[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [f-cpu] Re: Floating-Point



Yann Guidon a écrit :
> 
> hi !
> 
> Michael Riepe wrote:
> > On Sun, Aug 19, 2001 at 03:23:50PM -0400, nicO wrote:
> > > Just one point about SIMD FP. I think that SIMD flag should means an
> > > others thing that for integer (no need for 8 bit).
> > > What about 16 32 64 128(80 ?) ? 4 differents precisions, the last don't
> > > need to be implemented in FC0.
> >
> > The manual says:
> >
> >         00      32-bit
> >         01      64-bit
> >         1x      unassigned
> >
> > and the second one...
> 
> the two first codes are allocated, so we can use 2 other reserved sizes,
> for example 80 and 128.
> 
> > On Sun, Aug 19, 2001 at 05:33:05PM -0400, nicO wrote:
> > > Hello,
> > >
> > > I'm looking for the "usual" definition of the port of a unit :
> > >
> > > 3 data in,
> >
> > Or less.
> >
> > > 2 data out,
> >
> > Or more.
> >
> > > SIMD flag,
> >
> > Make that `chunk size'; I use std_ulogic_vector(2 downto 0) for it.
> 
> oh btw, the SIMD flag is useful for an EU _only_ if you optimize for speed
> and/or consumption. This flag is forwarded to the units but it is used mainly
> for the making of the writeback mask (in the register set).
> 

So the SIMD stuff is for the same thing for register bank. But we should
always take good habit for improving power consumption (speed and
blablabla).

nicO

> > > clk,
> > > enable or start,
> > > reset,
> > > something for the exception ?
> > >
> > > If there is something to say if the outed data is correct or not ?
> >
> > Currently not; the scheduler should know.  But we can add a `here is
> > the result, take it or I'll throw it away in the next cycle' signal.
> currently, only the IDIV has one.
> 
> > Something is missing: the lines that select the instruction to execute
> > (if the unit can handle more than one instruction).
> 
> ??
> 
> >  Michael "Tired" Riepe <Michael.Riepe@stud.uni-hannover.de>
> WHYGEE "Gimme Doop, Joana" :-) (JBO)
> ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> *************************************************************
> To unsubscribe, send an e-mail to majordomo@seul.org with
> unsubscribe f-cpu       in the body. http://f-cpu.seul.org/
*************************************************************
To unsubscribe, send an e-mail to majordomo@seul.org with
unsubscribe f-cpu       in the body. http://f-cpu.seul.org/