Magical 100x speedups

Article: Computational Efficiency in Modern Processors
By: David Kanter (dkanter.delete@this.realworldtech.com), November 9, 2009 11:41 am
Room: Moderated Discussions
>>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?

Anything in NV's marketing slides on GPGPU.

I'm extremely skeptical about any of their claims until I see the conditions under which the comparisons are made.

Here is what is claimed for current Tesla products:

19X - Transcoding HD to H264
146X - Interactive visualization of volumetric white matter connectivity
149X - Financial simulation of LIBOR model with swaptions
36X - Ionic placement for molecular dynamics simulation on GPU
17X - Simulation in Matlabusing .mexfile CUDA function
100X - Astrophysics N-body simulation
30X - Astrophysics N-body simulation
24X - Highly optimized object oriented molecular dynamics
20X - Ultrasound medical imaging for cancer diagnostics

These were shown on a slide that doesn't mention what that is compared to. Was it a core 2, a nehalem? Was it compiled with ICC, GCC? Did it use optimized math libraries, etc. etc.

Without that info, it's useless.

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? 🍊