Commits

Branch selector

 master

User selector

stevengj

Datepicker

All time

Commit History

Commits on Aug 5, 2015

• fix LaTeX typo, thanks to Gael Lorieul

  stevengj

  committed
  f6339ea

  Copy full SHA for f6339ea

Commits on Jan 30, 2015

• fix FFTW#29

  stevengj

  committed
  506c163

  Copy full SHA for 506c163

Commits on Dec 7, 2014

• Merge pull request FFTW#27 from mpip/master

  Show description for d946668
  stevengj

  committed
  d946668

  Copy full SHA for d946668

Commits on Aug 12, 2014

• fix FFTW#21 (don't use float128 on Portland compilers, which pretend to be gcc)

  stevengj

  committed
  3659757

  Copy full SHA for 3659757

Commits on Jul 10, 2014

• fix FFTW#19: missing Fortran interface for fftwq_alloc_real

  stevengj

  committed
  2493129

  Copy full SHA for 2493129

Commits on Jul 8, 2014

• fix FFTW#18 (disable float128 for CUDACC)

  stevengj

  committed
  07ef78d

  Copy full SHA for 07ef78d

Commits on Mar 4, 2014

• more .gitignore additions

  stevengj

  committed
  f8048af

  Copy full SHA for f8048af

• some fixes for make distcheck

  stevengj

  committed
  5a51b3f

  Copy full SHA for 5a51b3f

• copyright year update

  stevengj

  committed
  836af27

  Copy full SHA for 836af27

• updates for 3.3.4

  stevengj

  committed
  853f9f7

  Copy full SHA for 853f9f7

• another file in .gitignore

  stevengj

  committed
  bf30f5a

  Copy full SHA for bf30f5a

• add .gitignore

  stevengj

  committed
  c82b4fd

  Copy full SHA for c82b4fd

Commits on Jan 16, 2014

• added fftw_sprint_plan to output plan info to a string (so that the caller can be more flexible about how it is displayed)

  stevengj

  committed
  146fa8d

  Copy full SHA for 146fa8d

• document fftw_alignment_of (since I found it useful in Julia, other people may too)

  stevengj

  committed
  53e1fdb

  Copy full SHA for 53e1fdb

Commits on Sep 20, 2013

• fix typo

  stevengj

  committed
  c6acf03

  Copy full SHA for c6acf03

Commits on Feb 7, 2013

• use Win32 threads, not pthreads, if both are present (it's not clear why Windows users would ever want the latter); see also JuliaLang/julia#2015

  stevengj

  committed
  2f9d0a4

  Copy full SHA for 2f9d0a4

• I found it useful in the Julia interface to call fftw_alignment_of (in order to check plan applicability), in which case we need to IFFTW_EXTERN it for Windows; might be worth considering documenti…

  Show description for b862318
  stevengj

  committed
  b862318

  Copy full SHA for b862318

Commits on Nov 25, 2012

• fixed deadlock bug caused by bogosity flag getting out of synch between processes; thanks to Michael Pippig for the bug report

  stevengj

  committed
  01810ba

  Copy full SHA for 01810ba

Commits on Nov 20, 2012

• revert part of Taylor patch to acx_mpi.m4: do not link -lmpi if mpicc works without libraries, as -lmpi may be some completely different MPI implementation

  stevengj

  committed
  466f579

  Copy full SHA for 466f579

• fix deadlock bug (thanks to Michael Pippig for the bug report and patch, and to Graham Dennis for the bug report) in which some processes called MPI_Alltoall and some called MPI_Alltoallv

  stevengj

  committed
  6104602

  Copy full SHA for 6104602

Commits on Jun 29, 2012

• whoops, call omp_get_max_threads; thanks to Hanno Rein for the bug report

  stevengj

  committed
  6bc94ae

  Copy full SHA for 6bc94ae

Commits on Mar 6, 2012

• formatting tweak

  stevengj

  committed
  f9a0570

  Copy full SHA for f9a0570

Commits on Mar 2, 2012

• note that WISDOM_ONLY is a documented flag

  stevengj

  committed
  ad79a0a

  Copy full SHA for ad79a0a

• check for icc pretending to be gcc before including quad-precision decls; thanks to Michael Anselmi for the bug report

  stevengj

  committed
  adf4cda

  Copy full SHA for adf4cda

• foo_CFLAGS needs to manually include AM_CFLAGS; thanks to Henry Gomersall for the Windows bug report

  stevengj

  committed
  99aeb38

  Copy full SHA for 99aeb38

Commits on Feb 21, 2012

• added Fortran NEWS

  stevengj

  committed
  06fff65

  Copy full SHA for 06fff65

• move non-portable extended/quad precision F03 interfaces into separate .f03 files (while keeping double/single in fftw3.f03 for minimal ABI breakage)

  stevengj

  committed
  51e3386

  Copy full SHA for 51e3386

Commits on Nov 9, 2011

• typo

  stevengj

  committed
  bc9dc18

  Copy full SHA for bc9dc18

• add missing F77 set_timelimit function; thanks to Martin Diehl for the bug repory

  stevengj

  committed
  659e85e

  Copy full SHA for 659e85e

Commits on Aug 19, 2011

• make fftw_mpi_block routine 10x faster, since it is being called zillions of times (thanks to Tom Vacek for the profiling)

  stevengj

  committed
  7079b52

  Copy full SHA for 7079b52

Commits on Aug 11, 2011

• allow specifying TRANSPOSE_{IN/OUT} transpose plans, since libbench does not canonicalize rnk=1 n=1 plans as rnk=0

  stevengj

  committed
  8609b38

  Copy full SHA for 8609b38

• check.pl should occasionally check DESTROY_INPUT problems too (especially since those enable slightly different algorithms in MPI)

  stevengj

  committed
  341d3e1

  Copy full SHA for 341d3e1

• unify post-MPI transpose handling in pairwise and alltoall solvers; should make the former faster in the destroy-input out-of-place case, and the latter more widely applicable

  stevengj

  committed
  2845a3c

  Copy full SHA for 2845a3c

Commits on Aug 5, 2011

• more C++ paranoia

  stevengj

  committed
  8ec2b52

  Copy full SHA for 8ec2b52

• tentative version bump for 3.3.1

  stevengj

  committed
  6047a70

  Copy full SHA for 6047a70

Pagination

Previous

Next