| Age | Commit message (Collapse) | Author |
|
Signed-off-by: Mengchi Zhang <[email protected]>
|
|
|
|
|
|
|
|
uniform
|
|
dev-purdue-integration
|
|
causes ridiculous output file sizes
|
|
|
|
|
|
|
|
https://github.rcac.purdue.edu/abdallm/gpgpu-sim_distribution into dev-purdue-integration
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
interaction
|
|
|
|
|
|
|
|
truncating the address here fixes the issue and we start propoerly hitting in the L2
|
|
|
|
with the new hack and incrementing the cycle so that cudamemcopies take some time (if we don't do this the LRU in the cache does not work)
|
|
|
|
|
|
|
|
|
|
1- REEAD/WERITE buffer for DRAM
2- Fixing FETCH_ON_WRITE cahce policy bug
|
|
|
|
|
|
https://github.rcac.purdue.edu/abdallm/gpgpu-sim_distribution into dev-purdue-integration
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1- round robin inst issue for warp multiple schedulers
2- add sector mask in the memory request (to bused later for L2 sector cache)
3- Adding Fermi coalescer
4- Ensure different exen units are used in dual_issue mode
5- Report how many dual_issue happened
6- Adding oldest_first scheduler
|
|
|
|
|
|
memory mapping, turn off by default
|
|
|
|
|