| Age | Commit message (Collapse) | Author |
|
Signed-off-by: Mengchi Zhang <[email protected]>
|
|
Move GPGPU-Sim to no reentrant
|
|
Signed-off-by: Mengchi Zhang <[email protected]>
|
|
Signed-off-by: Mengchi Zhang <[email protected]>
|
|
Signed-off-by: Mengchi Zhang <[email protected]>
|
|
Signed-off-by: Mengchi Zhang <[email protected]>
|
|
Signed-off-by: Mengchi Zhang <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Adding comment to describe the issue resolved by the previous commit related to cudaStreamDestroy.
|
|
Update cudaStreamDestroy's functionality to synchronize before destroying streams.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
stuck in deadlock
|
|
|
|
|
|
libcuda: removed comment from cuobjdump.l
|
|
Changes to allow correct occupancy with newer cards, while still running PTXPlus
|
|
This comment made the build fail in ubuntu 18.04 due to a flex error. This error is probably produced by a flex bug.
|
|
|
|
cuDeviceGetAttribute; cuGetExportTable and cuDeviceTotalMem has dummy values
|
|
|
|
|
|
culaunchkernel
|
|
|
|
|
|
|
|
failing system calls
|
|
Fixed bug with 32bit rem
Fixed bug with launching kernels in ptxjitplus
Removed extraneous files
Cleaned up more pointers
Added documentation for ptxjitplus
|
|
when running ptxjit
|
|
|
|
|
|
|
|
|