Full Scale Performance: Single Process, Sharrow Off, Explicit Chunking

[aletzdy]

This is the issue to report on memory usage and runtime performance...

data_dir: "data-full" full scale skims (24333 MAZs)
households_sample_size: 0 (full scale 100% sample of households)
sharrow: "false"
multiprocess: false single process
chunk_training_mode: explicit

[aletzdy]

Run with full sample, sharrow on, and single process (1 TB memory, Intel Xeon Gold 6342 @ 2.8GHz machine).

Runtime is 1428.2 mins (compared to 1,433.1 mins for a similar run with NO chunking)
Chunking is set to explicit in settings_mp.yaml, and explicit chunking is enabled for a number of models whose memory usage was higher than 300Gb in a previous sharrow run with same specs but with NO chunking. These models are:

compute_accessbility
mandatory_tour_scheduling
non-mandatory_tour_scheduling
trip_destination

For these models, the argument explicit_chunk was set to 0.5 in each respective model's yaml file, indicating the need for 2 (=1/0.5) chunks. Further chunks may be added in other tests and as required.

timing_log.csv
activitysim.log
memory_profile.csv

Below is the run without chunking:

<style> </style>

event	full_rss_gb_chunking	full_rss_gb_No_chunking	Difference	% Diff accounting for skims
preload_injectables	2.167452	2.527322	-0.35987	NA
initialize_proto_population	173.9227	174.1077	-0.18509	NA
compute_disaggregate_accessibility	206.3356	201.5561	4.779454	17.4%
initialize_landuse	180.1346	175.3758	4.75886	375.3%
initialize_households	198.2141	193.3762	4.837839	25.1%
compute_accessibility	276.3907	367.4861	-91.0954	-47.1%
av_ownership	184.3127	180.3675	3.945181	63.0%
auto_ownership_simulate	202.3356	197.699	4.636545	19.7%
work_from_home	193.0878	192.2186	0.869179	4.8%
external_worker_identification	194.0765	192.6287	1.447735	7.8%
external_workplace_location	194.758	192.3864	2.371576	13.0%
school_location	292.9196	289.0295	3.890065	3.4%
workplace_location	402.6434	397.1514	5.49206	2.5%
transit_pass_subsidy	194.9363	192.3512	2.585076	14.2%
transit_pass_ownership	194.0668	193.3555	0.711307	3.7%
vehicle_type_choice	270.9691	265.4805	5.488607	6.0%
adjust_auto_operating_cost	183.9534	178.5603	5.393015	121.1%
transponder_ownership	188.1608	182.8532	5.30756	60.7%
free_parking	194.9765	193.1514	1.825108	9.6%
telecommute_frequency	195.4649	192.9583	2.506637	13.3%
cdap_simulate	195.6484	193.3964	2.252005	11.7%
mandatory_tour_frequency	195.0767	194.2196	0.857059	4.3%
mandatory_tour_scheduling	330.5758	453.69	-123.114	-44.0%
school_escorting	214.1988	208.6679	5.530911	16.0%
joint_tour_frequency_composition	205.0339	201.3234	3.710493	13.6%
external_joint_tour_identification	201.6065	201.7927	-0.18614	-0.7%
joint_tour_participation	199.2767	194.9526	4.324151	20.7%
joint_tour_destination	207.107	202.9316	4.175458	14.5%
external_joint_tour_destination	196.1608	191.8689	4.291928	24.2%
joint_tour_scheduling	212.2434	212.0547	0.188678	0.5%
non_mandatory_tour_frequency	238.0545	233.7386	4.315931	7.2%
external_non_mandatory_identification	208.9876	207.5797	1.407865	4.2%
non_mandatory_tour_destination	383.1723	379.6374	3.534909	1.7%
external_non_mandatory_destination	197.0708	192.72	4.350751	23.4%
non_mandatory_tour_scheduling	227.4625	275.858	-48.3955	-47.6%
vehicle_allocation	218.2018	217.5814	0.620433	1.4%
tour_mode_choice_simulate	217.6302	212.2314	5.398741	14.2%
atwork_subtour_frequency	196.0487	190.7215	5.327159	32.1%
atwork_subtour_destination	295.5799	290.2229	5.357048	4.6%
atwork_subtour_scheduling	211.7981	206.3961	5.401965	16.7%
atwork_subtour_mode_choice	198.8897	193.8696	5.020123	25.4%
stop_frequency	222.6066	217.8433	4.7633	10.9%
trip_purpose	199.3885	195.7768	3.611701	16.7%
trip_destination	426.6972	536.408	-109.711	-30.3%
trip_purpose_and_destination	206.8114	201.6604	5.150953	18.7%
trip_scheduling	208.1987	204.3938	3.804885	12.6%
trip_mode_choice	224.9043	219.6366	5.267706	11.6%
parking_location	292.0136	303.9549	-11.9413	-9.2%
write_data_dictionary	210.6467	207.9639	2.682831	7.9%
track_skim_usage	204.6225	202.1674	2.455048	8.7%
write_trip_matrices	298.8238	296.5611	2.262761	1.8%
write_tables	257.3621	255.2239	2.138206	2.6%
finalizing	230.174	228.311	1.862975	3.4%