In article
<b...@posting.google.com>,
Stifler <s...@hotmail.com> wrote:
>Also, custom instuctions are probably as stupid as a window register
>file. Why do you need a custom instuction so bad? I believe it's
>simply hardware acceleration. There's several ways to accomplish
>hardware acceleration. Altera's custom instuction can bog down your
>processor Fmax. It goes right into the middle of the pipe. Why not
>simply have your processor launch off a separate process while it
>continues to grind away at top speed?

Likewise, this is the whole BLEEPING point of having a coprocessor
interface: it gives you a separate pipeline for your instructions, etc
etc etc, so you can have the advantages of a "custom" extention to
your instruction set, without having it in the pipeline or even
necessarily in the critical path...


Chimaera (a hard processor design with an in-the-pipeline
reconfigurable unit for custom instructions) was, IMO, a failure
compared to GARP (a hard processor design with a reconfigurable unit
as a MIPS coprocessor, with its own specialized memory interfaces).

Yet Chimaera was a useful failure, an incredibly valuable negative
result: showing just how little one could achive with in-the-pipeline
custom instructions.

Especially since, for custom instructions, you are often dealing with
large working sets (otherwise you don't really benefit in the first
place), so having a coprocessor with its own optimized (eg, streaming,
strided-streaming) memory access ports is a huge win over
"in-the-pipeline" custom instructions.
-- 
Nicholas C. Weaver                                 n...@cs.berkeley.edu

Kenneth Land wrote:
> "E.S." <e...@ecubics.com> wrote in message
> news:GsOsc.20467$z...@fe39.usenetserver.com...

>>>Ever heard the term "Sour Grapes" ?
>>
>>Heard before, but why in this context ?
> 
> Uh.. Because you're saying you don't want something you can't have, even
> though it's of great value. (Custom Instructions with Nios (the grapes) vs.
> Microblaze (no grapes) - so you say "They are probably sour anyway")

OK, I got it. Thanks ;-)

But I wasn't even thinking about the NIOS <--> MicroBlaze
competition (?)

More along the lines, how I like to expand my processors. And
my software guys are trying to kill me each time we invent a new
instruction ;-)

Cheers

Kenneth Land wrote:

> "Jon Beniston" <j...@beniston.com> wrote in message
> news:e...@posting.google.com...
> <snip>
> 
>>You say it like it doesn't matter. Maybe it doesn't with FPGA CPUs as
>>you're obviously not concerned about price anyway ;)

I don't think it is so easy to calculate. Having a chance to change
"hardware" at a very late stage of a project, can save you a lot of
money.

BTW, how many poeple in this group are really selling millions of 
boards, so it make sense to cut a dollar on the chip, but spend it
in software instead ?

> Hard to imagine an embedded project without an fpga.  Might as well have
> only one chip (fpga + softcore cpu) and save the board space since you're
> most likely going to require an fpga anyway. (board space == $$$, parts
> count == $$$)

Sitting long nights to get the tools working ?
priceless ;-)

> The reason you would want to use a softcore over hard is because it can be
> *exactly* customized to any application.  Need 27 serial ports and timers?
> no problem.  Need none?  don't waste the pins or money.  Need more
> processing power?  add custom instructions/external parrallel logic or
> another softcore cpu (or 8!).

But probably you didn't spent enough time to get the 
requirements/specification straight in the first place ?

> I've seen hard core projects fail, but a soft core project can only fail
> from early abandonment.  

Or delays ...

> More/harder work can always find a solution,
> because the hardware can become anything you're willing to realize.

But you need a boss with a good sense of humour ;-)

cheers

>Can you explain how it "blows away" custom instructions?  I don't know what
>the FSL interface is, so I can't compare them myself.
>
>  
>
You should take a look at xilinx app.note529   
http://direct.xilinx.com/bvdocs/appnotes/xapp529.pdf
It will explain FSL a little more and also why FSL interfaces are better 
for HW acceleration that custom instructions.

Göran

"E.S." <e...@ecubics.com> wrote in message
news:v33tc.124$U...@fe39.usenetserver.com...
> Kenneth Land wrote:
> > "E.S." <e...@ecubics.com> wrote in message
> > news:GsOsc.20467$z...@fe39.usenetserver.com...
Microblaze (no grapes) - so you say "They are probably sour anyway")
>
> OK, I got it. Thanks ;-)
>
> But I wasn't even thinking about the NIOS <--> MicroBlaze
> competition (?)
>
> More along the lines, how I like to expand my processors. And
> my software guys are trying to kill me each time we invent a new
> instruction ;-)
>
> Cheers
>

You'd be treated better here!
I'm more of a software guy, but I'd be very happy if my hardware guy took
the initiative to add instructions to my NiosI/II!


Take care

"rickman" <s...@yahoo.com> wrote in message
news:4...@yahoo.com...
> Kenneth Land wrote:
> >
> > "Jon Beniston" <j...@beniston.com> wrote in message
> > news:e...@posting.google.com...
> > <snip>
> > >
> > > You say it like it doesn't matter. Maybe it doesn't with FPGA CPUs as
> > > you're obviously not concerned about price anyway ;)
> > >
> > > Cheers,
> > > JonB
> >
> > Hard to imagine an embedded project without an fpga.  Might as well have
> > only one chip (fpga + softcore cpu) and save the board space since
you're
> > most likely going to require an fpga anyway. (board space == $$$, parts
> > count == $$$)
> >
> > The reason you would want to use a softcore over hard is because it can
be
> > *exactly* customized to any application.  Need 27 serial ports and
timers?
> > no problem.  Need none?  don't waste the pins or money.  Need more
> > processing power?  add custom instructions/external parrallel logic or
> > another softcore cpu (or 8!).
> >
> > I've seen hard core projects fail, but a soft core project can only fail
> > from early abandonment.  More/harder work can always find a solution,
> > because the hardware can become anything you're willing to realize.
>
> Ok, how about an 8 bit CPU with an 8 input, 10 bit ADC and a brown out
> detector?  I think this costs less than $3 and comes in a 28 pin TSSOP
> or a 5 x 5 mm QFN.  MCUs often have advantages since they are typically
> mixed signal chips, not just digital.  It can be pretty hard to beat an
> MCU with an FPGA when you need even just a little bit of analog.
>
> -- 
>
> Rick "rickman" Collins
>
> r...@XYarius.com

If you didn't know you needed an ADC before you started then yes you are out
of luck.  Not so much because there's no ADC on your board, but because you
can't produce an initial design that's in the ballpark.  But yes you are
literally correct.  There are many things that an FPGA can't do.  I was
thinking more in the realm of what processing you might want to do on those
8 input channels - especially after the customer or salesmen started with
the post production design ideas :)

You sound like one of my kids "What if Godzilla shows up and steps on your
board?"

enough :)

Ken

"E.S." <e...@ecubics.com> wrote in message
news:ui3tc.160$U...@fe39.usenetserver.com...
>
> Sitting long nights to get the tools working ?
> priceless ;-)
>
> cheers
>

Yeah, but once you figure out all the quirks you're Super Man!  Able to
drive any nail with your new hammer!

(at least that's what I keep telling myself , but then comes along version
2,3,4... plus XP updates :)

Some of my favorite efforts in delving into this world of fpga's and soft
cores has been separating the truly usefull feature/tools from the marketing
checkoffs.  Altera support told me that to bring out internal signals using
Signal Probe would require placing the signal into a register.  But wasn't
the whole point of SP to avoid full rebuilds? :)

(I'm sure SP is extremely usefull once mastered, just don't have "priceless"
hours right now and no one here is letting loose with the secrets)

:)
Ken