find_package should now be the only way to import ROCclr. Also update
the build example comment.
The build scripts used 2 custom variables to manually specify the
build and source directories for where to find VDI. Once renamed to
ROCclr, these conflicted with the variables automatically set by
find_package(ROCclr). These hacks tried to satisfy this intermediate
step to try satisfying commit ordering problems to get through PSDB.
The INSTALL.md documentation should also be updated, but it's
completely missing any mention of ROCclr now, and still gives
directions for hcc.
Change-Id: I6fc94b6cb36241a9d4f22d24e49523367f803461
[ROCm/clr commit: a98920d9a3]
Fix compile error.
Before this change, there is compile error in my build computer. The cause is that /opt/rocm/include has an older version of CL header files.
When compiling, we should use header files from this opencl source code folders first.
This fix changes the order of include directories. Search the header files inside this opencl source code folders first.
Change-Id: I3420a634ed9e1b38b8e5201a0a39a36d61f97986
[ROCm/clr commit: a400051d3a]
When libamdhip64_static.a is built by Jenkin, sample square cannot been
built successfully because libamdhip64_static.a is archiveved in thin
mode. Thus in the patch it will be archiveved in full mode. Meanwhile
libamdhip64_static_temp.a will be useless and thus removed.
Change-Id: Ifd3882598ef0dc5e7af8db0e389e786025ceb455
[ROCm/clr commit: 51b6c1856c]
Use standard cmake option handling, and switch to standard ON/OFF for
boolean. Try to maintain compatability with the "yes" check that build
scripts are now using.
Change-Id: Ia932e93f818c0897a87bfc49b070e36c7be7dd74
[ROCm/clr commit: aa0c163066]
This points to the cmake directory where the find module was found,
not a prefix for where it was found.
Based on the search below looking in roctracer, searching in ROCclr
for the header doesn't make much sense. The header should be either
provided by ROCclr xor roctracer. Having it possibly be provided by
two different dependencies is confusing, and a potential source of
version mismatch problems.
Change-Id: Ic2f6ec03f9a7b86225cf7e5c43f39a1360318a34
[ROCm/clr commit: 1003128925]
Currently the opencl build hardcodes the path and directly includes
amdvdi_staticTargets.cmake. The proper way to find this is through
find_package, so start exporting the expected format.
Change-Id: Ic960a2dd467d57867cb96ab831dbd85bca336535
[ROCm/clr commit: 8988f34935]
If the start and stop events have same command internally
then measure command end to command start
Change-Id: Ie70cfa37c06c06573f0ed58dab2bbe4434c1724b
[ROCm/clr commit: fe9aa9356b]
Optimization for the fence release removed a sync for mem fill.
Add simple const buffer management forr the filled pattern to avoid
pattern overwriting with the async fills.
Change-Id: I63773ac09ceec31d5396d24570e4647ff096326b
[ROCm/clr commit: 2ce6bbebc4]
These are unnecessary and an obstacle to producing a relocatable
package.
Change-Id: I0059bf7a2d11fcece0cd7ab47d7545d0df4d7099
[ROCm/clr commit: 1d267c9c08]
7eda01ba broke this. This is still mostly a commit order hack until
the ROCclr change is submitted.
Change-Id: I43762963dbc66f1dc83916d2f0e9c90e4fcbf7c1
[ROCm/clr commit: 9f9d35ad86]
Evgeny
Chauncey Hui
kjayapra-amd
Dittakavi Satyanvesh
Mahesha Shivamallappa
Matt Arsenault
Vlad Sytchenko
Alex Xie
Tao Sang
Aryan Salmanpour
Laurent Morichetti
Sarbojit Sarkar
Saleel Kudchadker
German Andryeyev
Aakash Sudhanwa
Jason Tang
agodavar
Ramesh Errabolu
Christophe Paquot