yes for GPU programming you need non-public info

Article: Computational Efficiency in Modern Processors
By: Vincent Diepeveen (diep.delete@this.xs4all.nl), November 11, 2009 11:23 am
Room: Moderated Discussions
Potatoswatter (potswa_m@c.com) on 11/11/09 wrote:
---------------------------
>Vincent Diepeveen (diep@xs4all.nl) on 11/10/09 wrote:
>---------------------------
>>MoTheG (better@not.tell) on 11/9/09 wrote:
>>---------------------------
>>>a reader (a@b.c) on 11/9/09 wrote:
>>>---------------------------
>>>>stop blabbering.
>>>>
>>>>do you have access to GPU nda docs or not?
>>>
>>>I do not.
>>>Does one have to?
>>
>>Yes of course,
>
>"Of course"? The point of any highly multithreaded machine is to shift the focus
>from instruction latency to memory latency. NV gives a rough idea of the operations
>and their latencies and a better idea of the memory architecture.

Let's face it potatoswatter, the only successful software on GPU's right now has been programmed by NCSA type guys, be it the chinese organisation equivalent or the US version of it. Only those guys have lots of information that's not on the net, or have the tools and toys, and have them long before they ever got released.

That's the reality.

All other hard working amateurs at home, yes even total top coders, they all didn't manage to outperform quadcore hardware with ANY gpu; of course provided that their x86/x64 software was coded real well.

It is not only about having the best coder for a GPU, it's more than just that.

This has nothing to do with parallellisation, this has to do with knowing what instruction the hardware supports. If you're shifting right and the hardware doesn't have a fast equivalent for shift right, you're having a problem.

If you use branches and don't know that branches are ugly slow, especially at nvidia, then you're even more dicked.

But how many cycles do you lose to a lookup in register file?

What ipc can you achieve on a gpu?

Most ipc's right now at nvidia are around 0.2 to 0.3 a core, this is software written by very professional coders, NCSA type guys.

Not exactly idiots.

The few succesful codes on those gpu's are all always written by the same types of organisations, or with big support from the manufacturer in question.

Even for pilots you don't get that information from nvidia, at least that was the case. So gpgpu is a wet dream for now for most of us, even though i definitely feel that manycores are having a big future. They scale easier than cpu's, it's easier to get good yields, and they are efficient per watt. So why keep all that information that's so much needed secret?

>If your performance depends on completing each instruction in a thread right after
>the last, either GPU isn't best… or (in the case of no-bandwidth programs) gains
>should be so easy that optimality isn't as important.
>
>>>This is why I think arguing that one needs to be able to programm a GPU just like
>>>we used to programm single core CPUs is to much asked.
>>
>>Lucky just 1 guy has to solve the problem for each number crunching product. A
>>single programmer can have a huge impact on an entire field there. There is LOTS
>>of people who help you out then theoretically, as i figured out.
>
>So you're optimizing a generic number crunching product. You can run benchmarks
>that are constrained by ALU or by memory. Which are more important? Are you really
>having trouble seeing gains on embarrassingly parallel, ALU constrained programs?
>
>The cache issue you mentioned elsewhere is a separate problem from instruction latency, of course.
< Previous Post in ThreadNext Post in Thread >
TopicPosted ByDate
Article: Computational Efficiency in Modern Processors by DKMoTheG2009/11/08 07:02 AM
  Article: Computational Efficiency in Modern Processors by DKnone2009/11/08 07:15 AM
  Silverthorne and OoO vs. InOrdMoTheG2009/11/08 07:22 AM
    Silverthorne and OoO vs. InOrdDavid Kanter2009/11/08 04:11 PM
      Magical 100x speedupsAM2009/11/09 09:03 AM
        Magical 100x speedupsDavid Kanter2009/11/09 12:41 PM
          Magical 100x speedupsnone2009/11/09 01:36 PM
            Magical speedupsDavid Kanter2009/11/09 03:24 PM
              Magical speedupsnone2009/11/09 03:40 PM
              Hardware SpecsMS2009/11/09 05:49 PM
                44x faster than a single cpu coreVincent Diepeveen2009/11/10 08:17 AM
              Magical speedupsVincent Diepeveen2009/11/10 08:02 AM
          Xeon 130x speedup vs XeonEric Bron2009/11/10 08:20 AM
          Magical 100x speedupsAM2009/11/10 10:42 AM
            Magical 100x speedupsLinus Torvalds2009/11/10 01:19 PM
              Mega speedupsAM2009/11/11 06:21 AM
        Bogus 100x speedupsDavid Kanter2009/11/10 01:26 AM
          No speedups for CPUs for the general programming populaceMoTheG2009/11/10 05:26 AM
          Bogus 100x speedups?2009/11/10 05:45 AM
          Bogus 100x speedupshobold2009/11/10 07:31 AM
          Bogus 100x speedupsVincent Diepeveen2009/11/10 08:26 AM
          Bogus 100x speedupssylt2009/11/10 10:00 AM
          Bogus 100x speedupsAM2009/11/10 10:47 AM
      GPU vs. CPUMoTheG2009/11/09 11:30 AM
        GPU vs. CPUa reader2009/11/09 07:58 PM
          ease of programmingMoTheG2009/11/09 11:45 PM
            yes for GPU programming you need non-public infoVincent Diepeveen2009/11/10 08:36 AM
              yes for GPU programming you need non-public infoPotatoswatter2009/11/11 08:06 AM
                yes for GPU programming you need non-public infoVincent Diepeveen2009/11/11 11:23 AM
                  yes for GPU programming you need non-public infoPotatoswatter2009/11/11 01:26 PM
                  Real businesses use GPGPU.Jouni Osmala2009/11/11 11:00 PM
        GPU vs. CPU?2009/11/10 06:01 AM
          2. try but most is said, just clarifyingMoTheG2009/11/10 10:24 AM
            2. try but most is said, just clarifying?2009/11/11 01:11 AM
              you missread meMoTheG2009/11/12 12:33 AM
                you missread me?2009/11/12 01:18 AM
            2. try but most is said, just clarifyingPotatoswatter2009/11/11 08:22 AM
              2. try but most is said, just clarifying?2009/11/12 01:22 AM
                loose, not so orderlyMoTheG2009/11/12 12:47 PM
                  loose, not so orderlyPotatoswatter2009/11/12 06:50 PM
                2. try but most is said, just clarifyingrwessel2009/11/12 01:01 PM
                  2. try but most is said, just clarifyingGabriele Svelto2009/11/13 12:39 AM
                    2. try but most is said, just clarifying?2009/11/13 01:14 AM
                      2. try but most is said, just clarifyingGabriele Svelto2009/11/13 01:30 AM
                      2. try but most is said, just clarifyingrwessel2009/11/13 01:24 PM
                  2. try but most is said, just clarifyingMichael S2009/11/14 01:08 PM
                    2. try but most is said, just clarifyingGabriele Svelto2009/11/14 11:38 PM
                      2. try but most is said, just clarifyingAndi Kleen2009/11/15 01:19 AM
                      2. try but most is said, just clarifyingMichael S2009/11/15 01:58 AM
                        2. try but most is said, just clarifyingEric Bron2009/11/15 02:25 AM
                          /MP optionEric Bron2009/11/15 02:33 AM
                            /MP optionPaul2009/11/15 09:42 AM
                              /MP optionEric Bron2009/11/15 01:22 PM
                        2. try but most is said, just clarifying?2009/11/15 03:13 AM
                          2. try but most is said, just clarifyingMichael S2009/11/15 05:14 AM
                  2. try but most is said, just clarifyingEugene Nalimov2009/11/14 09:24 PM
    Atom pointAM2009/11/09 09:00 AM
      Atom TDPDavid Kanter2009/11/09 12:48 PM
        Atom TDPhobold2009/11/10 07:41 AM
        Atom TDPAM2009/11/10 10:49 AM
Reply to this Topic
Name:
Email:
Topic:
Body: No Text
How do you spell avocado?