cacount - enumerate finite space 1D CA state space

Age	Commit message (Collapse)	Author
2013-06-14	compute cycle redundancy again, refractor, optimize	Jan Huwald

2013-06-14	.	Jan Huwald

2013-06-14	refractor, change cycle identification	Jan Huwald
	Major changes: - compute cycle id (cycle minimum) in parallel to future state - skip computation of cycle stats for non-canonical cycles Minor changes: - move computation of several arrays around to improve locality and reduce random memory reads - distinguish between State and StateIter: the later can contain maxState + 1 and is used in loops and as pointer. - rename maxState to numState, add acutal maxState - time performance of memory allocation
2013-06-14	set default bit-width to 16	Jan Huwald
	Default value should be quick to see what the program does.
2013-06-14	remove packed_array	Jan Huwald
	In addition to being broken by design it was order_s_ of magnitude to slow. Adding cores to the computation increased runtime.
2013-06-07	add mmalloc.hpp, support hugetlbfs allocation	Jan Huwald

2013-06-04	add verbose timer function, replace bitset w/ packed_array	Jan Huwald
	Replacing bitset with packed_array is neccessary to allow parallel access to proximate array cells.
2013-06-04	go to 64-bit State, use bit-packed array	Jan Huwald

2013-06-03	more parallelism, cheap race check	Jan Huwald
	Assure that at last each parallel thread processes at least maxWorkdSize elements. This garantues that even for packed arrays of bit-sized elements that thread boundaries lie on machine word boundaries.
2013-06-03	count garden of eden states	Jan Huwald

2013-03-06	add compile-time variable bit length	Jan Huwald

2013-02-28	.	Jan Huwald

2013-02-28	add parallel execution	Jan Huwald

2013-02-28	get memory via mmap, try huge tables and prepopulation	Jan Huwald

2013-02-27	merge symmetric cycles	Jan Huwald

2013-02-27	make iterTrans verbose	Jan Huwald

2013-02-27	add cycle statistics function	Jan Huwald

2013-02-27	Initial commit	Jan Huwald