| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2020-05-23 | adding back titianC | Mahmoud | |
| 2020-05-23 | Merge branch 'dev' of https://github.com/purdue-aalp/gpgpu-sim_distribution ↵ | Mahmoud | |
| into dev-traces | |||
| 2020-05-22 | moving ISA def files to new folder | Mahmoud | |
| 2020-05-22 | code reformatting | Mahmoud | |
| 2020-05-21 | Merge pull request #178 from purdue-aalp/dev | Tor Aamodt | |
| Merging with the last few months of work at Purdue | |||
| 2020-05-20 | Merge branch 'dev-traces' of https://github.com/mkhairy/gpgpu-sim-traces ↵ | Mahmoud | |
| into dev-traces | |||
| 2020-05-20 | rmoving repeated line | Mahmoud | |
| 2020-05-18 | fixing some failing apps | Mahmoud Khairy A. Abdallah | |
| 2020-04-21 | some additional changes descriptions | tgrogers | |
| 2020-04-21 | Small change from the auto-formatter | tgrogers | |
| 2020-04-09 | another line deleted due to format check | tgrogers | |
| 2020-04-09 | for now commenting out the format check since it seems to fail. | tgrogers | |
| 2020-04-09 | Missed a line in the merge that was causing livelock on the asyncAPI app | tgrogers | |
| 2020-04-09 | Update README | 유용환 | |
| fix PATH (append to original path) | |||
| 2020-04-07 | Merge remote-tracking branch 'localpub/dev' into dev | tgrogers | |
| 2020-04-06 | A simple sciprt to clang-format the code | Tim Rogers | |
| 2020-04-02 | updating the turing config | Mahmoud Khairy A. Abdallah | |
| 2020-04-02 | updating config files | Mahmoud Khairy A. Abdallah | |
| 2020-03-31 | fixing the tensor unit failing | Mahmoud Khairy A. Abdallah | |
| 2020-03-31 | adding new comments | Mahmoud Khairy A. Abdallah | |
| 2020-03-31 | fixing the RF assertion | Mahmoud Khairy A. Abdallah | |
| 2020-03-31 | adding some RF stats | Mahmoud Khairy A. Abdallah | |
| 2020-03-31 | adding inst fetch throughput | Mahmoud Khairy A. Abdallah | |
| 2020-03-26 | increase inst fetch thoughput | Mahmoud Khairy A. Abdallah | |
| 2020-03-26 | fixing core fetch bw | Mahmoud Khairy A. Abdallah | |
| 2020-02-27 | Merge pull request #137 from gangmul12/deadlock_fix | Tor Aamodt | |
| Deadlock fix from stream_manager | |||
| 2020-02-13 | fixing pascal | Mahmoud Khairy A. Abdallah | |
| 2020-02-10 | removing assertion in random hashing | Mahmoud Khairy A. Abdallah | |
| 2020-02-10 | fixing the kepler stats | Mahmoud Khairy A. Abdallah | |
| 2020-02-10 | fixing kepler load in sass | Mahmoud Khairy A. Abdallah | |
| 2020-02-09 | adding missing kepler insts | Mahmoud Khairy A. Abdallah | |
| 2020-02-09 | adding kepler sass, skip-first-kernel and update config file | Mahmoud Khairy A. Abdallah | |
| 2020-01-08 | fixing the memcpy assertion | Mahmoud | |
| 2020-01-06 | fixing the dram read/write count | Mahmoud | |
| 2019-12-25 | adding memcpy traces | Mahmoud | |
| 2019-11-21 | adding pascal code and fixing atomic bug | Mahmoud | |
| 2019-11-21 | fixing the access alignment in trace-driven mode | Mahmoud | |
| 2019-11-20 | fixing atomic bug in trace-driven mode | Mahmoud | |
| 2019-11-15 | invalidate l1 cache at membar - fixing | Mahmoud | |
| 2019-11-15 | invalidate l1 cache at membar | Mahmoud | |
| 2019-11-15 | adding some comments | Mahmoud | |
| 2019-11-15 | fixing memory width bug in trace-driven mode | Mahmoud | |
| 2019-11-14 | fixing the missing instruction bug in trace-driven mode | Mahmoud | |
| 2019-11-12 | Merge pull request #156 from bftf/dev | Tor Aamodt | |
| Enabled CUDA 10. Added implementations for __cudaPushCallConfiguratio… | |||
| 2019-11-12 | Updated the ifdef flag which enables/disables the relevant code blocks for ↵ | bftf | |
| cuda 10; while assuring backwards compatibility for older cuda versions | |||
| 2019-11-12 | handling the atomics in trace-driven and add the missing two instructions of ↵ | Mahmoud | |
| Nvbits | |||
| 2019-11-12 | updating SASS config for tensor cores | Mahmoud | |
| 2019-11-11 | adding special cases for traces | Mahmoud | |
| 2019-11-11 | Enabled CUDA 10. Added implementations for __cudaPushCallConfiguration and ↵ | bftf | |
| __cudaPopCallConfiguration, neither of which are documented in the CUDA API but they preceed any cudaLaunchKernel() call and push the call configuration on a stack which is then popped when cudaLaunchKernel() is called. Currently the max stack size is 1, an assert will be triggered when this is violated. | |||
| 2019-10-25 | Merge pull request #33 from rgreen/max_cta | Roland Green | |
| Add a new config option to cap the max number of completed CTAs | |||
