| Author |
Message |
Guest
|
 Posted:
Fri Sep 23, 2005 4:15 pm Post subject:
Is the x86 clock stoppable? |
|
|
Do modern Intel and AMD processors operate down to zero clock speed?
On the PC architecture, is the processor clock independent of all other
system clocks, so that it can be stopped and resumed arbitrarily? |
|
| Back to top |
|
 |
CJT
Guest
|
| Posted:
Fri Sep 23, 2005 10:31 pm Post subject:
Re: Is the x86 clock stoppable? |
|
|
andrewspencers@yahoo.com wrote:
| Quote: | Do modern Intel and AMD processors operate down to zero clock speed?
On the PC architecture, is the processor clock independent of all other
system clocks, so that it can be stopped and resumed arbitrarily?
Homework? |
--
The e-mail address in our reply-to line is reversed in an attempt to
minimize spam. Our true address is of the form che...@prodigy.net. |
|
| Back to top |
|
|
Guest
|
| Posted:
Fri Sep 23, 2005 11:45 pm Post subject:
Re: Is the x86 clock stoppable? |
|
|
CJT wrote:
| Quote: | Homework?
I haven't had homework for a very long time. |
I vaguely remember being annoyed once upon a time about an unstoppable
6502. (Maybe because it used dram instead of sram for its registers, or
was there some other reason?) At the time I was told that CMOS
processors were stoppable, and that therefore maybe I'd want a 65C02.
Since AMD's and Intel's modern x86 processors are CMOS, and surely use
only sram registers, I assume that they're stoppable. But I wanted to
be sure.
I'm simply thinking about the possibility of a "pause" button on the
front of a computer, to be used instead of the power or reset button as
the emergency button of last resort to stop the operation of malicious
software, so that potentially valuable forensic evidence wouldn't be
wiped from the processor or from main memory.
That same idea was also the reason for my other posting in this
newsgroup at the same time (with subject "PC reset button resets
memory?"). |
|
| Back to top |
|
|
CJT
Guest
|
| Posted:
Sat Sep 24, 2005 12:15 am Post subject:
Re: Is the x86 clock stoppable? |
|
|
andrewspencers@yahoo.com wrote:
| Quote: | CJT wrote:
Homework?
I haven't had homework for a very long time.
I vaguely remember being annoyed once upon a time about an unstoppable
6502. (Maybe because it used dram instead of sram for its registers, or
was there some other reason?) At the time I was told that CMOS
processors were stoppable, and that therefore maybe I'd want a 65C02.
Since AMD's and Intel's modern x86 processors are CMOS, and surely use
only sram registers, I assume that they're stoppable. But I wanted to
be sure.
I'm simply thinking about the possibility of a "pause" button on the
front of a computer, to be used instead of the power or reset button as
the emergency button of last resort to stop the operation of malicious
software, so that potentially valuable forensic evidence wouldn't be
wiped from the processor or from main memory.
That same idea was also the reason for my other posting in this
newsgroup at the same time (with subject "PC reset button resets
memory?").
They're generally dynamic devices. Clock requirements are in the |
data sheets.
--
The e-mail address in our reply-to line is reversed in an attempt to
minimize spam. Our true address is of the form che...@prodigy.net. |
|
| Back to top |
|
|
glen herrmannsfeldt
Guest
|
| Posted:
Sat Sep 24, 2005 12:15 am Post subject:
Re: Is the x86 clock stoppable? |
|
|
andrewspencers@yahoo.com wrote:
| Quote: | Do modern Intel and AMD processors operate down to zero clock speed?
On the PC architecture, is the processor clock independent of all other
system clocks, so that it can be stopped and resumed arbitrarily?
|
Intel has traditionally built processors with a minimum clock
speed, at least from the 8080 to the 8086. One advantage of
the Z80 over the 8080 was that is used static logic so that
the clock could be stopped or slowed down.
More modern processors have a PLL between the external interface
and the internal logic which will have a restricted frequency
range, independent of the use of dynamic logic.
I believe, though, that there are ways to pause the software with
the appropriate interrupts. That is, it is fairly easy to write
a single step debugger.
The real reason for desiring to stop the clock is for hardware
debugging.
-- glen |
|
| Back to top |
|
|
Anthony J. Albert
Guest
|
| Posted:
Sat Sep 24, 2005 12:15 am Post subject:
Re: Is the x86 clock stoppable? |
|
|
On 23 Sep 2005 11:45:05 -0700, andrewspencers@yahoo.com wrote:
| Quote: | CJT wrote:
Homework?
I haven't had homework for a very long time.
I vaguely remember being annoyed once upon a time about an unstoppable
6502. (Maybe because it used dram instead of sram for its registers, or
was there some other reason?) At the time I was told that CMOS
processors were stoppable, and that therefore maybe I'd want a 65C02.
Since AMD's and Intel's modern x86 processors are CMOS, and surely use
only sram registers, I assume that they're stoppable. But I wanted to
be sure.
I'm simply thinking about the possibility of a "pause" button on the
front of a computer, to be used instead of the power or reset button as
the emergency button of last resort to stop the operation of malicious
software, so that potentially valuable forensic evidence wouldn't be
wiped from the processor or from main memory.
That same idea was also the reason for my other posting in this
newsgroup at the same time (with subject "PC reset button resets
memory?").
|
Despite the advantages of speed of static memory cells, for the
registers, I wouldn't be surprised if there were at least some on-chip
DRAM, especially in on-chip cache, because of the smaller size per
cell.
If that's the case, then I'd bet that there's a certain minimum speed
below which you couldn't trust the processor.
Anthony Albert |
|
| Back to top |
|
|
Scott Moore
Guest
|
| Posted:
Tue Sep 27, 2005 12:15 am Post subject:
Re: Is the x86 clock stoppable? |
|
|
Anthony J. Albert wrote On 09/23/05 14:42,:
| Quote: | On 23 Sep 2005 11:45:05 -0700, andrewspencers@yahoo.com wrote:
CJT wrote:
Homework?
I haven't had homework for a very long time.
I vaguely remember being annoyed once upon a time about an unstoppable
6502. (Maybe because it used dram instead of sram for its registers, or
was there some other reason?) At the time I was told that CMOS
processors were stoppable, and that therefore maybe I'd want a 65C02.
Since AMD's and Intel's modern x86 processors are CMOS, and surely use
only sram registers, I assume that they're stoppable. But I wanted to
be sure.
I'm simply thinking about the possibility of a "pause" button on the
front of a computer, to be used instead of the power or reset button as
the emergency button of last resort to stop the operation of malicious
software, so that potentially valuable forensic evidence wouldn't be
wiped from the processor or from main memory.
That same idea was also the reason for my other posting in this
newsgroup at the same time (with subject "PC reset button resets
memory?").
Despite the advantages of speed of static memory cells, for the
registers, I wouldn't be surprised if there were at least some on-chip
DRAM, especially in on-chip cache, because of the smaller size per
cell.
If that's the case, then I'd bet that there's a certain minimum speed
below which you couldn't trust the processor.
Anthony Albert
|
They can also have dynamic logic on the chip (horrors!), just because
it's CMOS does not mean no dynamic logic.
If you want a stop clock x86, then get one. Low power/embedded x86
CPUs will have specific methods to stop the clock, perhaps even a gating
line.
As another poster suggested the minimum clock frequency will be found
in the hardware manual for the CPU in question. |
|
| Back to top |
|
|
|
|
|
|
FAQ
Memberlist
Register
Profile
Log in to check your private messages
Log in