Janez Atmapuri Makovsek found some #XE6 array optimizations

-
Janez Atmapuri Makovsek found some #XE6  array optimizations
Inline declared setter and getter functions can yield up to six times the performance on one-dimensional arrays and up to four times the performance on 2D arrays, compared to XE5.

Spotted at the EMBT forums.
http://www.dewresearch.com/news/232-rad-studio-xe6-lo-and-behold

Comments

  1. Asbjørn HeidMay 6, 2014 at 7:04 AM

    Well now, that is great news indeed.

    ReplyDelete
  2. Asbjørn HeidMay 6, 2014 at 7:09 AM

    Word on the street is that this inline optimization has broken AtomicIncrement where the increment value is not a constant. So that's not so good news...

    ReplyDelete
  3. Carlos LeiteMay 6, 2014 at 9:44 AM

    We use MtxVec for years (since version 1.5 on D7), highly recommended (although we didn't try yet the OpenCL specific functions)

    ReplyDelete
  4. Leif UneusMay 7, 2014 at 12:57 AM

    Asbjørn Heid Is the AtomicIncrement issue documented somewhere?

    ReplyDelete
  5. Asbjørn HeidMay 7, 2014 at 1:00 AM

    Leif Uneus I only heard it via-via, but from reliable source. I presumed it would get logged in QC (due to source) but i can't seem to find it.

    ReplyDelete

Post a Comment