Slashdot Mirror

To start off, there's an error in your question. There's no such thing as ``the IA-64 CPU.'' IA-64 is the instruction set architecture behind Itanium and the around-the-corner McKinley, and while I could list all the features and shortcomings behind it, it'd be a boring and technical explanation.

You can jump to conclusions, if you wish, by looking at Ace's Hardware SPECmine database, which contains all current SPEC2000 results. In case you don't know, those are the industry standard benchmarks. Here is a sample query of the SPEC2000 integer benchmarks, and here is a sample query of floating point results. As you can see, there are always better choices than the Itanium, and mostly from vendors who have been in the field of 64-bit processors for long, and probably with better prices too. You can never underestimate how important vendor reputation and experience is.

I alluded to the shortcomings of the instruction set of Intel's 64-bit offerings. Indeed, the poor performance can mostly be attributed to it (although the Itanium's poor design has helped a lot -- let's see whether McKinley fares better.) The truth is, Intel took VLIW and redressed it as EPIC; but VLIW has never been a panacea. Serial designs with out of order execution have been around longer, and worked great. The Itanium is a strict in-order processor, and the SPECint results show. And compiler technology isn't there yet; but Intel has acquired Alpha from Compaq and employed their compiler and MPU design team, widely reputed as the best in the field. Whether clever design will be able to mend the instruction set flaws, only time will tell. Indeed, the best strategy now is to wait a few years; seeing as how hardly a thousand Itanium system were actually purchased and paid for, most people seem to be taking this route. With McKinley the situation will be better for Intel, but not until the 3rd or 4th generation will the mass purchases begin, if ever.

Another common misconception is about the performance of Sun hardware. Just look at the values linked above from the SPEC benchmarks. Sun is known for scalable, reliable hardware, stuff you can depend on. But they're not the best performers by any account. The best designs come, undoubtedly, from the Alpha team; the upcoming EV8 would be the most advanced processor for a long time to come, if it weren't for Intel (who cancelled the EV8 project, obviously.) Unfortunately, Alpha is no longer a good buy, though not by technical merits. Having a vendor who will vanish sometime in the future is never a good strategy. Luckily, IBM's POWER series and HP-PA still remain, although the Precision Architecture will be discontinued some time in the future as well. IBM's Power4 design is the current king of the hill in SPEC scores, beating the closest competitors by a fair amount.

Finally, a great source of information is the Real World Tech forum, and the ``Silicon Insider'' columns by Paul DeMone, on the same website. (Paul also regularly reads the forum, and posts quite frequently too.)

To start off, there's an error in your question. There's no such thing as ``the IA-64 CPU.'' IA-64 is the instruction set architecture behind Itanium and the around-the-corner McKinley, and while I could list all the features and shortcomings behind it, it'd be a boring and technical explanation.

You can jump to conclusions, if you wish, by looking at Ace's Hardware SPECmine database, which contains all current SPEC2000 results. In case you don't know, those are the industry standard benchmarks. Here is a sample query of the SPEC2000 integer benchmarks, and here is a sample query of floating point results. As you can see, there are always better choices than the Itanium, and mostly from vendors who have been in the field of 64-bit processors for long, and probably with better prices too. You can never underestimate how important vendor reputation and experience is.

I alluded to the shortcomings of the instruction set of Intel's 64-bit offerings. Indeed, the poor performance can mostly be attributed to it (although the Itanium's poor design has helped a lot -- let's see whether McKinley fares better.) The truth is, Intel took VLIW and redressed it as EPIC; but VLIW has never been a panacea. Serial designs with out of order execution have been around longer, and worked great. The Itanium is a strict in-order processor, and the SPECint results show. And compiler technology isn't there yet; but Intel has acquired Alpha from Compaq and employed their compiler and MPU design team, widely reputed as the best in the field. Whether clever design will be able to mend the instruction set flaws, only time will tell. Indeed, the best strategy now is to wait a few years; seeing as how hardly a thousand Itanium system were actually purchased and paid for, most people seem to be taking this route. With McKinley the situation will be better for Intel, but not until the 3rd or 4th generation will the mass purchases begin, if ever.

Another common misconception is about the performance of Sun hardware. Just look at the values linked above from the SPEC benchmarks. Sun is known for scalable, reliable hardware, stuff you can depend on. But they're not the best performers by any account. The best designs come, undoubtedly, from the Alpha team; the upcoming EV8 would be the most advanced processor for a long time to come, if it weren't for Intel (who cancelled the EV8 project, obviously.) Unfortunately, Alpha is no longer a good buy, though not by technical merits. Having a vendor who will vanish sometime in the future is never a good strategy. Luckily, IBM's POWER series and HP-PA still remain, although the Precision Architecture will be discontinued some time in the future as well. IBM's Power4 design is the current king of the hill in SPEC scores, beating the closest competitors by a fair amount.

Finally, a great source of information is the Real World Tech forum, and the ``Silicon Insider'' columns by Paul DeMone, on the same website. (Paul also regularly reads the forum, and posts quite frequently too.)

To start off, there's an error in your question. There's no such thing as ``the IA-64 CPU.'' IA-64 is the instruction set architecture behind Itanium and the around-the-corner McKinley, and while I could list all the features and shortcomings behind it, it'd be a boring and technical explanation.

You can jump to conclusions, if you wish, by looking at Ace's Hardware SPECmine database, which contains all current SPEC2000 results. In case you don't know, those are the industry standard benchmarks. Here is a sample query of the SPEC2000 integer benchmarks, and here is a sample query of floating point results. As you can see, there are always better choices than the Itanium, and mostly from vendors who have been in the field of 64-bit processors for long, and probably with better prices too. You can never underestimate how important vendor reputation and experience is.

I alluded to the shortcomings of the instruction set of Intel's 64-bit offerings. Indeed, the poor performance can mostly be attributed to it (although the Itanium's poor design has helped a lot -- let's see whether McKinley fares better.) The truth is, Intel took VLIW and redressed it as EPIC; but VLIW has never been a panacea. Serial designs with out of order execution have been around longer, and worked great. The Itanium is a strict in-order processor, and the SPECint results show. And compiler technology isn't there yet; but Intel has acquired Alpha from Compaq and employed their compiler and MPU design team, widely reputed as the best in the field. Whether clever design will be able to mend the instruction set flaws, only time will tell. Indeed, the best strategy now is to wait a few years; seeing as how hardly a thousand Itanium system were actually purchased and paid for, most people seem to be taking this route. With McKinley the situation will be better for Intel, but not until the 3rd or 4th generation will the mass purchases begin, if ever.

Another common misconception is about the performance of Sun hardware. Just look at the values linked above from the SPEC benchmarks. Sun is known for scalable, reliable hardware, stuff you can depend on. But they're not the best performers by any account. The best designs come, undoubtedly, from the Alpha team; the upcoming EV8 would be the most advanced processor for a long time to come, if it weren't for Intel (who cancelled the EV8 project, obviously.) Unfortunately, Alpha is no longer a good buy, though not by technical merits. Having a vendor who will vanish sometime in the future is never a good strategy. Luckily, IBM's POWER series and HP-PA still remain, although the Precision Architecture will be discontinued some time in the future as well. IBM's Power4 design is the current king of the hill in SPEC scores, beating the closest competitors by a fair amount.

Finally, a great source of information is the Real World Tech forum, and the ``Silicon Insider'' columns by Paul DeMone, on the same website. (Paul also regularly reads the forum, and posts quite frequently too.)

To start off, there's an error in your question. There's no such thing as ``the IA-64 CPU.'' IA-64 is the instruction set architecture behind Itanium and the around-the-corner McKinley, and while I could list all the features and shortcomings behind it, it'd be a boring and technical explanation.

You can jump to conclusions, if you wish, by looking at Ace's Hardware SPECmine database, which contains all current SPEC2000 results. In case you don't know, those are the industry standard benchmarks. Here is a sample query of the SPEC2000 integer benchmarks, and here is a sample query of floating point results. As you can see, there are always better choices than the Itanium, and mostly from vendors who have been in the field of 64-bit processors for long, and probably with better prices too. You can never underestimate how important vendor reputation and experience is.

I alluded to the shortcomings of the instruction set of Intel's 64-bit offerings. Indeed, the poor performance can mostly be attributed to it (although the Itanium's poor design has helped a lot -- let's see whether McKinley fares better.) The truth is, Intel took VLIW and redressed it as EPIC; but VLIW has never been a panacea. Serial designs with out of order execution have been around longer, and worked great. The Itanium is a strict in-order processor, and the SPECint results show. And compiler technology isn't there yet; but Intel has acquired Alpha from Compaq and employed their compiler and MPU design team, widely reputed as the best in the field. Whether clever design will be able to mend the instruction set flaws, only time will tell. Indeed, the best strategy now is to wait a few years; seeing as how hardly a thousand Itanium system were actually purchased and paid for, most people seem to be taking this route. With McKinley the situation will be better for Intel, but not until the 3rd or 4th generation will the mass purchases begin, if ever.

Another common misconception is about the performance of Sun hardware. Just look at the values linked above from the SPEC benchmarks. Sun is known for scalable, reliable hardware, stuff you can depend on. But they're not the best performers by any account. The best designs come, undoubtedly, from the Alpha team; the upcoming EV8 would be the most advanced processor for a long time to come, if it weren't for Intel (who cancelled the EV8 project, obviously.) Unfortunately, Alpha is no longer a good buy, though not by technical merits. Having a vendor who will vanish sometime in the future is never a good strategy. Luckily, IBM's POWER series and HP-PA still remain, although the Precision Architecture will be discontinued some time in the future as well. IBM's Power4 design is the current king of the hill in SPEC scores, beating the closest competitors by a fair amount.

Finally, a great source of information is the Real World Tech forum, and the ``Silicon Insider'' columns by Paul DeMone, on the same website. (Paul also regularly reads the forum, and posts quite frequently too.)

Spec2000 int here and Spec2000 fp here.

highlights for int base:
790-POWER4 1.3Ghz
677-AthlonXP 1.6Ghz
648-Pentium4 2.0Ghz
621-Alpha 21264C 1.0Ghz
569-PA-RISC 8700 0.75Ghz
537-UltraSPARC III 1.05Ghz
461-PentiumIII 1.13Ghz
410-MIPS 14000 0.5Ghz
379-Itanium 0.8Ghz
99-PowerPC 604e 0.25Ghz

highlights for fp base:
1169-POWER4 1.3Ghz
960-Alpha 21264C 1.0Ghz
827-UltraSPARCIII 1.05Ghz
734-PentiumIV 2.0Ghz
701-Itanium 0.8Ghz
624-AthlonXP 1.6Ghz
581-PA-RISC 8700 0.75Ghz
463-MIPS 1400 0.5Ghz
340-PentiumIII 1.0Ghz
91-PowerPC 604e 0.25Ghz

The Itanium gets wacked pretty badly in the int scores, but does respectably well in the fp code which is far easier to extract parallelism from although it is beat by the POWER4, UltraSPARC III, and Alpha 21264. Even HP's 8700 isn't far behind.

Even in the Itanium's strongest field, floating point, its little 32bit cousin, the PentiumIV, smokes it.

The reason you don't see many reviews is because its a pretty slow chip, especially compared against the POWER4. Actually the reason you don't see reviews is because gamers who own web sites write reviews for the large readership of gamers who care about the fastest video card and CPU for their games. The market for an expensive 64bit shootout is pretty small. But its easy to afford a new video card or CPU.

Heck, Intel gives them out for free if the site words a 10% win for Intel as "wiping the floor" and a 10% win for AMD as a "narrow victory"...

Spec2000 int here and Spec2000 fp here.

highlights for int base:
790-POWER4 1.3Ghz
677-AthlonXP 1.6Ghz
648-Pentium4 2.0Ghz
621-Alpha 21264C 1.0Ghz
569-PA-RISC 8700 0.75Ghz
537-UltraSPARC III 1.05Ghz
461-PentiumIII 1.13Ghz
410-MIPS 14000 0.5Ghz
379-Itanium 0.8Ghz
99-PowerPC 604e 0.25Ghz

highlights for fp base:
1169-POWER4 1.3Ghz
960-Alpha 21264C 1.0Ghz
827-UltraSPARCIII 1.05Ghz
734-PentiumIV 2.0Ghz
701-Itanium 0.8Ghz
624-AthlonXP 1.6Ghz
581-PA-RISC 8700 0.75Ghz
463-MIPS 1400 0.5Ghz
340-PentiumIII 1.0Ghz
91-PowerPC 604e 0.25Ghz

The Itanium gets wacked pretty badly in the int scores, but does respectably well in the fp code which is far easier to extract parallelism from although it is beat by the POWER4, UltraSPARC III, and Alpha 21264. Even HP's 8700 isn't far behind.

Even in the Itanium's strongest field, floating point, its little 32bit cousin, the PentiumIV, smokes it.

The reason you don't see many reviews is because its a pretty slow chip, especially compared against the POWER4. Actually the reason you don't see reviews is because gamers who own web sites write reviews for the large readership of gamers who care about the fastest video card and CPU for their games. The market for an expensive 64bit shootout is pretty small. But its easy to afford a new video card or CPU.

Heck, Intel gives them out for free if the site words a 10% win for Intel as "wiping the floor" and a 10% win for AMD as a "narrow victory"...

Yes. There is a comparison of IA64 -vs- The Rest.

You can check out the details at spec.org,
but I've found Ace's Hardware Top 20 Review to be a more concise and readable version.

You can see that IBM's POWER4 has a fp peak of 1169,
while Intel's Itaniam has a fp peak of 701. In int performance, the Itanium is pretty dismal.

Ace's Hardware and Real World Tech have great discussions and articles on the downfalls of the Pentium 4 processor.

Read this.

..."The peak power consumption of the UltraSPARC IIe is 13W at 500 MHz, which minimizes cooling requirements for the chip and in turn a potential threat to server stability should the datacenter cooling/environmental equipment malfunction.
In fact, one of the primary barriers to broad acceptance of the Itanium by OEMs is its large 130W power appetite -- literally 10 times that of our own UltraSPARC IIe."

I am aware that cisc vs risc is a flamebait in alot of areas but risc was specifically designed to have less complexity in the chip in exchange for higher clock speeds. In many ( not all ) situations risc is usually %25-%40 faster on equilivant megahertz basis or can run at a slower megahertz and consume less power for a similar speed. X86 has alot of baggage in it and consumes alot more power then powerpc's, sparcs, and even alpha's and offers less performance or the same if its clocked ridiculously high. This would make it less hot then x86 cpu's running. I think the pentium4 and the athlon are almost an embarrassment to the electrical engineering community.

Most people are unlikely/too lazy to follow the comment link above so I've repeated the first part of the response below:

Yes, I read quite a few snide comments on slashdot about this server not being able to handle the load and ridiculing the article because of it. Frankly these people dont have a clue. It would be pointless in the extreme to operate a server 24/7 to handle the kind of loads the "slashdot effect" generates unless those kind of loads are the norm... A well tuned properly designed website/server should be equipped to handle 2 to 3 times its _expected_ peak traffic rate (which seems about what this server can do as its tuned now). It is a waste of money and hardware trying to do anymore than that imho as 99.9% of the time you would have alot of $$$ sitting totally idle in the form of hardware and bandwidth. Being a server admin myself, I think the guys here did an EXCELLENT job explaining what is involved with hosting a fairly high-traffic website effeciently. And I also think the server/programming for this site is well designed and does its job admirably (better than 99% of the websites on the internet at least). They did an excellent job of explaining the pros and cons

of different approaches to dynamic sites. Knocking them for getting nailed by slashdot isnt exactly productive, I would like to see ANY site which uses database generated content on a single thousand dollar server handle that kind of load (my guess is > 1000 requests per second at its peak from what I have heard from others who have been slashdotted)... Caching can only do so much :)

[Rest of comment follows, see link above for full version]

On the x86 side of things, we found that much of the inexpensive x86 hardware is targetted towards the home market and, accordingly, was not really suitable to the task at hand. Intel-based servers offered by OEMs did not offer much of a price break over our SPARC options, if any at all. As for the DIY market, there was a premium associated with the more high-end motherboards and other components we desired. Commodity hardware prices aside, a platform change would incur its own costs in the form of investments in software that would have to be replaced.

What a great webserver... I think an increase in bandwidth is in order.

Linux is like a wigwam - no windows, no gates, apache inside!

It's been an hour now, and it's still down (root URL too). If I ever read this article, I'll be sure not to do whatever they recommend.

doh, I wish I learned how to copy and paste properly

Here you can see how the total number of threads varies with the workload throughout the day. The maximum number of concurrent threads shown here is 117. The average is around 90 to 100 until later on in the day when the thread count drops down into the 80s and then finally around 75 by midnight. Resident memory size for the web application (the entire Java process) remained at 260 MB for the entire day. In fact, it has never really grown far beyond this size. The size remains relatively static because the caches are a fixed size and the applications do not grow over time (i.e. no memory leaks). The database acquires a fixed amount of memory upon initialization, and it is configured to use 512 MB. Currently, the server reports a total of roughly 1 GB of free, unallocated memory. So, we have quite a bit of room to grow with our new system.

I really wanna see todays numbers...

It would be interesting to see an update from them tomorrow with the same graphs as on the Servers in Practice page with today's data.

Their site is slowing down under the /. load.

Aces Hardware shows a different story. There, the nForce board from MSI seems to beat out the MSI K7T266 Pro 2 (KT266A chipset) in most of the benchmarks by a good margin. Not to say that I believe one over the other, but they do have widely different results.

I build myself a quiet PC about 18 months ago. It has been upgraded a bit since (only the fans - they do get lounder as they get older and a new fan is not that expensive). The only thing that I can hear right now is the IBM Deskstar 7200RPM harddrive. I seriously consider switching those out with one of the new Seagate ultra quiet Barracuda IV disks which is mentioned somewhere in this thread also. Here is what I have:

Case: I bought a Noisecontrol case. They aren't cheap, but they are pretty okay and have a "door" in front of the your CD-drive which takes away a lot of the noise. I'm pretty happy with the board

Fans: I'm using fans from Papst (they are mentioned somewhere here also. They are great and I highly recommend them!) As said before, I can only hear my harddisk now, if I pull the plug in the harddisk, I can't hear my PC, even with the case open it's practically quiet.

You could also watercool your PC, Koolance is looking pretty okay and their latest version have gotten pretty good reviews.

Some people says that noise is not a problem and they don't think the noise from the computer is a problem. I think they haven't tried to use a quiet PC. You get used to the noise that comes from you PC, which makes you more or less ignore it, but when you first try a quiet PC - you don't want to go back!

Besides that, I plan on upgrading my current Celeron with one of the new Athlon XP processors. I haven't upgraded yet, because boards with the new VIA KT266A chipset has just arrived and furthermore boards with the new Nvidia Nforce chipset is finally starting to arrive. The Nforce is currently looking pretty good imho. Take a look at this review.

Question: What is the most quiet CPU fan for an Athlon XP?

Take a look at the Grand Canyon demo I linked in one of my other replies. It does quite a bit of processing, including scene culling and LOD calculations, all in 100% pure Java (JDK 1.4).

Modern VMs are quite competitive with C++, and gcj should be close to a wash. See Binaries vs. Bytecodes for one interesting set of benchmarks, with source code. Java outperforms both gcc and msvc in different instances.

299,792,458 m/s...not just a good idea, its the law!

On Ace's Hardware, this subject is discussed thoroughly the last days. An interesting article can be found here. Some thoughts from this article:
- the component needed for proper protection of the cpu costs $0.85 (in quantities of 1K).
- "Obviously, Siemens used an external temperature probe and tried to pass it off as using the internal diode."
- The reaction time of the thermal diode is certainly not 1 degree/second: "At our worst case rise of 300C/sec, that translates to a response time of less than 1ms. No way would this result in a fried CPU if power off is immediate upon the signal occurring."

For a matter of fact, an engineer told a friend of mine it would be very difficult, if not impossible, to develop a thermal diode with such characteristics (1 degree/sec response time).

You can find the main thread of this article here.

On Ace's Hardware, this subject is discussed thoroughly the last days. An interesting article can be found here. Some thoughts from this article:
- the component needed for proper protection of the cpu costs $0.85 (in quantities of 1K).
- "Obviously, Siemens used an external temperature probe and tried to pass it off as using the internal diode."
- The reaction time of the thermal diode is certainly not 1 degree/second: "At our worst case rise of 300C/sec, that translates to a response time of less than 1ms. No way would this result in a fried CPU if power off is immediate upon the signal occurring."

For a matter of fact, an engineer told a friend of mine it would be very difficult, if not impossible, to develop a thermal diode with such characteristics (1 degree/sec response time).

You can find the main thread of this article here.

On Ace's Hardware, this subject is discussed thoroughly the last days. An interesting article can be found here. Some thoughts from this article:
- the component needed for proper protection of the cpu costs $0.85 (in quantities of 1K).
- "Obviously, Siemens used an external temperature probe and tried to pass it off as using the internal diode."
- The reaction time of the thermal diode is certainly not 1 degree/second: "At our worst case rise of 300C/sec, that translates to a response time of less than 1ms. No way would this result in a fried CPU if power off is immediate upon the signal occurring."

For a matter of fact, an engineer told a friend of mine it would be very difficult, if not impossible, to develop a thermal diode with such characteristics (1 degree/sec response time).

You can find the main thread of this article here.

The 1.7GHz Xeon processors that you use at work are not P4's though, although to be fair, the option to use Xeons should have been mentioned in the initial article. It is perhaps important to note though that the current Xeon (such as the one that you have at work) is essentially identical to the current P4 except for the different socket used and the fact that it has been validated for SMP use. The actual processor core is the same.

That being said, the price tags of the P4 and the Xeon shows a definite difference between the two chips. Combine that with the fact that Xeon boards are quite expensive, and for the time being they require fairly expensive RDRAM memory, and you get a rather costly setup. However, in situations where cost doesn't matter as much as performance (which is what the original article was trying to get at), the dual Xeon would definitely be the closest competitor to the AthlonMP.

Now, as to just how close of a competitor the Xeon is to the AthlonMP, well, if you read this article at Ace's Hardware (one of the very few hardware websites run by people who actually know what the heck they're talking about), you'll notice that dual 1.2GHz AthlonMP's match or beat the dual 1.7GHz Xeons pretty much across the board. The high-end workstation market is one area where AMD currently has Intel beat solidly in terms of raw performance, and pretty much trounces them in price/performance. Of course, that hasn't stopped Intel from maintaining 95%+ of the high-end workstation marketshare... but I digress.

I'm doubtful this will happen. Since JIT'ed bytecode is much faster than MSVC in many cases, they would have to change their optimization stategies to get their compiled .NET platform to be close to as fast.

There was an article on VectorC on Ace's Hardware a while ago:

http://www.aceshardware.com/Spades/read_news.php?p ost_id=55000348&keyword_highlight=VectorC

Very substantial performance gains were claimed. However, there was some concern about how well the benchmarks were set up:

http://www.aceshardware.com/board/general/read.php ?message_id=65013137

http://www.aceshardware.com/board/general/read.php ?message_id=65013223

In short, I'd take a very careful look at the benchmark code and methods of compiling before making conclusions about VectorC's performance. It might still be great; however, past benchmarks that have been floated have been questioned.

DISCLAIMER: I have not used VectorC, or directly examined the test code or assembly code generated for any of the tests. I have no direct assessment of the benchmarks - I'm pointing to others' assessments in response to another article about the compiler.

There was an article on VectorC on Ace's Hardware a while ago:

http://www.aceshardware.com/Spades/read_news.php?p ost_id=55000348&keyword_highlight=VectorC

Very substantial performance gains were claimed. However, there was some concern about how well the benchmarks were set up:

http://www.aceshardware.com/board/general/read.php ?message_id=65013137

http://www.aceshardware.com/board/general/read.php ?message_id=65013223

In short, I'd take a very careful look at the benchmark code and methods of compiling before making conclusions about VectorC's performance. It might still be great; however, past benchmarks that have been floated have been questioned.

DISCLAIMER: I have not used VectorC, or directly examined the test code or assembly code generated for any of the tests. I have no direct assessment of the benchmarks - I'm pointing to others' assessments in response to another article about the compiler.

There was an article on VectorC on Ace's Hardware a while ago:

http://www.aceshardware.com/Spades/read_news.php?p ost_id=55000348&keyword_highlight=VectorC

Very substantial performance gains were claimed. However, there was some concern about how well the benchmarks were set up:

http://www.aceshardware.com/board/general/read.php ?message_id=65013137

http://www.aceshardware.com/board/general/read.php ?message_id=65013223

In short, I'd take a very careful look at the benchmark code and methods of compiling before making conclusions about VectorC's performance. It might still be great; however, past benchmarks that have been floated have been questioned.

DISCLAIMER: I have not used VectorC, or directly examined the test code or assembly code generated for any of the tests. I have no direct assessment of the benchmarks - I'm pointing to others' assessments in response to another article about the compiler.

The power4 is kicking everybody's ass on SPEC 2000. 783 SPECint2000 base and 1098 SPECfp2000 base. Check out the comparisons on Ace's Hardware.

Here is the real link to the PC1066 review: http://www.aceshardware.com/Spades/read.php?articl e_id=45000217

I also recommend checking out their new PC1066 RDRAM review, which really shows shows you just how bandwidth dependant the Pentium 4 is.

I also recommend checking out their new PC1066 RDRAM review, which really shows shows you just how bandwidth dependant the Pentium 4 is.

I know there will be some of you who'll say "Mah mama told me to not buy no AMD." But for the rest of us, this will be a no-brainer. For the difference in chip prices you will be able to pay for most of the 4 GB of DDR that AMD mobos will support. Or maybe yo' mama told you to send your money to Rambus...

Compiled Java is actually slower than JITted Java bytecode. Want proof that Java might actually be as fast as C? This article at Ace's Hardware shows off some pretty interesting numbers.

According to this site, you are wrong about SS10 being limited to two CPU. Using 2 Ross double-CPU module, you could get up to four CPU on a SS10. I don't have any first hand experience with SMP on SS10, I am just researching it for my own box.

Also, SS10 CPU module start at 33 Mhz (that is what I have in mine right now).

Compaq sold Alpha to Intel, check here http://aceshardware.com/Spades/read_news.php?post_ id=50000292 for more info!

--Sorry about my bad English!--

It's cool that Intel hit the 2GHz mark, but all that clock speed is really going to waste for the moment.

Right now, you should go for a Thunderbird (AMD Athlon). Later on a Palomino (AMD next-generation Athlon) or the upcoming Northwood (0.13 micron Intel P4) is a better option.

Am I just saying this? No, take a look at this.

Binaries vs. Byte-codes

There are some benchmarks at Ace's hardware (search for binaries vs. bytecodes) that aren't perfect, but make some very valid points. Perhaps a /. based C++ vs. Java coding contest would be interesting. Any interesting problems come to mind? I'm sure we have the talent around here to get close to max performance with both languages.

If you like, you may even compare it to a real OO C-based language like Objective-C, but not C++, which is one crappy OO language.

I'd expect Objective-C to be a bit slower than C++ in general, given the method lookup overhead, and lack of generic types. I do like Objective-C, but I really don't think it'll ever gain mainstream acceptance. Garbage collection is stronger than reference counting as well. Plus (assuming you're talking about a traditional compiler like gcc) you lose the advantages of bytecode like dynamic compilation tuned for the exact CPU (say Athlon for instance) that you're using.

Please give hard evidence that Java is on par with C (within 10% of both CPU and RAM usage) for a significant, parity task.

I didn't make that claim, so I'm not sure why I'd want to do that. I'll stand by my claim WRT C++ (used as an OOL).

Spoken like someone who doesn't really understand OO. OO programming can be done in any language, even C, though certain things are made easier for the programmer if the language has OO support.

I don't recall saying it was impossible to do OO in C, but why would one want to? That's the point of having OO support built into the language (which is of course what I was referring to).

Uh, how about C?

Do you honestly feel C is as productive as Java? I certainly don't. Both its language features and standard library are seriously lacking. Plus you can't move your app to a new architecture or OS without recompiling.

You also have to work a lot harder to write good cross-platform C code, and there is no really worthwhile solution for cross-platform GUI development (at least compared to Java).

For those of us who lived through the C++ hype, you people who are riding the Java bandwagon are downright funny. They're all just languages, not ways of life.

I lived through the C++ hype...and several before that. C++, though, was such a major disappointment...it sounded great on paper, but actually implementing software with it was a severe pain. Bugs were often very subtle and difficult to find. Java has been a massive breath of fresh air by comparison, and it looks like eventually they'll add back in a couple things I miss (generics and operator overloading). In the meantime, there are preprocessors.

The C++ people said the very same things . . .

To a large extent they were right. Have you checked the ratio of C++ to C jobs lately? And that was in spite of how badly C++ sucked... Java, on the other hand, is a major step in the right direction.

186,282 mi/s...not just a good idea, its the law!

• Spades

• Sosnoski

• Jeanpaul

Already done.

They even have a compiler plugin for VC++ that generates fast binaries. Check this out.

The comment from the submitter makes it seem as if this is something new and important. This is actually really old news. Intel's 845 (Brookdale) chipset, which supports regular SDRAM and DDR has been in the works and well known for a while now and even benchmarked. Intel is probably initially only releasing it in the SDRAM flavor because of exclusive contracts with Rambus Inc. It is expected that in less than a year the DDR version will be out. Intel publically stated they are less than pleased with Rambus Inc. a long time ago.

As another poster mentioned the performance of the P4 with SDRAM is terrible. This is because the P4 was designed for memory with high bandwidth such as Rambus RAM and DDR as opposed to regular SD RAM. Tom's Hardware, perhaps the foremost Rambus hater, has an article on the 845 chipset and its very poor performance with SDRAM. Ace's Harware also has a summary.

All and all Intel's relationship with Rambus and use of Rambus RAM has been very foolish. The P-III was not designed to take advantage of the high bandwidth of Rambus so the improvements versus SDRAM were limited and the price of Rambus made VIA's competing SDRAM chipsets and AMD's solutions much more attractive. Now that Intel finally has a chip (P4) for which it makes sense to use Rambus RAM, Intel is slowly moving toward abandoning Rambus probably in favor of DDR. Although, given how hated Rambus is among RAM makers and the continued superior price-performance of DDR RAM, Intel's moving away from Rambus makes a lot of sense.

As Ace's Hardware discovered, the best way to optimize is to use Intel's latest beta compiler. But you can't use this compiler to compile Linux, because Linux uses gcc-specific extensions to C that the Intel compiler does not support.

Hey man, be fair, don't just take the graph in favour to your conclusion.

How about this, this and this?

Don't believe everything you read.

Assumed you believe everything in aceshardware, do you believe the graphs above? :D
&nbsp_
/. / &nbsp&nbsp |\/| |\/| |\/| / Run, Bill!

Hey man, be fair, don't just take the graph in favour to your conclusion.

How about this, this and this?

Don't believe everything you read.

Assumed you believe everything in aceshardware, do you believe the graphs above? :D
&nbsp_
/. / &nbsp&nbsp |\/| |\/| |\/| / Run, Bill!

Hey man, be fair, don't just take the graph in favour to your conclusion.

How about this, this and this?

Don't believe everything you read.

Assumed you believe everything in aceshardware, do you believe the graphs above? :D
&nbsp_
/. / &nbsp&nbsp |\/| |\/| |\/| / Run, Bill!

Look at the final results:

bestover2.gif

Now look at the place where the P4 shows the most improvement over the Athlon: the first data point, Flops 8, with the P4 using the Intel compiler and the Athlon using Microsoft's.

From the graph, the Pentium 4 clocks in at about 1140 flops while the Athlon gets only 900 flops.

But wait! We're forgetting something. You're running the Pentium 4 at a faster clock speed! For the love of crumbcake, normalize those values for clock speed, please!

Pentium 4: 1140 flops / 1.5 GHz = 760 flops/GHz
Athlon: 900 flops / 1.2 GHz = 750 flops/GHz

Now things are a bit more fair. Yes, with the absolute latest compiler from the maker of the processor, the Pentium 4 beats the Athlon in one of eight tests by a measly ten flops per gigahertz. With the latest compiler from some big software company, the Athlon beats the Pentium 4 in the other seven categories, hands down.

Don't believe everything you read.

http://www.aceshardware.com/Spades/list_news.php?c ategory=CPU#N50000287

Oh, BTW, be sure to check Itanium's SPECint2k nubmers, calling them "bad" would be a nice way to put it.

My question is, why? I didn't believe this when I read it earlier, and still not now. The Alpha is a viable architecture, proven and powerful. Intel could gain patents and technology, but I thought these issues were, for the most part, resolved years ago in a secret settlement. Intel bought DEC's fabs, DEC dropped lawsuits against Intel over the P5 and other 'things.'

So Ace's says that the newest compilation of SPEC outperforms the Itanium (Merced). I think the Merced has a lot of potential, in the fact that it isn't the cleanest design (more of a proof of concept and a 1st attempt to learn from), and that I doubt the Intel compiler is very up to par. Yet it still gives an impressive performance, if you believe SPEC.

IA-64 and Alpha are both viable at scientific applications, and from the latest Compaq compiler, they are relatively equal in their current forms. The Alpha wouldn't die because of the 3rd party consortium (forget name: APR?). And I've read claims that many of the best engineers left when Compaq bought DEC and moved to AMD amongst others. So, what is the major gain Intel would get from this?


-----------------------------------------

Well, Java is faster than C for computational stuff, as this Slashdot article (June 2000!) covers -- so if that isn't fast enough for you, then what is?

Ace's Hardware posted what I feel is the best review yet of the 760MP. Instead of benching games and business apps, they go for the true workstation-class pieces of software. Caligari TrueSpace, Maya, 3DStudio MAX, SPEC APC, Microstation and Visual C++. They also do a bit of video editing and encoding. But on top of the benchmarks, they also go into detail on the architecture behind the 760MP. They look at how AMD's use of point to point topology is better than Intel's use of a shared bus topology. There's a lot more stuff there, but in regards to space, I'll ley you all find out for yourself.