1. fix load imbalance issue (CTA's were filling up first core in a cluster before moving to next)

   this improves correlation to 0.9471
2. update config to use sm_12 if available (goal: seems like BlackScholes has different ipc on hardware 
   from before, this didn't help though)
3. update comparison scripts since no ld_const stuff was removed

[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 7911]

1 files changed, 4 insertions, 3 deletions

diff --git a/src/gpgpu-sim/shader.cc b/src/gpgpu-sim/shader.cc
index 20910be..f723b78 100644
--- a/src/gpgpu-sim/shader.cc
+++ b/src/gpgpu-sim/shader.cc
@@ -1996,10 +1996,10 @@ simt_core_cluster::simt_core_cluster( class gpgpu_sim *gpu,
                                       const struct memory_config *mem_config,
                                       shader_core_stats *stats )
 {
-    m_cta_issue_next_core=0;
+    m_config = config;
+    m_cta_issue_next_core=m_config->n_simt_cores_per_cluster-1; // this causes first launch to use hw cta 0
     m_cluster_id=cluster_id;
     m_gpu = gpu;
-    m_config = config;
     m_stats = stats;
     m_core = new shader_core_ctx*[ config->n_simt_cores_per_cluster ];
     for( unsigned i=0; i < config->n_simt_cores_per_cluster; i++ ) 
@@ -2043,10 +2043,11 @@ unsigned simt_core_cluster::issue_block2core( class kernel_info_t &kernel )
 {
     unsigned num_blocks_issued=0;
     for( unsigned i=0; i < m_config->n_simt_cores_per_cluster; i++ ) {
-        unsigned core = (i+m_cta_issue_next_core)%m_config->n_simt_cores_per_cluster;
+        unsigned core = (i+m_cta_issue_next_core+1)%m_config->n_simt_cores_per_cluster;
         if( m_core[core]->get_n_active_cta() < m_config->max_cta(kernel) ) {
             m_core[core]->issue_block2core(kernel);
             num_blocks_issued++;
+            m_cta_issue_next_core=core; 
             break;
         }
     }