| Age | Commit message (Collapse) | Author |
|---|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
guaranteed to fail in functional simulation only mode. Hopefully this shouldn't introduce any new issues.
|
|
branch, incorporating Dynamic Parallelism and many bug fixes.
|
|
|
|
|
|
updatet the built number output when we run gpgpu-sim we need to recompile cuda-sim everytime the detailed_version has changed
|
|
# and branch will be embedded in the built executable and print out when gpgpu-sim runs
|
|
The block containing predicate ret instruction should add the
consecutive block to its successor_ids set. next_addr should be assigned
with current instruction address add instruction size instead of 1.
Signed-off-by: Mengchi Zhang <[email protected]>
|
|
shfl instruction implemented
|
|
Initial support of CUDA Dynamic Parallelism on GPGPUSim
|
|
|
|
memory mapping, turn off by default
|
|
|
|
|
|
|
|
|
|
|
|
initiation_interval numbers for bsmad
|
|
|
|
|
|
|
|
to complete the TODOs noted in bsmad_impl
|
|
in its warp
|
|
|
|
Now, sst_impl doesn't functionally execute on the last indexed element of an array, but instead on the actual last thread that executes
|
|
sst_impl
|
|
|
|
|
|
of elements instead of the device memory address
|
|
|
