6502s are faster than all modern computers!

[commodorejohn]

sark02 wrote:

This link: https://pavelfatin.com/typing-with-pleasure/ (linked from the subject webpage) illustrates how editor latency is a function of the editor application more than any intrinsic system problem. Editors that do on-the-fly spell-checking, autocompletion, or code suggestion are, necessarily, burdening every keypress with algorithms, pattern-matching, database lookups, etc. It's no wonder that they can feel sluggish, or behind the curve. But in the end it's an application complaint, not a platform constraint.

That would be a sensible argument if you were to completely ignore the fact that the measurements in the original article were taken using an application that doesn't do any of that: the command shell/terminal. (Yes, modern shells have tab-completion, but that's not the same thing as on-the-fly autocomplete and should only introduce meaningful lag when actually invoked.)

Quote:

As soon as a keyboard matrix is removed from the memory bus and put on the end of a serial link (be it PS/2 or USB 3.0), the absolute keyboard to photon latency is increased, but from a human interface perspective that increase is not significant.

This may be true; however, it does not absolve the OS from responsibility for latency issues, because there are much more significant layers of potential delay that an event must go through before ever arriving at the application than the keyboard serial link.

Quote:

I think it's absurd to make any real claim that modern computers are slower or higher-latency than 70s and 80s examples.

Despite the sourced and measured data in the article indicating pretty much exactly that?

Quote:

I mean: you can if it makes you feel happy, but I don't think it's useful.

And again, you personally may not feel that it matters to you. That's fine. You do whatever you like. But that doesn't change the measured data on the subject, nor does it mean that other people aren't impacted by this.

Quote:

Just because you were young and vital in the 70s doesn't make computers of the 70s better in any practical and useful measure than those of today.

And this is a nonsensical non-argument, not least because I wasn't even alive in the '70s.

[sark02]

commodorejohn wrote:

And again, you personally may not feel that it matters to you. That's fine. You do whatever you like. But that doesn't change the measured data on the subject, nor does it mean that other people aren't impacted by this.

I agree.

[BigEd]

I think what we see here is that a provocative headline will provoke some people.

We usually do a lot better than this.

I know it wasn't meant to be harmful, but the provocative title was probably not the best move. Everyone who has got themselves worked up and then posted should also take responsibility for raising the temperature instead of improving the quality of discussion.

If you feel you're angry, stop typing. If there's something posted which you disagree with, rest assured that many other readers will already have disagreed with it, as you do. If there's something which seems mistaken, let it stand as its own advertisement of mistaken thinking.

[BigEd]

BTW I see Dan Luu's article also was posted on Hacker News recently:
https://news.ycombinator.com/item?id=19443076

HN is usually rather good for informative discussions although sometimes there are people who haven't got the memo. As a moderated forum, sometimes there's intervention.

There's a link within that discussion to a thread here where some developers explain some of their latency reduction tactics in a specific low-latency application.

[Chromatix]

Yesterday I had to edit slides for an important talk I was due to give - in LibreOffice (not my first choice). The input-to-display lag was extremely annoying, and well beyond what I'd normally expect from the machine I ran it on. And it's not as if the layout was anything unusual - just a background, a title, and a main text box on most of the slides.

(In case you wonder what I do all day: here it is.)

[ElEctric_EyE]

Maybe the OP meant faster boot-up times? Surely, there's no argument there. I love the quick boot-up of the Commodore-64. With the advancement of technology, why have the boot-up times increased? It's sickening and a disgrace to the technology. Unless something is going on in the background.

[Tor]

My laptop is up from cold to full desktop in five seconds (running Linux, but my wife's similar laptop on Win10 isn't that much slower), which is at least good progress when compared to what it used to be. And then let's not forget that booting a MicroVAX back in the eighties would take at least 15 minutes. Not that it's much faster booting an AIX box today - due to hundreds of individual self-checks.

[whartung]

ElEctric_EyE wrote:

Maybe the OP meant faster boot-up times? Surely, there's no argument there. I love the quick boot-up of the Commodore-64. With the advancement of technology, why have the boot-up times increased? It's sickening and a disgrace to the technology. Unless something is going on in the background.

Because of all the self-diagnostics and waiting for the sub systems. Modern machines are waiting for far more than a UART to settle down to come on line.

Then there's the waiting for the internal processes to start. Things like phoning home, checking for upgrades, etc.

Much work has been done to try and parallelize start up processes to help improve boot times.

Then, there's systems like my Mac or my wife MacBook -- they simply never get turned off, they just go dormant. They come back to life very, very quickly.

Worse thing I have to suffer is when something decides to wake up the I/O bus and tickle an external drive to spin up, and having to wait for that.

[dolomiah]

whartung wrote:

ElEctric_EyE wrote:

Maybe the OP meant faster boot-up times? Surely, there's no argument there. I love the quick boot-up of the Commodore-64. With the advancement of technology, why have the boot-up times increased? It's sickening and a disgrace to the technology. Unless something is going on in the background.

Because of all the self-diagnostics and waiting for the sub systems. Modern machines are waiting for far more than a UART to settle down to come on line.

Then there's the waiting for the internal processes to start. Things like phoning home, checking for upgrades, etc.

Much work has been done to try and parallelize start up processes to help improve boot times.

Then, there's systems like my Mac or my wife MacBook -- they simply never get turned off, they just go dormant. They come back to life very, very quickly.

Worse thing I have to suffer is when something decides to wake up the I/O bus and tickle an external drive to spin up, and having to wait for that.

I hate to tell you, but I think the point about the boot up times and the quick boot of the C64 was a subtle joke - and a good one!

But your straight answer makes fair points!

[GARTHWILSON]

My laptop, which is faster than my desktop, takes four seconds to come up if it was only in suspend. That does not include time to type my password. If it was truly off, it's more like 75 seconds. Then it's ready to start loading applications, usually starting with the browser.

[White Flame]

The C64 only does the following tests at bootup, to my recollection:

• Check memory, by testing bytes
• Check if a cartridge is installed
• Maybe test if it's in PAL or NTSC mode and set up the jiffy timer

It doesn't talk to any peripherals on the serial bus. But if you consider "booting up" the C64 to also include loading in a utility environment from a disk drive, that'd be very slow.

However, this was also perceived as an annoyance in the 80s, that it couldn't initialize anything customized by the user from its storage devices, and that would have made it as slow as everything else, once you start using that feature.