You crunch numbers much better than me. Took more time too I see.
1. I understood the original poster's intent by saying that SDRAM only gives a 10% system boost. The point I was trying to make was that a ten percent system boost by using DDR RAM (and a supporting motherboard), all else being the same, is quite respectable. What did he want, a system to run twice as fast by changing the RAM? It's still gonna run in the same general neighborhood of preformance (due to efficient caching was my second point).
2. You're right. I ambiguously claimed that you could get a 10% increase without buying a new processor. I still think it was clear enough. I didn't say you didn't have to buy a new mobo. And besides, buying a new mobo is much cheaper than buying a new processor. But I said nothing about cost-free.
3. I will be the last one to claim that a new PIII/1000 is twice as fast as a PIII/500. My point was that it is much closer to double the speed on Sysmark than one wold expect. If you adjust PIII/533 =126 to the expected PIII/500 = 118, then you get that a PIII/500 gets around 100 sysmark (rounding grossly) and a PIII/1000 gets around 200, rounding less grossly.
Your number crunching is much more precise than mine. In reflection it should really be more like 60% difference between 500 and 1000. You got me there.
At the top of the charts, you really do see it waiting for the RAM. But not as much as one (e.g. I) expected.
And I would think that DDR RAM would bring the stats more in line with double the SYSMARK speed.
Lets look at this objectively: a 10% increase in speed over SDRAM, which is already way behind what modern processors need in terms of speed/bandwith.
Actually, it's a 100% increase in speed over SDRAM. It delivers data twice as fast. 100MHz clock speed * twice the data. Or another way, it yields 1600MB/s bandwidth.
Looking at the leaps and bounds with which processor speed is growing, a 10% increase is a drop in the bucket.
Yes, it is a drop in the bucket. But you're comparing apples to commodores. It's a 10% system performance increase over systems that use PC100 RAM. That's quite respectable without changing the processor. Wouldn't you like to make your processor run 10% faster without buying a new one?
Intel and AMD need to stop their Mhz/Ghz race and prod some chip maker into making decent, fast RAM.
Considering that Intel is pushing RDRAM running at 800 MHz and that still runs worse than DDR RAM, don't you think that this statement is a little off target? I understand that your and my idea of decent RAM is not Rambus. But as far as numbers on paper goes, RDRAM is quite fast.
Also, I take issue with what you say about modern processors needing more speed/bandwidth in memory. I thought I agreed with you until I took a look at Tom's Hardware. A 533 PIII gets a 126 sysmark rating. A 1 Ghz PIII gets a 194 rating, nearly twice as fast when thechip is nearly twice as fast! If modern processors are really waiting for RAM so much, why is processor speed a linear progression up the performance chart? It would be tailing off, with performance gains of a 1GHz PIII only marginally faster than a 700 or 800Mhz at the top of the chart.
It looks as if the fast cache on chip is the answer to slow RAM, and at least according to this chart, RAM speed does not make such a difference to fast processors.
Thanks for pointing that out. It didn't occur to me what a good thing this public domaining really was. I don't know how feasible your scenario really would be, but it sounds a lot like something a lot of other organizations might try.
note--the parent post makes a lot more sense if you read its title--"The Alternative outcome."
That's nice, but pure research is only useful when the results are released
Umm... I'm sure the results were useful to IBM. Just because they didn't release them to you and they aren't useful to you doesn't mean they aren't useful.
Windows 95 runs pretty darn fast on a 386. Okay, on a 486. It is hard to tell the difference (at boot time) between 95 on a 486 and Win98SE on a PIII 700. Especially with all the bloated crap that tends to run in the system tray. (Granted playing MP3's is something your 486 can't handle.) But at boot time--not much difference. Smoking crack? Maybe. Let's get out the machines and do a test.
Up until 4.0, FreeBSD di not have DMA enabled by default. Of course I realize that the tests were conducted with 4.0, but you say that BSD enables DMA by default which is by no means true across the board.
The drive was designed to avoid cavitation, I do believe. It was a caterpillar drive, designed to be silent, eliminating the cavitation noises created by a propeller driven system.
just like anything else in life, it's a subjective question. different ISP will have different needs.
What it really comes down to, IMHO, is that information itself is rarely bad. Having information is neither good nor bad in itself.
Consider a widespread DDOS attack--in this case tracking down the origin is difficult enough, and having profuse logs would be a real plus not just for the ISP, but for the net at large.
On the other hand, logging routing traffic which shows that users X,Y, and Z downloaded metallica songs which they did not own, thereby making it possible to prosecute and put them in jail for a long time would come under the heading of a Very Bad Thing.
Notice that in each of these cases, having the data in itself is not bad--it depends entirely on what is done with it. The real question which should determine what logs should be kept is, how likely is it that this information will be abused?
disclaimer: I don't think that people will really go to jail for downloading metallica MP3's-that was just an example to illustrate a point-that if the existence of logs in a given situation, in this case a police state situation, were this likely to be abused, it would be a consciencious netizens duty to come up with a convincing reason why logging was impossible. Something about the data bandwidth of (n-1)^10000 exceeding possible logging potential of network based systems under primary load conditions. Impossible to argue with that, now, isn't it?
Tom's hardware has the scoop here on overclocking the socketed processors.. Apparently they are easily overclockable, and no extra devices are needed to overclock--just an engineer's conductive silver pen. Only problem is getting ahold of one, apparently.
There once was a radio comp'ny which wanted to make lots of money we'll make them pay for the stations we play cause they cant get it free, now can they?;)
Not just a dialect, but a conscious effort on the part of American lexicographers, particularly Noah Webster, to promote American independence through breaking with traditional English spelling. This was at the beginning of the 1800's. Webster was also a simpleminded bastard who wanted to phoneticize English spellings. Fortunately, many of his more drastic changes did not last (dropping of final e's, etc), but changes such as flavour to flavor and civilisation to civilization stuck. Don't blame us poor Americans. Blame Noah Webster, and blame your own British imperialist tendencies which necessitated American etymological independence. Happy Independence Day, aka Fourth of July!
OK, a strange thing is that after sitting at an iMac for a couple of months at work, I don't mind the little hockey puck. It is actually surprisingly comfortable once you swallow the automatic distaste. I bought a tangerine iMac for my girlfriend (who is not a geek, see previous article...) and she actually likes is better than a full sized one.
Of course, not having 3 buttons for quake3 is the real crime there. But then again, I don't play quake3 on her imac.
Last I checked the G3 processor, being based on the older PPC 603e, was not SMP capable. This is one of the (many) reasons that Apple does not ship multi-processor PowerMacs. One of the major advantages of the G4 is the fact that it can support SMP fully. So the question is, what good does it do you to buy a board with multiple G3's? They could only support AMP, as far as I know, which is not something that really scales well. Also, would Linux even support AMP? Probably not--so the question is, what good are these boards? Or did they accomplish something that IBM and motorola could not and make the G3 processors SMP capable?
Slashdot Mirror
I'm thunderstruck.
1. I understood the original poster's intent by saying that SDRAM only gives a 10% system boost. The point I was trying to make was that a ten percent system boost by using DDR RAM (and a supporting motherboard), all else being the same, is quite respectable. What did he want, a system to run twice as fast by changing the RAM? It's still gonna run in the same general neighborhood of preformance (due to efficient caching was my second point).
2. You're right. I ambiguously claimed that you could get a 10% increase without buying a new processor. I still think it was clear enough. I didn't say you didn't have to buy a new mobo. And besides, buying a new mobo is much cheaper than buying a new processor. But I said nothing about cost-free.
3. I will be the last one to claim that a new PIII/1000 is twice as fast as a PIII/500. My point was that it is much closer to double the speed on Sysmark than one wold expect. If you adjust PIII/533 =126 to the expected PIII/500 = 118, then you get that a PIII/500 gets around 100 sysmark (rounding grossly) and a PIII/1000 gets around 200, rounding less grossly.
Your number crunching is much more precise than mine. In reflection it should really be more like 60% difference between 500 and 1000. You got me there.
At the top of the charts, you really do see it waiting for the RAM. But not as much as one (e.g. I) expected.
And I would think that DDR RAM would bring the stats more in line with double the SYSMARK speed.
7. Memory bandwidth is a big bottleneck, but very fast caching technology built on chip masks the slowdown caused by the memory bus.
Seriously, I was astounded when I saw that a PIII/1000 benchmarks nearly twice as fast as a PIII/500.
See for yourself at: http://www.tomshardware.com/cpu/00q2/000511/pentiu miii-11.html
Lets look at this objectively: a 10% increase in speed over SDRAM, which is already way behind what modern processors need in terms of speed/bandwith.
Actually, it's a 100% increase in speed over SDRAM. It delivers data twice as fast. 100MHz clock speed * twice the data. Or another way, it yields 1600MB/s bandwidth.
Looking at the leaps and bounds with which processor speed is growing, a 10% increase is a drop in the bucket.
Yes, it is a drop in the bucket. But you're comparing apples to commodores. It's a 10% system performance increase over systems that use PC100 RAM. That's quite respectable without changing the processor. Wouldn't you like to make your processor run 10% faster without buying a new one?
Intel and AMD need to stop their Mhz/Ghz race and prod some chip maker into making decent, fast RAM.
Considering that Intel is pushing RDRAM running at 800 MHz and that still runs worse than DDR RAM, don't you think that this statement is a little off target? I understand that your and my idea of decent RAM is not Rambus. But as far as numbers on paper goes, RDRAM is quite fast.
Also, I take issue with what you say about modern processors needing more speed/bandwidth in memory. I thought I agreed with you until I took a look at Tom's Hardware. A 533 PIII gets a 126 sysmark rating. A 1 Ghz PIII gets a 194 rating, nearly twice as fast when thechip is nearly twice as fast! If modern processors are really waiting for RAM so much, why is processor speed a linear progression up the performance chart? It would be tailing off, with performance gains of a 1GHz PIII only marginally faster than a 700 or 800Mhz at the top of the chart.
It looks as if the fast cache on chip is the answer to slow RAM, and at least according to this chart, RAM speed does not make such a difference to fast processors.
note--the parent post makes a lot more sense if you read its title--"The Alternative outcome."
Umm... I'm sure the results were useful to IBM. Just because they didn't release them to you and they aren't useful to you doesn't mean they aren't useful.
OTOH, I agree they should release the results.
What it really comes down to, IMHO, is that information itself is rarely bad. Having information is neither good nor bad in itself.
Consider a widespread DDOS attack--in this case tracking down the origin is difficult enough, and having profuse logs would be a real plus not just for the ISP, but for the net at large.
On the other hand, logging routing traffic which shows that users X,Y, and Z downloaded metallica songs which they did not own, thereby making it possible to prosecute and put them in jail for a long time would come under the heading of a Very Bad Thing.
Notice that in each of these cases, having the data in itself is not bad--it depends entirely on what is done with it. The real question which should determine what logs should be kept is, how likely is it that this information will be abused?
disclaimer: I don't think that people will really go to jail for downloading metallica MP3's-that was just an example to illustrate a point-that if the existence of logs in a given situation, in this case a police state situation, were this likely to be abused, it would be a consciencious netizens duty to come up with a convincing reason why logging was impossible. Something about the data bandwidth of (n-1)^10000 exceeding possible logging potential of network based systems under primary load conditions. Impossible to argue with that, now, isn't it?
Course I haven't been there. For that matter the moon could be made of cheese.
Of course, not having 3 buttons for quake3 is the real crime there. But then again, I don't play quake3 on her imac.
stinkin movie. where was that line in the book?
Since when does widespread use equal quality? More people drive Ford Tauruses than BMW's. Does that mean that Tauruses are the only decent cars?