| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2018-04-01 | Merge branch 'dev-purdue-integration' into dev-purdue-integration | Akshay Jain | |
| 2018-03-31 | Merge commit '89db73061e043c26df22c7f18d9adb106d8078ac' into ↵ | tgrogers | |
| dev-purdue-integration | |||
| 2018-03-31 | Getting rid of our constant, annoying prints. Running workloads of any size ↵ | tgrogers | |
| causes ridiculous output file sizes | |||
| 2018-03-30 | fixing gpu-tot-cycle bug | Mahmoud | |
| 2018-03-28 | Fixing a minor typo in an old config | tgrogers | |
| 2018-03-28 | adding new stats counter | Mahmoud | |
| 2018-03-28 | Merge branch 'dev-purdue-integration' of ↵ | Mahmoud | |
| https://github.rcac.purdue.edu/abdallm/gpgpu-sim_distribution into dev-purdue-integration | |||
| 2018-03-28 | adding new counters for parition level para and L2 BW | Mahmoud | |
| 2018-03-27 | Merge branch 'dev-purdue-integration' into dev-purdue-integration | Timothy G Rogers | |
| 2018-03-26 | Provide portable (non-x86) breakpoint method which should work on all ↵ | Nathan Conrad | |
| linuxes. Tested on PowerPC. | |||
| 2018-03-26 | Merge branch 'dev-purdue-integration' into dev-purdue-integration | Timothy G Rogers | |
| 2018-03-26 | Fixing resources limitation assertion for compute cab 61 | Mahmoud | |
| 2018-03-25 | Need to make sure we don't kill the L1 too | tgrogers | |
| 2018-03-22 | Change 332 by jain156@akshayj-lt1 on 2018/02/01 05:20:33 | Akshay Jain | |
| Added shmem_divergence_hist and warp_inst_classification | |||
| 2018-03-22 | Change 283 by jain156@akshayj-lt1 on 2017/07/03 19:52:55 | Akshay Jain | |
| Adding the global load and store divergence statistics. The previous histogram has been modified to look at all memory requests, but that is not meaningful - so it can as well be removed. | |||
| 2018-03-22 | Change 257 by jain156@akshayj-lt1 on 2017/06/03 16:32:52 | Akshay Jain | |
| Adding gpuwattch power stats to the output. Enabled inst and mem breakdown stats in config file. | |||
| 2018-03-22 | Change 253 by jain156@akshayj-lt1 on 2017/05/30 00:40:03 | Akshay Jain | |
| Replaced the mem div stats with mem div histogram | |||
| 2018-03-22 | Change 252 by jain156@akshayj-lt1 on 2017/05/29 10:51:32 | Akshay Jain | |
| 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 | |||
| 2018-03-22 | Change 180 by jain156@akshayj-lt1 on 2017/03/30 11:48:07 | Akshay Jain | |
| Added Memory Access breakdown statistics. Divided INST stats into INST type and INST Mem accesses. | |||
| 2018-03-21 | Change 124 by jain156@akshayj-lt1 on 2016/12/08 20:17:53 | Akshay Jain | |
| Added Memory divergence stats Data shows same divergence characteristics across PTX and PTX+ | |||
| 2018-03-12 | fixibg sectir l1 deadlock bug | Mahmoud | |
| 2017-11-19 | Doing lazy fetch-on-read policy | Mahmoud | |
| 2017-11-18 | removing another assert | tgrogers | |
| 2017-11-18 | Getting rid of another assert that crops up cause of our memcpy and L2 ↵ | tgrogers | |
| interaction | |||
| 2017-11-18 | copy to the L2 by default | tgrogers | |
| 2017-11-18 | fixing the cycle issues with using the cudamemcpies | tgrogers | |
| 2017-11-18 | Adding a subpartion trace to help in figuring out what the hell is going on | tgrogers | |
| 2017-11-18 | 64-address used on the CPU side, but GPGPU-Sim Truncates it to 32-bit.... ↵ | tgrogers | |
| truncating the address here fixes the issue and we start propoerly hitting in the L2 | |||
| 2017-11-18 | fixing a stupid inheritance bug | tgrogers | |
| 2017-11-18 | Making the perf sim copy optional, getting rid of an assert that will happen ↵ | tgrogers | |
| 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) | |||
| 2017-11-18 | vectoradd is successfully filling the l2 | tgrogers | |
| 2017-10-30 | adding new stats and change the PascalP100-HBM config | Mahmoud | |
| 2017-10-27 | add more statistics and chaging Pascal config | Mahmoud | |
| 2017-10-26 | Changing the Titan X config file to use the last modifications | Mahmoud | |
| 2017-10-25 | The commits includes: | Mahmoud | |
| 1- REEAD/WERITE buffer for DRAM 2- Fixing FETCH_ON_WRITE cahce policy bug | |||
| 2017-10-13 | ensure that first launch uses simt cluster 0 | Mahmoud | |
| 2017-10-12 | remove Tex cache assertion and prevent spunit to execute DP insts | Mahmoud | |
| 2017-10-11 | Merge branch 'dev-purdue-integration' of ↵ | Mahmoud | |
| https://github.rcac.purdue.edu/abdallm/gpgpu-sim_distribution into dev-purdue-integration | |||
| 2017-10-11 | Sector Cache - first commit | Mahmoud | |
| 2017-10-11 | Fixing deadlock because of dp_unit (2) | Mahmoud Khairy A. Abdallah | |
| 2017-10-11 | Fixing deadlock because of dp_unit | Mahmoud Khairy A. Abdallah | |
| 2017-09-14 | adding some condig comments | Mahmoud | |
| 2017-09-14 | changing the DRAM bank indexing policy | Mahmoud | |
| 2017-09-13 | Adding sperate dp_unit | Mahmoud | |
| 2017-09-13 | Fixing some typos | Mahmoud | |
| 2017-09-12 | Adding HBM model | Mahmoud | |
| 2017-08-17 | Merged all work on the dev branch since the divergence point into the dnn ↵ | speverel | |
| branch, incorporating Dynamic Parallelism and many bug fixes. | |||
| 2017-07-20 | Fixing BankGroup Indexing Bug | Mahmoud | |
| 2017-07-18 | Fixing deadlock bug | Mahmoud | |
| 2017-07-17 | Fixing some typos and adding comments | Mahmoud | |
