| Age | Commit message (Collapse) | Author |
|
|
|
|
|
|
|
|
|
|
|
|
|
into dev-traces
|
|
|
|
|
|
|
|
|
|
|
|
|
|
This reverts commit 9c9b1341613e767f306b2b73b5b8a5317b6ee563.
|
|
This reverts commit ca563ea85ead434e0d579026b5e66e829af5efe5.
|
|
|
|
|
|
into dev-traces
|
|
|
|
|
|
|
|
into dev-private
|
|
|
|
|
|
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]>
|
|
Signed-off-by: Mengchi Zhang <[email protected]>
|
|
Signed-off-by: Mengchi Zhang <[email protected]>
|
|
|
|
|
|
|
|
into dev
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Checking in the data footprint stats as reported in the micro paper.
The implementation uses gpgpu pointer, due to which I don't feel fine pushing to mainline.
May be I can do the stats check and increment in l2cache.cc through a public function
to avoid exposing gpgpu pointer to public
|
|
|
|
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)
|
|
|
|
|
|
|