Optomized S5 SSE3

Forums › Cruncher's Corner

Dronak
Dronak
Joined: 21 Mar 05
Posts: 28
Credit: 10402879
RAC: 0

As far as I know, yes, if

25 Jun 2006 21:58:31 UTC
Message 39290
(moderation:
    )

    As far as I know, yes, if "Checked, but no consensus yet" shows up on a work unit done with a patched (unofficial) application, then it's not going to validate when a third result comes in. I have one, maybe two, of those, but hopefully that will be it.

    I think that if you do the patch correctly, you'll see some message at the end saying "Done" or something similar. If you didn't see that, the patch probably wasn't successful. You could also download one of the pre-patched versions posted here; those should be fine.

    Crunchers For More Power
    Crunchers For M...
    Joined: 3 Aug 05
    Posts: 69
    Credit: 1071273
    RAC: 0

    the problem is that by the

    25 Jun 2006 22:01:10 UTC
    Message 39291
    (moderation:
      )

      the problem is that by the S5T0713 patch in the stderr.txt you can read E@H S5R1 4.10 0712 TEST

      Stefan
      Stefan
      Joined: 15 Nov 05
      Posts: 52
      Credit: 761198
      RAC: 0

      This optimized version

      25 Jun 2006 22:01:48 UTC
      Message 39292 in response to message 39290
      (moderation:
        )

        This optimized version doesn't have a big speed up does it, under 10% or so?

        Human Stupidity Is Infinite...

        Norman_RKN
        Norman_RKN
        Joined: 9 Feb 06
        Posts: 27
        Credit: 1368075
        RAC: 0

        RE: the problem is that by

        25 Jun 2006 22:03:15 UTC
        Message 39293 in response to message 39291
        (moderation:
          )

          Quote:
          the problem is that by the S5T0713 patch in the stderr.txt you can read E@H S5R1 4.10 0712 TEST

          i think akos has only decreased the size of the patch. not more not less ;) ?

          Crunchers For More Power
          Crunchers For M...
          Joined: 3 Aug 05
          Posts: 69
          Credit: 1071273
          RAC: 0

          RE: This optimized version

          25 Jun 2006 22:04:39 UTC
          Message 39294 in response to message 39292
          (moderation:
            )

            Quote:
            This optimized version doesn't have a big speed up does it, under 10% or so?

            S5T0712 and S5T0713 has the same speed, ca. 32%

            Norman_RKN
            Norman_RKN
            Joined: 9 Feb 06
            Posts: 27
            Credit: 1368075
            RAC: 0

            RE: This optimized version

            25 Jun 2006 22:05:33 UTC
            Message 39295 in response to message 39292
            (moderation:
              )

              Quote:
              This optimized version doesn't have a big speed up does it, under 10% or so?


              i´ve a speedup from 35-39% (so far) with the version 0712 °|^

              Stefan
              Stefan
              Joined: 15 Nov 05
              Posts: 52
              Credit: 761198
              RAC: 0

              RE: RE: This optimized

              25 Jun 2006 22:08:15 UTC
              Message 39296 in response to message 39295
              (moderation:
                )

                Quote:
                Quote:
                This optimized version doesn't have a big speed up does it, under 10% or so?

                i�ve a speedup from 35-39% (so far) with the version 0712

                Really...now is this on the big WU's or the smaller version?

                There are 2 diff sizes aren't there, I thought I read something about that somewhere along the way...

                Human Stupidity Is Infinite...

                Barrie
                Barrie
                Joined: 23 Mar 05
                Posts: 219
                Credit: 21449106
                RAC: 0

                RE: RE: RE: This

                25 Jun 2006 22:17:14 UTC
                Message 39297 in response to message 39296
                (moderation:
                  )

                  Quote:
                  Quote:
                  Quote:
                  This optimized version doesn't have a big speed up does it, under 10% or so?

                  i�ve a speedup from 35-39% (so far) with the version 0712

                  Really...now is this on the big WU's or the smaller version?

                  There are 2 diff sizes aren't there, I thought I read something about that somewhere along the way...

                  The speed you get will probably depend on whether your processor supports SSE3 or just vanilla SSE.

                  Dead men don't get the baby washed. HTH

                  Pepperammi
                  Pepperammi
                  Joined: 20 Feb 05
                  Posts: 131
                  Credit: 437943
                  RAC: 0

                  RE: RE: RE: This

                  25 Jun 2006 22:17:47 UTC
                  Message 39298 in response to message 39296
                  (moderation:
                    )

                    Quote:
                    Quote:
                    Quote:
                    This optimized version doesn't have a big speed up does it, under 10% or so?

                    i�ve a speedup from 35-39% (so far) with the version 0712

                    Really...now is this on the big WU's or the smaller version?

                    There are 2 diff sizes aren't there, I thought I read something about that somewhere along the way...


                    i was seeing about 26% on my long units with S5T0709

                    Norman_RKN
                    Norman_RKN
                    Joined: 9 Feb 06
                    Posts: 27
                    Credit: 1368075
                    RAC: 0

                    RE: There are 2 diff sizes

                    25 Jun 2006 22:18:15 UTC
                    Message 39299 in response to message 39296
                    (moderation:
                      )

                      Quote:

                      There are 2 diff sizes aren't there, I thought I read something about that somewhere along the way...

                      mmh.
                      this ?

                      Quote:

                      I have tested all available apps from akosf with the same short WU.
                      I backed up the whole BOINC directory and ran the tests:

                      Pentium 930D (3000MHz) @ 3600MHz:

                      stock : 4171 sec
                      0302 (SSE3): 3263 sec - 21,76% speedup
                      0303 (SSE3): 3212 sec - 22,99% speedup
                      0304 (SSE) : 3674 sec - 11,91% speedup
                      0305 (SSE) : 3323 sec - 20,33% speedup
                      0306 (SSE) : 3265 sec - 21,72% speedup
                      0307 (SSE) : 3186 sec - 23,61% speedup
                      0709 (SSE) : 3199 sec - 23,30% speedup
                      0711 (SSE) : 3025 sec - 27,47% speedup
                      0712 (SSE) : 2712 sec - 34,97% speedup

                      AthlonXP 2700+ (2166MHz) @ 2166MHz:

                      stock : 3704 sec
                      0304 (SSE) : 3439 sec - 7,15% speedup
                      0305 (SSE) : 3324 sec - 10,23% speedup
                      0306 (SSE) : 3234 sec - 12,68% speedup
                      0307 (SSE) : 3166 sec - 14,52% speedup
                      0709 (SSE) : 3164 sec - 14,57% speedup
                      0711 (SSE) : 3058 sec - 17,44% speedup

                      So, thats impressive work, akosf!!!!


                      Comment viewing options

                      Select your preferred way to display the comments and click "Save settings" to activate your changes.

                      Forums › Cruncher's Corner