This makes hipLaunchKernelGGL take a variable argument list, that will be
expanded before being fed to hipLaunchKernelGGLInternal.
This is different from 4dfef9a25b.
We try to accomodate the case when a kernel template has multiple
type parameters.
Change-Id: I87577d402c92b0f3b51e298f8293f4065e1f6de8
[ROCm/clr commit: 133251a6e1]
This makes hipLaunchKernelGGL take a variable argument list, that will be
expanded before being fed to hipLaunchKernelGGLInternal.
Change-Id: Id76e2bf91acd5d68f56a24fc39f219f2eeb06d33
[ROCm/clr commit: fb6bb04f03]
Let hipMalloc() be called in main() so that global variable can be initialized.
Change-Id: I9aa1f0a0bb4fa0825d10af0b58c843e7b928e9a3
[ROCm/clr commit: d27880ac39]
SWDEV-225266: [HIP-VDI] HIP-VDI disabled tests (p2p_copy_coherency.cpp)
SWDEV-225388: hipTestDeviceSymbol.cpp & hipTestConstant.cpp failed to build on hip-vdi
For hipTestDeviceSymbol.cpp & hipTestConstant.cpp tests:
Currently "__HIP_VDI__" flag is enabled in CMakeLists.txt, but when application is compiled with hipcc,
__HIP_VDI__ is not defined to differentiate if compiled for VDI/HCC for headers.
For ./src/runtimeApi/memory/p2p_copy_coherency.cpp:
Fixed compilation issue to include only when compile for HCC runtime "<hc_am.hpp> not found"
Currently test is disabled to run on all platforms. When validated on multi-GPU machine,
memcpy between multiple GPUs via GPU synchronization is not working on hcc and vdi path.
Need to validate on nvidia machine to know if test is valid. Disabled GPU synchronization test for now.
For ./src/runtimeApi/module/hipModuleTexture2dDrv.cpp:
updated test to generate tex2d_kernel.code object in build directory. Currently ctest looks for it in build directory.
Change-Id: I629d395a919c2440d921422716944c7940ed6010
[ROCm/clr commit: ae465bc338]
Temporarily comment out Hcc-specific template functions
hipExtLaunchKernelGGL and hipOccupancyMaxPotentialBlockSize for CLang
compiler so that all test cases under hip/samples can be built
successfully for Clang + Hip/Hcc runtime.
Change-Id: Iafc761257be4a7b34eafa6759a01f369570cd6ce
[ROCm/clr commit: 15b91e9f1e]
The current implementation skips this procedure for a given device
object when a global symbol is found in the cache. This is incorrect:
- There could be other undefined globals that have not been previously
encountered further down the list
- If a symbol is found in the cache, it doesn't need to be pinned again
but it still need to be defined for the current executable
Added special case for the printf buffer symbol (already pinned by HCC)
The bug was exposed by running printf on different GPUs.
[ROCm/clr commit: 8fc7cad90f]
* Removed unwanted #include sys/time.h , gettimeofday() and timeval variables and this also helps avavoid compilation error in windows due to gettimeofday() call equivalent of which is not available in windows
* Changed the Macro name from GPU_PRINT_TIME to MY_LAUNCH_MACRO
[ROCm/clr commit: 36977dc276]
- Uses c++11 features. Added it to nvcc options
- Arguments for some kernels exceeded 4096 bytes which is the limit
imposed by nvcc. Reduced BLOCK_DIM_SIZE to 512 to handle this
- Fixed compilation issues on nvcc path
Change-Id: I14f6b28afcb7c6b24a085fd707b2104e2ed64627
[ROCm/clr commit: 51307ac705]
Ronak Chauhan
Jatin
Tao Sang
Lad, Aditya
agodavar
Jatin Chaudhary
Nick Curtis
Payam
Laurent Morichetti
Siu Chi Chan
Alex Voicu
amd-lthakur
Maneesh Gupta
Yaxun Sam Liu
Srinivasuluch
rohit pathania
Phaneendr-kumar Lanka
Phaneendr-kumar Lanka
Ben Sander