1. 03 May, 2016 1 commit
  2. 25 Apr, 2016 1 commit
    • Andreas Marek's avatar
      Alignment error due to wrong stripe_width · f5feb969
      Andreas Marek authored
      In case of single precision calculations the stripe_width needs to
      be a multiple, which differs from the double precision by a factor of 2
      since one needs 32 bytes alignment and the sizeof(float) and sizeof(double)
      is different by a factor of two
      This commit closes issue #18
  3. 13 Apr, 2016 1 commit
    • Andreas Marek's avatar
      Abort on AVX BLOCK 4 kernel with FMA4 · c72fa66a
      Andreas Marek authored
      Quite likely the FMA4 (AMD) implementation has never been tested.
      There is a fishy intrinsic call, which is most likely an typo
      Abort with #error at compile time
  4. 12 Apr, 2016 1 commit