summaryrefslogtreecommitdiff
path: root/src/gpgpusim_entrypoint.h
diff options
context:
space:
mode:
authorTor Aamodt <[email protected]>2010-08-08 21:15:00 -0800
committerTor Aamodt <[email protected]>2010-08-08 21:15:00 -0800
commitb400820185db543ff98fd823a15958444e12fee6 (patch)
treefc72d4bf6364da371db434849a78022ca81803fc /src/gpgpusim_entrypoint.h
parentb26dda933fe84d54cad47762ae80be3acdfda91b (diff)
** fully decouple kernel compilation from kernel launch for opencl
changes required to do this (this enables oclReduction SDK 3.1 to pass and is a prerequisite to Fermi style concurrent kernel launching) - separate kernel launch for cuda and opencl (and init_grid functions) - add pgm_info structure for holding kernel function_info pointer in _cl_program object after ptx compilation ** added support for clEnqueueNDRangeKernel with local_work_size==NULL which is part of OpenCL spec and used in oclSortingNetworks (however, this is a braindead implementation that only handles the case where global_work_size[0] is smaller than the max number of threads per shader; moreover oclSortingNetworks is still not working but for what looks like another reason) ** refactoring / cleanup - g_global_symbol_table made static to ptx_parser.cc - remove g_kernel_name_to_symtab_lookup (not really being used) - moving various function prototypes into headers (e.g., if foo() defined in bar.cc, then place prototype in bar.h) - adding icnt_reg_options() [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 7168]
Diffstat (limited to 'src/gpgpusim_entrypoint.h')
-rw-r--r--src/gpgpusim_entrypoint.h18
1 files changed, 17 insertions, 1 deletions
diff --git a/src/gpgpusim_entrypoint.h b/src/gpgpusim_entrypoint.h
index 8de05c7..2563c5e 100644
--- a/src/gpgpusim_entrypoint.h
+++ b/src/gpgpusim_entrypoint.h
@@ -67,7 +67,23 @@
#include "abstract_hardware_model.h"
+#include <time.h>
+extern time_t g_simulation_starttime;
+
void gpgpu_ptx_sim_init_perf();
-int gpgpu_ptx_sim_main_perf( const char *kernel_key, struct dim3 gridDim, struct dim3 blockDim, struct gpgpu_ptx_sim_arg *grid_params );
+int gpgpu_cuda_ptx_sim_main_perf( const char *kernel_key,
+ struct dim3 gridDim,
+ struct dim3 blockDim,
+ struct gpgpu_ptx_sim_arg *grid_params );
+
+int gpgpu_opencl_ptx_sim_main_perf( class function_info *entry,
+ struct dim3 gridDim,
+ struct dim3 blockDim,
+ struct gpgpu_ptx_sim_arg *grid_params );
+
+int gpgpu_opencl_ptx_sim_main_func( class function_info *entry,
+ struct dim3 gridDim,
+ struct dim3 blockDim,
+ struct gpgpu_ptx_sim_arg *grid_params );
#endif