| Age | Commit message (Collapse) | Author |
|---|
|
* add automated clang formatter
* Automated clang-format
* use /bin/bash and add print
* use default checkout ref
* Format only after tests are success
* Run CI on merge group
---------
Co-authored-by: barnes88 <[email protected]>
Co-authored-by: JRPAN <[email protected]>
|
|
* remove implicit casting, cleanup unused bank_warp_shift parameter
* update cu init function prototype
* remove m_bank_warp_shift from function call
|
|
|
|
LDGSTS/LDGDEPBAR was introduced #62, but it's increment part was deleted
by mistake. So add it.
In some applications, ldgsts may not exist between ldgdepbar. In
such cases, add exception handling logic to insert an empty vector.
Reported-by: Okkyun Woo <[email protected]>
Signed-off-by: Wonhyuk Yang <[email protected]>
|
|
CMAKE_BUILD_TYPE should be inside ${}
|
|
|
|
|
|
* migrate_cmake: add package dependency checking
* migrate_cmake: port setup_environment to CMake
* migrate_cmake: break dependency checking and env export gen to different .cmake files
* migrate_cmake: use CUDAToolkit_FOUND to test for CUDA compiler
* migrate_cmake: use CUDAToolkit_FOUND to test for CUDA compiler
* migrate_cmake: use CUDAToolkit_FOUND to test for CUDA compiler
* migrate_cmake: properly parse for cuda version number
* migrate_cmake: set highest CUDA supported to be 11.10.x
* migrate_cmake: specify top level CMake file
* migrate_cmake: add libcuda cmake file
* migrate_cmake: use global compiler options and definitions
* migrate_cmake: add cmake file to src
* migrate_cmake: add cmake files for cuda-sim folder
* migrate_cmake: add cmake files to gpgpu-sim folder
* migrate_cmake: add cmake files for intersim
* migrate_cmake: add short test using cmake
* migrate_cmake: bump CXX standard requirement to 17
* Add cmake files for accelwattch
* migrate_cmake: remove use of GLOB to grab source files
* migrate_cmake: comment out the write protection on generated instructions.h
* migrate_cmake: create sym folder and add newline to generated setup file
* migrate_cmake: fix some path issues
* migrate_cmake: let cmake thinks flex and bison generate CXX files
* migrate_cmake: fix not linking pthread properly
* migrate_cmake: remove debug message
* migrate_cmake: add empty libopencl cmake file
* migrate_cmake: install phase and runtime version detect
* Added install phase to install the shared object
and add symlinks
* Changes with CUDA toolkit will be detected and
triggered a rebuild
* GPGPU-Sim detailed version string will be updated
on each build
* Typo fix and fix correct bin dir
* Replace gcc -> g++ in intersim
* ignore setup
* check CMAKE_BUILD_TYPE
* set DCMAKE_BUILD_TYPE
---------
Co-authored-by: JRPAN <[email protected]>
|
|
Adding a non-zero return on error
|
|
|
|
rename ci tests
|
|
|
|
Adding GitHub CI
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Update gpgpusim.config
|
|
|
|
|
|
Fixed an outdated comment line
|
|
|
|
shared mem bank conflicts
|
|
|
|
|
|
|
|
|
|
|
|
Compare warnings
|
|
|
|
|
|
|
|
Addresses accel-sim issue 137. For sector cache, the sector size must be 32B (hard-coded and not configurable) and cache line size must be set to 128B; a runtime parameter check will terminate simulation if the cache line size is not 128B.
|
|
|
|
Revert QV100 config and add GV100 config
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
anyway, it should fix warning in done() fun
|
|
* fixing bunch of formating warrnings
* remove unintialized and unused results warnnings
* revert the changes , as it doenst fix the warning
---------
Co-authored-by: Fangjia Shen <[email protected]>
|
|
|
|
|
