From b400820185db543ff98fd823a15958444e12fee6 Mon Sep 17 00:00:00 2001 From: Tor Aamodt Date: Sun, 8 Aug 2010 21:15:00 -0800 Subject: ** 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] --- src/gpgpu-sim/gpu-sim.h | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) (limited to 'src/gpgpu-sim/gpu-sim.h') diff --git a/src/gpgpu-sim/gpu-sim.h b/src/gpgpu-sim/gpu-sim.h index 27d83ad..2e9794f 100644 --- a/src/gpgpu-sim/gpu-sim.h +++ b/src/gpgpu-sim/gpu-sim.h @@ -66,16 +66,6 @@ * Vancouver, BC V6T 1Z4 */ -#include -#include -#include -#include "zlib.h" - -#include "../option_parser.h" -#include "shader.h" -#include "dram.h" -#include "mem_fetch.h" - #ifndef GPU_SIM_H #define GPU_SIM_H @@ -113,5 +103,8 @@ int mem_ctrl_full( int mc_id ); void dramqueue_latency_log_dump(); void dump_pipeline_impl( int mask, int s, int m ); +unsigned int run_gpu_sim(int grid_num); +extern void gpu_reg_options(class OptionParser * opp); +extern void init_gpu(); #endif -- cgit v1.3