FPGA's - the future

I am wondering if any ofyou share my vision of an FPGA (or equivalent)
type future. By this I mean programmable hardware. Your PC will be
nothing but a massive array of gates on which you download your own
custom processor. You use high level languages which compiles direct
to silicon and runs 100 times faster than ordinary software.
A silicon compiler, full floating point. Suppose we need a modem -
just download it. A dual processor - no problem, just download it.


Hardy

>I am wondering if any ofyou share my vision of an FPGA (or equivalent)
>type future. By this I mean programmable hardware. Your PC will be
>nothing but a massive array of gates on which you download your own
>custom processor. You use high level languages which compiles direct
>to silicon and runs 100 times faster than ordinary software.
>A silicon compiler, full floating point. Suppose we need a modem -
>just download it. A dual processor - no problem, just download it.
>
>
>Hardy
>
Sounds pretty cool. 

On Wed, 11 Apr 2012 14:09:10 -0700 (PDT)
HardySpicer <gyansorova@gmail.com> wrote:

> I am wondering if any ofyou share my vision of an FPGA (or equivalent)
> type future. By this I mean programmable hardware. Your PC will be
> nothing but a massive array of gates on which you download your own
> custom processor. You use high level languages which compiles direct
> to silicon and runs 100 times faster than ordinary software.
> A silicon compiler, full floating point. Suppose we need a modem -
> just download it. A dual processor - no problem, just download it.
> 
> 
> Hardy

I don't think you'll ever manage to get programmable hardware to be as
fast as fixed hardware.  Right now I've got an Intel processor in my
machine running at 3.6 GHz.  The fastest FPGAs I can buy max out at a
few hundred MHz, and even that's for very little logic between register
stages.  A typical soft processor's even worse, you're lucky to get 300
MHz.  And that's on thousands of dollars of high end FPGA.

Notice that FPGAs are in fact going the other direction.  Less
programmability, farther from the regular "sea of gates", more
dedicated resources like DSP blocks, hard processors, PCIe
transceivers, etc.

At a given process node, programmable hardware has to lack performance
relative to dedicated hardware.  At that point you're hoping you can
make it up in parallel, but parallel complicates most problems far more
than it helps them.

-- 
Rob Gaddi, Highland Technology -- www.highlandtechnology.com
Email address domain is currently out of order.  See above to fix.

On Apr 12, 9:17=A0am, Rob Gaddi <rga...@technologyhighland.invalid>
wrote:
> On Wed, 11 Apr 2012 14:09:10 -0700 (PDT)
>
> HardySpicer <gyansor...@gmail.com> wrote:
> > I am wondering if any ofyou share my vision of an FPGA (or equivalent)
> > type future. By this I mean programmable hardware. Your PC will be
> > nothing but a massive array of gates on which you download your own
> > custom processor. You use high level languages which compiles direct
> > to silicon and runs 100 times faster than ordinary software.
> > A silicon compiler, full floating point. Suppose we need a modem -
> > just download it. A dual processor - no problem, just download it.
>
> > Hardy
>
> I don't think you'll ever manage to get programmable hardware to be as
> fast as fixed hardware. =A0Right now I've got an Intel processor in my
> machine running at 3.6 GHz. =A0The fastest FPGAs I can buy max out at a
> few hundred MHz, and even that's for very little logic between register
> stages. =A0A typical soft processor's even worse, you're lucky to get 300
> MHz. =A0And that's on thousands of dollars of high end FPGA.
>
> Notice that FPGAs are in fact going the other direction. =A0Less
> programmability, farther from the regular "sea of gates", more
> dedicated resources like DSP blocks, hard processors, PCIe
> transceivers, etc.
>
> At a given process node, programmable hardware has to lack performance
> relative to dedicated hardware. =A0At that point you're hoping you can
> make it up in parallel, but parallel complicates most problems far more
> than it helps them.
>
> --
> Rob Gaddi, Highland Technology --www.highlandtechnology.com
> Email address domain is currently out of order. =A0See above to fix.

I agree but as with micro technology, the principle remains the same
whilst the technology gets smaller and faster. It may never be as fast
but the versatility is a trade off provided it can be done fast enough
to be useable. When compiled, a silicon program is always faster than
software.


Hardy

Hi Hardy,



On 11-04-12 23:09, HardySpicer wrote:
> I am wondering if any ofyou share my vision of an FPGA (or equivalent)
> type future. By this I mean programmable hardware. Your PC will be
> nothing but a massive array of gates on which you download your own
> custom processor. You use high level languages which compiles direct
> to silicon and runs 100 times faster than ordinary software.
> A silicon compiler, full floating point. Suppose we need a modem -
> just download it. A dual processor - no problem, just download it.

Do you mean open source hardware FPGA IP-cores?

Something like this?
http://opencores.org/


> Hardy
Cheerio! Kr. Bonne.

On Wed, 11 Apr 2012 14:17:47 -0700, Rob Gaddi
<rgaddi@technologyhighland.invalid> wrote:

>On Wed, 11 Apr 2012 14:09:10 -0700 (PDT)
>HardySpicer <gyansorova@gmail.com> wrote:
>
>> I am wondering if any ofyou share my vision of an FPGA (or equivalent)
>> type future. By this I mean programmable hardware. Your PC will be
>> nothing but a massive array of gates on which you download your own
>> custom processor. You use high level languages which compiles direct
>> to silicon and runs 100 times faster than ordinary software.
>> A silicon compiler, full floating point. Suppose we need a modem -
>> just download it. A dual processor - no problem, just download it.
>> 
>> 
>> Hardy
>
>I don't think you'll ever manage to get programmable hardware to be as
>fast as fixed hardware. 

Or as cheap or as low-power.   With power consumption being an
ever-growing concern this alone may drive.


Eric Jacobsen
Anchor Hill Communications
www.anchorhill.com

On 4/11/2012 2:09 PM, HardySpicer wrote:
> I am wondering if any ofyou share my vision of an FPGA (or equivalent)
> type future. By this I mean programmable hardware. Your PC will be
> nothing but a massive array of gates on which you download your own
> custom processor. You use high level languages which compiles direct
> to silicon and runs 100 times faster than ordinary software.
> A silicon compiler, full floating point. Suppose we need a modem -
> just download it. A dual processor - no problem, just download it.

Interconnect (within the silicon) eats your lunch if you
want to treat the array as "generic silicon".

A processor achieves lots of efficiency (and redundancy!)
by exploiting geometries of particular features -- register
files, ALUs, etc. -- that free the layout from trying to
accommodate "anyTHING, anyWHERE".

And, as geometries get smaller and smaller, there is a HUGE role
for "extra stuff" on the die to cover a certain "defect expectation".

On Wed, 11 Apr 2012 14:09:10 -0700, HardySpicer wrote:

> I am wondering if any ofyou share my vision of an FPGA (or equivalent)
> type future. By this I mean programmable hardware. Your PC will be
> nothing but a massive array of gates on which you download your own
> custom processor. You use high level languages which compiles direct to
> silicon and runs 100 times faster than ordinary software. A silicon
> compiler, full floating point. Suppose we need a modem - just download
> it. A dual processor - no problem, just download it.

I don't think it'll happen in my lifetime.  I think that FPGAs will be a 
valuable way to address niche products for a long time to come -- but if 
they were all that good for general purpose logic (much less computing), 
PC motherboards would use FPGAs instead of hard-wired chipsets.

-- 
My liberal friends think I'm a conservative kook.
My conservative friends think I'm a liberal kook.
Why am I not happy that they have found common ground?

Tim Wescott, Communications, Control, Circuits & Software
http://www.wescottdesign.com

HardySpicer <gyansorova@gmail.com> wrote:

> I am wondering if any ofyou share my vision of an FPGA (or equivalent)
> type future. By this I mean programmable hardware. Your PC will be
> nothing but a massive array of gates on which you download your own
> custom processor. 

Is sounds nice, but doesn't seem likely.

Maybe 40 years ago, we had microprogammed processors with writable
control store, to allow adding new instructions. A nice feature,
but rarely used.

> You use high level languages which compiles direct
> to silicon and runs 100 times faster than ordinary software.

I might believe a small FPGA such that one could load logic optimal
to the problem at hand. Presumably it would have to be part of
the context, saved and restored, though maybe with enough to
avoid too much swapping. (That is, more than one program could be
running, each with its own custom logic block.)

> A silicon compiler, full floating point. Suppose we need a modem -
> just download it. A dual processor - no problem, just download it.

Floating point is especially inefficient in most FPGAs.

I do believe that FPGAs are nice for legacy processors. You could
build a nice box that could emulate popular machines from the 1970's,
1980's, and even 1990's. I have thought about a board with a medium
to large FPGA, with an ISA, PCI, Sbus, Apple II bus, S-100, NuBus,
and maybe more, slot. (One of each.) Also, parallel, two serial,
VGA, PS/2 keyboard and mouse, IDE, and floppy port.

That would allow one machine to emulate a large number of older
systems. (The whole system, not just processor.)

-- glen

On Apr 13, 1:28&#4294967295;am, glen herrmannsfeldt <g...@ugcs.caltech.edu> wrote:
> HardySpicer <gyansor...@gmail.com> wrote:
> > I am wondering if any ofyou share my vision of an FPGA (or equivalent)
> > type future. By this I mean programmable hardware. Your PC will be
> > nothing but a massive array of gates on which you download your own
> > custom processor.
>
> Is sounds nice, but doesn't seem likely.
>
> Maybe 40 years ago, we had microprogammed processors with writable
> control store, to allow adding new instructions. A nice feature,
> but rarely used.
>
> > You use high level languages which compiles direct
> > to silicon and runs 100 times faster than ordinary software.
>
> I might believe a small FPGA such that one could load logic optimal
> to the problem at hand. Presumably it would have to be part of
> the context, saved and restored, though maybe with enough to
> avoid too much swapping. (That is, more than one program could be
> running, each with its own custom logic block.)
>
> > A silicon compiler, full floating point. Suppose we need a modem -
> > just download it. A dual processor - no problem, just download it.
>
> Floating point is especially inefficient in most FPGAs.
>
> I do believe that FPGAs are nice for legacy processors. You could
> build a nice box that could emulate popular machines from the 1970's,
> 1980's, and even 1990's. I have thought about a board with a medium
> to large FPGA, with an ISA, PCI, Sbus, Apple II bus, S-100, NuBus,
> and maybe more, slot. (One of each.) Also, parallel, two serial,
> VGA, PS/2 keyboard and mouse, IDE, and floppy port.
>
> That would allow one machine to emulate a large number of older
> systems. (The whole system, not just processor.)
>
> -- glen
That's a great idea which to me tells me we are around 20 years behind
where we could be.
We need faster FPGA programming and devices etc. surely new
technologies will emerge in time.


Hardy