From 6070f320f59b2375ba859c86074f8027545a3f11 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Constantin=20F=C3=BCrst?= Date: Thu, 8 Feb 2024 17:19:38 +0100 Subject: [PATCH] add results for distributed locations prefetching --- .../evaluation-results/distprefetch/perf.svg | 2685 +++++++++++++++++ ...cb1-tcj1-tmul32-wl4294967296-cs8388608.csv | 6 + ...cb1-tcj1-tmul32-wl4294967296-cs8388608.csv | 6 + 3 files changed, 2697 insertions(+) create mode 100644 qdp_project/evaluation-results/distprefetch/perf.svg create mode 100644 qdp_project/evaluation-results/distprefetch/qdp-xeonmax-distprefetch-tca1-tcb1-tcj1-tmul32-wl4294967296-cs8388608.csv create mode 100644 qdp_project/evaluation-results/distprefetch/qdp-xeonmax-prefetch-tca1-tcb1-tcj1-tmul32-wl4294967296-cs8388608.csv diff --git a/qdp_project/evaluation-results/distprefetch/perf.svg b/qdp_project/evaluation-results/distprefetch/perf.svg new file mode 100644 index 0000000..395b1fe --- /dev/null +++ b/qdp_project/evaluation-results/distprefetch/perf.svg @@ -0,0 +1,2685 @@ + + + + + + + + + + + + + + +Flame Graph + +Reset Zoom +Search +ic + + + +memcg_check_events (2,291,810,479 samples, 3.53%) +mem.. + + +update_process_times (26,405,058 samples, 0.04%) + + + +preempt_count_add (14,687,350 samples, 0.02%) + + + +qi_submit_sync (42,287,985 samples, 0.07%) + + + +page_remove_rmap (230,418,721 samples, 0.35%) + + + +_int_malloc (6,418,356 samples, 0.01%) + + + +asm_sysvec_apic_timer_interrupt (9,511,188 samples, 0.01%) + + + +perf_event_mmap (13,927,337 samples, 0.02%) + + + +perf_adjust_freq_unthr_context (17,289,103 samples, 0.03%) + + + +inherit_event.isra.0 (29,260,484 samples, 0.05%) + + + +preempt_count_add (6,345,189 samples, 0.01%) + + + +unmap_page_range (972,820,059 samples, 1.50%) + + + +pmd_val (10,366,329 samples, 0.02%) + + + +perf_adjust_freq_unthr_context (20,254,481 samples, 0.03%) + + + +folio_test_hugetlb (9,495,290 samples, 0.01%) + + + +sysvec_apic_timer_interrupt (16,429,960 samples, 0.03%) + + + +cgroup_rstat_updated (8,634,637 samples, 0.01%) + + + +vma_alloc_folio (7,912,403 samples, 0.01%) + + + +__rcu_read_lock (7,023,622 samples, 0.01%) + + + +__mem_cgroup_uncharge_list (17,257,799 samples, 0.03%) + + + +__sysvec_apic_timer_interrupt (9,510,812 samples, 0.01%) + + + +lru_gen_add_folio (128,621,100 samples, 0.20%) + + + +__list_add_valid (19,008,161 samples, 0.03%) + + + +perf_event_task_tick (9,510,812 samples, 0.01%) + + + +tick_sched_timer (9,510,812 samples, 0.01%) + + + +__mem_cgroup_charge (775,053,231 samples, 1.19%) + + + +__list_del_entry_valid (10,355,987 samples, 0.02%) + + + +__mod_node_page_state (22,787,073 samples, 0.04%) + + + +preempt_count_add (8,031,211 samples, 0.01%) + + + +count_memcg_events.constprop.0 (134,777,535 samples, 0.21%) + + + +preempt_count_add (8,075,394 samples, 0.01%) + + + +irqentry_exit_to_user_mode (38,354,757 samples, 0.06%) + + + +asm_sysvec_apic_timer_interrupt (6,050,543 samples, 0.01%) + + + +cgroup_rstat_updated (6,990,872 samples, 0.01%) + + + +clear_page_erms (151,208,587 samples, 0.23%) + + + +__memset_avx512_unaligned_erms (4,675,890,216 samples, 7.19%) +__memset_.. + + +perf_event_task_tick (17,289,103 samples, 0.03%) + + + +scan_a (7,446,350,994 samples, 11.46%) +scan_a + + +check_preemption_disabled (8,628,689 samples, 0.01%) + + + +_raw_spin_unlock (21,583,744 samples, 0.03%) + + + +tick_sched_timer (8,645,992 samples, 0.01%) + + + +__mod_zone_page_state (29,352,515 samples, 0.05%) + + + +__free_one_page (122,586,240 samples, 0.19%) + + + +do_user_addr_fault (2,159,432,973 samples, 3.32%) +do_.. + + +do_syscall_64 (15,499,112 samples, 0.02%) + + + +sysvec_apic_timer_interrupt (6,473,946 samples, 0.01%) + + + +do_syscall_64 (12,395,668 samples, 0.02%) + + + +__sysvec_apic_timer_interrupt (8,206,329 samples, 0.01%) + + + +__handle_mm_fault (32,470,924 samples, 0.05%) + + + +scan_b (10,597,764 samples, 0.02%) + + + +__mod_zone_page_state (30,233,969 samples, 0.05%) + + + +perf_event_init_task (30,985,521 samples, 0.05%) + + + +__count_memcg_events (2,217,301,775 samples, 3.41%) +__c.. + + +__x64_sys_get_mempolicy (11,878,357 samples, 0.02%) + + + +__free_one_page (67,264,571 samples, 0.10%) + + + +scheduler_tick (9,510,812 samples, 0.01%) + + + +sync_regs (694,446,588 samples, 1.07%) + + + +check_preemption_disabled (18,810,776 samples, 0.03%) + + + +__list_add_valid (6,044,583 samples, 0.01%) + + + +unsigned long std::uniform_int_distribution<unsigned long>::operator (2,314,034,004 samples, 3.56%) +uns.. + + +irqentry_enter (7,717,455 samples, 0.01%) + + + +charge_memcg (5,896,057,871 samples, 9.07%) +charge_memcg + + +__x64_sys_mprotect (181,659,392 samples, 0.28%) + + + +do_user_addr_fault (40,539,248 samples, 0.06%) + + + +perf_adjust_freq_unthr_context (21,609,061 samples, 0.03%) + + + +entry_SYSCALL_64_after_hwframe (20,626,042 samples, 0.03%) + + + +folio_batch_move_lru (468,010,823 samples, 0.72%) + + + +handle_mm_fault (1,985,385,380 samples, 3.05%) +han.. + + +perf_event_alloc (25,815,196 samples, 0.04%) + + + +update_process_times (17,289,103 samples, 0.03%) + + + +sysvec_apic_timer_interrupt (12,104,828 samples, 0.02%) + + + +up_read (69,117,053 samples, 0.11%) + + + +tick_sched_timer (29,909,692 samples, 0.05%) + + + +uncharge_folio (12,944,766 samples, 0.02%) + + + +mmap_region (18,904,997 samples, 0.03%) + + + +check_preemption_disabled (6,051,875 samples, 0.01%) + + + +unmap_vmas (1,029,770,107 samples, 1.58%) + + + +sysvec_apic_timer_interrupt (8,959,591 samples, 0.01%) + + + +clone3 (35,297,884 samples, 0.05%) + + + +free_unref_page_prepare (28,488,101 samples, 0.04%) + + + +perf_event_task_tick (8,645,992 samples, 0.01%) + + + +pmd_val (6,048,187 samples, 0.01%) + + + +tick_sched_timer (17,579,002 samples, 0.03%) + + + +tick_sched_timer (9,511,188 samples, 0.01%) + + + +change_protection (116,335,188 samples, 0.18%) + + + +scheduler_tick (12,433,026 samples, 0.02%) + + + +__list_del_entry_valid (22,450,482 samples, 0.03%) + + + +perf_adjust_freq_unthr_context (6,050,543 samples, 0.01%) + + + +__hrtimer_run_queues (17,289,103 samples, 0.03%) + + + +perf_event_task_tick (7,738,669 samples, 0.01%) + + + +tick_sched_timer (7,738,669 samples, 0.01%) + + + +check_preemption_disabled (242,548,501 samples, 0.37%) + + + +inherit_task_group.isra.0 (29,260,484 samples, 0.05%) + + + +debug_smp_processor_id (6,040,141 samples, 0.01%) + + + +percpu_counter_add_batch (47,299,036 samples, 0.07%) + + + +perf_adjust_freq_unthr_context (8,645,992 samples, 0.01%) + + + +intel_invalidate_range (14,958,137 samples, 0.02%) + + + +tick_sched_timer (7,754,397 samples, 0.01%) + + + +__rcu_read_lock (38,896,719 samples, 0.06%) + + + +__mod_lruvec_state (56,099,216 samples, 0.09%) + + + +tlb_batch_pages_flush (603,433,450 samples, 0.93%) + + + +__mmu_notifier_invalidate_range (18,995,383 samples, 0.03%) + + + +tick_sched_timer (5,613,196 samples, 0.01%) + + + +free_unref_page_commit (11,218,669 samples, 0.02%) + + + +sum_check (14,472,830,107 samples, 22.27%) +sum_check + + +tlb_batch_pages_flush (307,133,084 samples, 0.47%) + + + +scheduler_tick (17,289,103 samples, 0.03%) + + + +exit_to_user_mode_prepare (99,325,508 samples, 0.15%) + + + +__mem_cgroup_charge (11,263,198 samples, 0.02%) + + + +__this_cpu_preempt_check (8,634,099 samples, 0.01%) + + + +count_memcg_events.constprop.0 (66,290,592 samples, 0.10%) + + + +inc_mm_counter (82,863,586 samples, 0.13%) + + + +check_preemption_disabled (7,182,369 samples, 0.01%) + + + +preempt_count_add (10,366,528 samples, 0.02%) + + + +pgd_none (6,904,384 samples, 0.01%) + + + +__hrtimer_run_queues (9,510,812 samples, 0.01%) + + + +pud_val (12,964,293 samples, 0.02%) + + + +asm_sysvec_apic_timer_interrupt (9,505,799 samples, 0.01%) + + + +sysvec_apic_timer_interrupt (5,711,704 samples, 0.01%) + + + +sysvec_apic_timer_interrupt (9,511,188 samples, 0.01%) + + + +__mod_memcg_lruvec_state (63,851,304 samples, 0.10%) + + + +perf_try_init_event (6,895,785 samples, 0.01%) + + + +policy_node (5,645,487 samples, 0.01%) + + + +preempt_count_sub (6,912,533 samples, 0.01%) + + + +_mm512_stream_load_si512 (1,518,274,336 samples, 2.34%) +_.. + + +__GI_madvise (15,499,112 samples, 0.02%) + + + +lock_vma_under_rcu (194,314,863 samples, 0.30%) + + + +__mod_node_page_state (34,533,925 samples, 0.05%) + + + +__mod_memcg_lruvec_state (39,695,346 samples, 0.06%) + + + +_raw_spin_lock (32,374,364 samples, 0.05%) + + + +kernel_get_mempolicy (11,878,357 samples, 0.02%) + + + +percpu_counter_add_batch (76,811,406 samples, 0.12%) + + + +check_preemption_disabled (16,404,298 samples, 0.03%) + + + +free_unref_page_list (225,313,637 samples, 0.35%) + + + +_raw_spin_trylock (63,928,432 samples, 0.10%) + + + +__rmqueue_pcplist (159,760,773 samples, 0.25%) + + + +qi_flush_piotlb (8,633,747 samples, 0.01%) + + + +free_swap_cache (17,265,659 samples, 0.03%) + + + +__mod_memcg_lruvec_state (27,847,379 samples, 0.04%) + + + +mem_cgroup_charge_statistics (284,705,375 samples, 0.44%) + + + +do_syscall_64 (20,626,042 samples, 0.03%) + + + +__sysvec_apic_timer_interrupt (22,678,492 samples, 0.03%) + + + +perf_event_task_tick (16,429,960 samples, 0.03%) + + + +__GI_munmap (1,412,816,971 samples, 2.17%) +_.. + + +check_preemption_disabled (14,675,237 samples, 0.02%) + + + +cgroup_rstat_updated (6,053,484 samples, 0.01%) + + + +perf_adjust_freq_unthr_context (7,734,458 samples, 0.01%) + + + +pmd_pfn (6,049,980 samples, 0.01%) + + + +release_pages (299,363,911 samples, 0.46%) + + + +Filter<unsigned long, LT, (7,445,621,211 samples, 11.46%) +Filter<unsigned l.. + + +sysvec_apic_timer_interrupt (17,040,033 samples, 0.03%) + + + +__rcu_read_unlock (6,916,171 samples, 0.01%) + + + +__count_memcg_events (116,628,195 samples, 0.18%) + + + +do_madvise (15,499,112 samples, 0.02%) + + + +sysvec_apic_timer_interrupt (17,289,103 samples, 0.03%) + + + +__mmu_notifier_invalidate_range_end (14,958,137 samples, 0.02%) + + + +handle_mm_fault (34,194,242 samples, 0.05%) + + + +vma_alloc_folio (418,398,661 samples, 0.64%) + + + +tick_sched_timer (16,529,381 samples, 0.03%) + + + +update_process_times (12,104,828 samples, 0.02%) + + + +free_pcppages_bulk (138,122,499 samples, 0.21%) + + + +__this_cpu_preempt_check (5,837,485 samples, 0.01%) + + + +unmap_region (1,407,642,639 samples, 2.17%) +u.. + + +perf_event_mmap (6,914,920 samples, 0.01%) + + + +hrtimer_interrupt (22,678,492 samples, 0.03%) + + + +__mod_node_page_state (15,521,997 samples, 0.02%) + + + +asm_sysvec_apic_timer_interrupt (12,104,828 samples, 0.02%) + + + +try_charge_memcg (1,097,604,038 samples, 1.69%) + + + +exit_to_user_mode_prepare (6,011,232 samples, 0.01%) + + + +preempt_count_sub (6,914,382 samples, 0.01%) + + + +hrtimer_interrupt (7,738,669 samples, 0.01%) + + + +__rmqueue_pcplist (77,785,307 samples, 0.12%) + + + +__mmu_notifier_invalidate_range_end (56,950,048 samples, 0.09%) + + + +folio_batch_move_lru (220,621,181 samples, 0.34%) + + + +tick_sched_handle (12,104,828 samples, 0.02%) + + + +error_entry (14,664,534 samples, 0.02%) + + + +check_preemption_disabled (18,012,966 samples, 0.03%) + + + +__alloc_pages (680,598,820 samples, 1.05%) + + + +__mod_zone_page_state (17,252,374 samples, 0.03%) + + + +intel_invalidate_range (56,950,048 samples, 0.09%) + + + +do_anonymous_page (32,470,924 samples, 0.05%) + + + +check_preemption_disabled (6,900,222 samples, 0.01%) + + + +cpuset_nodemask_valid_mems_allowed (9,101,936 samples, 0.01%) + + + +do_vmi_munmap (1,409,365,019 samples, 2.17%) +d.. + + +check_preemption_disabled (14,666,373 samples, 0.02%) + + + +__handle_mm_fault (8,227,729,309 samples, 12.66%) +__handle_mm_fault + + +__hrtimer_run_queues (7,754,397 samples, 0.01%) + + + +__mod_memcg_lruvec_state (18,129,747 samples, 0.03%) + + + +get_page_from_freelist (263,384,546 samples, 0.41%) + + + +tick_sched_handle (16,429,960 samples, 0.03%) + + + +__count_memcg_events (247,180,943 samples, 0.38%) + + + +rwsem_down_write_slowpath (53,128,731 samples, 0.08%) + + + +allocate_slab (8,575,652 samples, 0.01%) + + + +tick_sched_handle (17,289,103 samples, 0.03%) + + + +check_preemption_disabled (20,713,744 samples, 0.03%) + + + +asm_sysvec_apic_timer_interrupt (9,510,812 samples, 0.01%) + + + +__sysvec_apic_timer_interrupt (5,613,196 samples, 0.01%) + + + +hrtimer_interrupt (31,982,056 samples, 0.05%) + + + +free_pages_and_swap_cache (18,991,546 samples, 0.03%) + + + +update_process_times (9,510,812 samples, 0.01%) + + + +pmd_val (5,990,438 samples, 0.01%) + + + +lru_add_fn (177,737,578 samples, 0.27%) + + + +tick_sched_handle (17,579,002 samples, 0.03%) + + + +all (64,991,973,043 samples, 100%) + + + +std::mersenne_twister_engine<unsigned long, 32ul, 624ul, 397ul, 31ul, 2567483615ul, 11ul, 4294967295ul, 7ul, 2636928640ul, 15ul, 4022730752ul, 18ul, 1812433253ul>::_M_gen_rand (1,747,398,373 samples, 2.69%) +st.. + + +__bitmap_intersects (22,784,942 samples, 0.04%) + + + +do_syscall_64 (5,673,909 samples, 0.01%) + + + +exc_page_fault (40,539,248 samples, 0.06%) + + + +__mod_memcg_lruvec_state (36,260,979 samples, 0.06%) + + + +__hrtimer_run_queues (12,104,828 samples, 0.02%) + + + +__mod_lruvec_page_state (151,097,571 samples, 0.23%) + + + +__hrtimer_run_queues (16,429,960 samples, 0.03%) + + + +preempt_count_add (25,049,290 samples, 0.04%) + + + +asm_sysvec_apic_timer_interrupt (17,040,033 samples, 0.03%) + + + +cgroup_rstat_updated (6,857,435 samples, 0.01%) + + + +qi_flush_piotlb (8,855,138 samples, 0.01%) + + + +check_preemption_disabled (38,011,346 samples, 0.06%) + + + +hrtimer_interrupt (5,613,196 samples, 0.01%) + + + +do_anonymous_page (7,967,897,633 samples, 12.26%) +do_anonymous_page + + +unsigned int std::uniform_int_distribution<unsigned long>::_S_nd<unsigned long, std::mersenne_twister_engine<unsigned long, 32ul, 624ul, 397ul, 31ul, 2567483615ul, 11ul, 4294967295ul, 7ul, 2636928640ul, 15ul, 4022730752ul, 18ul, 1812433253ul>, unsigned int> (6,585,496,889 samples, 10.13%) +unsigned int s.. + + +check_preemption_disabled (33,766,615 samples, 0.05%) + + + +__irqentry_text_end (10,075,024 samples, 0.02%) + + + +do_syscall_64 (35,297,884 samples, 0.05%) + + + +check_preemption_disabled (39,365,895 samples, 0.06%) + + + +rwsem_spin_on_owner (52,315,504 samples, 0.08%) + + + +hrtimer_interrupt (17,289,103 samples, 0.03%) + + + +perf_adjust_freq_unthr_context (15,915,529 samples, 0.02%) + + + +check_preemption_disabled (7,361,679 samples, 0.01%) + + + +hrtimer_interrupt (17,579,002 samples, 0.03%) + + + +do_syscall_64 (1,411,954,555 samples, 2.17%) +d.. + + +fpregs_assert_state_consistent (21,608,637 samples, 0.03%) + + + +asm_sysvec_apic_timer_interrupt (16,429,960 samples, 0.03%) + + + +check_preemption_disabled (1,309,943,404 samples, 2.02%) +c.. + + +Vector_Loader<unsigned long, (1,518,274,336 samples, 2.34%) +V.. + + +check_preemption_disabled (18,974,295 samples, 0.03%) + + + +_mm512_mask_add_epi64 (3,182,454,112 samples, 4.90%) +_mm512.. + + +perf_iterate_ctx (13,927,337 samples, 0.02%) + + + +mas_walk (83,753,881 samples, 0.13%) + + + +__mod_zone_page_state (11,216,803 samples, 0.02%) + + + +folio_lruvec_lock_irqsave (7,778,754 samples, 0.01%) + + + +__folio_throttle_swaprate (17,635,670 samples, 0.03%) + + + +__mod_lruvec_page_state (139,805,839 samples, 0.22%) + + + +__list_add_valid (16,399,943 samples, 0.03%) + + + +__count_memcg_events (57,580,911 samples, 0.09%) + + + +syscall (12,911,986 samples, 0.02%) + + + +hrtimer_interrupt (17,040,033 samples, 0.03%) + + + +__mod_lruvec_state (35,430,350 samples, 0.05%) + + + +clear_page_erms (69,644,171 samples, 0.11%) + + + +__mod_memcg_lruvec_state (35,403,259 samples, 0.05%) + + + +__this_cpu_preempt_check (9,493,934 samples, 0.01%) + + + +std::mersenne_twister_engine<unsigned long, 32ul, 624ul, 397ul, 31ul, 2567483615ul, 11ul, 4294967295ul, 7ul, 2636928640ul, 15ul, 4022730752ul, 18ul, 1812433253ul>::operator (2,314,034,004 samples, 3.56%) +std.. + + +update_process_times (8,645,992 samples, 0.01%) + + + +__sysvec_apic_timer_interrupt (33,527,817 samples, 0.05%) + + + +__mod_zone_page_state (34,534,551 samples, 0.05%) + + + +void fill_mt<unsigned long> (23,749,328,379 samples, 36.54%) +void fill_mt<unsigned long> + + +__mod_zone_page_state (8,576,807 samples, 0.01%) + + + +__this_cpu_preempt_check (72,480,633 samples, 0.11%) + + + +check_preemption_disabled (12,950,783 samples, 0.02%) + + + +tick_sched_handle (22,166,282 samples, 0.03%) + + + +uncharge_folio (18,129,567 samples, 0.03%) + + + +mod_lruvec_page_state.constprop.0 (6,053,672 samples, 0.01%) + + + +check_preemption_disabled (222,532,903 samples, 0.34%) + + + +vm_normal_page (7,763,652 samples, 0.01%) + + + +cgroup_rstat_updated (38,261,936 samples, 0.06%) + + + +preempt_count_sub (6,052,963 samples, 0.01%) + + + +update_process_times (22,166,282 samples, 0.03%) + + + +perf_adjust_freq_unthr_context (7,738,669 samples, 0.01%) + + + +asm_sysvec_apic_timer_interrupt (6,473,946 samples, 0.01%) + + + +qi_flush_dev_iotlb_pasid (10,361,636 samples, 0.02%) + + + +check_preemption_disabled (15,543,022 samples, 0.02%) + + + +free_unref_page_list (123,359,259 samples, 0.19%) + + + +free_unref_page_prepare (21,573,803 samples, 0.03%) + + + +entry_SYSCALL_64_after_hwframe (5,673,909 samples, 0.01%) + + + +__this_cpu_preempt_check (12,075,342 samples, 0.02%) + + + +kernel_clone (35,297,884 samples, 0.05%) + + + +__mem_cgroup_uncharge_list (24,172,551 samples, 0.04%) + + + +qi_flush_dev_iotlb_pasid (24,164,091 samples, 0.04%) + + + +update_process_times (9,511,188 samples, 0.01%) + + + +__alloc_pages (349,167,754 samples, 0.54%) + + + +lru_add_fn (369,541,983 samples, 0.57%) + + + +mtree_range_walk (67,377,128 samples, 0.10%) + + + +scheduler_tick (21,525,164 samples, 0.03%) + + + +asm_sysvec_apic_timer_interrupt (5,711,704 samples, 0.01%) + + + +_raw_spin_unlock (11,229,571 samples, 0.02%) + + + +sysvec_apic_timer_interrupt (20,977,829 samples, 0.03%) + + + +folio_lruvec_lock_irqsave (6,043,000 samples, 0.01%) + + + +free_unref_page_commit (27,625,441 samples, 0.04%) + + + +__list_add_valid (8,632,847 samples, 0.01%) + + + +perf_event_task_tick (21,609,061 samples, 0.03%) + + + +__this_cpu_preempt_check (6,908,018 samples, 0.01%) + + + +asm_exc_page_fault (59,690,456 samples, 0.09%) + + + +entry_SYSCALL_64_after_hwframe (15,499,112 samples, 0.02%) + + + +preempt_count_sub (6,050,782 samples, 0.01%) + + + +fpregs_assert_state_consistent (42,332,487 samples, 0.07%) + + + +lock_vma_under_rcu (95,096,586 samples, 0.15%) + + + +blk_cgroup_congested (14,914,659 samples, 0.02%) + + + +do_mmap (19,765,056 samples, 0.03%) + + + +update_process_times (7,754,397 samples, 0.01%) + + + +intel_invalidate_range (68,150,099 samples, 0.10%) + + + +qi_flush_dev_iotlb_pasid (6,102,999 samples, 0.01%) + + + +__mod_memcg_lruvec_state (16,387,942 samples, 0.03%) + + + +perf_adjust_freq_unthr_context (9,511,188 samples, 0.01%) + + + +_raw_spin_lock_irqsave (6,050,474 samples, 0.01%) + + + +scheduler_tick (16,429,960 samples, 0.03%) + + + +sysvec_apic_timer_interrupt (7,738,669 samples, 0.01%) + + + +_raw_spin_trylock (24,135,669 samples, 0.04%) + + + +__folio_throttle_swaprate (43,179,114 samples, 0.07%) + + + +do_mprotect_pkey (181,659,392 samples, 0.28%) + + + +perf_adjust_freq_unthr_context (8,341,353 samples, 0.01%) + + + +tick_sched_timer (16,429,960 samples, 0.03%) + + + +internal_get_user_pages_fast (7,741,046 samples, 0.01%) + + + +folio_add_new_anon_rmap (102,823,885 samples, 0.16%) + + + +entry_SYSCALL_64_after_hwframe (1,411,954,555 samples, 2.17%) +e.. + + +__mem_cgroup_charge (6,067,981,414 samples, 9.34%) +__mem_cgroup_.. + + +__hrtimer_run_queues (8,645,992 samples, 0.01%) + + + +__x64_sys_munmap (1,409,365,019 samples, 2.17%) +_.. + + +__sysvec_apic_timer_interrupt (9,511,188 samples, 0.01%) + + + +entry_SYSCALL_64_after_hwframe (181,659,392 samples, 0.28%) + + + +try_charge_memcg (83,382,579 samples, 0.13%) + + + +mem_cgroup_charge_statistics (2,310,584,504 samples, 3.56%) +mem.. + + +mtree_range_walk (32,923,807 samples, 0.05%) + + + +x86_pmu_event_init (6,895,785 samples, 0.01%) + + + +do_anonymous_page (1,737,463,601 samples, 2.67%) +do.. + + +__this_cpu_preempt_check (23,008,785 samples, 0.04%) + + + +page_counter_try_charge (68,277,143 samples, 0.11%) + + + +__mod_lruvec_state (44,893,835 samples, 0.07%) + + + +Sum<unsigned long>::simd_agg (3,182,454,112 samples, 4.90%) +Sum<un.. + + +__alloc_pages (7,912,403 samples, 0.01%) + + + +__pte_alloc (12,965,388 samples, 0.02%) + + + +__GI___mmap64 (20,626,042 samples, 0.03%) + + + +get_page_from_freelist (571,772,565 samples, 0.88%) + + + +free_swap_cache (7,769,173 samples, 0.01%) + + + +__irqentry_text_end (13,825,748 samples, 0.02%) + + + +cgroup_rstat_updated (314,465,630 samples, 0.48%) + + + +__sysvec_apic_timer_interrupt (16,429,960 samples, 0.03%) + + + +qi_flush_dev_iotlb_pasid (42,287,985 samples, 0.07%) + + + +debug_smp_processor_id (50,981,972 samples, 0.08%) + + + +qi_submit_sync (8,855,138 samples, 0.01%) + + + +hrtimer_interrupt (8,206,329 samples, 0.01%) + + + +do_vmi_align_munmap (1,409,365,019 samples, 2.17%) +d.. + + +__folio_alloc (688,379,067 samples, 1.06%) + + + +check_preemption_disabled (9,491,383 samples, 0.01%) + + + +_raw_spin_lock (51,833,243 samples, 0.08%) + + + +check_preemption_disabled (42,345,167 samples, 0.07%) + + + +cpuset_nodemask_valid_mems_allowed (10,363,240 samples, 0.02%) + + + +__hrtimer_run_queues (5,613,196 samples, 0.01%) + + + +policy_nodemask (44,546,205 samples, 0.07%) + + + +__sysvec_apic_timer_interrupt (7,738,669 samples, 0.01%) + + + +_raw_spin_unlock (6,183,240 samples, 0.01%) + + + +debug_smp_processor_id (729,766,929 samples, 1.12%) + + + +unsigned long std::uniform_int_distribution<unsigned long>::operator (10,093,380,459 samples, 15.53%) +unsigned long std::unif.. + + +sync_regs (364,157,302 samples, 0.56%) + + + +__get_vma_policy (9,087,820 samples, 0.01%) + + + +tick_sched_timer (6,050,543 samples, 0.01%) + + + +__mod_node_page_state (58,700,929 samples, 0.09%) + + + +__rcu_read_unlock (7,778,737 samples, 0.01%) + + + +scheduler_tick (6,050,543 samples, 0.01%) + + + +__irqentry_text_end (8,781,167 samples, 0.01%) + + + +check_preemption_disabled (10,368,622 samples, 0.02%) + + + +update_process_times (17,579,002 samples, 0.03%) + + + +hrtimer_interrupt (6,050,543 samples, 0.01%) + + + +folio_add_lru_vma (6,043,674 samples, 0.01%) + + + +sysvec_apic_timer_interrupt (6,050,543 samples, 0.01%) + + + +mprotect_fixup (125,262,271 samples, 0.19%) + + + +copy_process (34,433,198 samples, 0.05%) + + + +error_entry (23,732,433 samples, 0.04%) + + + +folio_mapping (6,004,635 samples, 0.01%) + + + +p4d_offset (6,911,876 samples, 0.01%) + + + +tick_sched_handle (6,050,543 samples, 0.01%) + + + +__handle_mm_fault (1,865,778,996 samples, 2.87%) +__.. + + +__x64_sys_get_mempolicy (5,673,909 samples, 0.01%) + + + +lru_gen_add_folio (231,435,793 samples, 0.36%) + + + +policy_node (13,829,466 samples, 0.02%) + + + +__this_cpu_preempt_check (25,036,992 samples, 0.04%) + + + +scheduler_tick (25,768,610 samples, 0.04%) + + + +__libc_start_call_main (44,315,550,673 samples, 68.19%) +__libc_start_call_main + + +__mod_node_page_state (49,195,761 samples, 0.08%) + + + +__rcu_read_unlock (12,068,856 samples, 0.02%) + + + +qi_submit_sync (25,031,737 samples, 0.04%) + + + +free_pages_and_swap_cache (7,769,173 samples, 0.01%) + + + +tick_sched_timer (17,289,103 samples, 0.03%) + + + +release_pages (583,578,170 samples, 0.90%) + + + +perf_event_task_tick (15,915,529 samples, 0.02%) + + + +__this_cpu_preempt_check (6,915,204 samples, 0.01%) + + + +qi_submit_sync (24,164,091 samples, 0.04%) + + + +up_read (31,730,466 samples, 0.05%) + + + +__folio_alloc (352,416,523 samples, 0.54%) + + + +__sysvec_apic_timer_interrupt (9,505,799 samples, 0.01%) + + + +perf_event_task_tick (8,341,353 samples, 0.01%) + + + +entry_SYSCALL_64_after_hwframe (12,395,668 samples, 0.02%) + + + +__sysvec_apic_timer_interrupt (12,104,828 samples, 0.02%) + + + +__this_cpu_preempt_check (9,496,380 samples, 0.01%) + + + +__mod_lruvec_state (32,238,000 samples, 0.05%) + + + +pmd_pfn (8,413,664 samples, 0.01%) + + + +hrtimer_interrupt (9,510,812 samples, 0.01%) + + + +preempt_count_add (7,717,915 samples, 0.01%) + + + +__mod_node_page_state (28,517,118 samples, 0.04%) + + + +folio_add_lru (286,247,113 samples, 0.44%) + + + +tick_sched_handle (26,405,058 samples, 0.04%) + + + +__mod_lruvec_state (69,931,680 samples, 0.11%) + + + +down_read_trylock (74,295,681 samples, 0.11%) + + + +qi_flush_piotlb (43,986,008 samples, 0.07%) + + + +perf_iterate_sb.constprop.0 (13,927,337 samples, 0.02%) + + + +__slab_alloc.isra.0 (12,888,877 samples, 0.02%) + + + +__hrtimer_run_queues (22,678,492 samples, 0.03%) + + + +__this_cpu_preempt_check (24,149,544 samples, 0.04%) + + + +debug_smp_processor_id (12,032,227 samples, 0.02%) + + + +kernel_get_mempolicy (5,673,909 samples, 0.01%) + + + +__hrtimer_run_queues (9,511,188 samples, 0.01%) + + + +___slab_alloc (12,026,412 samples, 0.02%) + + + +__x64_sys_madvise (15,499,112 samples, 0.02%) + + + +start_thread (18,042,741,960 samples, 27.76%) +start_thread + + +__sysvec_apic_timer_interrupt (17,040,033 samples, 0.03%) + + + +kmem_cache_alloc_node (12,888,877 samples, 0.02%) + + + +tick_sched_timer (22,678,492 samples, 0.03%) + + + +down_write_killable (53,513,247 samples, 0.08%) + + + +qi_flush_piotlb (73,250,576 samples, 0.11%) + + + +get_mem_cgroup_from_mm (41,948,149 samples, 0.06%) + + + +qi_submit_sync (6,102,999 samples, 0.01%) + + + +[libstdc++.so.6.0.32] (18,042,288,348 samples, 27.76%) +[libstdc++.so.6.0.32] + + +tick_sched_handle (8,645,992 samples, 0.01%) + + + +qi_submit_sync (43,986,008 samples, 0.07%) + + + +access_error (6,169,844 samples, 0.01%) + + + +__rcu_read_unlock (5,995,936 samples, 0.01%) + + + +sysvec_apic_timer_interrupt (23,318,018 samples, 0.04%) + + + +scheduler_tick (12,104,828 samples, 0.02%) + + + +__list_add_valid (7,764,873 samples, 0.01%) + + + +exc_page_fault (2,174,303,117 samples, 3.35%) +exc.. + + +scheduler_tick (9,511,188 samples, 0.01%) + + + +__get_vma_policy (16,423,842 samples, 0.03%) + + + +sysvec_apic_timer_interrupt (9,505,799 samples, 0.01%) + + + +unsigned int std::uniform_int_distribution<unsigned long>::_S_nd<unsigned long, std::mersenne_twister_engine<unsigned long, 32ul, 624ul, 397ul, 31ul, 2567483615ul, 11ul, 4294967295ul, 7ul, 2636928640ul, 15ul, 4022730752ul, 18ul, 1812433253ul>, unsigned int> (2,314,034,004 samples, 3.56%) +uns.. + + +get_mem_cgroup_from_mm (139,952,940 samples, 0.22%) + + + +scheduler_tick (8,645,992 samples, 0.01%) + + + +hrtimer_interrupt (12,104,828 samples, 0.02%) + + + +qi_submit_sync (8,633,747 samples, 0.01%) + + + +scheduler_tick (7,738,669 samples, 0.01%) + + + +asm_exc_page_fault (4,145,503,245 samples, 6.38%) +asm_exc_.. + + +intel_invalidate_range (18,995,383 samples, 0.03%) + + + +aggr_j (10,585,259,737 samples, 16.29%) +aggr_j + + +check_preemption_disabled (8,402,056 samples, 0.01%) + + + +inc_mm_counter (50,218,216 samples, 0.08%) + + + +__sysvec_apic_timer_interrupt (17,579,002 samples, 0.03%) + + + +__GI_mprotect (182,048,336 samples, 0.28%) + + + +numa_bitmask_clearall (5,599,589 samples, 0.01%) + + + +__mod_lruvec_page_state (6,053,672 samples, 0.01%) + + + +perf_iterate_sb.constprop.0 (6,914,920 samples, 0.01%) + + + +check_preemption_disabled (68,262,730 samples, 0.11%) + + + +__rcu_read_unlock (13,815,728 samples, 0.02%) + + + +check_preemption_disabled (10,133,079 samples, 0.02%) + + + +free_pcppages_bulk (76,758,745 samples, 0.12%) + + + +vma_alloc_folio (772,127,209 samples, 1.19%) + + + +syscall (6,532,384 samples, 0.01%) + + + +perf_event_task_tick (12,104,828 samples, 0.02%) + + + +do_syscall_64 (181,659,392 samples, 0.28%) + + + +policy_nodemask (22,453,804 samples, 0.03%) + + + +asm_sysvec_apic_timer_interrupt (9,666,473 samples, 0.01%) + + + +__list_del_entry_valid (10,470,700 samples, 0.02%) + + + +charge_memcg (6,174,403 samples, 0.01%) + + + +blk_cgroup_congested (40,586,924 samples, 0.06%) + + + +qi_submit_sync (10,361,636 samples, 0.02%) + + + +qi_submit_sync (31,918,311 samples, 0.05%) + + + +update_process_times (6,050,543 samples, 0.01%) + + + +__hrtimer_run_queues (16,529,381 samples, 0.03%) + + + +__mmu_notifier_invalidate_range_end (115,936,904 samples, 0.18%) + + + +check_preemption_disabled (63,253,965 samples, 0.10%) + + + +unsigned long std::uniform_int_distribution<unsigned long>::operator (10,042,408,719 samples, 15.45%) +unsigned long std::unif.. + + +preempt_count_add (9,510,957 samples, 0.01%) + + + +check_preemption_disabled (13,830,042 samples, 0.02%) + + + +__this_cpu_preempt_check (190,911,889 samples, 0.29%) + + + +perf_iterate_ctx (6,914,920 samples, 0.01%) + + + +__folio_alloc (7,912,403 samples, 0.01%) + + + +scheduler_tick (16,752,938 samples, 0.03%) + + + +__next_zones_zonelist (53,945,455 samples, 0.08%) + + + +__hrtimer_run_queues (6,050,543 samples, 0.01%) + + + +asm_sysvec_apic_timer_interrupt (17,289,103 samples, 0.03%) + + + +perf_adjust_freq_unthr_context (16,429,960 samples, 0.03%) + + + +preempt_count_add (19,015,696 samples, 0.03%) + + + +QDPBench (64,991,973,041 samples, 100.00%) +QDPBench + + +__hrtimer_run_queues (30,941,206 samples, 0.05%) + + + +sysvec_apic_timer_interrupt (33,708,710 samples, 0.05%) + + + +charge_memcg (720,764,264 samples, 1.11%) + + + +exit_to_user_mode_prepare (37,494,429 samples, 0.06%) + + + +tick_sched_handle (9,511,188 samples, 0.01%) + + + +Aggregation<unsigned long, Sum, (10,559,503,981 samples, 16.25%) +Aggregation<unsigned long.. + + +down_read_trylock (34,461,877 samples, 0.05%) + + + +vm_mmap_pgoff (20,626,042 samples, 0.03%) + + + +__this_cpu_preempt_check (7,768,823 samples, 0.01%) + + + +folio_mapping (27,627,618 samples, 0.04%) + + + +__hrtimer_run_queues (7,738,669 samples, 0.01%) + + + +tick_sched_handle (7,738,669 samples, 0.01%) + + + +folio_add_new_anon_rmap (211,516,817 samples, 0.33%) + + + +_raw_spin_unlock (9,387,571 samples, 0.01%) + + + +check_preemption_disabled (17,249,086 samples, 0.03%) + + + +__mod_lruvec_state (24,529,700 samples, 0.04%) + + + +folio_add_lru (626,071,517 samples, 0.96%) + + + +asm_sysvec_apic_timer_interrupt (37,352,688 samples, 0.06%) + + + +entry_SYSCALL_64_after_hwframe (35,297,884 samples, 0.05%) + + + +update_process_times (16,429,960 samples, 0.03%) + + + +check_preemption_disabled (5,617,155 samples, 0.01%) + + + +__bitmap_intersects (8,634,504 samples, 0.01%) + + + +error_entry (49,248,297 samples, 0.08%) + + + +qi_submit_sync (73,250,576 samples, 0.11%) + + + +mas_walk (45,045,753 samples, 0.07%) + + + +asm_sysvec_apic_timer_interrupt (24,226,978 samples, 0.04%) + + + +__mod_lruvec_page_state (83,466,536 samples, 0.13%) + + + +qi_flush_dev_iotlb_pasid (25,031,737 samples, 0.04%) + + + +__next_zones_zonelist (56,964,967 samples, 0.09%) + + + +__this_cpu_preempt_check (9,946,903 samples, 0.02%) + + + +main (38,226,843,486 samples, 58.82%) +main + + +perf_event_task_tick (7,734,458 samples, 0.01%) + + + +__hrtimer_run_queues (17,579,002 samples, 0.03%) + + + +std::mersenne_twister_engine<unsigned long, 32ul, 624ul, 397ul, 31ul, 2567483615ul, 11ul, 4294967295ul, 7ul, 2636928640ul, 15ul, 4022730752ul, 18ul, 1812433253ul>::operator (3,845,999,512 samples, 5.92%) +std::me.. + + +release_pages (36,291,547 samples, 0.06%) + + + +intel_invalidate_range (115,936,904 samples, 0.18%) + + + +tick_sched_handle (13,970,459 samples, 0.02%) + + + +__mmu_notifier_invalidate_range (68,150,099 samples, 0.10%) + + + +__sysvec_apic_timer_interrupt (6,050,543 samples, 0.01%) + + + +asm_sysvec_apic_timer_interrupt (7,738,669 samples, 0.01%) + + + +check_preemption_disabled (9,448,828 samples, 0.01%) + + + +__mod_lruvec_state (17,248,509 samples, 0.03%) + + + +perf_event_task_tick (20,254,481 samples, 0.03%) + + + +perf_event_task_tick (6,050,543 samples, 0.01%) + + + +perf_event_task_tick (9,511,188 samples, 0.01%) + + + +exc_page_fault (8,805,563,396 samples, 13.55%) +exc_page_fault + + +hrtimer_interrupt (9,511,188 samples, 0.01%) + + + +perf_adjust_freq_unthr_context (9,510,812 samples, 0.01%) + + + +handle_mm_fault (8,460,936,359 samples, 13.02%) +handle_mm_fault + + +release_pages (20,246,708 samples, 0.03%) + + + +qi_flush_piotlb (31,918,311 samples, 0.05%) + + + +__sysvec_apic_timer_interrupt (17,289,103 samples, 0.03%) + + + +memcg_check_events (325,458,098 samples, 0.50%) + + + +check_preemption_disabled (6,904,971 samples, 0.01%) + + + +__do_sys_clone3 (35,297,884 samples, 0.05%) + + + +sysvec_apic_timer_interrupt (9,510,812 samples, 0.01%) + + + +lru_gen_del_folio.constprop.0 (112,145,661 samples, 0.17%) + + + +hrtimer_interrupt (9,505,799 samples, 0.01%) + + + +hrtimer_interrupt (16,429,960 samples, 0.03%) + + + +page_counter_try_charge (10,955,647 samples, 0.02%) + + + +irqentry_exit_to_user_mode (6,011,232 samples, 0.01%) + + + +scheduler_tick (7,734,458 samples, 0.01%) + + + +debug_smp_processor_id (9,510,684 samples, 0.01%) + + + +access_error (13,827,514 samples, 0.02%) + + + +tick_sched_handle (7,754,397 samples, 0.01%) + + + +__GI___mmap64 (20,626,042 samples, 0.03%) + + + +tlb_finish_mmu (377,008,847 samples, 0.58%) + + + +asm_exc_page_fault (11,048,516,068 samples, 17.00%) +asm_exc_page_fault + + +__vm_munmap (1,409,365,019 samples, 2.17%) +_.. + + +update_process_times (7,738,669 samples, 0.01%) + + + +asm_sysvec_apic_timer_interrupt (26,989,061 samples, 0.04%) + + + +update_process_times (13,970,459 samples, 0.02%) + + + +zap_page_range_single (15,499,112 samples, 0.02%) + + + +irqentry_exit_to_user_mode (102,779,969 samples, 0.16%) + + + +perf_adjust_freq_unthr_context (12,104,828 samples, 0.02%) + + + +pte_alloc_one (12,100,915 samples, 0.02%) + + + +check_preemption_disabled (270,308,138 samples, 0.42%) + + + +tick_sched_timer (12,104,828 samples, 0.02%) + + + +lru_gen_del_folio.constprop.0 (253,811,943 samples, 0.39%) + + + +do_user_addr_fault (8,783,092,560 samples, 13.51%) +do_user_addr_fault + + +tick_sched_handle (9,510,812 samples, 0.01%) + + + +preempt_count_sub (6,052,275 samples, 0.01%) + + + +__mod_node_page_state (21,781,465 samples, 0.03%) + + + +check_preemption_disabled (15,547,728 samples, 0.02%) + + + + diff --git a/qdp_project/evaluation-results/distprefetch/qdp-xeonmax-distprefetch-tca1-tcb1-tcj1-tmul32-wl4294967296-cs8388608.csv b/qdp_project/evaluation-results/distprefetch/qdp-xeonmax-distprefetch-tca1-tcb1-tcj1-tmul32-wl4294967296-cs8388608.csv new file mode 100644 index 0000000..53385f7 --- /dev/null +++ b/qdp_project/evaluation-results/distprefetch/qdp-xeonmax-distprefetch-tca1-tcb1-tcj1-tmul32-wl4294967296-cs8388608.csv @@ -0,0 +1,6 @@ +run;rt-ns;rt-s;result[0];scana-run;scana-wait;scanb-run;scanb-wait;aggrj-run;aggrj-wait;cache-hr; +0;115654584;0.115655;13289362112;52779129;910269;40396919;18510;38023885;57801940;0.630859; +1;106320156;0.10632;13289362112;54035883;811222;30772712;2099;35307890;58523290;0.867188; +2;109649444;0.109649;13289362112;55323012;172051;25431929;1944;42405751;53954172;0.904297; +3;103917217;0.103917;13289362112;55017317;563932;18917532;1851;33247331;58456679;0.951172; +4;109026019;0.109026;13289362112;57698280;163979;17124680;1901;33128356;59639003;0.929688; diff --git a/qdp_project/evaluation-results/distprefetch/qdp-xeonmax-prefetch-tca1-tcb1-tcj1-tmul32-wl4294967296-cs8388608.csv b/qdp_project/evaluation-results/distprefetch/qdp-xeonmax-prefetch-tca1-tcb1-tcj1-tmul32-wl4294967296-cs8388608.csv new file mode 100644 index 0000000..2f2b0a3 --- /dev/null +++ b/qdp_project/evaluation-results/distprefetch/qdp-xeonmax-prefetch-tca1-tcb1-tcj1-tmul32-wl4294967296-cs8388608.csv @@ -0,0 +1,6 @@ +run;rt-ns;rt-s;result[0];scana-run;scana-wait;scanb-run;scanb-wait;aggrj-run;aggrj-wait;cache-hr; +0;160344607;0.160345;13289362112;90128445;1234179;19263417;2363;54818256;91926384;0.828125; +1;157383436;0.157383;13289362112;98793808;1667533;20995896;2638;44546581;98991684;0.978516; +2;155334228;0.155334;13289362112;94452676;955473;22749211;2593;47506425;96586451;0.980469; +3;164084763;0.164085;13289362112;84127485;1682755;28712319;2339;58561965;87205796;0.789062; +4;160060161;0.16006;13289362112;90740477;3807158;29278218;2472;54141520;91080799;0.851562;