2017-09-12 boud
	* v0.1.7.1 - the private routine report_request_too_much_mem
	was incorrectly exported in 0.1.7; a libtool Makefile.am
	option now prevents the export
	* v0.1.7 portability: casting protection (size_t) in
	alloc_big_array.*() for parameters given to malloc();
	test_alloc_big_array: if allocation fails, do not assign to the
	unallocated array.

2017-09-10 boud
	* v0.1.6.1 include the NEWS file update for v0.1.6
	* v0.1.6 test_alloc_big_array, Omega_D_precalc: cast preprocessor
	constants before passing them as arguments to functions;
	library: 0.1.0 because of minor (non-interface) change in 	Omega_D_precalc

2017-08-18 boud
	* v0.1.5 version ready for Debian GNU/Linux distribution

2017-08-17 boud
	* v0.1.4.5 remove inhomog_shared binary from top Makefile.am
	* v0.1.4.4 reorganise minor tests to reduce unnecessary symbols
	in .h files
	* v0.1.4.3 run TESTS_SLOW only with ./configure --enable-devmode
	* v0.1.4.2 remove inclusion of fftw3.h in lib/test_sigma_invariants.c
	* v0.1.4.1 add file "compile"
	* v0.1.4 dpkg-configure .pc.in file and Makefile.am changes;
	preparing for debian version

2017-08-16 boud
	* v0.1.3 libtoolize - both shared and static libraries;
	install include files in subdirectory of include/;
	remove obsolete system.h include file;
	doc/examples/ demo C program + README

2017-08-10 boud
	* v0.1.2 int64_t in Omega_D_precalc input parameters;
	bug fix in alloc_big_array free RAM check for linux;
	Omega_D_precalc exits politely if out of memory.

2017-07-30 boud
	* v0.1.1 main program: allow I II III command line inputs;
	add reference to arxiv:1706.06179; first draft of
	doxygen documentation.

2017-06-18 boud
	* v0.1.0 first public release @bitbucket

2017-06-16 boud
	* v0.0.70 update configure.ac
	* v0.0.69 inhomog.c front end -> biscale front end; man page

2017-06-15 boud
	* v0.0.68 +(test_)biscale_partition

2017-05-25 boud
	* v0.0.67 revert 0.0.66; enable DETECT_SUDDEN_COLLAPSE in find_collapse_time()
	* v0.0.66 Omega_D_precalc: consider !isnormal a_D to be the collapsed case
	* v0.0.65 Omega_D_precalc: print uncollapsed count

2017-05-03 boud
	* v0.0.64 minor: +lib/c_gsl_wrap.c for f90 front ends

2017-03-17 boud
	* v0.0.63 scale_factor_D_(Ray|Ham).c - bug fix: do not leave N_T_SPLINE'th value undefined
	* v0.0.62 scale_factor_D_(Ray|Ham).c - bug fix: DISABLE_Q block for EdS background

2017-02-09 boud
	* v0.0.60 scale_factor_D_Ray.c - remove obsolete DISABLE_Q block
	* v0.0.61 update test_power_spectrum_flatspace.c, test_Omega_D.c to test unnormalised case

2016-12-18 boud
	* v0.0.59 scale_factor_D_(Ray|Ham).c - allow either Q or Lambda to
	be disabled in ODE integration

2016-12-02 boud
	* v0.0.58 Omega_D_example - disable Giga-printing want_verbose option

2016-12-01 boud
	* v0.0.57 Omega_D_example - high mass end - 50-90 Mpc/h

2016-12-01 boud
	* v0.0.56 Omega_D_precalc - tiny corrections - LCDM Planck 2015

2016-11-20 boud
	* v0.0.55 allow -DDISABLE_Q=1 for scale_factor_D_Ray.c
	- Omega_D_precalc - redefine a_D_linear as section-weighted mean

2016-11-14 boud
	* v0.0.54 separate print loop for sqrt(E[sigma(I)])
	* v0.0.53.1  N_INITCOND_KBS 32768
	* v0.0.53 rza_integrand_params -> pointers at all intermediate levels
	* v0.0.52 Omega_D_example - normal chimera-level numbers
	* v0.0.51 experimental - calculate invariants only once per R

2016-11-11 boud
	* v0.0.50 "unphysical" array in case user gives unsafe parameters;
	- Omega_D_precalc seems OK now;
	- _SCALE_FACTOR_ normalisations no longer hardwired
	- some front end programs still need _SCALE_FACTOR_ updating
	- make check -> 8 passes

2016-11-09 boud
	* v0.0.49 *power_spectrum_flatspace* updated, numerically safer
	  + omega_d_precalc_  as routine callable from fortran

2016-11-05 boud
	* v0.0.48 Omega_D_example - solve detached HEAD/branch confusion
	* v0.0.47 Omega_D_example - fix missing [i_R] bug in find_collapse_time call

2016-11-02 boud
	* v0.0.46 Omega_D_example - N_INITCOND_KBS: s/8/512/; print_a_few_omegas = 1

2016-11-01 boud
	* v0.0.45 inhomog.h: revert to standard scale factor normalisation

2016-10-31 boud
	* v0.0.44 modularise collapse detection: find_collapse_time();
	+Omega_D_precalc
	+find_collapse_time in Omega_D_example - bug correction, should
	find more collapses

2016-10-26 boud
	* v0.0.43 Omega_D_example: linear R intervals;
	+structure precalculated_invariants_s

2016-10-25 boud
	* v0.0.42 Omega_D_example: EdS case only;
	- power_spectrum_flatspace.h normalisation 1.0;
	- sigma8 normalisation;
	- clearer naming of init condition strategies

2016-06-05 boud
	* v0.0.41 Omega_D_example: EdS case only; power_spectrum_flatspace.h normalisation 0.5

2016-06-02 boud
	* v0.0.40 Omega_D_example: LCDM case only (N_COSM_(I|1))

2016-02-09 boud
	* v0.0.39 Omega_D_example: i_KBS case 7: linear theory+spherical

2016-01-27 boud
	* v0.0.38 N_RZA2 512, n_calls_invariants = 300000

2015-10-12 boud
	* v0.0.37 Omega_D_example:  N_RZA2 256, n_calls_invariants = 100000; scripts/plot_OmD_small*
	* Omega_D_example: z_c unnormalised, clearer calculation; small N's for small computer

2015-10-03 boud
	* v0.0.36 Omega_D_example: dynamically alloc and free multiD arrays
	* v0.0.35 Omega_D_example:  N_RZA2 256, n_calls_invariants = 100000
	* Omega_D_example: I_KBS_CASE and N_SIGMA_SIGMA as compile level or default defines
	* Omega_D_example - setting up for chimera run (unfinished): modified i_KBS cases
	* lib/inhomog.h #defines for init cond and integration choices; minor cleanups
	* scale_factor_D_Ray: added missing a_initial factor; growth_function.c updates; Omega_D_BAO OK
	* Hamiltonian init conditions; integrator switched to Raychaudhuri; based on 1RJS work session
	* scale_factor_Ham_one_try: restart from beginning when re-estimating t_neg_sqrt
	* test_gsl_multifit for least-squares fitting of some non-linear functions

2015-02-16 boud
	* v0.0.34
	* Omega_D_example minor bug: replace A_D_NULL by SCALE_FACTOR_A_D_NEARLY_ZERO and shift to inhomog.h
	* scale_factor_D: Ham enabled

2015-02-16 boud
	* v0.0.32.1 [31 was committed but reverted]
	* new front ends: Omega_D_BAO, Omega_D_effWEC, Omega_D_example
	* curvature_backreaction( ) written
	* scale_factor_D forks to either scale_factor_Ray or scale_factor_Ham
	* want_planar parameter introduced for all main work functions
	* Omega_D_example illustrates redshift of collapse distributions
	* Omega_D_example: high values of n_calls_invariants, N_RZA2 for supercomputer check

2013-11-11 boud
	* v0.0.30: test_Omega_D: make check - unused test commented out

2013-11-08 boud
	* v0.0.29: test_Omega_D: new RZA2-based check values - make check
	should give pass = 0

2013-11-08 boud
	* v0.0.28: delta_tilde_integrals: DEFN 0 of (C22): one replacement
	s/k_mod_3_sq/k_mod_3_4th/

2013-10-28  boud
	* v0.0.27: oscillatory EisHu98 power_spectrum survives tests;
	its test function should be OK with make check
	* v0.0.27.1: same as 0.0.27 but includes updated configure*

2013-10-20  boud
	* v0.0.26: test_sigma_invariants: better openmp usage (parallel
	for, schedule(dynamic))

2013-10-18  boud
	* v0.0.25: non-oscillatory EisHu98 power_spectrum seems OK

2013-10-17  boud
	* v0.0.24: test_sigma_invariants gsl_rng handling improved
	(RANLUX/ranlxd2; GSL_RNG_SEED read once and further seeds generated
	internally)

2013-10-13  boud
	* v0.0.21: test_sigma_invariants rewritten; III OK.
	* v0.0.22: malloc for possibly big arrays -> avoid seg viol.
	* v0.0.23: test_sigma_invariants anisotropic i,j,k_arrays: III still OK :).

2013-10-12  boud
	* v0.0.20: delta_tilde_interp(): discretise to
	avoid interpolation subtleties in a complex
	discrete Fourier spectrum (series) - linear 3D
	rectangular interpolation loses power

2013-10-10  boud
	* v0.0.18: fftw3 for test_sigma_invariants delta realisations
	* v0.0.19: C9, C20 bug corrections

2013-10-09  boud
	* v0.0.17: valgrind clean of test_sigma_invariants:
	free gsl_rng, fftw3 allocations

2013-10-08  boud
	* v0.0.16: fftw3 for test_sigma_invariants

2013-10-07  boud
	* v0.0.13: version for BKS Appendix C testing: Invs I, II
	* v0.0.14: inhomog.c: corrected header include
	* v0.0.15: sigma_square_invariant_III.c + delta_tilde_integrands.c bug correction in III:
	three dot products had not been squared;
	parameters chosen for 32-core multi-hour calculation

2013-10-04  boud
	* v0.0.12: scale_factor_D, Omega_D: flat Lambda case seems OK

2013-10-02  boud
	* v0.0.11: seven checks now run with make checks

2013-10-01  boud
	* v0.0.10: Omega_D; scale factor normalisations to inhomog.h;
	new normalisation of \xi (avoids dimensional violation);
	kinematic_backreaction.c: bug removed: inv_II wasn't squared in Q_D denominator;
	spherical test RZA2 V.B.3 in kinematic_backreaction;
	all FLRW scale factor functions shifted to FLRW_background;
	rough first draft of spatial Ricci curvature code;
	growth_function;
	unit testing: make check should generate five different test passes.

2013-09-24  boud
	* v0.0.9.2: with tag in git (hopefully)
	* v0.0.9.1: with tag in git (hopefully)
	* v0.0.9: scale_factor_D.c: looks consistent with
	a_D/a for RZA2 Fig 2.left top, bottom curves without
	modifying parameters; values about 10% lower than
	in RZA2 Fig 2 - not yet "precise cosmology" ;)

2013-02-16  boud
	* v0.0.8: kinematic_backreaction.c: rza_Q_D from (49) of
	Buchert et al RZA2 20120722 preprint; testing difficult
	until a_D is programmed;
	* inhomog.h: switching to INHOM_INV_III_DEFN 0 for comparison
	with existing calculations

2013-02-15  boud
	* v0.0.7.1: bug fix: power_spectrum_flatspace.c - static
	should't be used in functions called by competing openmp
	threads

2013-02-15  boud
	* v0.0.7: optional shell window function instead of sphere;
	dependence on astromisc-0.1.18.20 for parse_noempty_strtox

2013-02-14  boud
	* v0.0.6.1: new formula for sigma_sq_invariant_III hidden
	temporarily while analytical calculation is checked

2013-02-09  boud
	* v0.0.6: openmp to parallelise  test_sigma_sq_invariants()
	* v0.0.5: sigma_sq_invariant_III: new analytical formula - choose
	new vs old in inhomog.h

2013-02-05  boud
	* v0.0.4.1: factor of 8 was not validated in 0.0.3, normalisation
	wrt BKS00 Fig 13 now 201^{-3};
	sigma_sq_invariant_II: matches BKS00 Fig 13 main curve;
	sigma_sq_invariant_III: matches BKS00 claim to order of magnitude
	if sign is reversed.

2013-02-05  boud
	* v0.0.3: sigma_sq_invariant_I matches BKS00 Fig 13 main curve
	with 1e-6 renormalisation, calculation t = 5 s; script provided.

2013-02-04  boud
	* v0.0.2: sigma_sq_invariant_I programmed, z=201 vs z=0 issues buggy,
	BKS00 Fig 13 not reproduced; individual tests via -t option.

2012-11-08  boud
	* example of Monte Carlog integration

2012-10-29  Boud Roukema - boud cosmo.torun.pl

	* inhomog: initial version 0.0.1. Buggy.
