dfatool - Performance Model Generation for Configurable System Components

Age	Commit message (Collapse)	Author	Lines
2021-01-14	energytrace drift compensation: Handle undetected transitions	Daniel Friesel	-5/+76

2021-01-14	EnergyTrace drift compensation: optimize via shortest paths	Daniel Friesel	-68/+68
	Right now performance is worse than the previous greedy approach as the dijkstra variant does not take into account that a transition may be missing from the set of detected changepoints (i.e., it assumes that the set of detected changepoints contains the transition timestamp, which is not always the case). This will be fixed in the next commit by adding nodes for the expected transition timestamp (with a slightly higher weight to ensure there are no proper nodes in the vicinity) -- or something similar.
2021-01-13	pelt: Allow overrides via environment variables	Daniel Friesel	-4/+13

2021-01-13	EnergyTrace loader: remove bogus tail sync data as well	Daniel Friesel	-7/+14

2021-01-08	model transition power, not energy	Daniel Friesel	-5/+2
	in contrast to duration/energy, duration/power are independent
2020-12-15	add proof of concept for EnergyTrace++ based drift compensation	Daniel Friesel	-2/+35

2020-12-15	dataprocessor: export drift compensation data	Daniel Friesel	-0/+14

2020-12-14	energytrace: add pelt-based drift compensation experiment.	Daniel Friesel	-1/+128
	Enable with DFATOOL_COMPENSATE_DRIFT=1 so far it's pretty unreliable.
2020-12-03	use common energytrace loader code	Daniel Friesel	-25/+12
	this also fixes a nasty off-by-one in the barcode loader (now _load_energytrace): wrong: interval_start_timestamp = data[:-1, 0] * 1e-6 correct: interval_start_timestamp = data[1:, 0] * 1e-6
2020-11-27	clean up energytrace drift compensation and raw model generation code	Daniel Friesel	-146/+132

2020-11-26	some comments	Daniel Friesel	-5/+0

2020-11-19	DataProcessor: Handle broken LA measurements	Daniel Friesel	-0/+9

2020-11-16	do not parse energytrace logs with large sync offset	Daniel Friesel	-1/+1

2020-11-09	DataProcessor: Warn for positive and negative offset errors	Daniel Friesel	-1/+1

2020-10-30	Add DFATOOL_EXPORT_LASYNC variable for ET+LA / ET+Timer sync eval	Daniel Friesel	-0/+17

2020-10-23	minor refactoring	Daniel Friesel	-1/+1

2020-10-22	Improve sync=la timing restoration. There's still something fishy though...	Daniel Friesel	-2/+3

2020-10-22	unfuck LA<->ET drift calculation	Daniel Friesel	-2/+8

2020-10-21	--plot-traces: use the correct time base for each backend	Daniel Friesel	-6/+9

2020-10-20	DataProcessor: comments	Daniel Friesel	-10/+13

2020-10-20	DataProcessor: improve drift compensation	Daniel Friesel	-30/+27
	it still isn't satisfactory
2020-10-19	ET+LA: add --plot-traces support, actually calculate standard deviation.	Daniel Friesel	-12/+15
	Jungejungejungejungejunge...
2020-10-19	debug log	Daniel Friesel	-3/+14

2020-10-16	Code aus Lennarts BA-repo	Daniel Friesel	-0/+374