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/l2cache.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'src/gpgpu-sim/l2cache.h') diff --git a/src/gpgpu-sim/l2cache.h b/src/gpgpu-sim/l2cache.h index ccf9b70..65c9c38 100644 --- a/src/gpgpu-sim/l2cache.h +++ b/src/gpgpu-sim/l2cache.h @@ -52,15 +52,16 @@ class partition_mf_allocator : public mem_fetch_allocator { return NULL; } virtual mem_fetch *alloc(new_addr_type addr, mem_access_type type, - unsigned size, bool wr, - unsigned long long cycle) const; + unsigned size, bool wr, unsigned long long cycle, + unsigned long long streamID) const; virtual mem_fetch *alloc(new_addr_type addr, mem_access_type type, const active_mask_t &active_mask, const mem_access_byte_mask_t &byte_mask, const mem_access_sector_mask_t §or_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; private: const memory_config *m_memory_config; -- cgit v1.3