| Age | Commit message (Collapse) | Author |
|
|
|
behave correctly
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pointer
cuda-sim.cc: counts matches between cudaBinTextureToArray texref param (pointer)
to texref pointers in m_NameToTextureRef
|
|
|
|
right one
|
|
|
|
Support for ld operand in register space
Approved-by: tgrogers-purdue <[email protected]>
|
|
Support for -gpgpu_registers_per_block and addition of -save_embedded_ptx 1 to config files for mnistCUDNN
Approved-by: tgrogers-purdue <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Adding support for additional device attributes in cudaDeviceGetAttributes function for mnistCUDNN
|
|
|
|
|
|
|
|
|
|
|
|
normal operation. This helps immensely in a clustered environmrnt where jobs randomly fail
|
|
|
|
|
|
|
|
happen, something bad has happened
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
causes ridiculous output file sizes
|
|
to crash
this still fails regressions
|
|
am stopping this by gaurding against it in the same way we do for updating the stat counts (checking if we have executed any cycles before printing). I am not sure what this does to CDP stat prints - as I am not sure what CDP kernels so to sim_cycles.... However EVERY other app except CDP is spewing junk to the output and it really messes up any per-kernel stat collection scripts.
|
|
|
|
|
|
|
|
|
|
|