diff options
| author | Akshay Jain <[email protected]> | 2018-03-22 04:20:13 -0400 |
|---|---|---|
| committer | Akshay Jain <[email protected]> | 2018-03-22 04:20:13 -0400 |
| commit | 777ab7fd6761a6250bc8e4f37994125a3f8d331b (patch) | |
| tree | bdd53057d454ba5b84d951e2444b71ee5141a93d /src/gpgpu-sim/gpu-sim.cc | |
| parent | 2d8d4455aa710914e87c5611cbb71f9330cdbc73 (diff) | |
Change 252 by jain156@akshayj-lt1 on 2017/05/29 10:51:32
Checking in the data footprint stats as reported in the micro paper.
The implementation uses gpgpu pointer, due to which I don't feel fine pushing to mainline.
May be I can do the stats check and increment in l2cache.cc through a public function
to avoid exposing gpgpu pointer to public
Diffstat (limited to 'src/gpgpu-sim/gpu-sim.cc')
| -rw-r--r-- | src/gpgpu-sim/gpu-sim.cc | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/src/gpgpu-sim/gpu-sim.cc b/src/gpgpu-sim/gpu-sim.cc index 121e079..9a28b55 100644 --- a/src/gpgpu-sim/gpu-sim.cc +++ b/src/gpgpu-sim/gpu-sim.cc @@ -668,7 +668,7 @@ gpgpu_sim::gpgpu_sim( const gpgpu_sim_config &config ) m_memory_partition_unit = new memory_partition_unit*[m_memory_config->m_n_mem]; m_memory_sub_partition = new memory_sub_partition*[m_memory_config->m_n_mem_sub_partition]; for (unsigned i=0;i<m_memory_config->m_n_mem;i++) { - m_memory_partition_unit[i] = new memory_partition_unit(i, m_memory_config, m_memory_stats); + m_memory_partition_unit[i] = new memory_partition_unit(i, m_memory_config, m_memory_stats, this); for (unsigned p = 0; p < m_memory_config->m_n_sub_partition_per_memory_channel; p++) { unsigned submpid = i * m_memory_config->m_n_sub_partition_per_memory_channel + p; m_memory_sub_partition[submpid] = m_memory_partition_unit[i]->get_sub_partition(p); |