From e7b3dd442fceb30eaa8008d97429a1d33dad2044 Mon Sep 17 00:00:00 2001 From: Tor Aamodt Date: Tue, 28 Dec 2010 14:09:12 -0800 Subject: - 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] --- src/cuda-sim/cuda-sim.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/cuda-sim/cuda-sim.h') diff --git a/src/cuda-sim/cuda-sim.h b/src/cuda-sim/cuda-sim.h index e7c1965..ef045fb 100644 --- a/src/cuda-sim/cuda-sim.h +++ b/src/cuda-sim/cuda-sim.h @@ -25,7 +25,7 @@ extern class kernel_info_t gpgpu_opencl_ptx_sim_init_grid(class function_info *e struct dim3 gridDim, struct dim3 blockDim, class gpgpu_t *gpu ); -extern void gpgpu_cuda_ptx_sim_main_func( kernel_info_t kernel, dim3 gridDim, dim3 blockDim, gpgpu_ptx_sim_arg_list_t args); +extern void gpgpu_cuda_ptx_sim_main_func( kernel_info_t kernel ); extern void print_splash(); extern void gpgpu_ptx_sim_register_const_variable(void*, const char *deviceName, size_t size ); extern void gpgpu_ptx_sim_register_global_variable(void *hostVar, const char *deviceName, size_t size ); -- cgit v1.3