Crunch Time S5 Workunits

Forums › Cruncher's Corner

Jayargh
Jayargh
Joined: 9 Feb 05
Posts: 64
Credit: 1205159
RAC: 0

Thanks Dan for your

22 Jun 2006 11:43:46 UTC
Message 38205
(moderation:
    )

    Thanks Dan for your explanations....I think I understand the complexity of it all a bit more

    somebodley
    somebodley
    Joined: 3 Mar 06
    Posts: 119
    Credit: 180339
    RAC: 0

    Oh dear! Just changed my

    22 Jun 2006 14:53:33 UTC
    Message 38206
    (moderation:
      )

      Oh dear!
      Just changed my MacBook Pro to S5R
      My BIG gun has just hit " h1_1339.0_S5R1__3203_S5Ra_0 "
      predicted .... 5 hours 20 mins!!!!!!!!
      What will happen when I get a big WU?????????

      ... my Measured Flops = 1742 million ops/sec
      and Measured Integer Speed = 4734 million ops/sec

      This is like atacking an elephant with a water pistol!!!!!!!

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

      RE: Oh dear! Just changed

      22 Jun 2006 14:59:38 UTC
      Message 38207 in response to message 38206
      (moderation:
        )

        Quote:

        Oh dear!
        Just changed my MacBook Pro to S5R
        My BIG gun has just hit " h1_1339.0_S5R1__3203_S5Ra_0 "
        predicted .... 5 hours 20 mins!!!!!!!!
        What will happen when I get a big WU?????????

        ... my Measured Flops = 1742 million ops/sec
        and Measured Integer Speed = 4734 million ops/sec

        This is like atacking an elephant with a water pistol!!!!!!!


        "h1_xxxx....."'s are long units-> that time will be way off. If its the first S5 units you've got on that machine it wont have got use to its times yet.

        Quote:
        from Bruce Allen
        "The short data files (l1_XXXX.X) are from the LIGO Livingston Observatory...The long data files (h1_XXXX.X) are from LIGO Hanford"


        Odysseus
        Odysseus
        Joined: 17 Dec 05
        Posts: 372
        Credit: 21002129
        RAC: 4878

        RE: "h1_xxxx....."'s are

        22 Jun 2006 15:55:28 UTC
        Message 38208 in response to message 38207
        (moderation:
          )

          Quote:
          "h1_xxxx....."'s are long units-> that time will be way off. If its the first S5 units you've got on that machine it wont have got use to its times yet.
          Quote:
          from Bruce Allen
          "The short data files (l1_XXXX.X) are from the LIGO Livingston Observatory...The long data files (h1_XXXX.X) are from LIGO Hanford"


          I think you’re confusing WUs and the data files from which they’re ‘sliced’. Short WUs can come from long data files and vice versa. Right now I’m crunching some short ones (@3-4h on an old Mac) whose names start with “h1_0384.0�; they come from a long (15.4-MB) Hanford file.

          somebodley
          somebodley
          Joined: 3 Mar 06
          Posts: 119
          Credit: 180339
          RAC: 0

          RE: RE: "h1_xxxx....."'s

          22 Jun 2006 16:22:43 UTC
          Message 38209 in response to message 38208
          (moderation:
            )

            Quote:
            Quote:
            "h1_xxxx....."'s are long units-> that time will be way off. If its the first S5 units you've got on that machine it wont have got use to its times yet.
            Quote:
            from Bruce Allen
            "The short data files (l1_XXXX.X) are from the LIGO Livingston Observatory...The long data files (h1_XXXX.X) are from LIGO Hanford"

            I think you’re confusing WUs and the data files from which they’re ‘sliced’. Short WUs can come from long data files and vice versa. Right now I’m crunching some short ones (@3-4h on an old Mac) whose names start with “h1_0384.0�; they come from a long (15.4-MB) Hanford file.

            I am 41.2% through " h1_1339.0_S5R1__3203_S5Ra_0 " ..... at 2 hrs 19 mins

            So THAT part of the equation is right.
            How do I find out what that WU is?
            Is it a short WU?
            Is it a "long" short WU?
            Is it a "short" long WU?
            Is it a long WU?

            Anybody out there with a hazard at the answer?

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

            RE: RE: "h1_xxxx....."'s

            22 Jun 2006 16:23:07 UTC
            Message 38210 in response to message 38208
            (moderation:
              )

              Quote:
              Quote:
              "h1_xxxx....."'s are long units-> that time will be way off. If its the first S5 units you've got on that machine it wont have got use to its times yet.
              Quote:
              from Bruce Allen
              "The short data files (l1_XXXX.X) are from the LIGO Livingston Observatory...The long data files (h1_XXXX.X) are from LIGO Hanford"

              I think you’re confusing WUs and the data files from which they’re ‘sliced’. Short WUs can come from long data files and vice versa. Right now I’m crunching some short ones (@3-4h on an old Mac) whose names start with “h1_0384.0�; they come from a long (15.4-MB) Hanford file.

              I originally thought that at first. Someone before in this thred I think said (think quoting bruce too) it was 0xxx.x=short and xxxx.x=long but i find that even more alarming. all the units a have are 'h1' and are '0xxx.x' and three i've got throught so far have taken over 11hours others estimated at over 13hours. If they are in fact short units then i'm frightend to think what a actual long one looks like! These are on a Pentium d 830 3.2ghz.

              Seems that niether way works at distinguishing long/short.

              DanNeely
              DanNeely
              Joined: 4 Sep 05
              Posts: 1364
              Credit: 3591946038
              RAC: 650372

              IIRC the short/long break is

              22 Jun 2006 16:28:04 UTC
              Message 38211
              (moderation:
                )

                IIRC the short/long break is at XX_0400_....

                somebodley
                somebodley
                Joined: 3 Mar 06
                Posts: 119
                Credit: 180339
                RAC: 0

                This is what Bruce said

                22 Jun 2006 16:32:28 UTC
                Message 38212
                (moderation:
                  )

                  This is what Bruce said :-

                  Quote:

                  I'll update this as our generation and testing of our first S5 workunits proceeds
The names of these workunits are of the form h1_XXXX.X_S5R1x_* and l1_XXXX.X_S5R1x_*.

                  There are two types of workunits: short and long. The short workunits have XXXX.X less than or equal to 0400.0.

There are also two types of data files: short and long. The short data files (l1_XXXX.X) are from the LIGO Livingston Observatory, and are about 4.5MB in size. The long data files (h1_XXXX.X) are from LIGO Hanford and are about 16MB in size. Note: once your computer downloads one of these data files, it should be able to do many workunits for that same file.

                  So I am crunching a LOOOONG WU in 5hrs 20 mins ! This gives me 2 WU's in that time ... or a crunch time of 2 hrs 10 mins for a LOOOOOOOOOOONG WU!!!!

                  WOOTY - WOOT! WOOT!!!!!Anybody wanna buy a really good MacBook Pro????????? (REEEL CHEEEP!!!!!)
                  :-))))))))))))))

                  ErichZann
                  ErichZann
                  Joined: 11 Feb 05
                  Posts: 120
                  Credit: 81582
                  RAC: 0

                  RE: So I am crunching a

                  22 Jun 2006 16:37:22 UTC
                  Message 38213 in response to message 38212
                  (moderation:
                    )

                    Quote:


                    So I am crunching a LOOOONG WU in 5hrs 20 mins ! This gives me 2 WU's in that time ... or a crunch time of 2 hrs 10 mins for a LOOOOOOOOOOONG WU!!!!

                    WOOTY - WOOT! WOOT!!!!!Anybody wanna buy a really good MacBook Pro????????? (REEEL CHEEEP!!!!!)
                    :-))))))))))))))

                    i think there are still differences between long ones. How much credit did you get for those?
                    Because i dont think you crunch a WU my Athlon 64 3500+ makes in 9:15 hours in 2:10 hours...

                    somebodley
                    somebodley
                    Joined: 3 Mar 06
                    Posts: 119
                    Credit: 180339
                    RAC: 0

                    RE: RE: So I am

                    22 Jun 2006 16:52:23 UTC
                    Message 38214 in response to message 38213
                    (moderation:
                      )

                      Quote:
                      Quote:


                      So I am crunching a LOOOONG WU in 5hrs 20 mins ! This gives me 2 WU's in that time ... or a crunch time of 2 hrs 10 mins for a LOOOOOOOOOOONG WU!!!!

                      WOOTY - WOOT! WOOT!!!!!Anybody wanna buy a really good MacBook Pro????????? (REEEL CHEEEP!!!!!)
                      :-))))))))))))))

                      i think there are still differences between long ones. How much credit did you get for those?
                      Because i dont think you crunch a WU my Athlon 64 3500+ makes in 9:15 hours in 2:10 hours...

                      SORRY!!!! I was looking at wrong end of telescope!!!!
                      I apologise ... my mind was running away with me ...
                      EACH WU is being crunched in 5hr 20min
                      sorry ... I was wrong!!!

                      BUT IT IS STILL MAGNIFICENT, in that each 5hr 20 min, I turn in 2 WU's ..... which is EFFECTIVELY ... what I said (but not QUITE the same !!!!!)
                      Apologies!

                      Comment viewing options

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

                      Forums › Cruncher's Corner