summaryrefslogtreecommitdiff
path: root/src/gpgpu-sim/icnt_wrapper.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/gpgpu-sim/icnt_wrapper.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/gpgpu-sim/icnt_wrapper.h')
-rw-r--r--src/gpgpu-sim/icnt_wrapper.h10
1 files changed, 2 insertions, 8 deletions
diff --git a/src/gpgpu-sim/icnt_wrapper.h b/src/gpgpu-sim/icnt_wrapper.h
index 998a4f3..0961fc4 100644
--- a/src/gpgpu-sim/icnt_wrapper.h
+++ b/src/gpgpu-sim/icnt_wrapper.h
@@ -75,26 +75,20 @@ typedef void (*icnt_transfer_p)( );
typedef unsigned (*icnt_busy_p)( );
typedef void (*icnt_drain_p)( );
-
extern icnt_has_buffer_p icnt_has_buffer;
extern icnt_push_p icnt_push;
extern icnt_pop_p icnt_pop;
extern icnt_transfer_p icnt_transfer;
extern icnt_busy_p icnt_busy;
extern icnt_drain_p icnt_drain;
+extern int g_network_mode;
-/*
-// definition of valid gpu network mode.
-extern enum {
- INTERSIM = 1,
- N_NETWORK_MODE
-} gpu_network_mode;
-*/
enum network_mode {
INTERSIM = 1,
N_NETWORK_MODE
};
void icnt_init( unsigned int n_shader, unsigned int n_mem );
+void icnt_reg_options( class OptionParser * opp );
#endif