1brc - my implementations for the billion row challenge

	Commit message (Collapse)	Author	Age	Files	Lines
*	nobody should try this at home (#709)	Jaromir Hamala	2024-02-01	1	-63/+104
\|
*	jerrinot - final(?) improvements (#690)	Jaromir Hamala	2024-01-31	1	-165/+182
\| \| \| \| \| \| \| \| \| \| \|	* decrease instruction level parallelism it turns out doing 2 things was too much. perf annotate showed spilling. * more trickery with latency hiding * work-stealing, lookp tables, credits * do not assume gender
*	jerrinot - running out of ideas (#631)	Jaromir Hamala	2024-01-28	1	-19/+14
\| \| \| \| \|	* another shameless copycat from thomas: less safepoints * I have no idea what I am doing
*	jerrinot's improvement (#607)	Jaromir Hamala	2024-01-28	1	-111/+167
\| \| \| \| \| \| \| \| \| \|	* some random changes with minimal, if any, effect * use munmap() trick credit: thomaswue * some smaller tweaks * use native image
*	jerrinot's improvement - fast-path for short keys (#545)	Jaromir Hamala	2024-01-23	1	-160/+273
\| \| \| \| \| \| \| \| \| \| \|	* fast-path for keys<16 bytes * fix off by one error the mask is wrong for he 2nd word when len == 16 * less chunks per thread seems like compact code wins. on my test box anyway.
*	jerrinot's improvement (#514)	Jaromir Hamala	2024-01-20	1	-84/+67
\| \| \| \| \| \| \|	* refactoring * segregated heap for names also a different hashing function. turns out hashing just first word is good enough
*	edge-case in hashing fixed (#459)	Jaromir Hamala	2024-01-17	1	-152/+151
\| \| \|	also a bunch of smaller improvements
*	jerrinot's initial submission (#424)	Jaromir Hamala	2024-01-15	1	-0/+482
	* initial version let's exploit that superscalar beauty! * give credits where credits is due also: added ideas I don't want to forget