From 38b4df5653ecbd9907a3d39b125640cd4fb7d012 Mon Sep 17 00:00:00 2001 From: JRPan <25518778+JRPan@users.noreply.github.com> Date: Tue, 20 Aug 2024 20:43:32 -0400 Subject: 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 Co-authored-by: Justin Qiao <71228724+ShichenQiao@users.noreply.github.com> Co-authored-by: Tim Rogers Co-authored-by: JRPan Co-authored-by: purdue-jenkins --- src/stream_manager.cc | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'src/stream_manager.cc') diff --git a/src/stream_manager.cc b/src/stream_manager.cc index 0ce3c6a..72f8bb0 100644 --- a/src/stream_manager.cc +++ b/src/stream_manager.cc @@ -302,6 +302,14 @@ bool stream_manager::register_finished_kernel(unsigned grid_uid) { void stream_manager::stop_all_running_kernels() { pthread_mutex_lock(&m_lock); + std::vector finished_streams; + std::vector running_kernels = m_gpu->get_running_kernels(); + for (kernel_info_t *k : running_kernels) { + if (k != NULL) { + finished_streams.push_back(k->get_streamID()); + } + } + // Signal m_gpu to stop all running kernels m_gpu->stop_all_running_kernels(); @@ -312,7 +320,9 @@ void stream_manager::stop_all_running_kernels() { } // If any kernels completed, print out the current stats - if (count > 0) m_gpu->print_stats(); + for (unsigned long long streamID : finished_streams) { + m_gpu->print_stats(streamID); + } pthread_mutex_unlock(&m_lock); } -- cgit v1.3