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/gpgpu-sim/mem_fetch.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'src/gpgpu-sim/mem_fetch.h') diff --git a/src/gpgpu-sim/mem_fetch.h b/src/gpgpu-sim/mem_fetch.h index 283fe80..7704218 100644 --- a/src/gpgpu-sim/mem_fetch.h +++ b/src/gpgpu-sim/mem_fetch.h @@ -54,9 +54,10 @@ class memory_config; class mem_fetch { public: mem_fetch(const mem_access_t &access, const warp_inst_t *inst, - unsigned ctrl_size, unsigned wid, unsigned sid, unsigned tpc, - const memory_config *config, unsigned long long cycle, - mem_fetch *original_mf = NULL, mem_fetch *original_wr_mf = NULL); + unsigned long long streamID, unsigned ctrl_size, unsigned wid, + unsigned sid, unsigned tpc, const memory_config *config, + unsigned long long cycle, mem_fetch *original_mf = NULL, + mem_fetch *original_wr_mf = NULL); ~mem_fetch(); void set_status(enum mem_fetch_status status, unsigned long long cycle); @@ -105,6 +106,7 @@ class mem_fetch { unsigned get_timestamp() const { return m_timestamp; } unsigned get_return_timestamp() const { return m_timestamp2; } unsigned get_icnt_receive_time() const { return m_icnt_receive_time; } + unsigned long long get_streamID() const { return m_streamID; } enum mem_access_type get_access_type() const { return m_access.get_type(); } const active_mask_t &get_access_warp_mask() const { @@ -163,6 +165,8 @@ class mem_fetch { // requesting instruction (put last so mem_fetch prints nicer in gdb) warp_inst_t m_inst; + unsigned long long m_streamID; + static unsigned sm_next_mf_request_uid; const memory_config *m_mem_config; -- cgit v1.3