1. refactoring cuda api code for loading PTX (removing external PTX loading entirely)

2. some bug fixes for warp_inst_t
3. creating a new class, gpgpu_t, which contains the functional "memory" state visible
   to all threads running on a GPU (doing this as part of my continuing effort to hunt 
   down and eradicate every global variable that is not the top level "the gpu")
4. other misc. changes

Almost passing CUDA 3.1 regression?  oclHistogram keeps failing under torque, but
does not fail when run on the command line from the same directory.

[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 7827]

1 files changed, 2 insertions, 2 deletions

diff --git a/src/gpgpusim_entrypoint.h b/src/gpgpusim_entrypoint.h
index f77a906..689dcf9 100644
--- a/src/gpgpusim_entrypoint.h
+++ b/src/gpgpusim_entrypoint.h
@@ -77,12 +77,12 @@ int gpgpu_cuda_ptx_sim_main_perf( kernel_info_t grid,
                                    struct dim3 blockDim, 
                                    gpgpu_ptx_sim_arg_list_t grid_params );
 
-int gpgpu_opencl_ptx_sim_main_perf( class function_info *entry, 
+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( class function_info *entry, 
+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 );