Okay before we get going with the same discussion about ECC vs. Non ECC, and all the flames start from people perusing slashdot who think they are more in the know than the PhD's at VT who have been working on this for months I want to point a few things out.
1. The majority if not all of the bit errors that ECC corrects are caused by thermal noise. Thermal noise is an issue in a cluster of rack mounted 1U units due to the difficulty of cooling such tightly spaced units generating so much heat in so small a space. It is not an issue in a cluster of DESKTOP machines utilizing a Liebert system with way more cooling capacity than is needed.
2. Even if somehow a none-thermal bit error occurs, each node has 4GB RAM. The probability of it being in an OS or application critical (especially given the converging nature of many long running calculations) piece of RAM as opposed to an empty piece of RAM is small.
How many of you are reading this from a desktop without ECC RAM that has an obnoxiously huge uptime? ECC is a non-issue in a well-cooled cluster of desktop cased machines.
I would advise you to have a little more faith in your alma mater....whoever told you there is a:
"more cost effective solution, that provides higher capacity, greater throughput, and more overall compute capability at lower cost..."
was smoking crack. If it was yourself than I respectfully disagree (and would like to see said solution).
Each PPC970 has two independent FPU, each of which is capable of executing a fused multiply/add instruction. This allows the PPC970 to function as if it had FOUR FPU's when doing all that nifty matrix math that makes up a large part of scientific calculations. This puts the machine's peak performance at over 17 Teraflops. If you don't believe me read the article over at arstechnica, or just look at the PPC970 documentation. Not to mention that the Altivec SIMD unit (for any repetitive single precision calculations) SMOKES AMD & Intel's vector solutions. Also the Mellanox Infiniband communication fabric has ridiculously low latencies and extremely high bandwidth..beats Myrinet on both counts from what I've seen...
The long and the short of it is that a dual-Opteron built cluster would have to have significantly more nodes (== more expensive) to deliver the same peak (or average for that matter) performance, and would take longer to be built.
Apple wins on price. Apple wins on performance. Apple wins on delivery time.
I'm sure the decision to use the G5 was not made lightly or frivoulusly, and that all the options were carefully weighed before choosing the one made the most sense.
Is there anyone onilne keeping a listing of which CD's are being released with DRM protection? I sure as hell don't want to go support an artist and then find out I can't even play the CD on my machine....
You are forgetting one of the biggest advantages to generics such as templates, speed. When templates are used much if not all of the binding is accomplished statically at compile time, when inheritance is used much if not all of the binding occurs at runtime. When you use inheritance every call to a virtual method requires a lookup to the vtable, this overhead is non-exsistent in templates. This is not an issue if you are writing bloated desktop apps in Java, but embedded or system-level applications demand the highest speeds possible.
oh how true it is. I worked for a extremely large telecommunications company that had attained "SEI CMM 5" status, and our inspections were by and by a joke, the majority of people just wanted a rubber stamp and get out of the meeting....some engineers would get somewhat upset if you starting to point out blatant quality issues in their code like duplication or horrible variable names....certain engineers (myself included) earned a reputation as "tough inspectors" and subsequently would no longer be invited to inspections......code reviews only work if they are done properly, but I wonder how many companies actually do them right....
I guess a better way to put the question would be: What services are provided by Java and.NET that you guys are looking to replicate without being able to install any type of virtual machine on the PC's?
btw before I get flamed, I want to reiterate strongly, I am _against_ any censoring of scientific research of any kind, I just don't think the security comparison holds any water, there are a lot of better reasons not to censor research.
I fail to see how this is the "same" as security disclosures. When a software bug or security hole is released publicly, users and corporations have the option to either update or turn off the compromised products, and increases pressure on the proprietor of the offending product to fix it in due haste. The argument against censoring security disclosures is that you prevent people from doing things to protect themselves they could have done had they known of the problem.
OTOH, when scientifc research is published that allows chemical or biological weapons to be produced, there isn't anything joe consumer can do to protect himself because he saw the publication.
Believe me, I am an aspiring Ph.D. student and very anti-science censorship...but comparing it to software security censorship is like apples and oranges.
Bravo, I was using the UIC site from 1998 until 2002 when I moved away from Chicago, so it is at least five years old. Nothing depresses you more when you are about to leave work then seeing that the O'hare to downtown delay estimated at 95 minutes:-)
Compelling evidence was presented at the UN on Wed. Did Colin Powell neatly lineup the names of all the sources and disclose all means of electronic surveillance so Saddam could clean up(kill) all the leaks? No. Can we (Americans at least) believe what he said? Yes.
You either don't believe the US or you don't believe Saddam. You can't have it both ways.
Excellent. This is much more to my liking. I will attempt to address your points one-by-one. I think that we will just have to agree to disagree, but I do appreciate your perspective on the matter.
1."I happen to believe that there should be some more levels of negotiation in between failure to comply and ALL OUT WAR."
I couldn't agree more. But this charade has been going on for 12 YEARS. Saddam has continued his WMD program in blatant defiance of UN sanctions even going so far as to oust the inspectors completely in 1998. It took nothing short of the threat of all-out war for him to even let the inspectors back in, and we now know that even that gesture was just for show. Negotiation requires some measure of willingness on both sides of the table, and there is none on Saddam's. He will string this along for as long as possible.
2."how about if we reword that with "appropriate authority" being "US Congress" and "solid legal demand" being a request for VP DC to turn over information about his energy policy meetings, and HE OUTRIGHT REFUSED!"
I don't know how you can even attempt to make this comparison, and I am recluctant to appear as if I am justifying it, but here goes: There was absolutely _zero_ legal precedence for the disclosure demands that Congress attempted to place on Dick Cheney. Don't you think if there was a shred of law to back them up they would have used it and Cheney would have been forced to comply? It was a majority Democrat Senate and they had the power to pursure legal sanctions. It is exactly similar to right now as they are demanding with _zero_ legal authority that classified solicitor general internal memos be turned over in the Estrada appointment hearing. Congress has no right to make those demands.The laws of checks and balances apply to them as well.
3."He wants weapons to maintain power inside Iraq, not outside."
If you truly believe this you are at best naive and at worst willfully ignorant. Iraq is a police state. Saddam rules with an iron fist and subjects his people to horrible atrocities against human rights. Do you TRULY believe that Saddam needs nuclear weapons, smallpox, and VX nerve gas to keep the Iraqi people in check?! The Iraqi people are kept in line through fear of brutal torture and death from police and soldiers who use conventional guns and tanks. I am afraid that WMD are intended for much more sinister means then merely maintaining the status quo.
4."Now because of Bush's "Heroic, No non-since, Take control, Total domination threats", we have North Korea, a REAL international threat, breathing down our necks. What is "our hero" George doing about them? NOTHING! I guess he wanted an easy target for his "Pet Project" war, not a "real enemy" that he might actually have to negotiate with."
Reality check. North Korea surreptiously restarted its WMD program after signing a treaty agreeing not too. This happened _years_ before George W. even ran for office.Once they successfully created a nuclear weapon....they announced it to the world. NONE of that is because of anything GW said or did. This was put into motion before he took office. North Korea _is_ doing this now because we are occupied with Iraq, but only because they are attempting to optimize their leverage for gaining economic aid. North Korea is a shining example of why we CANT afford to let Saddam gain WMD. Once Saddam gets nukes you can bet that the same thing that is happening with NK will happen with him. Are they an easy target?...you are damn right they are, and we want to ensure that this is taken care before they aren't.
5."The best way to save American lives is NOT TO GO TO WAR IN THE FIRST PLACE. Why was Bush so desperate to start one where it wasn't necessary? Obviously not to save lives."
If we don't follow through our current course a small nuke goes off in Manhattan, or x00,000 people die of a smallpox outbreak in Chicago, because Saddam was allowed to build these WMD and give them to terrorists, I wonder if you will continue to hold this view? Will stopping Saddam stop terrorists or their quest for WMD? No way. Will it cut off a major avenue where they could approriate these weapons from?..Yes. Developing truly horrific large scale WMD requires significant mechanical infrastructure and funding. The only places that these are available are in countries that support terrorism and WMD research The writing is on the wall. Saddam and Al Qaeda are setting aside their differences to focus on a common enemy...America.
6."Economy in a slump, severe deficit. So lets make it worse by inventing an expensive war, runnin up the deficit even more and strangling the economy to death."
Personally I am predicting resounding success in Iraq and a strong economic recovery. Time will tell if the economy rebounds. But you should feel good about that, because if the economy is still bad in 2004 Bush will lose the election irregardless of foreign policy success, and I am sure that will please you:-)
I don't know what is more disheartening, the fact that this was the best excuse for political debate you could come up with that or the fact that people are actually modding it up as "Insightful".
Saddam is _not_ going to disarm peacefully. All the UN circus acts and smoke shows are not going to change that fact. We (US and the coalition of 20+ countries that support us) _are_ going to war. Irregardless of whether or not you and I agree over that course of action, you have to agree that _any_ nonviolent attacks (CYBER) that will shut down radar installtions and missile batteries, or otherwise protect our soldiers lives has merit.
President Bush is being responsible in the fact that he recognizes that if we are to engage in a new form of warfare, we should first draw up the rules of engagement.
I never cease to be amazed at the overwhelmingly liberal bias on this website. Especially considering all the great things for technology like the DMCA that President Clinton did for us.
I welcome intelligent, thought-out political debate, the freedom of speech to do that that is what make America great. People posting nonsensical, sophmorish rubbish like this and getting modded up as "Insightful" is what makes Slashdot so sad.
sigh....now I will probably get modded as a troll or flamebait....guess that's life
These letters mean nothing. Jules Verne "wrote" about the submarine and a time machine too, doesn't mean he invented them. For all we know these could be test manuscripts for Sci-Fi never realized. Science requires incontrovertable physical evidence, or at least a complete mathematical description if the hypothesis is currently untestable due to physical limitations. These letters provide neither, and very well may be a hoax. Have they tested the ink and paper to _prove_ it was even written that long ago?
Is anyone aware of how extensive their support for non-C++ projects will be. Are they going to include full debugging capabilities? Perhaps have a javadoc tab similar to the current QT documentation tab?
This is extremely exciting stuff, I am not aware of any other IDE that let you develop in multiple languages AND multiple toolkits...if they are fully supporting those other languages and toolkits like they do with C++ and QT.....wow....I'm going to be using this for everything I do from now on.....
Am I missing something? I don't want to start a stupid flamewar..."my distro is better than yours!", but I didn't read anything in that article that Mandrake doesn't do at least as well, and usually better. Not to mention that 9.0 is right around the corner....I am a full time grad student and researcher...have been Windows free for years...and when I get home at night I just want my distro to work, be highly customizable, and not have to dick with config files....and the only thing I have seen that rivals Mandrake on the desktop for that is the latest Redhat....and I don't like the direction they are taking with the bastardized Gnome/KDE....good for the masses but not for me.....who is this author that he is already proclaiming this Xandros to be a top competitor for the desktop.....?
There is a GPS system available for download.
Of course you need to pay for it (one time fee) and have a more costly "Network Aware" subscription plan...but if you need it its there
Most Slashdotters are probably aware of this, but KDevelop is a great IDE that ships with KDE and has IMHO phenomenal CVS integration.
Just my $0.02 USD
Re:Knode and Kmail were better in 2.1.1
on
KDE 2.2.1 Up
·
· Score: 1
What the heck is the world coming to when we're saying..."even on my 1.2 GHz".
damn, I'm thinking of my old 386 WANG....i don't even want to know how slow that was.
Slashdot Mirror
Okay before we get going with the same discussion about ECC vs. Non ECC, and all the flames start from people perusing slashdot who think they are more in the know than the PhD's at VT who have been working on this for months I want to point a few things out.
1. The majority if not all of the bit errors that ECC corrects are caused by thermal noise. Thermal noise is an issue in a cluster of rack mounted 1U units due to the difficulty of cooling such tightly spaced units generating so much heat in so small a space. It is not an issue in a cluster of DESKTOP machines utilizing a Liebert system with way more cooling capacity than is needed.
2. Even if somehow a none-thermal bit error occurs, each node has 4GB RAM. The probability of it being in an OS or application critical (especially given the converging nature of many long running calculations) piece of RAM as opposed to an empty piece of RAM is small.
How many of you are reading this from a desktop without ECC RAM that has an obnoxiously huge uptime? ECC is a non-issue in a well-cooled cluster of desktop cased machines.
I would advise you to have a little more faith in your alma mater....whoever told you there is a:
"more cost effective solution, that provides higher capacity, greater throughput, and more overall compute capability at lower cost..."
was smoking crack. If it was yourself than I respectfully disagree (and would like to see said solution).
Each PPC970 has two independent FPU, each of which is capable of executing a fused multiply/add instruction. This allows the PPC970 to function as if it had FOUR FPU's when doing all that nifty matrix math that makes up a large part of scientific calculations. This puts the machine's peak performance at over 17 Teraflops. If you don't believe me read the article over at arstechnica, or just look at the PPC970 documentation. Not to mention that the Altivec SIMD unit (for any repetitive single precision calculations) SMOKES AMD & Intel's vector solutions. Also the Mellanox Infiniband communication fabric has ridiculously low latencies and extremely high bandwidth..beats Myrinet on both counts from what I've seen...
The long and the short of it is that a dual-Opteron built cluster would have to have significantly more nodes (== more expensive) to deliver the same peak (or average for that matter) performance, and would take longer to be built.
Apple wins on price.
Apple wins on performance.
Apple wins on delivery time.
I'm sure the decision to use the G5 was not made lightly or frivoulusly, and that all the options were carefully weighed before choosing the one made the most sense.
Mod parent up to +5, he is the only one to make a comment on this page that truly understands why this will be a monstrous machine.....
Is there anyone onilne keeping a listing of which CD's are being released with DRM protection? I sure as hell don't want to go support an artist and then find out I can't even play the CD on my machine....
You are forgetting one of the biggest advantages to generics such as templates, speed. When templates are used much if not all of the binding is accomplished statically at compile time, when inheritance is used much if not all of the binding occurs at runtime. When you use inheritance every call to a virtual method requires a lookup to the vtable, this overhead is non-exsistent in templates. This is not an issue if you are writing bloated desktop apps in Java, but embedded or system-level applications demand the highest speeds possible.
oh how true it is. I worked for a extremely large telecommunications company that had attained "SEI CMM 5" status, and our inspections were by and by a joke, the majority of people just wanted a rubber stamp and get out of the meeting....some engineers would get somewhat upset if you starting to point out blatant quality issues in their code like duplication or horrible variable names....certain engineers (myself included) earned a reputation as "tough inspectors" and subsequently would no longer be invited to inspections......code reviews only work if they are done properly, but I wonder how many companies actually do them right....
What issues do you guys have with using C++?
.NET that you guys are looking to replicate without being able to install any type of virtual machine on the PC's?
I guess a better way to put the question would be: What services are provided by Java and
btw before I get flamed, I want to reiterate strongly, I am _against_ any censoring of scientific research of any kind, I just don't think the security comparison holds any water, there are a lot of better reasons not to censor research.
I fail to see how this is the "same" as security disclosures. When a software bug or security hole is released publicly, users and corporations have the option to either update or turn off the compromised products, and increases pressure on the proprietor of the offending product to fix it in due haste. The argument against censoring security disclosures is that you prevent people from doing things to protect themselves they could have done had they known of the problem.
OTOH, when scientifc research is published that allows chemical or biological weapons to be produced, there isn't anything joe consumer can do to protect himself because he saw the publication.
Believe me, I am an aspiring Ph.D. student and very anti-science censorship...but comparing it to software security censorship is like apples and oranges.
For games like Final Fantasy or Zelda, you probably will need to replace the cartridge battery
Bravo, I was using the UIC site from 1998 until 2002 when I moved away from Chicago, so it is at least five years old. Nothing depresses you more when you are about to leave work then seeing that the O'hare to downtown delay estimated at 95 minutes :-)
They are making opposing claims. When two people take complete opposite sides of a story:
Saddam: I am NOT supporting terrorism
USA: Saddam IS supporting terrorism
One of them is lying. Who you believe is up to you.
Compelling evidence was presented at the UN on Wed. Did Colin Powell neatly lineup the names of all the sources and disclose all means of electronic surveillance so Saddam could clean up(kill) all the leaks? No. Can we (Americans at least) believe what he said? Yes.
You either don't believe the US or you don't believe Saddam. You can't have it both ways.
Excellent. This is much more to my liking. I will attempt to address your points one-by-one. I think that we will just have to agree to disagree, but I do appreciate your perspective on the matter.
1."I happen to believe that there should be some more levels of negotiation in between failure to comply and ALL OUT WAR."
I couldn't agree more. But this charade has been going on for 12 YEARS. Saddam has continued his WMD program in blatant defiance of UN sanctions even going so far as to oust the inspectors completely in 1998. It took nothing short of the threat of all-out war for him to even let the inspectors back in, and we now know that even that gesture was just for show. Negotiation requires some measure of willingness on both sides of the table, and there is none on Saddam's. He will string this along for as long as possible.
2."how about if we reword that with "appropriate authority" being "US Congress" and "solid legal demand" being a request for VP DC to turn over information about his energy policy meetings, and HE OUTRIGHT REFUSED!"
I don't know how you can even attempt to make this comparison, and I am recluctant to appear as if I am justifying it, but here goes: There was absolutely _zero_ legal precedence for the disclosure demands that Congress attempted to place on Dick Cheney. Don't you think if there was a shred of law to back them up they would have used it and Cheney would have been forced to comply? It was a majority Democrat Senate and they had the power to pursure legal sanctions. It is exactly similar to right now as they are demanding with _zero_ legal authority that classified solicitor general internal memos be turned over in the Estrada appointment hearing. Congress has no right to make those demands.The laws of checks and balances apply to them as well.
3."He wants weapons to maintain power inside Iraq, not outside."
If you truly believe this you are at best naive and at worst willfully ignorant. Iraq is a police state. Saddam rules with an iron fist and subjects his people to horrible atrocities against human rights. Do you TRULY believe that Saddam needs nuclear weapons, smallpox, and VX nerve gas to keep the Iraqi people in check?! The Iraqi people are kept in line through fear of brutal torture and death from police and soldiers who use conventional guns and tanks. I am afraid that WMD are intended for much more sinister means then merely maintaining the status quo.
4."Now because of Bush's "Heroic, No non-since, Take control, Total domination threats", we have North Korea, a REAL international threat, breathing down our necks. What is "our hero" George doing about them? NOTHING! I guess he wanted an easy target for his "Pet Project" war, not a "real enemy" that he might actually have to negotiate with."
Reality check. North Korea surreptiously restarted its WMD program after signing a treaty agreeing not too. This happened _years_ before George W. even ran for office.Once they successfully created a nuclear weapon....they announced it to the world. NONE of that is because of anything GW said or did. This was put into motion before he took office. North Korea _is_ doing this now because we are occupied with Iraq, but only because they are attempting to optimize their leverage for gaining economic aid.
North Korea is a shining example of why we CANT afford to let Saddam gain WMD. Once Saddam gets nukes you can bet that the same thing that is happening with NK will happen with him. Are they an easy target?...you are damn right they are, and we want to ensure that this is taken care before they aren't.
5."The best way to save American lives is NOT TO GO TO WAR IN THE FIRST PLACE. Why was Bush so desperate to start one where it wasn't necessary? Obviously not to save lives."
If we don't follow through our current course a small nuke goes off in Manhattan, or x00,000 people die of a smallpox outbreak in Chicago, because Saddam was allowed to build these WMD and give them to terrorists, I wonder if you will continue to hold this view? Will stopping Saddam stop terrorists or their quest for WMD? No way. Will it cut off a major avenue where they could approriate these weapons from?..Yes. Developing truly horrific large scale WMD requires significant mechanical infrastructure and funding. The only places that these are available are in countries that support terrorism and WMD research The writing is on the wall. Saddam and Al Qaeda are setting aside their differences to focus on a common enemy...America.
6."Economy in a slump, severe deficit. So lets make it worse by inventing an expensive war, runnin up the deficit even more and strangling the economy to death."
Personally I am predicting resounding success in Iraq and a strong economic recovery. Time will tell if the economy rebounds. But you should feel good about that, because if the economy is still bad in 2004 Bush will lose the election irregardless of foreign policy success, and I am sure that will please you:-)
I wish you good day.
lol...I was being sarcastic....next time I'll use the proper end tag
believe me, I could not hate the DMCA more....
I don't know what is more disheartening, the fact that this was the best excuse for political debate you could come up with that or the fact that people are actually modding it up as "Insightful".
Saddam is _not_ going to disarm peacefully. All the UN circus acts and smoke shows are not going to change that fact. We (US and the coalition of 20+ countries that support us) _are_ going to war. Irregardless of whether or not you and I agree over that course of action, you have to agree that _any_ nonviolent attacks (CYBER) that will shut down radar installtions and missile batteries, or otherwise protect our soldiers lives has merit.
President Bush is being responsible in the fact that he recognizes that if we are to engage in a new form of warfare, we should first draw up the rules of engagement.
I never cease to be amazed at the overwhelmingly liberal bias on this website. Especially considering all the great things for technology like the DMCA that President Clinton did for us.
I welcome intelligent, thought-out political debate, the freedom of speech to do that that is what make America great. People posting nonsensical, sophmorish rubbish like this and getting modded up as "Insightful" is what makes Slashdot so sad.
sigh....now I will probably get modded as a troll or flamebait....guess that's life
ahhhhh, once again my ignorance rears its ugly head, I appreciate the kernel-enlightened folk above correcting me :-)
I imagine not, syntax errors and all you know, but this comment might exsist: /* I wonder why this works? */
:-)
I apologize for being so anal
Yes but it could be easily tested to see if the ink had been applied 125 years ago or last week.
These letters mean nothing. Jules Verne "wrote" about the submarine and a time machine too, doesn't mean he invented them. For all we know these could be test manuscripts for Sci-Fi never realized. Science requires incontrovertable physical evidence, or at least a complete mathematical description if the hypothesis is currently untestable due to physical limitations. These letters provide neither, and very well may be a hoax. Have they tested the ink and paper to _prove_ it was even written that long ago?
-J0ey4
Is anyone aware of how extensive their support for non-C++ projects will be. Are they going to include full debugging capabilities? Perhaps have a javadoc tab similar to the current QT documentation tab?
This is extremely exciting stuff, I am not aware of any other IDE that let you develop in multiple languages AND multiple toolkits...if they are fully supporting those other languages and toolkits like they do with C++ and QT.....wow....I'm going to be using this for everything I do from now on.....
Am I missing something? I don't want to start a stupid flamewar..."my distro is better than yours!", but I didn't read anything in that article that Mandrake doesn't do at least as well, and usually better. Not to mention that 9.0 is right around the corner....I am a full time grad student and researcher...have been Windows free for years...and when I get home at night I just want my distro to work, be highly customizable, and not have to dick with config files....and the only thing I have seen that rivals Mandrake on the desktop for that is the latest Redhat....and I don't like the direction they are taking with the bastardized Gnome/KDE....good for the masses but not for me.....who is this author that he is already proclaiming this Xandros to be a top competitor for the desktop.....?
don't mod me down too much...:-)
cheers,
J0ey4
There is a GPS system available for download. Of course you need to pay for it (one time fee) and have a more costly "Network Aware" subscription plan...but if you need it its there
Most Slashdotters are probably aware of this, but KDevelop is a great IDE that ships with KDE and has IMHO phenomenal CVS integration. Just my $0.02 USD
What the heck is the world coming to when we're saying..."even on my 1.2 GHz".
damn, I'm thinking of my old 386 WANG....i don't even want to know how slow that was.
l8r