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.cc | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'src/cuda-sim/cuda-sim.cc') diff --git a/src/cuda-sim/cuda-sim.cc b/src/cuda-sim/cuda-sim.cc index 9b65c25..b6a15e8 100644 --- a/src/cuda-sim/cuda-sim.cc +++ b/src/cuda-sim/cuda-sim.cc @@ -1331,6 +1331,8 @@ int g_ptx_sim_mode; // if non-zero run functional simulation only (i.e., no noti extern "C" int ptx_debug; +bool g_cuda_launch_blocking = false; + void read_sim_environment_variables() { ptx_debug = 0; @@ -1375,7 +1377,12 @@ void read_sim_environment_variables() fflush(stdout); g_override_embedded_ptx = true; } + char *blocking = getenv("CUDA_LAUNCH_BLOCKING"); + if( blocking && !strcmp(blocking,"1") ) { + g_cuda_launch_blocking = true; + } #else + g_cuda_launch_blocking = true; g_override_embedded_ptx = true; #endif @@ -1388,7 +1395,7 @@ ptx_cta_info *g_func_cta_info = NULL; #define MAX(a,b) (((a)>(b))?(a):(b)) -void gpgpu_cuda_ptx_sim_main_func( kernel_info_t kernel, dim3 gridDim, dim3 blockDim, gpgpu_ptx_sim_arg_list_t args) +void gpgpu_cuda_ptx_sim_main_func( kernel_info_t kernel ) { printf("GPGPU-Sim: Performing Functional Simulation...\n"); -- cgit v1.3