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, 15 insertions, 14 deletions

diff --git a/src/gpgpu-sim/l2cache.cc b/src/gpgpu-sim/l2cache.cc
index 8469453..52eed0e 100644
--- a/src/gpgpu-sim/l2cache.cc
+++ b/src/gpgpu-sim/l2cache.cc
@@ -51,12 +51,12 @@
 
 mem_fetch *partition_mf_allocator::alloc(new_addr_type addr,
                                          mem_access_type type, unsigned size,
-                                         bool wr,
-                                         unsigned long long cycle) const {
+                                         bool wr, unsigned long long cycle,
+                                         unsigned long long streamID) const {
   assert(wr);
   mem_access_t access(type, addr, size, wr, m_memory_config->gpgpu_ctx);
-  mem_fetch *mf = new mem_fetch(access, NULL, WRITE_PACKET_SIZE, -1, -1, -1,
-                                m_memory_config, cycle);
+  mem_fetch *mf = new mem_fetch(access, NULL, streamID, WRITE_PACKET_SIZE, -1,
+                                -1, -1, m_memory_config, cycle);
   return mf;
 }
 
@@ -65,12 +65,12 @@ mem_fetch *partition_mf_allocator::alloc(
     const mem_access_byte_mask_t &byte_mask,
     const mem_access_sector_mask_t &sector_mask, unsigned size, bool wr,
     unsigned long long cycle, unsigned wid, unsigned sid, unsigned tpc,
-    mem_fetch *original_mf) const {
+    mem_fetch *original_mf, unsigned long long streamID) const {
   mem_access_t access(type, addr, size, wr, active_mask, byte_mask, sector_mask,
                       m_memory_config->gpgpu_ctx);
-  mem_fetch *mf =
-      new mem_fetch(access, NULL, wr ? WRITE_PACKET_SIZE : READ_PACKET_SIZE,
-                    wid, sid, tpc, m_memory_config, cycle, original_mf);
+  mem_fetch *mf = new mem_fetch(access, NULL, streamID,
+                                wr ? WRITE_PACKET_SIZE : READ_PACKET_SIZE, wid,
+                                sid, tpc, m_memory_config, cycle, original_mf);
   return mf;
 }
 memory_partition_unit::memory_partition_unit(unsigned partition_id,
@@ -436,9 +436,9 @@ memory_sub_partition::memory_sub_partition(unsigned sub_partition_id,
   m_mf_allocator = new partition_mf_allocator(config);
 
   if (!m_config->m_L2_config.disabled())
-    m_L2cache =
-        new l2_cache(L2c_name, m_config->m_L2_config, -1, -1, m_L2interface,
-                     m_mf_allocator, IN_PARTITION_L2_MISS_QUEUE, gpu);
+    m_L2cache = new l2_cache(L2c_name, m_config->m_L2_config, -1, -1,
+                             m_L2interface, m_mf_allocator,
+                             IN_PARTITION_L2_MISS_QUEUE, gpu, L2_GPU_CACHE);
 
   unsigned int icnt_L2;
   unsigned int L2_dram;
@@ -733,7 +733,7 @@ memory_sub_partition::breakdown_request_to_sector_requests(mem_fetch *mf) {
           mf->get_access_warp_mask(), mf->get_access_byte_mask() & mask,
           std::bitset<SECTOR_CHUNCK_SIZE>().set(i), SECTOR_SIZE, mf->is_write(),
           m_gpu->gpu_tot_sim_cycle + m_gpu->gpu_sim_cycle, mf->get_wid(),
-          mf->get_sid(), mf->get_tpc(), mf);
+          mf->get_sid(), mf->get_tpc(), mf, mf->get_streamID());
 
       result.push_back(n_mf);
     }
@@ -756,7 +756,7 @@ memory_sub_partition::breakdown_request_to_sector_requests(mem_fetch *mf) {
           mf->get_access_byte_mask() & mask,
           std::bitset<SECTOR_CHUNCK_SIZE>().set(i), SECTOR_SIZE, mf->is_write(),
           m_gpu->gpu_tot_sim_cycle + m_gpu->gpu_sim_cycle, mf->get_wid(),
-          mf->get_sid(), mf->get_tpc(), mf);
+          mf->get_sid(), mf->get_tpc(), mf, mf->get_streamID());
 
       result.push_back(n_mf);
     }
@@ -772,7 +772,8 @@ memory_sub_partition::breakdown_request_to_sector_requests(mem_fetch *mf) {
             mf->get_access_warp_mask(), mf->get_access_byte_mask() & mask,
             std::bitset<SECTOR_CHUNCK_SIZE>().set(i), SECTOR_SIZE,
             mf->is_write(), m_gpu->gpu_tot_sim_cycle + m_gpu->gpu_sim_cycle,
-            mf->get_wid(), mf->get_sid(), mf->get_tpc(), mf);
+            mf->get_wid(), mf->get_sid(), mf->get_tpc(), mf,
+            mf->get_streamID());
 
         result.push_back(n_mf);
       }