Re: memory reading and writing
From: wolfgang kern (nowhere_at_nevernet.at)
Date: 07/18/04
- Next message: hutch--: "Re: Why RosAsm Breaks on a large number of symbols"
- Previous message: Gyps: "Re: memory reading and writing"
- In reply to: Gyps: "Re: memory reading and writing"
- Next in thread: Robert Redelmeier: "Re: memory reading and writing"
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Date: Sun, 18 Jul 2004 12:14:56 +0200
"Gyps" asked:
| We all seem to throw out frequencies, but how does, say, 133Mhz
| actually translate into time for a single memory access??
time= 1/frequency ? ;)
| I heard somewhere that the access speed for typical RAM are
| around 70 nanoseconds...but, as you say, there are so many
| specialised devices and complicating factors, it's probably
| not accurate to determine the access speed by doing some simple
| math...
the timing printed onto RAM-chips means access cycle time,
so a 70 nS RAM is a slow <15MHz device found in my i286 8/12MHz PC.
| > Consider something like a 3GHz machine with only a 200Mhz bus or
| > whatever...makes quite a bit of difference...which is why we
| > notice that there's a kind of "trend" towards taking things away
| > from the CPU and distributing the processing around...
| Yes, nowadays, simple microprocessing chips are a common part of
| most peripheral devices like disk-drives, VGA, modems etc.
Static memory (like L1-cache) is quite fast (>2GHz), but expensive.
The cheaper dynamic RAM (just capacitor-cells) had become
fast too recently (up to 200MHz already = 5nS) or look
at newer graphics card's RAM-chips with >500MHz (2nS) dynamic memory.
__
wolfgang
- Next message: hutch--: "Re: Why RosAsm Breaks on a large number of symbols"
- Previous message: Gyps: "Re: memory reading and writing"
- In reply to: Gyps: "Re: memory reading and writing"
- Next in thread: Robert Redelmeier: "Re: memory reading and writing"
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]