2.1.0: parallel resolution using PETSc solvers; new Gmsh2 output
format; new experimental SLEPc-based eigensolvers; various bug and
performance fixes (missing face basis functions, slow PETSc assembly
with global quantities, ...)

2.0.0: general code cleanup (separated interface from legacy code;
removed various undocumented, unstable and otherwise experimental
features; moved to C++); updated input file formats; default solvers
are now based on PETSc; small bug fixes (binary .res read, Newmark
-restart).

1.2: Windows versions do not depend on Cygwin anymore; major parser
cleanup (loops & co).

1.1: New eigensolver based on Arpack (EigenSolve); generalized old
Lanczos solver to work with GSL+lapack; reworked PETSc interface,
which now requires PETSc 2.3; documented many previously undocumented
features (loops, conditionals, strings, link constraints, etc.);
various improvements and bug fixes.

1.0: New license (GNU GPL); added support for latest Gmsh mesh file
format; more code cleanups.

0.91: Merged moving band and multi-harmonic code; new loops and
conditionals in the parser; removed old readline code (just use GNU
readline if available); upgraded to latest Gmsh post-processing
format; various small enhancements and bug fixes.

0.89: Code cleanup.

0.88: Integrated FMM code.

0.87: Fixed major performance problem on Windows (matrix assembly and
post-processing can be up to 3-4 times faster with 0.87 compared to
0.86, bringing performance much closer to Unix versions); fixed stack
overflow on Mac OS X; Re-introduced face basis functions mistakenly
removed in 0.86; fixed post-processing bug with pyramidal basis
functions; new build system based on autoconf.

0.86: Updated Gmsh output format; many small bug fixes.

0.85: Upgraded communication interface with Gmsh; new ChangeOfValues
option in PostOperation; many internal changes.

0.84: New ChangeOfCoordinate option in PostOperation; fixed crash in
InterpolationAkima; improved interactive postprocessing (-ipos);
changed syntax of parametric OnGrid ($S, $T -> $A, $B, $C); corrected
Skin for non simplicial meshes; fixed floating point exception in
diagonal matrix scaling; many other small fixes and cleanups.

0.83: Fixed bugs in SaveSolutions[] and InitSolution[]; fixed
corrupted binary post-processing files in the harmonic case for the
Gmsh format; output files are now created relatively to the input file
directory; made solver options available on the command line; added
optional matrix scaling and changed default parameter file name to
'solver.par' (Warning: please check the scaling definition in your old
SOLVER.PAR files); generalized syntax for lists (start:[incr]end ->
start:end:incr); updated reference guide; added a new short
presentation on the web site; OnCut -> OnSection; new functional
syntax for resolution operations (e.g. Generate X -> Generate[X]);
many other small fixes and cleanups.

0.82: Added communication socket for interactive use with Gmsh;
corrected (again) memory problem (leak + seg. fault) in time stepping
schemes; corrected bug in Update[].

0.81: Generalization of transformation jacobians (spherical and
rectangular, with optional parameters); changed handling of missing
command line arguments; enhanced Print OnCut; fixed memory leak for
time domain analysis of coupled problems; -name option; fixed
seg. fault in ILUK.

0.80: Fixed computation of time derivatives on first time step (in
post-processing); added tolerance in transformation jacobians; fixed
parsing of DOS files (carriage return problems); automatic memory
reallocation in ILUD/ILUK.

0.79: Various bug fixes (mainly for the post-processing of intergal
quantities); automatic treatment of degenerated cases in
axisymmetrical problems.

0.78: Various bug fixes.

0.77: Changed syntax for PostOperations (Plot suppressed in favour of
Print; Plot OnRegion becomes Print OnElementsOf); changed table
oriented post-processing formats; new binary formats; new error
diagnostics.

0.76: Reorganized high order shape functions; optimization of the
post-processing (faster and less bloated); lots of internal cleanups.

0.74: High order shape functions; lots of small bug fixes.

0.73: Eigen value problems (Lanczos); minor corrections.

0.7: constraint syntax; fourier transform; unary minus correction;
complex integral quantity correction; separate iteration matrix
generation.

0.6: Second order time derivatives; Newton nonlinear scheme; Newmark
time stepping scheme; global quantity syntax; interactive
post-processing; tensors; integral quantities; post-processing
facilities.

0.3: First distributed version.
