home *** CD-ROM | disk | FTP | other *** search
- Path: w254zrz.zrz.TU-Berlin.DE!rawneiha
- From: rawneiha@w254zrz.zrz.TU-Berlin.DE (Philipp Boerker)
- Newsgroups: comp.sys.amiga.programmer
- Subject: Re: Processors
- Date: 28 Mar 1996 14:28:40 GMT
- Organization: Technical University Berlin, Germany
- Message-ID: <4je7mo$o6a@brachio.zrz.TU-Berlin.DE>
- References: <4iri6d$lim@columba.udac.uu.se> <1665.6656T1237T1226@teclink.net> <4j5rm3$cq9@brachio.zrz.TU-Berlin.DE> <2862.6660T1334T2954@teclink.net>
- NNTP-Posting-Host: w254zrz.zrz.tu-berlin.de
-
- rad@teclink.net (rad) writes:
-
-
- >>No, there is no double clock, there is only a clock, that is delayed half a
- >>cycle. The fractional cycle is only a timing problem that needs the second
- >>clock for handling! Believe me!
-
- >Ok, you're going to make this difficult. First from the 68040 User's manual
- >MC68040UM/AD Rev. 1 Page 5-2 to 5-3 Table 5-1 "Signal Index":
-
- >signal name Mnemonic Function
- >Bus Clock BCLK Clock input used to derive all bus signal timing
- >Processor Cl PCLK Clock input used for internal logic timing. The PCLK
- > frequency is exactly 2x the BCLK frequency.
-
- >I refered to the PCLK as the "double" clock since the term would be more
- >meaningful to those not familiar with the data-book. The CPU speed rating is
- >the rated BCLK frequency. Therefor there IS a clock at twice this frequency.
-
- Have you ever (really) looked inside a computer? There is one oszillator
- in it (a small metal 'box'). The frequency of this oscillator is written on
- top of it. The number on it is the highest frequency that is used in the whole
- system. Note: it is possible to half the frequency of a oscillator but it is
- *impossible* to double it without having an oszillator at a higher frequency!
- This means that the 40 MHz on this oscillator IS the doubled clock, and it
- is halfed (on the board) for the bus (20 MHz = very reasonable busclock compared to
- a 40 MHz bus). The 040 delays this 40 MHz clock for half a cycle and uses the 2nd
- clock for the mentioned timing problems in the 040 FPU.
-
-
- >There however is no mention in the user's manual of a clock delayed half a
- >cycle. Perhaps you could give a reference for this?
-
- As you mentioned it is only a *user* (that is a person who wants to build
- a computer with that chip) manual and therfor no inside information are
- given.
-
-
- >I would like to know
- >how exactly integer and fraction cycle instructions can occur simultaneously
- >without effectively operating at the double clock frequency?
-
- Every single transistor that is `passed` by the clock-voltage delays the signal
- for a very short time. Since that signal (not only the clock but also the
- computations) pass a lot of transistors in the FPU (that is usually at least as big
- as the whole rest of the CPU = many,many transistors) it can happen that your result
- will be late for some time - round that up to .5 cycles and you know where the
- fractional cycle comes from.
-
-
- Do you believe me now ?
-
- Greets,
- Phil.
- grond/matrix
-