• Re: Graphics card fans

    From jlarkin@jlarkin@highlandsniptechnology.com to sci.electronics.design,sci.electronics.equipment on Tue Jul 14 08:36:44 2020
    From Newsgroup: sci.electronics.equipment

    On Tue, 14 Jul 2020 16:10:17 +0100, "Commander Kinsey" <CFKinsey@military.org.jp> wrote:

    Why do graphics cards only monitor the speed of one fan? If the other one fails, it won't know!

    Are graphic cards used mostly for games? And maybe bitcoin mining?
    It's weird that one PC can contain more compute power than existed on
    Earth in 1970, and be used for games.

    I suggested to Mike E that LT Spice should use a graphic card for
    computation, but I guess that's not going to happen now.

    A modest Windows PC can spin Solidworks 3D images around just fine.
    --

    John Larkin Highland Technology, Inc

    Science teaches us to doubt.

    Claude Bernard

    --- Synchronet 3.21d-Linux NewsLink 1.2
  • From bitrex@user@example.net to sci.electronics.design,sci.electronics.equipment on Tue Jul 14 11:50:08 2020
    From Newsgroup: sci.electronics.equipment

    On 7/14/2020 11:36 AM, jlarkin@highlandsniptechnology.com wrote:
    On Tue, 14 Jul 2020 16:10:17 +0100, "Commander Kinsey" <CFKinsey@military.org.jp> wrote:

    Why do graphics cards only monitor the speed of one fan? If the other one fails, it won't know!

    Are graphic cards used mostly for games? And maybe bitcoin mining?
    It's weird that one PC can contain more compute power than existed on
    Earth in 1970, and be used for games.

    I suggested to Mike E that LT Spice should use a graphic card for computation, but I guess that's not going to happen now.

    A modest Windows PC can spin Solidworks 3D images around just fine.




    Is SPICE trivially parallelize-able in that way?

    Graphics cards have thousands of compute cores. Most operations on 3D
    mesh vertices and pixel "shading" are trivially parallelize-able; the operation pipeline is programmed for a given task and then each core
    runs its algorithm on a given vertex or pixel of the scene without
    needing any information from the others.

    Early graphics cards didn't have re-programmable pipelines there was a somewhat fixed set of operations with some configurable options that
    could be applied in series to vertices and pixels.

    Modern GPU code is written in a dialect of C with some features not
    relevant to single instruction multiple data operations removed, like
    pointers
    --- Synchronet 3.21d-Linux NewsLink 1.2
  • From Phil Hobbs@pcdhSpamMeSenseless@electrooptical.net to sci.electronics.design,sci.electronics.equipment on Tue Jul 14 11:53:41 2020
    From Newsgroup: sci.electronics.equipment

    On 2020-07-14 11:36, jlarkin@highlandsniptechnology.com wrote:
    On Tue, 14 Jul 2020 16:10:17 +0100, "Commander Kinsey" <CFKinsey@military.org.jp> wrote:

    Why do graphics cards only monitor the speed of one fan? If the other one fails, it won't know!

    Are graphic cards used mostly for games? And maybe bitcoin mining?
    It's weird that one PC can contain more compute power than existed on
    Earth in 1970, and be used for games.

    I suggested to Mike E that LT Spice should use a graphic card for computation, but I guess that's not going to happen now.

    A modest Windows PC can spin Solidworks 3D images around just fine.




    GPUs are limited to single-precision floating point IIRC.

    Cheers

    Phil Hobbs
    --
    Dr Philip C D Hobbs
    Principal Consultant
    ElectroOptical Innovations LLC / Hobbs ElectroOptics
    Optics, Electro-optics, Photonics, Analog Electronics
    Briarcliff Manor NY 10510

    http://electrooptical.net
    http://hobbs-eo.com

    --- Synchronet 3.21d-Linux NewsLink 1.2
  • From bitrex@user@example.net to sci.electronics.design,sci.electronics.equipment on Tue Jul 14 12:00:05 2020
    From Newsgroup: sci.electronics.equipment

    On 7/14/2020 11:50 AM, bitrex wrote:
    On 7/14/2020 11:36 AM, jlarkin@highlandsniptechnology.com wrote:
    On Tue, 14 Jul 2020 16:10:17 +0100, "Commander Kinsey"
    <CFKinsey@military.org.jp> wrote:

    Why do graphics cards only monitor the speed of one fan? If the other
    one fails, it won't know!

    Are graphic cards used mostly for games? And maybe bitcoin mining?
    It's weird that one PC can contain more compute power than existed on
    Earth in 1970, and be used for games.

    I suggested to Mike E that LT Spice should use a graphic card for
    computation, but I guess that's not going to happen now.

    A modest Windows PC can spin Solidworks 3D images around just fine.




    Is SPICE trivially parallelize-able in that way?

    Graphics cards have thousands of compute cores. Most operations on 3D
    mesh vertices and pixel "shading" are trivially parallelize-able; the operation pipeline is programmed for a given task and then each core
    runs its algorithm on a given vertex or pixel of the scene without
    needing any information from the others.

    Every frame if the scene is in motion the lighting reflections and
    shadows have to be re-computed, as one example.
    --- Synchronet 3.21d-Linux NewsLink 1.2
  • From bitrex@user@example.net to sci.electronics.design,sci.electronics.equipment on Tue Jul 14 12:04:18 2020
    From Newsgroup: sci.electronics.equipment

    On 7/14/2020 11:53 AM, Phil Hobbs wrote:
    On 2020-07-14 11:36, jlarkin@highlandsniptechnology.com wrote:
    On Tue, 14 Jul 2020 16:10:17 +0100, "Commander Kinsey"
    <CFKinsey@military.org.jp> wrote:

    Why do graphics cards only monitor the speed of one fan? If the other
    one fails, it won't know!

    Are graphic cards used mostly for games? And maybe bitcoin mining?
    It's weird that one PC can contain more compute power than existed on
    Earth in 1970, and be used for games.

    I suggested to Mike E that LT Spice should use a graphic card for
    computation, but I guess that's not going to happen now.

    A modest Windows PC can spin Solidworks 3D images around just fine.




    GPUs are limited to single-precision floating point IIRC.

    Cheers

    Phil Hobbs


    Was true circa 2005.

    Many modern GPUs can do double precision floating point, how well any particular one does it depends on the particular architecture, though.
    --- Synchronet 3.21d-Linux NewsLink 1.2
  • From bitrex@user@example.net to sci.electronics.design,sci.electronics.equipment on Tue Jul 14 12:07:31 2020
    From Newsgroup: sci.electronics.equipment

    On 7/14/2020 11:53 AM, Phil Hobbs wrote:
    On 2020-07-14 11:36, jlarkin@highlandsniptechnology.com wrote:
    On Tue, 14 Jul 2020 16:10:17 +0100, "Commander Kinsey"
    <CFKinsey@military.org.jp> wrote:

    Why do graphics cards only monitor the speed of one fan? If the other
    one fails, it won't know!

    Are graphic cards used mostly for games? And maybe bitcoin mining?
    It's weird that one PC can contain more compute power than existed on
    Earth in 1970, and be used for games.

    I suggested to Mike E that LT Spice should use a graphic card for
    computation, but I guess that's not going to happen now.

    A modest Windows PC can spin Solidworks 3D images around just fine.




    GPUs are limited to single-precision floating point IIRC.

    Cheers

    Phil Hobbs


    That is to say they can do double but they're in general not optimized
    for it.
    --- Synchronet 3.21d-Linux NewsLink 1.2
  • From Gerhard Hoffmann@dk4xp@arcor.de to sci.electronics.design,sci.electronics.equipment on Tue Jul 14 18:14:04 2020
    From Newsgroup: sci.electronics.equipment

    Am 14.07.20 um 17:50 schrieb bitrex:

    I suggested to Mike E that LT Spice should use a graphic card for
    computation, but I guess that's not going to happen now.

    A modest Windows PC can spin Solidworks 3D images around just fine.




    Is SPICE trivially parallelize-able in that way?

    No. Inverting the conductivity matrix is hard because you
    cannot do the pivoting in advance. The necessity shows
    up during work.

    For transient analysis, every time step builds on the previous one(s)
    and you cannot parallelize a lot of them because you don't know
    the starting condition of the future ones.

    It has been tried often, a working solution would have been worth gold.
    I remember the Weitek array coprocessor back in 80386 times and
    a try with the NS16032. They never got a factor of more than 2 or 3.

    Everything really interesting is np-complete. :-(

    Cheers, Gerhard

    --- Synchronet 3.21d-Linux NewsLink 1.2
  • From bitrex@user@example.net to sci.electronics.design,sci.electronics.equipment on Tue Jul 14 12:18:03 2020
    From Newsgroup: sci.electronics.equipment

    On 7/14/2020 12:14 PM, Gerhard Hoffmann wrote:
    Am 14.07.20 um 17:50 schrieb bitrex:

    I suggested to Mike E that LT Spice should use a graphic card for
    computation, but I guess that's not going to happen now.

    A modest Windows PC can spin Solidworks 3D images around just fine.




    Is SPICE trivially parallelize-able in that way?

    No. Inverting the conductivity matrix is hard because you
    cannot do the pivoting in advance. The necessity shows
    up during work.

    For transient analysis, every time step builds on the previous one(s)
    and you cannot parallelize a lot of them because you don't know
    the starting condition of the future ones.

    It has been tried often, a working solution would have been worth gold.
    I remember the Weitek array coprocessor back in 80386 times and
    a try with the NS16032. They never got a factor of more than 2 or 3.

    Everything really interesting is np-complete.-a :-(

    Cheers, Gerhard


    That's what I figured.

    There are probably ways to leverage GPUs in the process somehow but I
    expect it's going to be a 3 or 4 times speedup over using a general
    purpose CPU not like a ten thousand times speedup in the way rendering
    scenes is.
    --- Synchronet 3.21d-Linux NewsLink 1.2
  • From bitrex@user@example.net to sci.electronics.design,sci.electronics.equipment on Tue Jul 14 12:25:17 2020
    From Newsgroup: sci.electronics.equipment

    On 7/14/2020 12:14 PM, Gerhard Hoffmann wrote:
    Am 14.07.20 um 17:50 schrieb bitrex:

    I suggested to Mike E that LT Spice should use a graphic card for
    computation, but I guess that's not going to happen now.

    A modest Windows PC can spin Solidworks 3D images around just fine.




    Is SPICE trivially parallelize-able in that way?

    No. Inverting the conductivity matrix is hard because you
    cannot do the pivoting in advance. The necessity shows
    up during work.

    For transient analysis, every time step builds on the previous one(s)
    and you cannot parallelize a lot of them because you don't know
    the starting condition of the future ones.

    It has been tried often, a working solution would have been worth gold.
    I remember the Weitek array coprocessor back in 80386 times and
    a try with the NS16032. They never got a factor of more than 2 or 3.

    Everything really interesting is np-complete.-a :-(

    Cheers, Gerhard


    Another problem of practical value that's NP-complete is the pen-plotter problem or the "postal-route inspection" problem; how do you connect
    vertices of a vector image with lines such that the total Manhattan
    distance the plotter head covers in the process is minimal.

    as opposed to the shortest path problem on directed and directed graphs,
    exact solution to that one is np-complete. There are heuristics that do
    pretty good
    --- Synchronet 3.21d-Linux NewsLink 1.2
  • From bitrex@user@example.net to sci.electronics.design,sci.electronics.equipment on Tue Jul 14 12:26:56 2020
    From Newsgroup: sci.electronics.equipment

    On 7/14/2020 12:25 PM, bitrex wrote:
    On 7/14/2020 12:14 PM, Gerhard Hoffmann wrote:
    Am 14.07.20 um 17:50 schrieb bitrex:

    I suggested to Mike E that LT Spice should use a graphic card for
    computation, but I guess that's not going to happen now.

    A modest Windows PC can spin Solidworks 3D images around just fine.




    Is SPICE trivially parallelize-able in that way?

    No. Inverting the conductivity matrix is hard because you
    cannot do the pivoting in advance. The necessity shows
    up during work.

    For transient analysis, every time step builds on the previous one(s)
    and you cannot parallelize a lot of them because you don't know
    the starting condition of the future ones.

    It has been tried often, a working solution would have been worth gold.
    I remember the Weitek array coprocessor back in 80386 times and
    a try with the NS16032. They never got a factor of more than 2 or 3.

    Everything really interesting is np-complete.-a :-(

    Cheers, Gerhard


    Another problem of practical value that's NP-complete is the pen-plotter problem or the "postal-route inspection" problem; how do you connect vertices of a vector image with lines such that the total Manhattan
    distance the plotter head covers in the process is minimal.

    as opposed to the shortest path problem on directed and directed graphs, exact solution to that one is np-complete. There are heuristics that do pretty good

    it's similar but distinct from the traveling salesman problem
    --- Synchronet 3.21d-Linux NewsLink 1.2
  • From jlarkin@jlarkin@highlandsniptechnology.com to sci.electronics.design,sci.electronics.equipment on Tue Jul 14 09:27:18 2020
    From Newsgroup: sci.electronics.equipment

    On Tue, 14 Jul 2020 18:14:04 +0200, Gerhard Hoffmann <dk4xp@arcor.de>
    wrote:

    Am 14.07.20 um 17:50 schrieb bitrex:

    I suggested to Mike E that LT Spice should use a graphic card for
    computation, but I guess that's not going to happen now.

    A modest Windows PC can spin Solidworks 3D images around just fine.




    Is SPICE trivially parallelize-able in that way?

    No. Inverting the conductivity matrix is hard because you
    cannot do the pivoting in advance. The necessity shows
    up during work.

    For transient analysis, every time step builds on the previous one(s)
    and you cannot parallelize a lot of them because you don't know
    the starting condition of the future ones.

    It has been tried often, a working solution would have been worth gold.
    I remember the Weitek array coprocessor back in 80386 times and
    a try with the NS16032. They never got a factor of more than 2 or 3.

    Everything really interesting is np-complete. :-(

    Cheers, Gerhard

    LT Spice can already use multiple cores, so something is
    parallel-izable. The petaflop computers, used for weather and physics simulation, have thousands of CPUs.

    Spice is usually fine, but once in a while I want 1000x or so more
    speed.
    --

    John Larkin Highland Technology, Inc

    Science teaches us to doubt.

    Claude Bernard

    --- Synchronet 3.21d-Linux NewsLink 1.2
  • From bitrex@user@example.net to sci.electronics.design,sci.electronics.equipment on Tue Jul 14 12:41:50 2020
    From Newsgroup: sci.electronics.equipment

    On 7/14/2020 12:27 PM, jlarkin@highlandsniptechnology.com wrote:
    On Tue, 14 Jul 2020 18:14:04 +0200, Gerhard Hoffmann <dk4xp@arcor.de>
    wrote:

    Am 14.07.20 um 17:50 schrieb bitrex:

    I suggested to Mike E that LT Spice should use a graphic card for
    computation, but I guess that's not going to happen now.

    A modest Windows PC can spin Solidworks 3D images around just fine.




    Is SPICE trivially parallelize-able in that way?

    No. Inverting the conductivity matrix is hard because you
    cannot do the pivoting in advance. The necessity shows
    up during work.

    For transient analysis, every time step builds on the previous one(s)
    and you cannot parallelize a lot of them because you don't know
    the starting condition of the future ones.

    It has been tried often, a working solution would have been worth gold.
    I remember the Weitek array coprocessor back in 80386 times and
    a try with the NS16032. They never got a factor of more than 2 or 3.

    Everything really interesting is np-complete. :-(

    Cheers, Gerhard

    LT Spice can already use multiple cores, so something is
    parallel-izable. The petaflop computers, used for weather and physics simulation, have thousands of CPUs.

    Spice is usually fine, but once in a while I want 1000x or so more
    speed.




    GPU cores aren't general-purpose CPUs, they're serial-pipelined and
    optimized for SIMD-instructions.

    A mutlicore general-purpose CPU has good cache coherency there's a fast
    on-die cache for all 4 or 8 cores or w/e that any of the processors can
    look at data the others are working on quickly.

    It's hard to achieve that kind of cache coherency with thousands of
    cores. If core #127 needs to "see" what core #562 is working on it
    usually has to go out to video RAM. which is not nearly as fast as
    on-die cache.
    --- Synchronet 3.21d-Linux NewsLink 1.2
  • From bitrex@user@example.net to sci.electronics.design,sci.electronics.equipment on Tue Jul 14 12:53:10 2020
    From Newsgroup: sci.electronics.equipment

    On 7/14/2020 12:27 PM, jlarkin@highlandsniptechnology.com wrote:
    On Tue, 14 Jul 2020 18:14:04 +0200, Gerhard Hoffmann <dk4xp@arcor.de>
    wrote:

    Am 14.07.20 um 17:50 schrieb bitrex:

    I suggested to Mike E that LT Spice should use a graphic card for
    computation, but I guess that's not going to happen now.

    A modest Windows PC can spin Solidworks 3D images around just fine.




    Is SPICE trivially parallelize-able in that way?

    No. Inverting the conductivity matrix is hard because you
    cannot do the pivoting in advance. The necessity shows
    up during work.

    For transient analysis, every time step builds on the previous one(s)
    and you cannot parallelize a lot of them because you don't know
    the starting condition of the future ones.

    It has been tried often, a working solution would have been worth gold.
    I remember the Weitek array coprocessor back in 80386 times and
    a try with the NS16032. They never got a factor of more than 2 or 3.

    Everything really interesting is np-complete. :-(

    Cheers, Gerhard

    LT Spice can already use multiple cores, so something is
    parallel-izable. The petaflop computers, used for weather and physics simulation, have thousands of CPUs.

    Spice is usually fine, but once in a while I want 1000x or so more
    speed.




    People with advanced credentials in e.g. meteorology or computational
    biology or physics plus the computer science of optimizing
    multiprocessing systems get paid the biggo buckos
    --- Synchronet 3.21d-Linux NewsLink 1.2
  • From Phil Hobbs@pcdhSpamMeSenseless@electrooptical.net to sci.electronics.design,sci.electronics.equipment on Tue Jul 14 14:54:37 2020
    From Newsgroup: sci.electronics.equipment

    On 2020-07-14 12:14, Gerhard Hoffmann wrote:
    Am 14.07.20 um 17:50 schrieb bitrex:

    I suggested to Mike E that LT Spice should use a graphic card for
    computation, but I guess that's not going to happen now.

    A modest Windows PC can spin Solidworks 3D images around just fine.




    Is SPICE trivially parallelize-able in that way?

    No. Inverting the conductivity matrix is hard because you
    cannot do the pivoting in advance. The necessity shows
    up during work.

    For transient analysis, every time step builds on the previous one(s)
    and you cannot parallelize a lot of them because you don't know
    the starting condition of the future ones.

    It has been tried often, a working solution would have been worth gold.
    I remember the Weitek array coprocessor back in 80386 times and
    a try with the NS16032. They never got a factor of more than 2 or 3.

    Everything really interesting is np-complete.-a :-(

    Cheers, Gerhard


    It probably could be, if you changed the scheme so as to impose a speed-of-light propagation limit. That way you could divide the
    schematic up into chunks, do time steps locally, and then propagate the changes to adjacent chunks.

    That gets rid of every node having to know about every other node on
    every time step, and makes FDTD codes such as my POEMS facility
    parallelize well. (It works that way.)

    Linear algebra also can be made to vectorize well on the right hardware.

    Cheers

    Phil Hobbs
    --
    Dr Philip C D Hobbs
    Principal Consultant
    ElectroOptical Innovations LLC / Hobbs ElectroOptics
    Optics, Electro-optics, Photonics, Analog Electronics
    Briarcliff Manor NY 10510

    http://electrooptical.net
    http://hobbs-eo.com

    --- Synchronet 3.21d-Linux NewsLink 1.2
  • From Commander Kinsey@CFKinsey@military.org.jp to sci.electronics.design,sci.electronics.equipment on Tue Jul 14 20:31:56 2020
    From Newsgroup: sci.electronics.equipment

    On Tue, 14 Jul 2020 17:07:31 +0100, bitrex <user@example.net> wrote:

    On 7/14/2020 11:53 AM, Phil Hobbs wrote:
    On 2020-07-14 11:36, jlarkin@highlandsniptechnology.com wrote:
    On Tue, 14 Jul 2020 16:10:17 +0100, "Commander Kinsey"
    <CFKinsey@military.org.jp> wrote:

    Why do graphics cards only monitor the speed of one fan? If the other
    one fails, it won't know!

    Are graphic cards used mostly for games? And maybe bitcoin mining?
    It's weird that one PC can contain more compute power than existed on
    Earth in 1970, and be used for games.

    I suggested to Mike E that LT Spice should use a graphic card for
    computation, but I guess that's not going to happen now.

    A modest Windows PC can spin Solidworks 3D images around just fine.




    GPUs are limited to single-precision floating point IIRC.

    Cheers

    Phil Hobbs


    That is to say they can do double but they're in general not optimized
    for it.

    Some are. I always buy the ones that are, since Milkyway at home loves them. --- Synchronet 3.21d-Linux NewsLink 1.2
  • From Commander Kinsey@CFKinsey@military.org.jp to sci.electronics.design,sci.electronics.equipment on Tue Jul 14 20:35:09 2020
    From Newsgroup: sci.electronics.equipment

    On Tue, 14 Jul 2020 16:36:44 +0100, <jlarkin@highlandsniptechnology.com> wrote:

    On Tue, 14 Jul 2020 16:10:17 +0100, "Commander Kinsey" <CFKinsey@military.org.jp> wrote:

    Why do graphics cards only monitor the speed of one fan? If the other one fails, it won't know!

    Are graphic cards used mostly for games? And maybe bitcoin mining?
    It's weird that one PC can contain more compute power than existed on
    Earth in 1970, and be used for games.

    But much better games than you could play in 1970.

    And there's distributed computing - see Folding at home, Einstein at home, Milkyway at home, etc.

    And many normal programs use graphics cards aswell nowadays - even stuff like Photoshop.

    I suggested to Mike E that LT Spice should use a graphic card for computation, but I guess that's not going to happen now.

    A modest Windows PC can spin Solidworks 3D images around just fine.

    Some programs can't.
    --- Synchronet 3.21d-Linux NewsLink 1.2
  • From bitrex@user@example.net to sci.electronics.design,sci.electronics.equipment on Tue Jul 14 16:42:20 2020
    From Newsgroup: sci.electronics.equipment

    On 7/14/2020 3:31 PM, Commander Kinsey wrote:
    On Tue, 14 Jul 2020 17:07:31 +0100, bitrex <user@example.net> wrote:

    On 7/14/2020 11:53 AM, Phil Hobbs wrote:
    On 2020-07-14 11:36, jlarkin@highlandsniptechnology.com wrote:
    On Tue, 14 Jul 2020 16:10:17 +0100, "Commander Kinsey"
    <CFKinsey@military.org.jp> wrote:

    Why do graphics cards only monitor the speed of one fan? If the other >>>>> one fails, it won't know!

    Are graphic cards used mostly for games? And maybe bitcoin mining?
    It's weird that one PC can contain more compute power than existed on
    Earth in 1970, and be used for games.

    I suggested to Mike E that LT Spice should use a graphic card for
    computation, but I guess that's not going to happen now.

    A modest Windows PC can spin Solidworks 3D images around just fine.




    GPUs are limited to single-precision floating point IIRC.

    Cheers

    Phil Hobbs


    That is to say they can do double but they're in general not optimized
    for it.

    Some are.a I always buy the ones that are, since Milkyway at home loves them.

    I suppose one has to buy the "Pro" variant rather than the
    gamer/consumer variant.

    Moychendizing, moychendizing
    --- Synchronet 3.21d-Linux NewsLink 1.2
  • From Commander Kinsey@CFKinsey@military.org.jp to sci.electronics.design,sci.electronics.equipment on Tue Jul 14 21:50:16 2020
    From Newsgroup: sci.electronics.equipment

    On Tue, 14 Jul 2020 21:42:20 +0100, bitrex <user@example.net> wrote:

    On 7/14/2020 3:31 PM, Commander Kinsey wrote:
    On Tue, 14 Jul 2020 17:07:31 +0100, bitrex <user@example.net> wrote:

    On 7/14/2020 11:53 AM, Phil Hobbs wrote:
    On 2020-07-14 11:36, jlarkin@highlandsniptechnology.com wrote:
    On Tue, 14 Jul 2020 16:10:17 +0100, "Commander Kinsey"
    <CFKinsey@military.org.jp> wrote:

    Why do graphics cards only monitor the speed of one fan? If the other >>>>>> one fails, it won't know!

    Are graphic cards used mostly for games? And maybe bitcoin mining?
    It's weird that one PC can contain more compute power than existed on >>>>> Earth in 1970, and be used for games.

    I suggested to Mike E that LT Spice should use a graphic card for
    computation, but I guess that's not going to happen now.

    A modest Windows PC can spin Solidworks 3D images around just fine.




    GPUs are limited to single-precision floating point IIRC.

    Cheers

    Phil Hobbs


    That is to say they can do double but they're in general not optimized
    for it.

    Some are. I always buy the ones that are, since Milkyway at home loves
    them.

    I suppose one has to buy the "Pro" variant rather than the
    gamer/consumer variant.

    Moychendizing, moychendizing

    I get them second hand, so I don't know what they were aimed at originally. Four of them are R9 280X. I thought those were high end games cards in their day. It could have been before they stopped putting double in everything. But it could be that the double precision ones are made in smaller quantities, so you don't get the mass production discount. Or it could be that it's more expensive to make them. But the reason they make them without is that games don't make use of double precision. Less double processing means space for more single processing on the die.
    --- Synchronet 3.21d-Linux NewsLink 1.2
  • From Gerhard Hoffmann@dk4xp@arcor.de to sci.electronics.design,sci.electronics.equipment on Wed Jul 15 02:22:24 2020
    From Newsgroup: sci.electronics.equipment

    Am 14.07.20 um 20:54 schrieb Phil Hobbs:
    On 2020-07-14 12:14, Gerhard Hoffmann wrote:
    Am 14.07.20 um 17:50 schrieb bitrex:

    I suggested to Mike E that LT Spice should use a graphic card for
    computation, but I guess that's not going to happen now.

    A modest Windows PC can spin Solidworks 3D images around just fine.




    Is SPICE trivially parallelize-able in that way?

    No. Inverting the conductivity matrix is hard because you
    cannot do the pivoting in advance. The necessity shows
    up during work.

    For transient analysis, every time step builds on the previous one(s)
    and you cannot parallelize a lot of them because you don't know
    the starting condition of the future ones.

    It has been tried often, a working solution would have been worth gold.
    I remember the Weitek array coprocessor back in 80386 times and
    a try with the NS16032. They never got a factor of more than 2 or 3.

    Everything really interesting is np-complete.-a :-(

    Cheers, Gerhard


    It probably could be, if you changed the scheme so as to impose a speed-of-light propagation limit.-a That way you could divide the
    schematic up into chunks, do time steps locally, and then propagate the changes to adjacent chunks.

    This was my proposal at Z80 / AM9511/AM9512 times, just one node
    per square mm of DUT chip. I also tried to port Spice 2G6
    to Interactive Unix on my 80286/287 Bullet board. What a fiasco.
    64K segments conspiring with f2c as a Fortran compiler. Never could
    have worked.

    But this computer had 2 MB and a 70 MB Fujitsu disk. That was pure
    hubris in the hands of a EE & CS student. Our VAX11 at the semiconductor institute had 2 300 MB Fujitsu Eagles for all people together. :-)
    And we made real chip designs on it.

    Later I had a T800 transputer cluster, that would have mapped nicely
    to this problem. But I never could find a customer for any T800
    solution I proposed. All went X86.

    The only exception was smuggling a Parsytec cluster to east Berlin.
    But little Gerhard did not dare to. Few did I know. Some weeks
    later, all the sudden, was the German re-unification and nobody would
    have cared anymore about smuggling technology to an east-German
    railway company that went belly-up anyway. Sigh.

    That gets rid of every node having to know about every other node on
    every time step, and makes FDTD codes such as my POEMS facility
    parallelize well.-a (It works that way.)

    Linear algebra also can be made to vectorize well on the right hardware.

    Cheers

    Gerhard
    --- Synchronet 3.21d-Linux NewsLink 1.2
  • From upsidedown@upsidedown@downunder.com to sci.electronics.design,sci.electronics.equipment on Wed Jul 15 06:43:49 2020
    From Newsgroup: sci.electronics.equipment

    On Tue, 14 Jul 2020 11:50:08 -0400, bitrex <user@example.net> wrote:

    On 7/14/2020 11:36 AM, jlarkin@highlandsniptechnology.com wrote:
    On Tue, 14 Jul 2020 16:10:17 +0100, "Commander Kinsey"
    <CFKinsey@military.org.jp> wrote:

    Why do graphics cards only monitor the speed of one fan? If the other one fails, it won't know!

    Are graphic cards used mostly for games? And maybe bitcoin mining?
    It's weird that one PC can contain more compute power than existed on
    Earth in 1970, and be used for games.

    I suggested to Mike E that LT Spice should use a graphic card for
    computation, but I guess that's not going to happen now.

    A modest Windows PC can spin Solidworks 3D images around just fine.




    Is SPICE trivially parallelize-able in that way?

    How about Monte Carlo simulation ?

    --- Synchronet 3.21d-Linux NewsLink 1.2