OT Dual core CPUs versus faster single core CPUs?

CutePDF is not a reader. It coverts just about anything that can be printed into a PDF file. It's a PDF creator or more specifically, a Windoze front end for Ghostscript (which incidentally is open sourced). It is not a PDF editor as that is a different product:

--
Jeff Liebermann     jeffl@cruzio.com
150 Felker St #D    http://www.LearnByDestroying.com
Santa Cruz CA 95060 http://802.11junk.com
Skype: JeffLiebermann     AE6KS    831-336-2558
Reply to
Jeff Liebermann
Loading thread data ...

Your next nym should be MissGrundy.

John

Reply to
John Larkin

Oh, I get it. All those ghastly-grammar, incomprehensible error messages are actually elegant humor.

Like the way everybody calls it a "disk drive." How dull of me not to notice.

I suppose prongie spells is "kernel" because his real expertise is with corn.

John

Reply to
John Larkin

For which I am extremely grateful.

CutePDF is a pdf creator; it works as a printer driver. It's so fast that, first few times you run it, you think it's not working. It is.

I didn't say it was required. I said that it would, if properly done, simplify the overall structure and make it easier to build a crash-proof OS. Of course, anybody with enough programmers and advanced tools can screw up any architecture.

Why? Transistors keep getting faster, and the real limit to cpu power is thermal. A CPU doesn't take many transistors, so doing X amount of computing dissipates about the same power whether it's done on 1 CPU or 256. Less, if you avoid context switching overhead.

I guess that if we are hitting a wall

Exactly my point. We don't need more speed, and we sure don't need more complexity. Let's use all those transistors to make things simpler and more reliable. WIntel was and still is decades behind other architectures in applying fundamental hardware protections to computing, hence atrocities like buffer overflow exploits.

A request to print should start printing NOW. It would if a CPU was assigned to do nothing but print your file.

Does it really take

Acrobat and Windows are salient examples of what's broken about computing. Imagine grannie trying to zap a trojan by editing the registry!

John

Reply to
John Larkin

Sorry, I was looking at Foxit when I wrote that. My point is that none of the open source PDF programs actually do what Acrobat does. The commercial programs that do are paid for programs and I have no idea if they work any better. Foxit puts stamps on each page it modifies. I also see similar crappy behavior to Acrobat. For example, every time I switch focus away from the program and back, the toolbars become disorganized and take up four rows instead of two. If the bleeding program can't even remember where I put the toolbars, how well is it going to handle the hard stuff?

So for the short term, I am stuck with Acrobat. As crappy as it is, it is the devil I know.

I don't mean to be rude, but that is not saying anything. "IF properly done" is a catch phrase that eliminates any meaning. If operating systems were "properly done" we wouldn't even be having this discussion. But if you have some basis for saying that multi- processor actually facilitate correctly working software, I would like to hear it. So far everything you have posted applies to any software, on single processors as well as multi-processors.

Transistors may get faster, but systems don't. The critical limits are being reached where logic built of smaller geometries do *NOT* get faster. I thought this was discussed already. The smaller geometries require lower voltages. The lower voltages are reaching the point where they turn on and off fully. This is limiting the improvements they can make in speed. Why else have CPUs been limited to about 3 GHz for the last 5 or 6 years?

Transistors are getting smaller, but the circuits they are in are not getting significantly faster.

I hate to tell you, but using hundreds of processors *is* complexity compared to using one processor.

Why do you say that? Printing on my 1.4 GHz machine often is limited by the CPU speed. On a chip with hundreds of CPUs, each one will be slower than a single CPU using the same technology. So that print job will take longer to process.

I agree 100% with that statement. But nothing you have said relates to multi-processors.

Your point about Granny is very valid. I have a friend who is in his

70's. He is the sort that is self taught and been a welder, AC repairman, electrician and general all around mechanic and machinist. So the man is not at all dumb. But he has no interest in learning about computers. They are basically wicked, cantankerous, malodorous piles of scrap metal. They don't follow any line of normal reasoning and can only be handled in unique ways that require you to learn a new mindset. There are some thing he would like to do with a PC, such as record his cassette tapes on to CD. But I can't figure out a way to educate him on how to do this sort of stuff.

Rick

Reply to
rickman

I use Acrobat v4 for creating PDF's and v7 for reading new stuff that balks at v4. I also use v7 for "signing".

If your toolbars are moving it's most likely cockpit error. Set them the way you want, then exit and restart so that your settings are preserved.

[snip]

Sounds familiar. My just-months-shy-of-90 father can do anything but cope with PC's (in his younger years he was an electrician, rode motorcycles, owned a radio and TV repair shop and a hardware store).

But he still uses the PC I bought him to write letters and print photographs; but he balked at the Internet and had me cancel his account (I was paying for it).

...Jim Thompson

--
| James E.Thompson, P.E.                           |    mens     |
| Analog Innovations, Inc.                         |     et      |
| Analog/Mixed-Signal ASIC\'s and Discrete Systems  |    manus    |
| Phoenix, Arizona  85048    Skype: "skypeanalog"  |             |
| Voice:(480)460-2350  Fax: Available upon request |  Brass Rat  |
| E-mail Icon at http://www.analog-innovations.com |    1962     |
             
         America: Land of the Free, Because of the Brave
Reply to
Jim Thompson

Yes, of course, I should have known that software was not capable of having problems. The source of the trouble has to be me! I guess that also applies to Microsoft programs!

Reply to
rickman

Data is also cached, and then there is also total memory bandwidth which makes doing video so hard. See Amdahl's Law.

Reply to
JosephKK

Actually, it seems to be power dissipation.

Reply to
JosephKK

In that respect I was positively surprised. Did a few >1/2h heavy duty SPICE sims lately and the CPU fan barely picked up speed. It's very quiet.

--
Regards, Joerg

http://www.analogconsultants.com/

"gmail" domain blocked because of excessive spam.
Use another domain or send PM.
Reply to
Joerg

1/2 hour is NOT "heavy-duty" ;-)

...Jim Thompson

--
| James E.Thompson, P.E.                           |    mens     |
| Analog Innovations, Inc.                         |     et      |
| Analog/Mixed-Signal ASIC\'s and Discrete Systems  |    manus    |
| Phoenix, Arizona  85048    Skype: "skypeanalog"  |             |
| Voice:(480)460-2350  Fax: Available upon request |  Brass Rat  |
| E-mail Icon at http://www.analog-innovations.com |    1962     |
             
         America: Land of the Free, Because of the Brave
Reply to
Jim Thompson

I have seen cases where a process takes 100% of both CPUs and you can't kill the process. In those cases you can set the affinity to only one CPU, so the other CPU is free to let you work on fixing the problem.

--

Reply in group, but if emailing add another
zero, and remove the last word.
Reply to
Tom Del Rosso

They will find a way to crash it. The processes will need some transfer of data and control.

--

Reply in group, but if emailing add another
zero, and remove the last word.
Reply to
Tom Del Rosso

Run increasingly bloated programs on severely hardware-protected processors, whether you want to or not.

--

Reply in group, but if emailing add another
zero, and remove the last word.
Reply to
Tom Del Rosso

Ok, it's not like your chip designs. Just came across a puzzler. A circuit works on the screen, puts out lots of energy but doesn't consume any. I can set the voltage source series resistance to 1M or whatever and nothing changes. Hey, I might really be on to something here, solving global warming and all that.

Guess I'll waltz over to the lab and hit that red button on the Weller. I do not trust sims all that much.

--
Regards, Joerg

http://www.analogconsultants.com/

"gmail" domain blocked because of excessive spam.
Use another domain or send PM.
Reply to
Joerg

Probably have an extra source in there somewhere, or you AC source is providing the power. There are no such things as "puzzlers", just cockpit errors ;-)

...Jim Thompson

--
| James E.Thompson, P.E.                           |    mens     |
| Analog Innovations, Inc.                         |     et      |
| Analog/Mixed-Signal ASIC\'s and Discrete Systems  |    manus    |
| Phoenix, Arizona  85048    Skype: "skypeanalog"  |             |
| Voice:(480)460-2350  Fax: Available upon request |  Brass Rat  |
| E-mail Icon at http://www.analog-innovations.com |    1962     |
             
         America: Land of the Free, Because of the Brave
Reply to
Jim Thompson

No other sources except one low voltage to the small stuff. It cannot generate the levels coming out. Yeah, it might be a cockpit error but there is nothing obvious and mostly it's faster to lash up something in the lab.

The only time that's a pain is when it entails waiting for a Digikey order to arrive. Then I tell the shepherd to "keep a good watch". She immediately understands and moves over to a place where she can see the road, then almost explodes when the Fedex truck comes around the corner. This avoids a packages sitting there at the entrance without me knowing it has arrived.

--
Regards, Joerg

http://www.analogconsultants.com/

"gmail" domain blocked because of excessive spam.
Use another domain or send PM.
Reply to
Joerg

Probably something modeled with a macro rather than devices?

My dog barks also, but FedEx and UPS always ring the doorbell here, whether a signature is needed or not.

...Jim Thompson

--
| James E.Thompson, P.E.                           |    mens     |
| Analog Innovations, Inc.                         |     et      |
| Analog/Mixed-Signal ASIC\'s and Discrete Systems  |    manus    |
| Phoenix, Arizona  85048    Skype: "skypeanalog"  |             |
| Voice:(480)460-2350  Fax: Available upon request |  Brass Rat  |
| E-mail Icon at http://www.analog-innovations.com |    1962     |
             
         America: Land of the Free, Because of the Brave
Reply to
Jim Thompson

separate

It's all transistors, discretes, transformers and such. No chips.

I wish they would always do that out here. UPS can be a real issue so when I have a choice I prefer not to use them. Several times they selected the backyard entrance (closer to the road ...) to drop off packages and then it started to rain. Other times they claimed that our address did not exist. Yet it does since almost 40 years.

--
Regards, Joerg

http://www.analogconsultants.com/

"gmail" domain blocked because of excessive spam.
Use another domain or send PM.
Reply to
Joerg

The CPU's don't have bugs; the software does.

John

Reply to
John Larkin

ElectronDepot website is not affiliated with any of the manufacturers or service providers discussed here. All logos and trade names are the property of their respective owners.