This changelist implements the following:

1. Adds support for using cuobjdump for both ptx and ptxplus execution. This has been tested with CUDA 4.0
  . Ptxplus is no longer supported through decuda/decuda_to_ptxplus
2. Adds support for converting the SASS output by cuobjdump to ptxplus. This has been tested with CUDA 4.0
  . The old path that extracts ptx from cubin files is still preserved
3. Adds a bank group model. (WARNING: memory config has changed, please adapt yours). To disable the bank groups model, set nbkgrp to 1 and tCCDL and tRTPL to 0

Diff the configuration files to learn about how to use those new options.

Merging

//depot/gpgpu_sim_research/fermi-test/distribution/...

to //depot/gpgpu_sim_research/fermi/distribution/...

[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12023]

1 files changed, 2 insertions, 9 deletions

diff --git a/src/gpgpusim_entrypoint.cc b/src/gpgpusim_entrypoint.cc
index e18b088..add9a22 100644
--- a/src/gpgpusim_entrypoint.cc
+++ b/src/gpgpusim_entrypoint.cc
@@ -238,15 +238,8 @@ int gpgpu_opencl_ptx_sim_main_perf( kernel_info_t *grid )
    return 0;
 }
 
-//! Functional simulation of OpenCL
-/*!
- * This function call the CUDA PTX functional simulator
- */
 int gpgpu_opencl_ptx_sim_main_func( kernel_info_t *grid )
 {
-    //calling the CUDA PTX simulator, sending the kernel by reference and a flag set to true,
-    //the flag used by the function to distinguish OpenCL calls from the CUDA simulation calls which
-    //it is needed by the called function to not register the exit the exit of OpenCL kernel as it doesn't register entering in the first place as the CUDA kernels does
-   gpgpu_cuda_ptx_sim_main_func( *grid, true );
-   return 0;
+   printf("GPGPU-Sim PTX API: OpenCL functional-only simulation not yet implemented (use performance simulation)\n");
+   exit(1);
 }