Re: Historical evolution of CPU perf

Liste des GroupesRevenir à c arch 
Sujet : Re: Historical evolution of CPU perf
De : admin (at) *nospam* 127.0.0.1 (Kerr-Mudd, John)
Groupes : comp.arch
Date : 09. Oct 2024, 20:18:40
Autres entêtes
Organisation : Dis
Message-ID : <20241009201840.31c1e818f9d5e789691c718b@127.0.0.1>
References : 1 2
User-Agent : Sylpheed 3.7.0 (GTK+ 2.24.30; i686-pc-mingw32)
On Wed, 9 Oct 2024 13:23:22 -0500
BGB <cr88192@gmail.com> wrote:

On 10/9/2024 11:33 AM, Stefan Monnier wrote:
I'm looking for a chart illustrating the evolution of CPU performance
(e.g. single-threaded or maybe performance per watt) over the years,
covering something like 1990-2020.
 
Any good candidates?
 
 
Yeah, I would also like something like this, or maybe some way to
"sensibly" compare the relative performance of modern stuff with vintage
stuff.
 
Like, for example, I can't make sense of whether the performance of my
current project is similar to similarly-clocked vintage hardware, or
potentially significantly faster.
 
Based simply on Dhrystone score, it would likely be placed in a similar
area to a 90s era PowerPC in terms of perf/MHz.
 
 
 
But, if I add an early 2000s laptop as a reference point, stuff gets
weird. In various benchmarks, the difference in performance is
significantly smaller than the relative difference in clock-speed.
 
Though, the laptop is also break-even with a RasPi2 in terms of general
perf (in theory, the laptop should be faster). Seems like the laptop
suffers a relative deficit in terms of memory bandwidth (*).
 
But, can note that Dhrystone doesn't really measure memory bandwidth...
 
 
*: The 100MHz DDR1 RAM in the laptop gets roughly 7x the memory
bandwidth of a 16-bit DDR2 chip being run at 50MHz. Sort of makes sense
if one assumes 4x the width and 2x the clock-speed.
 
I am not sure if just the laptop, or if RAM access in general was
proportionally slower in the 90s. Or, if it is just a case that late 90s
/ early 2000s, CPUs had gotten faster much faster than RAM had gotten
faster, so there was a performance lag here.
 
I suspect it may be the latter, if one linearly extrapolated backwards,
it would mean 486 PCs running at ~ 10-16 MB/sec for RAM bandwidth, which
in my own testing seems insufficient to run Doom at acceptable speeds
(actual 486's having no issues running Doom).
 

As a complete non-cpu chap, what I care about is (my) consumer experience;
- i.e no delays. So ditch the fancy graphics - get me a fast boot time and
a responsive OS. Only a few are doing FFTs & so-called AI.

--
Bah, and indeed Humbug.

Date Sujet#  Auteur
9 Oct 24 * Historical evolution of CPU perf12Stefan Monnier
9 Oct 24 `* Re: Historical evolution of CPU perf11BGB
9 Oct 24  `* Re: Historical evolution of CPU perf10Kerr-Mudd, John
9 Oct 24   `* Re: Historical evolution of CPU perf9MitchAlsup1
11 Oct 24    `* Re: Historical evolution of CPU perf8Sarr Blumson
11 Oct 24     +* Re: Historical evolution of CPU perf3BGB
11 Oct 24     i`* Re: core memory, Historical evolution of CPU perf2John Levine
12 Oct 24     i `- Re: core memory, Historical evolution of CPU perf1Stephen Fuld
11 Oct 24     +- Re: Historical evolution of CPU perf1Thomas Koenig
12 Oct 24     `* Re: Historical evolution of CPU perf3Michael S
12 Oct 24      `* Re: Historical evolution of CPU perf2Lars Poulsen
12 Oct 24       `- Re: core memory, Historical evolution of CPU perf1John Levine

Haut de la page

Les messages affichés proviennent d'usenet.

NewsPortal