1. refactoring cuda api code for loading PTX (removing external PTX loading entirely)

2. some bug fixes for warp_inst_t
3. creating a new class, gpgpu_t, which contains the functional "memory" state visible
   to all threads running on a GPU (doing this as part of my continuing effort to hunt 
   down and eradicate every global variable that is not the top level "the gpu")
4. other misc. changes

Almost passing CUDA 3.1 regression?  oclHistogram keeps failing under torque, but
does not fail when run on the command line from the same directory.

[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 7827]

1 files changed, 8 insertions, 1 deletions

diff --git a/src/gpgpu-sim/gpu-sim.h b/src/gpgpu-sim/gpu-sim.h
index ac03cbc..d690fab 100644
--- a/src/gpgpu-sim/gpu-sim.h
+++ b/src/gpgpu-sim/gpu-sim.h
@@ -178,7 +178,7 @@ extern int   g_ptx_inst_debug_thread_uid;
 
 
 
-class gpgpu_sim {
+class gpgpu_sim : public gpgpu_t {
 public:
    gpgpu_sim();
 
@@ -211,6 +211,10 @@ public:
    void gpu_print_stat() const;
    void dump_pipeline( int mask, int s, int m ) const;
 
+   unsigned get_forced_capability() const { return m_ptx_force_max_capability; }
+   bool convert_to_ptxplus() const { return m_ptx_convert_to_ptxplus; }
+   bool saved_converted_ptxplus() const { return m_ptx_save_converted_ptxplus; }
+
 private:
    // clocks
    void init_clock_domains(void);
@@ -271,6 +275,9 @@ private:
 
    // options
    bool gpu_deadlock_detect;
+   int   m_ptx_convert_to_ptxplus;
+   int   m_ptx_save_converted_ptxplus;
+   unsigned m_ptx_force_max_capability;
 
    // stats
    struct shader_core_stats  *m_shader_stats;