Announcement

Collapse
No announcement yet.

NVIDIA's PTX Back-End For GCC Has Been Published

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • NVIDIA's PTX Back-End For GCC Has Been Published

    Phoronix: NVIDIA's PTX Back-End For GCC Has Been Published

    As part of the work to bring OpenACC 2.0 and NVIDIA GPU support to GCC, a large set of patches were published this morning for adding NVIDIA's PTX back-end to the Free Software Foundation's compiler...

    Phoronix, Linux Hardware Reviews, Linux hardware benchmarks, Linux server benchmarks, Linux benchmarking, Desktop Linux, Linux performance, Open Source graphics, Linux How To, Ubuntu benchmarks, Ubuntu hardware, Phoronix Test Suite

  • #2
    Question

    Will it give GCC compiled apps any boost on execution?
    I can see FFMPEG and similar projects can seriously take advantage of that.
    Or even GCC itself. Like kernel compilation for example.
    Also, only some special apps can take advantage of this new thingy or theoretically all?(providing they are multiprocess apps)
    is it integer vs floating point sorta thing?
    Last edited by dimko; 09 December 2013, 01:16 PM. Reason: added more of a question

    Comment


    • #3
      Nice news! Waiting for OpenCL backend

      Originally posted by dimko View Post
      Will it give GCC compiled apps any boost on execution?
      Only to the applications that use OpenACC

      Comment


      • #4
        Originally posted by Annabel View Post
        Only to the applications that use OpenACC
        And the nvidia binary drivers.

        Comment


        • #5
          Originally posted by dimko View Post
          Will it give GCC compiled apps any boost on execution?
          I can see FFMPEG and similar projects can seriously take advantage of that.
          Or even GCC itself. Like kernel compilation for example.
          Also, only some special apps can take advantage of this new thingy or theoretically all?(providing they are multiprocess apps)
          is it integer vs floating point sorta thing?
          They're already leverage OpenCL. Get in line.

          Comment

          Working...
          X