summaryrefslogtreecommitdiff
path: root/src/gpgpusim_entrypoint.h
diff options
context:
space:
mode:
authorTor Aamodt <[email protected]>2010-12-28 14:09:12 -0800
committerTor Aamodt <[email protected]>2010-12-28 14:09:12 -0800
commite7b3dd442fceb30eaa8008d97429a1d33dad2044 (patch)
tree3f1a9da5de24518bc9859283d46e8e83614e668c /src/gpgpusim_entrypoint.h
parentd864c51b9fee6b2808e4752a556d6de4ba376b7c (diff)
- Checkpointing new support for concurrent kernel execution (CUDA only, not OpenCL)
This changelist adds full support for streams supported by a new class, stream_manager and enables concurrent execution of kernels from different streams. - fast_regression.sh fails for simpleMultiCopy, simpleStreams (other tests passing) ** Known issues ** - Kernel parameter passing is not done correctly for concurrent kernel execution (somehow concurrentKernels is not affected by this): the parameters are stored inside function_info, which is shared among parallel kernel launches so that the values passed into the launch are likely to get overwritten if multiple grids are launched in parallel streams. - Statistics are printed out whenever the simulation thread runs out of cuda commands (doesn't make sense to print out when a kernel ends during concurrent kernel execution). This will probably require further tweaking so as to be more compatible with data collection scripts. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 8302]
Diffstat (limited to 'src/gpgpusim_entrypoint.h')
-rw-r--r--src/gpgpusim_entrypoint.h17
1 files changed, 4 insertions, 13 deletions
diff --git a/src/gpgpusim_entrypoint.h b/src/gpgpusim_entrypoint.h
index 689dcf9..b310752 100644
--- a/src/gpgpusim_entrypoint.h
+++ b/src/gpgpusim_entrypoint.h
@@ -71,19 +71,10 @@
extern time_t g_simulation_starttime;
class gpgpu_sim *gpgpu_ptx_sim_init_perf();
+void start_sim_thread(int api);
-int gpgpu_cuda_ptx_sim_main_perf( kernel_info_t grid,
- struct dim3 gridDim,
- struct dim3 blockDim,
- gpgpu_ptx_sim_arg_list_t grid_params );
+int gpgpu_cuda_ptx_sim_main_perf( kernel_info_t grid );
+int gpgpu_opencl_ptx_sim_main_perf( kernel_info_t grid );
+int gpgpu_opencl_ptx_sim_main_func( kernel_info_t grid );
-int gpgpu_opencl_ptx_sim_main_perf( kernel_info_t grid,
- struct dim3 gridDim,
- struct dim3 blockDim,
- gpgpu_ptx_sim_arg_list_t grid_params );
-
-int gpgpu_opencl_ptx_sim_main_func( kernel_info_t grid,
- struct dim3 gridDim,
- struct dim3 blockDim,
- gpgpu_ptx_sim_arg_list_t grid_params );
#endif