual test, for example, run
performance_tests/memory/hipPerfMemMallocCpyFree
Change-Id: I168c1b9ef1ec21b392d48648d0c71e8fbd37d57b
Saleel Kudchadker
Christophe Paquot
Karthik Jayaprakash
Matt Arsenault
Payam Ghafari
Icarus Sparry
Michael Hong Bin Liao
Vlad Sytchenko
Anusha Godavarthy Surya
Aaron Enye Shi
Sarbojit Sarkar
Aaron En Ye Shi
Tao Sang
Rahul Garg
Aakash Sudhanwa
Yaxun Liu