Stream stats (#71)

* Temp commit for Justin and Cassie to sync on
code changes for adding per-stream status.

* Resolved compile errors.

* Removed redundant parameter

* Passed cuda_stream_id from accelsim to gpgpusim

* Cleaned up unused changes

* Changed vector to map, having operator problems.

* StreamID defaults to zero

* Implemented streams to inc_stats and so on

* Fixed TOTAL_ACCESS counts

* Implemented GLOBAL_TIMER.

* Fixed m_shader->get_kernel SEGFAULT issue in shader.cc.

* Use warp_init to track streamID instead of issue_warp

* Removed temp debug print

* Modified cache_stats to only print data from latest finished stream

Added optional arg to cache_stats::print_stats, cache_stats::print_fail_stats and their upstream functions. When streamID is specified, print stats
from that stream. When not specified, print all stats.

NOTE: current implementation depending on streamid never equals -1

* Removed default arg values of streamID

* modified constructor of mem_fetch to pass in streamID

* changed get_streamid to get_streamID

* Added TODO to gpgpusim_entrypoint.cc and power_stat.cc

* Only collect power stats when enabled

* print last finished stream in PTX mode using last_streamID

* take out additional printf

* Add a field to baseline cache to indicate cache level

* save gpu object in cache

* Print stream ID only once per kernel

* rm test print

* use -1 for default stream id

* cleanup debug prints

* remove GLOABL_TIMER

* Automated clang-format

* Should be correct to print everything in power model

* addressing concerns & errors

* Automated clang-format

* add m_stats_pw in operator+

* Automated Format

---------

Co-authored-by: Justin Qiao <[email protected]>
Co-authored-by: Justin Qiao <[email protected]>
Co-authored-by: Tim Rogers <[email protected]>
Co-authored-by: JRPan <[email protected]>
Co-authored-by: purdue-jenkins <[email protected]>

1 files changed, 16 insertions, 2 deletions

diff --git a/src/gpgpu-sim/gpu-sim.h b/src/gpgpu-sim/gpu-sim.h
index d43b399..8e81451 100644
--- a/src/gpgpu-sim/gpu-sim.h
+++ b/src/gpgpu-sim/gpu-sim.h
@@ -539,7 +539,7 @@ class gpgpu_sim : public gpgpu_t {
            (m_config.gpu_max_completed_cta_opt &&
             (gpu_completed_cta >= m_config.gpu_max_completed_cta_opt));
   }
-  void print_stats();
+  void print_stats(unsigned long long streamID);
   void update_stats();
   void deadlock_check();
   void inc_completed_cta() { gpu_completed_cta++; }
@@ -568,7 +568,7 @@ class gpgpu_sim : public gpgpu_t {
   void decrement_kernel_latency();
 
   const gpgpu_sim_config &get_config() const { return m_config; }
-  void gpu_print_stat();
+  void gpu_print_stat(unsigned long long streamID);
   void dump_pipeline(int mask, int s, int m) const;
 
   void perf_memcpy_to_gpu(size_t dst_start_addr, size_t count);
@@ -685,6 +685,17 @@ class gpgpu_sim : public gpgpu_t {
   occupancy_stats gpu_occupancy;
   occupancy_stats gpu_tot_occupancy;
 
+  typedef struct {
+    unsigned long long start_cycle;
+    unsigned long long end_cycle;
+  } kernel_time_t;
+  std::map<unsigned long long, std::map<unsigned, kernel_time_t>>
+      gpu_kernel_time;
+  unsigned long long last_streamID;
+  unsigned long long last_uid;
+  cache_stats aggregated_l1_stats;
+  cache_stats aggregated_l2_stats;
+
   // performance counter for stalls due to congestion.
   unsigned int gpu_stall_dramfull;
   unsigned int gpu_stall_icnt2sh;
@@ -712,6 +723,9 @@ class gpgpu_sim : public gpgpu_t {
  public:
   bool is_functional_sim() { return m_functional_sim; }
   kernel_info_t *get_functional_kernel() { return m_functional_sim_kernel; }
+  std::vector<kernel_info_t *> get_running_kernels() {
+    return m_running_kernels;
+  }
   void functional_launch(kernel_info_t *k) {
     m_functional_sim = true;
     m_functional_sim_kernel = k;