| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2018-07-30 | some changes to help get pytorch working | J | |
| 2018-07-25 | Merging conlicted travis line. Just use the new one. | tgrogers | |
| 2018-07-23 | brought back ptxinfo | Jonathan | |
| 2018-07-23 | Getting the regressions to pass by explicitly setting the CUDA version. The ↵ | tgrogers | |
| image now contains 2 CUDA versions and the default one is CUDA 9.1 | |||
| 2018-07-22 | added regression and debugged the failing testcase | aamir | |
| 2018-07-21 | adding the cutlass examples | aamir | |
| 2018-07-21 | merging the changes of cutlass on negar tensorcore branch | aamir | |
| 2018-07-20 | load param offsets with refactored code and look in middle of malloc'd area ↵ | J | |
| for pointer | |||
| 2018-07-18 | added c++filt that works better, param offset dumping, protection for ↵ | Jonathan | |
| failing system calls | |||
| 2018-07-16 | fp32 to fp16 and fp16 to fp32 cvt | Jonathan | |
| 2018-07-16 | fix pipline for tensor_core and change config | negargoli93 | |
| 2018-07-13 | Add more print statements to debug api calls | Jonathan | |
| Fixed bug with 32bit rem Fixed bug with launching kernels in ptxjitplus Removed extraneous files Cleaned up more pointers Added documentation for ptxjitplus | |||
| 2018-07-09 | fixed pointer bug in ptx jit and added support for executing ptxjitconfig ↵ | Jonathan | |
| when running ptxjit | |||
| 2018-07-09 | better launchkernels and more printouts for debugging | Jonathan | |
| 2018-07-04 | dumps ptx kernels and scripts to launch all kernels | Jonathan | |
| 2018-07-04 | dump and load block and grid size and launch | Jonathan | |
| 2018-07-03 | loading params works now | Jonathan | |
| 2018-07-03 | correctly load params | Jonathan | |
| 2018-07-03 | minor bug fix | Jonathan | |
| 2018-07-01 | Adding Pascal_TITANX config files | Mahmoud | |
| 2018-06-30 | Explicitly setting the env vars in the docker call | tgrogers | |
| 2018-06-30 | Explicitly calling out CUDA in the 480 build too | tgrogers | |
| 2018-06-30 | oops - you should set this if it does not exist, not the other way around... | tgrogers | |
| 2018-06-30 | oops | tgrogers | |
| 2018-06-30 | Explicitly saying what CUDA to use | tgrogers | |
| 2018-06-30 | use CUDA 9.1 | tgrogers | |
| 2018-06-30 | Adding in a check to not blow away the PTXAS variable if you already had it set | tgrogers | |
| 2018-06-30 | oops - need a yml list of envs | tgrogers | |
| 2018-06-30 | Adding the 9.2 option to the PASCAL config | tgrogers | |
| 2018-06-30 | Cleaning up the setup env message a bit and having the simulator properly ↵ | tgrogers | |
| dump to stderr on error | |||
| 2018-06-30 | Preventing bad git commit numbers from printing when you run setup_env from ↵ | tgrogers | |
| a dir that is not the gpgpusim_distr dir | |||
| 2018-06-30 | changing the flow s.t. you cannot compile the simulator with a different ↵ | tgrogers | |
| version of CUDA from the app. | |||
| 2018-06-29 | Fixing the PTXPLUS + new CUDA execution case. | tgrogers | |
| 2018-06-29 | dumps global using pointer, dump output from ptxjit to file | Jonathan | |
| 2018-06-29 | Allowing modern GPU configrations to properly run PTXPLUS. | tgrogers | |
| There are several problems with this: 1) To get proper occupancy, based on register file usage, you must querry ptxas with the sm version that corresponds to the register usage in the config file. To enable this, a new config option has been added that determines what sm version you pass to ptxas to compute reg-usage. This configuration option is always required in the gpgpusim.config file 2) If you are running PTXPLUS with a modern card (i.e. volta/pascal), you need ptxas from CUDA 9.1. However since PTXPLUS only supports sm_13 - you need a version of CUDA where cudaobjectdump supports sm_1x. This ended at CUDA 5 - and PTXPLUS requires CUDA 4.2. Therefore, to run PTXPLUS on a modern card, you need CUDA 4.2 + modern CUDA installed. To fascilitate this, a new envronment varaible is added and the setup envrionment script prints an appropraite warning if you are using a newer CUDA. We have tried to make this as fail-proof as possible - and die appropraitely when something is wrong. | |||
| 2018-06-29 | Whitespace edits - removing tabs - replacing with spaces | tgrogers | |
| 2018-06-29 | Adding a print to indicate which PTX version we are actually using | tgrogers | |
| 2018-06-28 | loads params | Jonathan | |
| 2018-06-28 | dumps pointers by accessing global memory | Jonathan | |
| 2018-06-28 | Tests to find conditions that a value is a pointer and new mallocPtr_Size | Jonathan | |
| 2018-06-27 | WIP dump params | Jonathan | |
| 2018-06-26 | gitignore | Jonathan | |
| 2018-06-26 | exports and imports param data in new debug tool: WatchYourStep | Jonathan | |
| 2018-06-22 | Merge pull request #72 from tgrogers/dev | Tim Rogers | |
| Getting the simulator to compile with older versions of g++ | |||
| 2018-06-22 | All required PTX JIT functions supported | Jonathan | |
| 2018-06-22 | No need to change the config file for adding tensor-core | negargoli | |
| 2018-06-21 | WIP adding support for PTX JIT and dumping params to cudaLaunches | Jonathan | |
| 2018-06-20 | Tensor core timing model | negargoli93 | |
| 2018-06-15 | memory partition indexing | Mahmoud | |
| 2018-06-14 | bfe bug fix | Jonathan | |
 |
index : weft | |
| CPEN 511 Project - Weft: Improving SIMD Utilization through MIMD-like Co-issue and Thread Compaction | Davit Grigoryan |
| aboutsummaryrefslogtreecommitdiff |