diff options
| author | Ayub Gubran <[email protected]> | 2013-04-20 16:19:21 -0800 |
|---|---|---|
| committer | Andrew Boktor <[email protected]> | 2014-08-14 13:50:47 -0700 |
| commit | cd7a97f045cb9bf33fcb9b8bb7b9d1e3ff5caca2 (patch) | |
| tree | 165da75f4b4b1144e30321ee25d217b4c4191a14 | |
| parent | 12ed0d7358d6f43e9de0a677ba5541ea57042a89 (diff) | |
Restoring the functional simulation entry function for OpenCL, which was undone in CL 12023 probably by mistake.
Reveiw ID: 17001
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15885]
| -rw-r--r-- | CHANGES | 1 | ||||
| -rw-r--r-- | src/gpgpusim_entrypoint.cc | 11 |
2 files changed, 10 insertions, 2 deletions
@@ -23,6 +23,7 @@ Version 3.2.1+edits (development branch) versus 3.2.1 warning message display - Removed a spamming print at kernel finish that dumped a warp issuing histogram. + - Fixing OpenCL functional simulation. Now the functional simulation routine is called instead of mistakenly printing that the functional simulation is not implemented. Version 3.2.1 versus 3.2.0 - Added kernel name and launch uids to performance statistics log. - Added l2_cache_config class to extend baseline cache_config. Allows for diff --git a/src/gpgpusim_entrypoint.cc b/src/gpgpusim_entrypoint.cc index f19537b..9999bb1 100644 --- a/src/gpgpusim_entrypoint.cc +++ b/src/gpgpusim_entrypoint.cc @@ -244,8 +244,15 @@ int gpgpu_opencl_ptx_sim_main_perf( kernel_info_t *grid ) return 0; } +//! Functional simulation of OpenCL +/*! + * This function call the CUDA PTX functional simulator + */ int gpgpu_opencl_ptx_sim_main_func( kernel_info_t *grid ) { - printf("GPGPU-Sim PTX API: OpenCL functional-only simulation not yet implemented (use performance simulation)\n"); - exit(1); + //calling the CUDA PTX simulator, sending the kernel by reference and a flag set to true, + //the flag used by the function to distinguish OpenCL calls from the CUDA simulation calls which + //it is needed by the called function to not register the exit the exit of OpenCL kernel as it doesn't register entering in the first place as the CUDA kernels does + gpgpu_cuda_ptx_sim_main_func( *grid, true ); + return 0; } |
