Magical 100x speedups

Article: Computational Efficiency in Modern Processors
By: AM (myname4rwt.delete@this.jee.male), November 9, 2009 8:03 am
Room: Moderated Discussions
David Kanter (dkanter@realworldtech.com) on 11/8/09 wrote:
---------------------------
>MoTheG (better@not.tell) on 11/8/09 wrote:
>---------------------------
>>I still am surprised that the Atom scored so well.
>
>I was as well when I was putting this together. Initially I just had high performance
>CPUs, and I thought for fun I'd throw in GPUs and Atom and see where they stand.
>I was more than a little surprised at the results.
>
>>ofcause the benchmark was parallel and explicit at that, >thus there was no gain
>>from OoO-processing but a factor of >3 ?
>
>Well there wasn't a benchmark, but you are absolutely correct the metric didn't
>incorporate the advantages of OOO. Or caches for that matter.
>
>>Doesn't the article make a good argument for keeping CPUs >and GPUs different?
>>A CPU can not be as good at large parallel tasks because >it carrys its sequential strength as a burden.
>
>Actually that strength really is a strength. Many workloads are very difficult
>to parallelize or vectorize with a compiler. Think GCC or most latency sensitive applications.
>
>There's no reason why a CPU cannot have a bunch of massively parallel execution
>resources like a GPU and simply use the most appropriate hardware for the task.
>
>From a physical perspective, the distinction is really about power consumption and memory bandwidth vs. latency.
>
>A separate GPU makes a lot of sense where you need lots of power and memory bandwidth
>AND the CPU guys don't want to provide it. As you can see from Intel and AMD, they
>are now interested in figuring out how to work with the folks who do have those needs.
>
>>with the GPU getting easyer to use (OpenCL, DirectX11, >CUDA, Brook+) and better
>>connected (PEG), CPUs should concentrate on those tasks >that are to small to be off-loaded.
>
>GPUs are getting easier to use means they are improving relatively speaking to
>prior generations. It says nothing about suitability for the general programming populace.
>
>Explicitly parallel stuff is easy to exploit, and if you're going to rewrite software,
>then you need to compare optimized CPU code vs. GPU code. That's something NV has
>a big problem understanding - most of their magical 100X speed ups are probably
>comparing poorly optimized CPU code with optimized GPU code.

Can you be specific wrt "magical 100x speedups" you're talking about?

>David
< Previous Post in ThreadNext Post in Thread >
TopicPosted ByDate
Article: Computational Efficiency in Modern Processors by DKMoTheG2009/11/08 06:02 AM
  Article: Computational Efficiency in Modern Processors by DKnone2009/11/08 06:15 AM
  Silverthorne and OoO vs. InOrdMoTheG2009/11/08 06:22 AM
    Silverthorne and OoO vs. InOrdDavid Kanter2009/11/08 03:11 PM
      Magical 100x speedupsAM2009/11/09 08:03 AM
        Magical 100x speedupsDavid Kanter2009/11/09 11:41 AM
          Magical 100x speedupsnone2009/11/09 12:36 PM
            Magical speedupsDavid Kanter2009/11/09 02:24 PM
              Magical speedupsnone2009/11/09 02:40 PM
              Hardware SpecsMS2009/11/09 04:49 PM
                44x faster than a single cpu coreVincent Diepeveen2009/11/10 07:17 AM
              Magical speedupsVincent Diepeveen2009/11/10 07:02 AM
          Xeon 130x speedup vs XeonEric Bron2009/11/10 07:20 AM
          Magical 100x speedupsAM2009/11/10 09:42 AM
            Magical 100x speedupsLinus Torvalds2009/11/10 12:19 PM
              Mega speedupsAM2009/11/11 05:21 AM
        Bogus 100x speedupsDavid Kanter2009/11/10 12:26 AM
          No speedups for CPUs for the general programming populaceMoTheG2009/11/10 04:26 AM
          Bogus 100x speedups?2009/11/10 04:45 AM
          Bogus 100x speedupshobold2009/11/10 06:31 AM
          Bogus 100x speedupsVincent Diepeveen2009/11/10 07:26 AM
          Bogus 100x speedupssylt2009/11/10 09:00 AM
          Bogus 100x speedupsAM2009/11/10 09:47 AM
      GPU vs. CPUMoTheG2009/11/09 10:30 AM
        GPU vs. CPUa reader2009/11/09 06:58 PM
          ease of programmingMoTheG2009/11/09 10:45 PM
            yes for GPU programming you need non-public infoVincent Diepeveen2009/11/10 07:36 AM
              yes for GPU programming you need non-public infoPotatoswatter2009/11/11 07:06 AM
                yes for GPU programming you need non-public infoVincent Diepeveen2009/11/11 10:23 AM
                  yes for GPU programming you need non-public infoPotatoswatter2009/11/11 12:26 PM
                  Real businesses use GPGPU.Jouni Osmala2009/11/11 10:00 PM
        GPU vs. CPU?2009/11/10 05:01 AM
          2. try but most is said, just clarifyingMoTheG2009/11/10 09:24 AM
            2. try but most is said, just clarifying?2009/11/11 12:11 AM
              you missread meMoTheG2009/11/11 11:33 PM
                you missread me?2009/11/12 12:18 AM
            2. try but most is said, just clarifyingPotatoswatter2009/11/11 07:22 AM
              2. try but most is said, just clarifying?2009/11/12 12:22 AM
                loose, not so orderlyMoTheG2009/11/12 11:47 AM
                  loose, not so orderlyPotatoswatter2009/11/12 05:50 PM
                2. try but most is said, just clarifyingrwessel2009/11/12 12:01 PM
                  2. try but most is said, just clarifyingGabriele Svelto2009/11/12 11:39 PM
                    2. try but most is said, just clarifying?2009/11/13 12:14 AM
                      2. try but most is said, just clarifyingGabriele Svelto2009/11/13 12:30 AM
                      2. try but most is said, just clarifyingrwessel2009/11/13 12:24 PM
                  2. try but most is said, just clarifyingMichael S2009/11/14 12:08 PM
                    2. try but most is said, just clarifyingGabriele Svelto2009/11/14 10:38 PM
                      2. try but most is said, just clarifyingAndi Kleen2009/11/15 12:19 AM
                      2. try but most is said, just clarifyingMichael S2009/11/15 12:58 AM
                        2. try but most is said, just clarifyingEric Bron2009/11/15 01:25 AM
                          /MP optionEric Bron2009/11/15 01:33 AM
                            /MP optionPaul2009/11/15 08:42 AM
                              /MP optionEric Bron2009/11/15 12:22 PM
                        2. try but most is said, just clarifying?2009/11/15 02:13 AM
                          2. try but most is said, just clarifyingMichael S2009/11/15 04:14 AM
                  2. try but most is said, just clarifyingEugene Nalimov2009/11/14 08:24 PM
    Atom pointAM2009/11/09 08:00 AM
      Atom TDPDavid Kanter2009/11/09 11:48 AM
        Atom TDPhobold2009/11/10 06:41 AM
        Atom TDPAM2009/11/10 09:49 AM
Reply to this Topic
Name:
Email:
Topic:
Body: No Text
How do you spell tangerine? 🍊