The Socket-A semprons are K7, the 754-pin are K8 based.
The power consumption is based on transistor count, frequency and switching probability. They don't say how they calculate TDP. It might be if ALL transistors switched at clock rate. It might be if 50%, it might be if 65%.
As for my "one anecdotal case"... I've been using AMD processors since the K6-2 started shipping. I've used quite a few K7s and I have one K8. you don't need a mobo sensor to tell the K7 is hotter... just put your damn hand on the heat sink. At full load you can really feel the heat from several inches away on a K7.
The point is I actually own a K8 and I know for a fact it runs cooler at idle/load than my previous K7 boxes.
Like I said I chalk it up to more efficient heat dissipation (heat spreader, larger HSF, etc...) and more efficient transistors (lower voltage, less leak, etc...).
x86_64 mode lets you run 32-bit apps as well. In fact the "64-bit opcodes" are just the 32-bit opcodes with a REX prefix byte [or two].
There are descriptor types that specify the size of addresses which can both be used in 64-bit "long mode" [the name of the 64-bit mode... protected mode is 32-bits].
Linux has been able todo this for quite some time with ease.
it's a 1.5V NewCastle. As for "old K7"... Barton cores are not new. Sempron [754-pin and up] cores are based on the K8 design not K7. They just have the x86_64/extra cache disabled....
You really ought to know what you are talking.
The point is even with the bus disconnect the K7s still idled warmer than a K8 idles. More to the point at full load the K7s are hotter than the K8s.
Maybe the K8 takes more power [I personally don't think so] but it certainly doesn't get as hot. Either that means it dissipates heat quicker or it just makes less heat [more efficient] who knows.
Well I own both a Barton 3200+ and a NewCastle 3200+ and the Barton [even with athcool which does the same thing as fvcool] it still runs fairly hot.
That's totally beside the point... cuz at FULL LOAD there is NO IDLE TIME.
When both [2.2Ghz] cpus are at full tilt the K8 is cooler by at least 10C. Both have Thermaltake HSFs and the K8 has the "SilentBoost" variant [which is very quiet].
"You should know that's not technically true. K8 processors seem cooler because of CnQ motherboards."
You do realize that CnQ is just marketing for what the mobile K7's already had right? that is, clock modding.
When you are at full load the cpu won't be clocking down or idling. So CnQ doesn't do jack shit.
The reason the K8 is cooler is
1. More surface area on the chip for heat dissipation.
2. Different fabs process (SOI), also lower voltage
I don't know how much both of those contribute... but given that I've used quite a few K7s in my time I know for a fact they suck back the power like there is no tommorow.
No, I'm just a happy loyal user. I have both a Prescott P4 3.2Ghz and an AMD64 Newcastle 2.2Ghz...
For what I do [building software] the AMD64 smokes the P4... and does it without getting to 50C or so...
The AMD approach is just common sense. Be more efficient at what you do and gradually do it faster. Intel went the market route and said "slow clockrate is for pansies!".
So you end up with a cpu that has a higher clock rate but it doesn't win because the efficency is too low.
AES on my AMD64 ranges around 260 [or so] cycles/block. On the P4 with Intels compiler I get around 410 cycles/block. If you scale 3.2Ghz to 2.2 Ghz that's still effectively 281 cycles [at 2.2Ghz]. Doesn't seem like much but keep in mind to get this speed they had to draw more power and run at a higher clock rate.
I did a benchmark a week ago where I built LibTomCrypt with/without hyperthreading and it took the prescott with hyperthreading at 3.2Ghz to even come close to matching the AMD64 speed. That's only on ~45,000 lines of code.
Now multiply that by say five or ten to get a larger project.
I'm not saying the Prescott isn't a neat design. Overall it's efficient enough to be useful. Just the AMD64 eats it's breakfast and spanks it's mother is all I'm saying.;-)
AMD64 carries more than just "bigger registers". It has more of them and the actual core is an overall improved K7 process with
- Slightly longer scheduling buffers - 128-bit L1 cache bus - Larger instruction window (means it can feed the alus better when constants/etc are found) - more registers [and they're bigger]
They also run cooler and takes less power than their k7 brothers.
1. Be less stupid about data. Environment Canada for instance keeps backups going like 10 years or so of crap like "how much corn grew here"... who gives a shit!!!
2. Use hardware accelerated crypto or just a fast processor. And AMD64 can keep cat-5 speeds without taxing the CPU and will set you back a couple of hundred dollars!!! OH NO NOT $200!!! How can we ever afford that?
3. Do smarter backups. Do you really generate TB's of new data a day? Somehow I doubt that. So rotate older crap out of the nightly/weekly backups.
4. Business costs money.
Really, if you're going to handle my data for a business [because essentially that's the business Ameritrade is in] you'd expect them to actually invest in proper networking, archiving, etc... otherwise why are you using their services?
This reminds me of the "RAM manufacturers don't test chips"... work isn't supposed to be cost free... that's why it's called work and why you get paid for it!
I run what I want, not what they want to sell me. e.g. an AMD64.... the P4 I recently bought was because "facing reality" means using the same platform your customers will.
Personally the P4 bothers me. It takes a wack of power and it's so f'ing slow by comparison...
They sell Intel only for the same reason they're a Windows only shop [well for the majority]. They're gonna milk the "wintel" success to the very last drop if it takes a decade or two to get there...
Which, interestingly enough, is why you shouldn't buy dell machines [or gateway, or compaq or...].
Walk into a local retail shop, design your own computer from the ground up and get what you *actually* want not just *what the cheapest thing Dell will hawk on ya* thing is.
Sure I paid more than 399$ for my machine... I also got a workstation that is efficient and lets me do my work (and play games)... oh and it doesn't churn through 250W constantly and even at full load [where it's much faster than the average Intel offering] it consumes less power makes less heat, etc...
1. Blow money on day trips to the states [from Canada]
2. Blow money on computers and the related
3. Get into a bit of debt with student loans...
Things I didn't do when I was a teenager
1. Do drugs
2. Have sex [though... I view that as a negative]
3. Be a dumbass in chatrooms talking about meeting COMPLETE STRANGERS.
Teenagers are expected "to do stupid things" but they're also expected to have "some wits about them". If at 17 you're not smart enough to not meet total strangers in non-public places, etc... you're gonna darwin out anyways...
The only thing that's being limited is the government's service of providing wifi at trucker rest spots. If the trucker wants to surf porn, he can buy a cellphone.
Whoa whoa. The trucker *IS* paying for the wifi. Ever heard of taxes?
Why should a tax funded service that is VERY LIKELY to be used by... say people old enough TO DRIVE be filtered?
This is another "think of the children" with a mix of "let's screw wifi".
Children don't pay for shit [cable, net, etc] so why should it be so controlled as to not hurt their feeble little minds?
I think *shock* the license should be product specific. Clearly a font and a PNG library are meant to be used differently. Why you'd use the GPL for both...
If anything fonts should be LGPL since they're part of the document but you're not modifying them...
Slashdot Mirror
The Socket-A semprons are K7, the 754-pin are K8 based.
... I've been using AMD processors since the K6-2 started shipping. I've used quite a few K7s and I have one K8. you don't need a mobo sensor to tell the K7 is hotter... just put your damn hand on the heat sink. At full load you can really feel the heat from several inches away on a K7.
The power consumption is based on transistor count, frequency and switching probability. They don't say how they calculate TDP. It might be if ALL transistors switched at clock rate. It might be if 50%, it might be if 65%.
As for my "one anecdotal case"
The point is I actually own a K8 and I know for a fact it runs cooler at idle/load than my previous K7 boxes.
Like I said I chalk it up to more efficient heat dissipation (heat spreader, larger HSF, etc...) and more efficient transistors (lower voltage, less leak, etc...).
Tom
You mean BSD right? [which is what MacOS is based on nowadays ain't it?]
Tom
x86_64 mode lets you run 32-bit apps as well. In fact the "64-bit opcodes" are just the 32-bit opcodes with a REX prefix byte [or two].
There are descriptor types that specify the size of addresses which can both be used in 64-bit "long mode" [the name of the 64-bit mode... protected mode is 32-bits].
Linux has been able todo this for quite some time with ease.
Tom
Why? You can run Linux on Macs ...
Tom
Um ... the only one related to crypto would be the theorem that a^p mod p == a if p is prime and a is co-prime to p.
That's not only not the famous Fermat Last Theorem but it's also trivially provable with basic number theory.
Tom
Don't forget the hot university chicks!
Oh and culture... yeah yeah the culture...
Tom
it's a 1.5V NewCastle. As for "old K7" ... Barton cores are not new. Sempron [754-pin and up] cores are based on the K8 design not K7. They just have the x86_64/extra cache disabled. ...
You really ought to know what you are talking.
The point is even with the bus disconnect the K7s still idled warmer than a K8 idles. More to the point at full load the K7s are hotter than the K8s.
Maybe the K8 takes more power [I personally don't think so] but it certainly doesn't get as hot. Either that means it dissipates heat quicker or it just makes less heat [more efficient] who knows.
Tom
Well I own both a Barton 3200+ and a NewCastle 3200+ and the Barton [even with athcool which does the same thing as fvcool] it still runs fairly hot.
... cuz at FULL LOAD there is NO IDLE TIME.
That's totally beside the point
When both [2.2Ghz] cpus are at full tilt the K8 is cooler by at least 10C. Both have Thermaltake HSFs and the K8 has the "SilentBoost" variant [which is very quiet].
Tom
... arrg I was gonna mod in this discussion... but ...
"long long" is eight bytes on __x86_64__ platforms [e.g. AMD64 with GCC].
long long is also C99 compatible and has been available in GCC and most unix cc's for a very long time.
Tom
They would if they took their job/security seriously.
This is like having your credit card stolen. It's in your best interest to get on top of that as soon as possible.
Tom
"You should know that's not technically true. K8 processors seem cooler because of CnQ motherboards."
You do realize that CnQ is just marketing for what the mobile K7's already had right? that is, clock modding.
When you are at full load the cpu won't be clocking down or idling. So CnQ doesn't do jack shit.
The reason the K8 is cooler is
1. More surface area on the chip for heat dissipation.
2. Different fabs process (SOI), also lower voltage
I don't know how much both of those contribute... but given that I've used quite a few K7s in my time I know for a fact they suck back the power like there is no tommorow.
Tom
Mag strips!
Put 32 random bytes on a magstrip and hand it to your user. Oh but Tom, what if they lose the card or it's stolen? Yeah simple plan for that.
USER: "Yeah hello sysadmin? I lost my card."
ADMIN: "Ok. Your account has been temporarily deactivated please pick up a new card."
If you're a company/group/etc that is worried about security you can afford a keyboard with a magstrip reader (they're not that expensive).
Tom
He said the amd64 is only for large databases... that's like wrong.
Tom
.... Me work for AMD? Ha!
... and does it without getting to 50C or so...
;-)
No, I'm just a happy loyal user. I have both a Prescott P4 3.2Ghz and an AMD64 Newcastle 2.2Ghz...
For what I do [building software] the AMD64 smokes the P4
The AMD approach is just common sense. Be more efficient at what you do and gradually do it faster. Intel went the market route and said "slow clockrate is for pansies!".
So you end up with a cpu that has a higher clock rate but it doesn't win because the efficency is too low.
AES on my AMD64 ranges around 260 [or so] cycles/block. On the P4 with Intels compiler I get around 410 cycles/block. If you scale 3.2Ghz to 2.2 Ghz that's still effectively 281 cycles [at 2.2Ghz]. Doesn't seem like much but keep in mind to get this speed they had to draw more power and run at a higher clock rate.
I did a benchmark a week ago where I built LibTomCrypt with/without hyperthreading and it took the prescott with hyperthreading at 3.2Ghz to even come close to matching the AMD64 speed. That's only on ~45,000 lines of code.
Now multiply that by say five or ten to get a larger project.
I'm not saying the Prescott isn't a neat design. Overall it's efficient enough to be useful. Just the AMD64 eats it's breakfast and spanks it's mother is all I'm saying.
Tom
AMD64 carries more than just "bigger registers". It has more of them and the actual core is an overall improved K7 process with
- Slightly longer scheduling buffers
- 128-bit L1 cache bus
- Larger instruction window (means it can feed the alus better when constants/etc are found)
- more registers [and they're bigger]
They also run cooler and takes less power than their k7 brothers.
Tom
Several points.
... work isn't supposed to be cost free ... that's why it's called work and why you get paid for it!
1. Be less stupid about data. Environment Canada for instance keeps backups going like 10 years or so of crap like "how much corn grew here"... who gives a shit!!!
2. Use hardware accelerated crypto or just a fast processor. And AMD64 can keep cat-5 speeds without taxing the CPU and will set you back a couple of hundred dollars!!! OH NO NOT $200!!! How can we ever afford that?
3. Do smarter backups. Do you really generate TB's of new data a day? Somehow I doubt that. So rotate older crap out of the nightly/weekly backups.
4. Business costs money.
Really, if you're going to handle my data for a business [because essentially that's the business Ameritrade is in] you'd expect them to actually invest in proper networking, archiving, etc... otherwise why are you using their services?
This reminds me of the "RAM manufacturers don't test chips"
Tom
You ***ENCRYPT*** [and authenticate] your backups.
So that even if you lose the media you don't leak the data...
Of course you have to be a Community College grad to figure that out.
I R SMRT!
Tom
This [like any other product] is why RAM costs money. ... If it didn't take effort to make they wouldn't be worth anything.
Tom
I run what I want, not what they want to sell me. e.g. an AMD64. ... the P4 I recently bought was because "facing reality" means using the same platform your customers will.
Personally the P4 bothers me. It takes a wack of power and it's so f'ing slow by comparison...
Tom
M O N O P O L Y BUIS-NESS!
...].
... oh and it doesn't churn through 250W constantly and even at full load [where it's much faster than the average Intel offering] it consumes less power makes less heat, etc...
They sell Intel only for the same reason they're a Windows only shop [well for the majority]. They're gonna milk the "wintel" success to the very last drop if it takes a decade or two to get there...
Which, interestingly enough, is why you shouldn't buy dell machines [or gateway, or compaq or
Walk into a local retail shop, design your own computer from the ground up and get what you *actually* want not just *what the cheapest thing Dell will hawk on ya* thing is.
Sure I paid more than 399$ for my machine... I also got a workstation that is efficient and lets me do my work (and play games)
Tom
Stupid things I did when I was a teenager
... I view that as a negative]
1. Blow money on day trips to the states [from Canada]
2. Blow money on computers and the related
3. Get into a bit of debt with student loans...
Things I didn't do when I was a teenager
1. Do drugs
2. Have sex [though
3. Be a dumbass in chatrooms talking about meeting COMPLETE STRANGERS.
Teenagers are expected "to do stupid things" but they're also expected to have "some wits about them". If at 17 you're not smart enough to not meet total strangers in non-public places, etc... you're gonna darwin out anyways...
Tom
Ah, true dat.
Just wish they practiced what they preach. Nothing like getting cut off at 65mph by a minivan with a "baby on board" sticker...
Tom
The only thing that's being limited is the government's service of providing wifi at trucker rest spots. If the trucker wants to surf porn, he can buy a cellphone.
... say people old enough TO DRIVE be filtered?
Whoa whoa. The trucker *IS* paying for the wifi. Ever heard of taxes?
Why should a tax funded service that is VERY LIKELY to be used by
This is another "think of the children" with a mix of "let's screw wifi".
Children don't pay for shit [cable, net, etc] so why should it be so controlled as to not hurt their feeble little minds?
Tom
"...include clauses to keep costs low and access open..."
...
...
Hahahahahahahahahaha... what planet are you from? They will of course market this per KB say at a low cost of $0.01 per KB! that's cheap!
They will then claim it's "to re-coop expenses" and use that excuse for the next THIRTY YEARS
Tom
Yes, there is public domain as well ;-)
...
Hehehe.
I think *shock* the license should be product specific. Clearly a font and a PNG library are meant to be used differently. Why you'd use the GPL for both
If anything fonts should be LGPL since they're part of the document but you're not modifying them...
Tom