- 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]

2 files changed, 9 insertions, 2 deletions

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");
 
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 );