I stand by my argument that Viscalc made the IBM PC which in turn made Microsoft. Sure Microsoft has some smart people working for it. Sale of DOS to IBM before they owned it was an incredible piece of business geneous (if some what ethically challenged).
Okay thanks for calling me an idiot. I already know he was misquoted but he also implied something that wasn't true. So was a certain vice president who reportly said he wished he studied more latin in school while visiting latin america. That doesn't change the fact that both are internet versions of urban legends.
Hmm that's not really true. The spreadsheet made the IBM PC the business computer of choice and Microsoft was taken along for a ride because of the license agreement IBM made with them. It's IBMs fault we are stuck with such a buggy collection of stolen ideas that Windows is.
The original article is just a load of baloney. The guy asking is obviously clueless.
Really what has microsoft given us?
Did they develop the GUI?
No Xerox did. And no Apple didn't develop it.
Hey they sell alot of mice. Did they develop mice?
No Xerox did.
Hey they support Ethernet. Did they develop ethernet?
No Xerox did.
Did they develop the Browser?
No NCSA did.
Did they develop the Internet?
No Darpa did. Yes that's right it wasn't Al Gore.
Did they develop the word processor?
No.
Did they develop Desktop Publishing Software?
No
Did they develop Diagramming software like visio?
No they bought visio.
So tell me what did Microsoft give us other than a combination of other peoples technologies and ideas?
ROFL. AMD has support for most of those intel commands (SSE3,etc). They use the intel command set for 32 bit processing (with 3DNow added and the like). The optimization should work on both in most cases. Also if Intel had anyone working on support for AMD processors, it would be to slow them down because the sure aren't going to go out of their way to support AMD in their compiler.
You misunderstood me. I saying that is pretty obvious that Intel is doing something because you need to force ICC compiler to use proper optimization on an opteron. Whether or not, you still get the best optimization, I'm not sure but you could probably find out fairly easily by comparing the binary from code compiled on a Xeon and code compiled on an Opteron.
This won't be hard to prove. Pretty much anyone who wants fast 32Bit code uses the Intel Compilers, even on AMD. However it is a known fact that you need to force the compiler to use optimizations if an Intel Processor is not detected.
Opteron has 40 Bit Real Memory Address and 48 Bit Virtual Memory addressing.
That allows for 1TB of Real and 256TB of Virtual Memory Access --- not 64GBs.
Also that's per CPU. A quad opteron could theoretically access 1024TB (Thats a PetaByte Right) of Virtual Memory Addresses.
I think it is fair to assume that they allowed for enough head room. Also you could always up the number of address lines in a future design if the need arose. It's been done before.
Don't forget that an IBM employee called Itanium a science project when IBM dropped there line of Itaniums.
The problem is and will remain that you don't get enough performance for what you pay for from Itanium.
When I can build a Athlon64 X2 cluster for under $500,000 that can place somewhere around 150 on the top 500 list. It's hard for itanium to compete pricewise.
Oh well, I love AMD for their work, but I really think they barked up the wrong tree. I would have supported whole heartedly an implementation of PPC 64-bit or even some grounded up archetecture just as much as I supported Itanium, but they decided to go the cheapest route, faking it for the sake of performance.
So what did AMD fake? The designed a 64 Bit processor with full backwards support to 32Bit code. That's nothing intel didn't do before remember 16/32Bit?
Also AMD Opteron technology was designed by some of the brightest people to ever come out of DEC. These are the guys that designed Alpha. In fact there are designs for the next generation Alpha that would compete with anything currently out there. Compaq just couldn't afford to pay the large cost of converting the FAB.
Given this, consider what a 2 or 3 Ghz Itanium could do.
Your comparison doesn't show the whole picture. You are listing clusters with 3 different interconnects. If you want a true comparison you need to compare clusters with all the same interconnects configured the same way. Also you are listing different architecture styles. The Opteron solution is a Cray with their own interconnect and specialized motherboard hardware.
Maybe the XT3 (or whatever it is called) sucks in comparison to myrinet or quadrics. (I wouldn't know)
Also with Xeon and newer Opteron processors proper cooling is an issue. If you aren't cooling the cpu properly it will slow itself down limiting performance.
Yeah I know all that stuff but you missed my point. My point is that his calculation for the number of cycles produced by AMD Athlon64 3400+ is incorrect. And that's still the case. No matter what you say his calculation still uses 3.4GHz instead of 2.2GHz. It is therefore wrong period. Trying to justify it by saying that he mean something that he didn't say is complete BS. An Athlon64 3400+ does not produce 3.4x10^9 cycles per second but 2.2x10^9 cycles per second. So the free number of cycles that he calculated is incorrect. Justifying his vodoo math with the claims you made doesn't make it correct.
Also electrically if you want to get down to it --- A cycle is a cycle is a cycle. It's a pulse of electricity with leading and falling edges that provides timing to a digital circuit. The difference between processors is what they are able to do during a cycle or multiple cycles.
"about 3.4 GHz worth of _P4_ cycles each second" there, happy? It is clearly what they meant...
That's just wrong. A Cycle is a Cycle and simple commands still run at one Cycle. The advantage Athlon64's have is that they can do complex commands in less cycles than the P4. Some processors also allow you to run multiple commands in parallel as well. But still a cycle is a cycle and in some applications clock speed is still king. Especially ones that need to be run serially and complex piping won't help because it can't maintain the required order of operation.
Yes but compiling an application to make use of parallel MPI is often necessary to distribute it. If I have an application that is serial, I still can't distribute it's load across a cluster running condor. I can send that specific application to a specific node to run and I can run multiple instances of the application but I cannot make the application run faster than a on a single box with similar hardware as the node. In fact it will run slightly slower because the process has to be moved from the master node to the node running it.
You will however get some advantage from cluster software that can migrate threads from a multithread application across a cluster.
So what makes the wikipedia the be all and end all of information? A collection of user contributed information. I would hardly use it as proof in an argument.
Suffice to say however AMD calculates it's PR rating really doesn't change the fact that it's to provide a comparison between Athlons and P4. I can guarrantee you if intel released a P4 processor that changed that correlation, AMD would change their PR rating on new processor to match it. Of course now that Intel itself is going to a PR rating of sorts that all changes.
That does not say that they base performance on comparison with a 1GHz Thunderbird anywhere. Thus you have provided nothing.
And I can guarrantee you there's a corrolation with the Performance Rating of 3400 and how it performs compared to a 3.4GHz P4. Whether AMD admits it or not, there's a reason why an Athlon64 3400+ Performs about the same or better than a P4 3.4GHz. AMD wants you to know that an Athlon64 3400+ runs about the same speed as a P4 3.4GHz so that the end user more easily compare these AMD Apples to Intel Oranges.
No that's not what AMD tells you. AMD tells you that a there 2.2GHz Processor performs about the same as a 3.4GHz P4. That makes the cycles calculation completely bogus as cycles from one processor don't compare with cycles from another.
I would agree that distributing the work load is cheaper in the long run
I think you have that backwards. Grid computing is cheaper upfront because you don't have the expensive of buying an extremely expensive serial supercomputer or a beowulf cluster. But it requires more administration, isn't as efficient powerwise. Thus you can end up spending more in the long run or just get no where near the same performance. (Unless you aren't paying the power bill for all the nodes)
Grid Computing makes sense for things like SETI online or DNETC where the cycles are donated. It also makes more sense if you want to Grid together big clusters because it allows you to leverage the high performance of several clusters for a combined project. However using your secretaries' computers at night really doesn't provide a great solution but it may look good to PHBs and shareholders.
Now say that we get about 3.4 GHz worth of cycles each second (that's what AMD tells you)
You should have used your mod points and not made a fool of yourself.
An Athlon64 3400+ does not run at 3.4GHz but 2.2GHz. Thus you're whole calculation of computer cycles is wrong. 3400+ is a PR rating comparing the performance of the Athlon64 to a Pentium4 of 3.4GHz.
Slashdot Mirror
Yeah that's the Mother Goose fairy tale version. Now how would the Brothers Grimm have written the story?
I stand by my argument that Viscalc made the IBM PC which in turn made Microsoft. Sure Microsoft has some smart people working for it. Sale of DOS to IBM before they owned it was an incredible piece of business geneous (if some what ethically challenged).
You missed my whole point. He was trying to say that Microsoft was some great innovator. I was just pointing out that not the case.
Okay thanks for calling me an idiot. I already know he was misquoted but he also implied something that wasn't true. So was a certain vice president who reportly said he wished he studied more latin in school while visiting latin america. That doesn't change the fact that both are internet versions of urban legends.
He worked at the Xerox research facility.
Hmm that's not really true. The spreadsheet made the IBM PC the business computer of choice and Microsoft was taken along for a ride because of the license agreement IBM made with them. It's IBMs fault we are stuck with such a buggy collection of stolen ideas that Windows is.
The original article is just a load of baloney. The guy asking is obviously clueless.
Really what has microsoft given us?
Did they develop the GUI?
No Xerox did. And no Apple didn't develop it.
Hey they sell alot of mice. Did they develop mice?
No Xerox did.
Hey they support Ethernet. Did they develop ethernet?
No Xerox did.
Did they develop the Browser?
No NCSA did.
Did they develop the Internet?
No Darpa did. Yes that's right it wasn't Al Gore.
Did they develop the word processor?
No.
Did they develop Desktop Publishing Software?
No
Did they develop Diagramming software like visio?
No they bought visio.
So tell me what did Microsoft give us other than a combination of other peoples technologies and ideas?
ROFL. AMD has support for most of those intel commands (SSE3,etc). They use the intel command set for 32 bit processing (with 3DNow added and the like). The optimization should work on both in most cases. Also if Intel had anyone working on support for AMD processors, it would be to slow them down because the sure aren't going to go out of their way to support AMD in their compiler.
You misunderstood me. I saying that is pretty obvious that Intel is doing something because you need to force ICC compiler to use proper optimization on an opteron. Whether or not, you still get the best optimization, I'm not sure but you could probably find out fairly easily by comparing the binary from code compiled on a Xeon and code compiled on an Opteron.
command line switches to turn on support for various things.
This won't be hard to prove. Pretty much anyone who wants fast 32Bit code uses the Intel Compilers, even on AMD. However it is a known fact that you need to force the compiler to use optimizations if an Intel Processor is not detected.
Opteron has 40 Bit Real Memory Address and 48 Bit Virtual Memory addressing.
That allows for 1TB of Real and 256TB of Virtual Memory Access --- not 64GBs.
Also that's per CPU. A quad opteron could theoretically access 1024TB (Thats a PetaByte Right) of Virtual Memory Addresses.
I think it is fair to assume that they allowed for enough head room. Also you could always up the number of address lines in a future design if the need arose. It's been done before.
True, they use Samsung's FAB but they still had to pay for the conversion. Samsung wasn't going to front the captial.
Man did you ever butcher that Wilfred Brimley quote from the Firm.
Don't forget that an IBM employee called Itanium a science project when IBM dropped there line of Itaniums.
The problem is and will remain that you don't get enough performance for what you pay for from Itanium.
When I can build a Athlon64 X2 cluster for under $500,000 that can place somewhere around 150 on the top 500 list. It's hard for itanium to compete pricewise.
Oh well, I love AMD for their work, but I really think they barked up the wrong tree. I would have supported whole heartedly an implementation of PPC 64-bit or even some grounded up archetecture just as much as I supported Itanium, but they decided to go the cheapest route, faking it for the sake of performance.
So what did AMD fake? The designed a 64 Bit processor with full backwards support to 32Bit code. That's nothing intel didn't do before remember 16/32Bit?
Also AMD Opteron technology was designed by some of the brightest people to ever come out of DEC. These are the guys that designed Alpha. In fact there are designs for the next generation Alpha that would compete with anything currently out there. Compaq just couldn't afford to pay the large cost of converting the FAB.
rank processor ghz (gflops / #procs) speed
#5 ppc970 2.2 (27910 / 4800) 5.81
#7 itanium2 1.4 (19940 / 4096) 4.86
#10 opteron 2.0 (15250 / 5000) 3.05
#20 xeon 3.06 (9819 / 2500) 3.92
Given this, consider what a 2 or 3 Ghz Itanium could do.
Your comparison doesn't show the whole picture. You are listing clusters with 3 different interconnects. If you want a true comparison you need to compare clusters with all the same interconnects configured the same way. Also you are listing different architecture styles. The Opteron solution is a Cray with their own interconnect and specialized motherboard hardware.
Maybe the XT3 (or whatever it is called) sucks in comparison to myrinet or quadrics. (I wouldn't know)
Also with Xeon and newer Opteron processors proper cooling is an issue. If you aren't cooling the cpu properly it will slow itself down limiting performance.
Yeah I know all that stuff but you missed my point. My point is that his calculation for the number of cycles produced by AMD Athlon64 3400+ is incorrect. And that's still the case. No matter what you say his calculation still uses 3.4GHz instead of 2.2GHz. It is therefore wrong period. Trying to justify it by saying that he mean something that he didn't say is complete BS. An Athlon64 3400+ does not produce 3.4x10^9 cycles per second but 2.2x10^9 cycles per second. So the free number of cycles that he calculated is incorrect. Justifying his vodoo math with the claims you made doesn't make it correct.
Also electrically if you want to get down to it --- A cycle is a cycle is a cycle. It's a pulse of electricity with leading and falling edges that provides timing to a digital circuit. The difference between processors is what they are able to do during a cycle or multiple cycles.
"about 3.4 GHz worth of _P4_ cycles each second"
there, happy? It is clearly what they meant...
That's just wrong. A Cycle is a Cycle and simple commands still run at one Cycle. The advantage Athlon64's have is that they can do complex commands in less cycles than the P4. Some processors also allow you to run multiple commands in parallel as well. But still a cycle is a cycle and in some applications clock speed is still king. Especially ones that need to be run serially and complex piping won't help because it can't maintain the required order of operation.
Yes but compiling an application to make use of parallel MPI is often necessary to distribute it. If I have an application that is serial, I still can't distribute it's load across a cluster running condor. I can send that specific application to a specific node to run and I can run multiple instances of the application but I cannot make the application run faster than a on a single box with similar hardware as the node. In fact it will run slightly slower because the process has to be moved from the master node to the node running it.
You will however get some advantage from cluster software that can migrate threads from a multithread application across a cluster.
So what makes the wikipedia the be all and end all of information? A collection of user contributed information. I would hardly use it as proof in an argument.
Suffice to say however AMD calculates it's PR rating really doesn't change the fact that it's to provide a comparison between Athlons and P4. I can guarrantee you if intel released a P4 processor that changed that correlation, AMD would change their PR rating on new processor to match it. Of course now that Intel itself is going to a PR rating of sorts that all changes.
That does not say that they base performance on comparison with a 1GHz Thunderbird anywhere. Thus you have provided nothing.
And I can guarrantee you there's a corrolation with the Performance Rating of 3400 and how it performs compared to a 3.4GHz P4. Whether AMD admits it or not, there's a reason why an Athlon64 3400+ Performs about the same or better than a P4 3.4GHz. AMD wants you to know that an Athlon64 3400+ runs about the same speed as a P4 3.4GHz so that the end user more easily compare these AMD Apples to Intel Oranges.
No that's not what AMD tells you. AMD tells you that a there 2.2GHz Processor performs about the same as a 3.4GHz P4. That makes the cycles calculation completely bogus as cycles from one processor don't compare with cycles from another.
I would agree that distributing the work load is cheaper in the long run
I think you have that backwards. Grid computing is cheaper upfront because you don't have the expensive of buying an extremely expensive serial supercomputer or a beowulf cluster. But it requires more administration, isn't as efficient powerwise. Thus you can end up spending more in the long run or just get no where near the same performance. (Unless you aren't paying the power bill for all the nodes)
Grid Computing makes sense for things like SETI online or DNETC where the cycles are donated. It also makes more sense if you want to Grid together big clusters because it allows you to leverage the high performance of several clusters for a combined project. However using your secretaries' computers at night really doesn't provide a great solution but it may look good to PHBs and shareholders.
Remind me to boycott that first customers airplanes. I really don't want to be used to alpha test a new aircraft.
Now say that we get about 3.4 GHz worth of cycles each second (that's what AMD tells you)
You should have used your mod points and not made a fool of yourself.
An Athlon64 3400+ does not run at 3.4GHz but 2.2GHz. Thus you're whole calculation of computer cycles is wrong. 3400+ is a PR rating comparing the performance of the Athlon64 to a Pentium4 of 3.4GHz.