 |
Search Sci.Electronics.Basics |
|
|
|
|
|
|
 |
|
|
Sci.Electronics.Basics -> Which uController to learn?
There are 124 messages in this thread.
You are currently looking at messages 80 to 100.
|
Author: krwDate: 21:37 18-03-07
|
|
In article <1174262118.454781.116300@n76g2000hsh.googlegroups.com>,
me@linnix.info-for.us says...
> On Mar 18, 3:33 pm, Terran Melconian
> <te_rem_ra_ove_an_fors...@consistent.org> wrote:
> > On 2007-03-18, John Barrett <ke5c...@verizon.net> wrote:
> >
> > > optimized... you've gotta be right on the ragged edge of what the chip is
> > > capable of before ASM is going to help you, and 99% of apps wont even
come
> > > close to that limit.
> >
> > Some people would say that if you're *not* at the edge of what the
> > microcontroller can do, you're using one that's too expensive. ;)
>
> Same for PCs. How many people really need the 3GHz Dual core PC to
> read this newsgroup?
>
I don't need a pickup truck to go to the pub either but it comes in
handy at the dump. This dual 1.86GHz laptop is kinda nice too (once
I put enough memory on it).
--
Keith
|
|
|
|
Author: linnixDate: 22:29 18-03-07
|
|
On Mar 18, 5:11 pm, "bungalow_st...@yahoo.com"
<bungalow_st...@yahoo.com> wrote:
> On Mar 18, 8:44 pm, "linnix" <m...@linnix.info-for.us> wrote:
>
>
>
> > On Mar 18, 4:26 pm, krw <k...@att.bizzzz> wrote:
>
> > > In article <1174244224.891818.310...@e1g2000hsg.googlegroups.com>,
> > > m...@linnix.info-for.us says...
>
> > > > > > I've played with a few different micros, but there are
still plenty left
> > > > > > that I haven't. I do want to play with some of those tiny
32 bit ARMs that
> > > > > > have lots of memory and speed.
>
> > > > > ARMs don't thrill me much. Too much power.
>
> > > > Too much for what? The one I am using draws 70mA typical.
> > > > Of course, you can run an AVR for less than 1mA.
> > > > In my case, I use an AVR to power control an ARM.
> > > > The ARM can do the job quicker so both can go back to sleep ASAP.
>
> > > Power as in MIPS, not as in mA.
>
> > Why would too much MIPS bother you?
> > You don't have to use pay per MIPS.
>
> > > If I want MIPS I'd go with a PPC of some sort.
>
> > I haven't seen any PPC in low pin count with internal memories yet.
> > The Arm I am using is 64K flash, 8K sram on chip in 48 pins QFP.
>
> And you are using a AVR to turn it on? I would think a small ARM like
> that can be throttled down to run at about the same power as an AVR
> ( 1 mA), the AVR and Atmel ARM's have about the same W/hz, as an
> example, but the AVR's have much better sleep modes
Mainly with the clock. The Avr can run down to 32KHz, but the Arm
cannot go much below 1MHz (I believe).
|
|
|
|
Author: linnixDate: 22:56 18-03-07
|
|
On Mar 18, 5:34 pm, krw <k...@att.bizzzz> wrote:
> In article <1174265095.406744.259...@e65g2000hsc.googlegroups.com>,
> m...@linnix.info-for.us says...
>
>
>
> > On Mar 18, 4:26 pm, krw <k...@att.bizzzz> wrote:
> > > In article <1174244224.891818.310...@e1g2000hsg.googlegroups.com>,
> > > m...@linnix.info-for.us says...
>
> > > > > > I've played with a few different micros, but there are
still plenty left
> > > > > > that I haven't. I do want to play with some of those tiny
32 bit ARMs that
> > > > > > have lots of memory and speed.
>
> > > > > ARMs don't thrill me much. Too much power.
>
> > > > Too much for what? The one I am using draws 70mA typical.
> > > > Of course, you can run an AVR for less than 1mA.
> > > > In my case, I use an AVR to power control an ARM.
> > > > The ARM can do the job quicker so both can go back to sleep ASAP.
>
> > > Power as in MIPS, not as in mA.
>
> > Why would too much MIPS bother you?
> > You don't have to use pay per MIPS.
>
> Certainly you pay for MIPS. They don't give processors away free.
The Arm and Avr are close to the same price, around $5 each.
>
> > > If I want MIPS I'd go with a PPC of some sort.
>
> > I haven't seen any PPC in low pin count with internal memories yet.
> > The Arm I am using is 64K flash, 8K sram on chip in 48 pins QFP.
>
> More variables not stated in the parameters.
Nothing wrong with PPC, but I would not call it a uC.
>
> > > > > I'd likely have to learn C. ;-)
>
> > > > Why? They work in assemblers too, even if I don't.
>
> > > With the MIPS available one wouldn't likely be doing bit-banging,
> > > which is where assembler excels.
So, you don't like it because it's too good for you?
>
> --
> Keith
|
|
|
|
Author: John BarrettDate: 00:15 19-03-07
|
|
"krw" <krw@att.bizzzz> wrote in message
news:MPG.2067b35614fd415b98a173@news.individual.net...
> In article <1174262118.454781.116300@n76g2000hsh.googlegroups.com>,
> me@linnix.info-for.us says...
>> On Mar 18, 3:33 pm, Terran Melconian
>> <te_rem_ra_ove_an_fors...@consistent.org> wrote:
>> > On 2007-03-18, John Barrett <ke5c...@verizon.net> wrote:
>> >
>> > > optimized... you've gotta be right on the ragged edge of what the
>> > > chip is
>> > > capable of before ASM is going to help you, and 99% of apps wont even
>> > > come
>> > > close to that limit.
>> >
>> > Some people would say that if you're *not* at the edge of what the
>> > microcontroller can do, you're using one that's too expensive. ;)
>>
>> Same for PCs. How many people really need the 3GHz Dual core PC to
>> read this newsgroup?
>>
> I don't need a pickup truck to go to the pub either but it comes in
> handy at the dump. This dual 1.86GHz laptop is kinda nice too (once
> I put enough memory on it).
>
> --
> Keith
Terran:
Its cheaper for me to buy a stick of chips with the quantity discount than
it is to buy the minimal chip that will do the job each time I come up with
a new project :) Plus I dont have to wait for the new chips to show up --
always have a few on hand :) I've probably got 4 or 5 flavors of AVR hangin
around... from 18 pin to 40 pin with various flash/ram/eeprom combos -- I
just use whatever I got that will do the job at all :) havent run into a
project yet where the processor was out of the idle loop more than 50% of
the time :) hehehe I guess I could meet your criteria by cranking the clock
speed down a bunch !! but for me -- the processor has only 2 speeds -- the
fastest it will do without a crystal -- and the fastest it will do with one
:) I dont see the point of putting a slower crystal in then having to bust
nuts to make the code work.
Linnix:
hehehehe ---- If I only used my Dual 2.8g hyperthreaded Xeon with 4 gigs ram
to read newsgroups -- welllll :) but between editing DVD masters,
programming AVRs and C#, designing databases, apps and websites, editing
graphics, controlling my CNC mill, running 8-10 hour spice simulations on
10kw power supplies, etc -- I tend to keep this sucker pretty busy most of
the time :)
KRW:
I dont have a (working) laptop at the moment -- but the pub sounds like a
good idea !!
|
|
|
|
Author: Tim WescottDate: 01:02 19-03-07
|
|
John E. wrote:
>>Actually, just about anything that has a stack-oriented architecture, or
>>a register-oriented architecture with an orthogonal instruction set and
>>decent indexing.
>
>
> Being a beginner in all this, I have no experience / reference to be able to
> put product names to these capabilities. Would you "name names" please?
I'll
> create a diversion to take all the flames while you do that... (c:
68HC11, but it's old. I'll bet the 'HC12 and 'HC16 (do they still make
those?) are good.
AVR, if you don't mind wimpy pins.
The TI MSP430 -- the small ones at least have oodles of pin drive, they
appear to have a rational architecture, they're fast, and you can get a
complete development system from TI for $20.
ARM, if you don't mind wading through all the different versions that
are available to find what you want (check those pin drive capacities!).
The instruction set is rational, but only in a screwy, RISC sort of
way. The capabilities are HUGE, and so is the set of mistakes you can
make -- I wouldn't recommend it for a beginner.
PowerPC -- Freescale has embedded versions. Same snarky comment about
the instruction set as ARM, but still way better than a PIC.
Those are the ones that I'm familiar with.
Oh -- _not_ the Intersil/RCA 1802, unless you want to be an ace assembly
language programmer. It was the very first processor I ever worked
with, in 8th grade. I call it a NHISC -- Never Had an Instruction Set.
I don't know if it's still around, but for quite a while it was the
king of little space apps, because it had a huge geometry that could
absorb cosmic rays without even noticing that they were there.
--
Tim Wescott
Wescott Design Services
http://www.wescottdesign.com
Posting from Google? See http://cfaj.freeshell.org/google/
"Applied Control Theory for Embedded Systems" came out in April.
See details at http://www.wescottdesign.com/actfes/actfes.html
|
|
|
|
Author: RiscyDate: 02:41 19-03-07
|
|
I recommend Microchip PIC, starting 18F series because it has build in
multiplier. =A3100 for complier package and =A3100 for ICD2 programmer/
debugger. MPLAB is free.
8052 and other processor is a consideration, but I started with PIC
becuase it supported with training package, available offshelve,
extensive range and easy to use. I developed successful project based
on PIC. I'm now working on 2191 Analog Device DSP processor.
Damn google no longer accept my email and change into more complex
emil, so I say goodbye to this discussion group.
|
|
|
|
Author: Anthony FremontDate: 05:34 19-03-07
|
|
Tim Wescott wrote:
> Oh -- _not_ the Intersil/RCA 1802, unless you want to be an ace
> assembly language programmer. It was the very first processor I ever
> worked with, in 8th grade. I call it a NHISC -- Never Had an
> Instruction Set. I don't know if it's still around, but for quite a
> while it was the king of little space apps, because it had a huge
> geometry that could absorb cosmic rays without even noticing that
> they were there.
www.cosmacelf.com You would not believe the followng this thing still has.
It has become a cult thing with kids building them all over. I built mine
in 1978 IIRC.
|
|
|
|
Author: mpmDate: 08:46 19-03-07
|
|
Somebody said...
> but for me -- the processor has only 2 speeds -- the
> fastest it will do without a crystal -- and the fastest it will do with one
> :) I dont see the point of putting a slower crystal in then having to bust
> nuts to make the code work.
This gets back to the "intended-application" discussion.
While it's nice to have a "family" of chips you've spent the better
part of your adult engineering life understanding, there are times
when you simply must stretch the envelope.
Like my current project for instance.
It has to "rob" power from something that was never intended to
deliver it.
I need to powerdown more than roughly 90% of the time, drawing no more
than a few uA.
And not much more than 100uA for the other 10% of the time.
Oh, and for that, the clock speed is barely 20kHz (+/- 10%).
I think "MIPS" is a pipe dream for this one.
-mpm
|
|
|
|
Author: krwDate: 09:14 19-03-07
|
|
In article <1174272960.913098.53010@y66g2000hsf.googlegroups.com>,
me@linnix.info-for.us says...
> On Mar 18, 5:34 pm, krw <k...@att.bizzzz> wrote:
> > In article <1174265095.406744.259...@e65g2000hsc.googlegroups.com>,
> > m...@linnix.info-for.us says...
> >
> >
> >
> > > On Mar 18, 4:26 pm, krw <k...@att.bizzzz> wrote:
> > > > In article
<1174244224.891818.310...@e1g2000hsg.googlegroups.com>,
> > > > m...@linnix.info-for.us says...
> >
> > > > > > > I've played with a few different micros, but there
are still plenty left
> > > > > > > that I haven't. I do want to play with some of those
tiny 32 bit ARMs that
> > > > > > > have lots of memory and speed.
> >
> > > > > > ARMs don't thrill me much. Too much power.
> >
> > > > > Too much for what? The one I am using draws 70mA typical.
> > > > > Of course, you can run an AVR for less than 1mA.
> > > > > In my case, I use an AVR to power control an ARM.
> > > > > The ARM can do the job quicker so both can go back to sleep
ASAP.
> >
> > > > Power as in MIPS, not as in mA.
> >
> > > Why would too much MIPS bother you?
> > > You don't have to use pay per MIPS.
> >
> > Certainly you pay for MIPS. They don't give processors away free.
>
> The Arm and Avr are close to the same price, around $5 each.
AIUI PICs are in the $1 range.
> > > > If I want MIPS I'd go with a PPC of some sort.
> >
> > > I haven't seen any PPC in low pin count with internal memories yet.
> > > The Arm I am using is 64K flash, 8K sram on chip in 48 pins QFP.
> >
> > More variables not stated in the parameters.
>
> Nothing wrong with PPC, but I would not call it a uC.
Embedded is embedded.
> > > > > > I'd likely have to learn C. ;-)
> >
> > > > > Why? They work in assemblers too, even if I don't.
> >
> > > > With the MIPS available one wouldn't likely be doing bit-banging,
> > > > which is where assembler excels.
>
> So, you don't like it because it's too good for you?
(now you sound like Dimbulb) I'm not a fscking programmer. I do it
because it sometimes needs to be done.
--
Keith
|
|
|
|
Author: linnixDate: 11:35 19-03-07
|
|
> Like my current project for instance.
> It has to "rob" power from something that was never intended to
> deliver it.
Or last at long as possible on battery.
> I need to powerdown more than roughly 90% of the time, drawing no more
> than a few uA.
> And not much more than 100uA for the other 10% of the time.
> Oh, and for that, the clock speed is barely 20kHz (+/- 10%).
I need uA in stand-by. Full speed (Usb or Serial) while connected.
So, I need it very slow and very fast. For Serial, Avr tops at 19,000
baud
and Arm tops at 920,000 baud. Avr has Usb option but Arm hasn't.
>
> I think "MIPS" is a pipe dream for this one.
> -mpm
|
|
|
|
Author: Anthony FremontDate: 16:43 19-03-07
|
|
mpm wrote:
> Somebody said...
>
>> but for me -- the processor has only 2 speeds -- the
>> fastest it will do without a crystal -- and the fastest it will do
>> with one :) I dont see the point of putting a slower crystal in then
>> having to bust nuts to make the code work.
>
> This gets back to the "intended-application" discussion.
> While it's nice to have a "family" of chips you've spent the better
> part of your adult engineering life understanding, there are times
> when you simply must stretch the envelope.
>
> Like my current project for instance.
> It has to "rob" power from something that was never intended to
> deliver it.
The phone line?
> I need to powerdown more than roughly 90% of the time, drawing no more
> than a few uA.
That would be a high duty cycle for a phone line, unless you need to wake up
frequently to see if touch tones are being sent.
> And not much more than 100uA for the other 10% of the time.
> Oh, and for that, the clock speed is barely 20kHz (+/- 10%).
>
> I think "MIPS" is a pipe dream for this one.
Yep, sounds right in line for a PIC though. 12F683 (my new favorite) ~500
uA at 5V running full tilt on the internal oscillator (8MHz, 1% accuracy),
11uA at 32KHz (2V). Change speeds on the fly. Who needs to sleep? ;-)
You can sleep if you want, bit it'll cost you 50nA.
|
|
|
|
Author: jasenDate: 05:10 22-03-07
|
|
On 2007-03-16, Anthony Fremont <spam-not@nowhere.com> wrote:
> TT_Man wrote:
>>> As you said, PIC is king and it is for a reason, they work.
>>>
>> Only if you can get to grips with the appalling op code set..... OK
>> if you can program in C , I suppose.I can't/won't
>
> I only do assembler on the PIC too. What's wrong with the op-code set?
> It's RISC,
no it's not, it has too few registers to qualify.
> it has 35 instructions, it's not supposed to be luxurious. It's
> supposed to be functional and fast....it succeeds.
It always seemed kind of awkward and slow slow to me.
Bye.
Jasen
|
|
|
|
Author: jasenDate: 05:31 22-03-07
|
|
On 2007-03-17, bungalow_steve@yahoo.com <bungalow_steve@yahoo.com> wrote:
> the AVR series hasen't increased in performance in years (speed, a/d
> resolution, DMA, fifo buffers, divide instructions etc).
Many of them are doing 20 MIPS now, that wasn't available two years ago,
built-in full speed USB is new too,
It's an 8-bit microcontroller it doesn't need that extra stuff ...
Bye.
Jasen
|
|
|
|
Author: jasenDate: 05:58 22-03-07
|
|
On 2007-03-19, linnix <me@linnix.info-for.us> wrote:
>
>> Like my current project for instance.
>> It has to "rob" power from something that was never intended to
>> deliver it.
>
> Or last at long as possible on battery.
>
>> I need to powerdown more than roughly 90% of the time, drawing no more
>> than a few uA.
>> And not much more than 100uA for the other 10% of the time.
>> Oh, and for that, the clock speed is barely 20kHz (+/- 10%).
>
> I need uA in stand-by. Full speed (Usb or Serial) while connected.
> So, I need it very slow and very fast. For Serial, Avr tops at 19,000
> baud
that'd be because you're running such a slow clock.
at only 1.8432 Mhz you can 115200 baud. basically 1/16 your clock.
> and Arm tops at 920,000 baud.
yeah, but at what clock speed.
Bye.
Jasen
|
|
|
|
Author: linnixDate: 11:07 22-03-07
|
|
On Mar 22, 1:58 am, jasen <j...@free.net.nz> wrote:
> On 2007-03-19, linnix <m...@linnix.info-for.us> wrote:
>
>
>
> >> Like my current project for instance.
> >> It has to "rob" power from something that was never intended to
> >> deliver it.
>
> > Or last at long as possible on battery.
>
> >> I need to powerdown more than roughly 90% of the time, drawing no more
> >> than a few uA.
> >> And not much more than 100uA for the other 10% of the time.
> >> Oh, and for that, the clock speed is barely 20kHz (+/- 10%).
>
> > I need uA in stand-by. Full speed (Usb or Serial) while connected.
> > So, I need it very slow and very fast. For Serial, Avr tops at 19,000
> > baud
>
> that'd be because you're running such a slow clock.
> at only 1.8432 Mhz you can 115200 baud. basically 1/16 your clock.
No, it won't. At 2 MHz, AVR have lock-ups for 38,400 baud.
My AVR clock toggles between 2 MHz and 32KHz.
>
> > and Arm tops at 920,000 baud.
>
> yeah, but at what clock speed.
>
20 MHz.
> Bye.
> Jasen
|
|
|
|
Author: Anthony FremontDate: 07:55 23-03-07
|
|
jasen wrote:
> On 2007-03-16, Anthony Fremont <spam-not@nowhere.com> wrote:
>> TT_Man wrote:
>>>> As you said, PIC is king and it is for a reason, they work.
>>>>
>>> Only if you can get to grips with the appalling op code set..... OK
>>> if you can program in C , I suppose.I can't/won't
>>
>> I only do assembler on the PIC too. What's wrong with the op-code
>> set? It's RISC,
>
> no it's not, it has too few registers to qualify.
By whose definition? It stands for Reduced Instruction Set. 35
instructions is pretty reduced IMO.
>> it has 35 instructions, it's not supposed to be luxurious. It's
>> supposed to be functional and fast....it succeeds.
>
> It always seemed kind of awkward and slow slow to me.
Compared to what? 10MIPs on a few mA is pretty good in my book.
|
|
|
|
Author: jasenDate: 07:57 23-03-07
|
|
On 2007-03-22, linnix <me@linnix.info-for.us> wrote:
> On Mar 22, 1:58 am, jasen <j...@free.net.nz> wrote:
>> On 2007-03-19, linnix <m...@linnix.info-for.us> wrote:
>>
>>
>>
>> >> Like my current project for instance.
>> >> It has to "rob" power from something that was never intended
to
>> >> deliver it.
>>
>> > Or last at long as possible on battery.
>>
>> >> I need to powerdown more than roughly 90% of the time, drawing no more
>> >> than a few uA.
>> >> And not much more than 100uA for the other 10% of the time.
>> >> Oh, and for that, the clock speed is barely 20kHz (+/- 10%).
>>
>> > I need uA in stand-by. Full speed (Usb or Serial) while connected.
>> > So, I need it very slow and very fast. For Serial, Avr tops at 19,000
>> > baud
>>
>> that'd be because you're running such a slow clock.
>> at only 1.8432 Mhz you can 115200 baud. basically 1/16 your clock.
>
> No, it won't. At 2 MHz, AVR have lock-ups for 38,400 baud.
"lock ups?"
The attiny2313 "data sheet" suggests it should be capable of 250Kbps
(asynchronous serial) at 2mhz
With a 2MHz clock 38400 baud isn't really an option on that hardware,
35714.3 or 41666.7 are the closest choices.
If you reduce the clock to 1.8432 Mhz (should be a standard size)
38400.0 is available (as are the other standard speeds upto 230400)
> My AVR clock toggles between 2 MHz and 32KHz.
Not with the uart running I hope!
>> > and Arm tops at 920,000 baud.
>>
>> yeah, but at what clock speed.
>
> 20 MHz.
How does it manage that? 920K doesn't divide 20M, is there an internal PLL
or something?
Anyway it seems kind of slow :^)
Some people bit-bang USB at 1.5Mb/s on 12Mz AVRs. (as a non-interruptable
foreground task) again the trick is to pick a clock rate that's a
sufficiently high multiple of the data rate.
Bye.
Jasen
|
|
|
|
Author: Anthony FremontDate: 08:53 23-03-07
|
|
jasen wrote:
> On 2007-03-17, bungalow_steve@yahoo.com <bungalow_steve@yahoo.com>
> wrote:
>
>> the AVR series hasen't increased in performance in years (speed, a/d
>> resolution, DMA, fifo buffers, divide instructions etc).
>
> Many of them are doing 20 MIPS now, that wasn't available two years
> ago, built-in full speed USB is new too,
20 MIPS, on a MEGA. Those aren't backwards compatible with the tradition
AVRs are they?
> It's an 8-bit microcontroller it doesn't need that extra stuff ...
Speak for yourself. Since when is A/D resolution not important for an 8
bitter?
|
|
|
|
Author: krwDate: 09:49 23-03-07
|
|
In article <1307g1itfi6is9d@news.supernews.com>, spam-not@nowhere.com
says...
> jasen wrote:
> > On 2007-03-16, Anthony Fremont <spam-not@nowhere.com> wrote:
> >> TT_Man wrote:
> >>>> As you said, PIC is king and it is for a reason, they work.
> >>>>
> >>> Only if you can get to grips with the appalling op code set..... OK
> >>> if you can program in C , I suppose.I can't/won't
> >>
> >> I only do assembler on the PIC too. What's wrong with the op-code
> >> set? It's RISC,
> >
> > no it's not, it has too few registers to qualify.
>
> By whose definition? It stands for Reduced Instruction Set. 35
> instructions is pretty reduced IMO.
Actually, it stands for "Reduced Instruction Set Complexity". It has
nothing to do with the number of instructions (PowerPC is certainly
RISC, yet has hundreds of instructions in even more varieties),
rather the complexity of the instructions. For example, no
arithmetic operations on memory are allowed, only load/stores.
> >> it has 35 instructions, it's not supposed to be luxurious. It's
> >> supposed to be functional and fast....it succeeds.
> >
> > It always seemed kind of awkward and slow slow to me.
>
> Compared to what? 10MIPs on a few mA is pretty good in my book.
>
--
Keith
|
|
|
|
Author: John BarrettDate: 12:57 23-03-07
|
|
"krw" <krw@att.bizzzz> wrote in message
news:MPG.206da510f80eb5e298a216@news.individual.net...
> In article <1307g1itfi6is9d@news.supernews.com>, spam-not@nowhere.com
> says...
>> jasen wrote:
>> > On 2007-03-16, Anthony Fremont <spam-not@nowhere.com> wrote:
>> >> TT_Man wrote:
>> >>>> As you said, PIC is king and it is for a reason, they work.
>> >>>>
>> >>> Only if you can get to grips with the appalling op code set.....
OK
>> >>> if you can program in C , I suppose.I can't/won't
>> >>
>> >> I only do assembler on the PIC too. What's wrong with the op-code
>> >> set? It's RISC,
>> >
>> > no it's not, it has too few registers to qualify.
>>
>> By whose definition? It stands for Reduced Instruction Set. 35
>> instructions is pretty reduced IMO.
>
> Actually, it stands for "Reduced Instruction Set Complexity". It has
> nothing to do with the number of instructions (PowerPC is certainly
> RISC, yet has hundreds of instructions in even more varieties),
> rather the complexity of the instructions. For example, no
> arithmetic operations on memory are allowed, only load/stores.
>
>> >> it has 35 instructions, it's not supposed to be luxurious. It's
>> >> supposed to be functional and fast....it succeeds.
>> >
>> > It always seemed kind of awkward and slow slow to me.
>>
>> Compared to what? 10MIPs on a few mA is pretty good in my book.
>>
> --
> Keith
RISC essentially means that EVERY instruction takes ONE clock cycle, so your
clock speed is your IPS -- CISC chips like the 80x86 take anywhere from
4-??? instructions per clock, they internally decode instructions through a
micro-code rom in the CPU that sequences the internal processing elements of
the chip through the steps neccessary to perform the instruction -- for
instance -- a single instruction may read memory, add it to a register, and
write the result back to memory -- all in one instruction, but across
multiple clock cycles.
Therefore there are things a CISC chip can do in one ASM instruction that a
RISC chip cannot do, simply because there is no way to perform the operation
in a single clock cycle... for instance -- the 80x86 has a single
instruction memory copy capability for moving data around -- makes things a
little easier on the compiler developers.
|
|
|
|
|
|
|
|
|
Contact | Electronic Portal
|
|
|
