Look at how many trouble Intel has trouble admitting they are wrong and following AMD on something. Intel is so used to AMD copycating them on everything, they don't seem to know how to deal with the shoe being on the other foot.
So far Intel has followed AMD onto DDR memory, after dragging their feet for a year. Now it's happening with 64 bits. Next expect to see it with integrated memory controller, desktop dynamic power management(like quick 'n cool) and hypertransport. I'm sure when they come around the technologies might be similar, but they'll have some other name for it. Hopefully, Intel doesn't try the old Microsoft embrace and extend.
Huh?! Apple doesn't make CPUs, IBM makes the CPUs marketed as G5. Where do you think the G5 comes from?? Motorola was the one who made G4 and I believe IBM was still a second source on those. I don't remember the specifics of the arrangement.
Apache Jakarta: major in java world
on
2003: Year of Apache
·
· Score: 2, Insightful
The jakarta project (including ant which is now a top level apache project) has spawned a number of projects that are almost de facto in their area like struts, tomcat, cactus and many more.
Struts is an MVC framework that even includes tools to generate javascript validation code. This is a very common method to create a model 2 architecture J2EE site. Tomcat is the standard in open source servlet containers and often refered to as the reference implementation on a JSP and Servlet spec. Cactus is for unit testing J2EE components and is starting to become more popular.
If you intend to program java, then you should visit the Jakarta site.
As for who these people are, there are usually some pages on a project to mention that sort of thing. I'm most familiar with struts and their page for that sort of information is the volunteers page. Ant is already the defacto java build tool. Originally designed as a replacement for make, it's abilities can be extended using java classes.
Jakarta and Apache projects will continue to be a source of innovation, especially within the java world.
I've gone to AMD related articles and gotten Intel adds so many times I got used to it. I'm glad to see the opposite happening. I just hope in Q2 they start advertising so that AMD64 really takes off and 64 bit software will become very mainstream. The reason I say Q2 is that this is when the socket shakedown should be over and the windows alternative will be available.
Let's face it. Those of us on slashdot are the ones most likely to be utilizing the new 64 bitness.:)
There are a bunch of us techies that know their stuff in computers. The real way to do is to work together and make an employee owned version of a dell.
Here's how we do it:
1. we get a central group together that sets up a distribution center, gets the asian low cost, volume deals and then a JIT supply chain. The center assembles and ships the computers either to customers or our local reps. This entity would have a salary cap on "executives" so that there wouldn't be some big CEO, CFO, etc that takes the company profits. There would be an employee based oversight committee on major changes or those affecting executive salaries. All profits by this main entity would be put towards the business, marketing the main brand or profit sharing. News and technical information would be shared with all members.
2. In local comminities, those like us would be trained / certified to handle PC support. These reps would work somewhat like technical francises. There would be a shared repository for problems and solutions that would be shared. We'd quickly develop support best practices and our high level of knowledge would enshure customer loyalty. Certain support plans would cost more money.
We'd stick to some standardized PC choices to limit the number of configurations, like just 1 or 2 motherboards for each of the AMD/Intel lines.
Bottom line, if we worked together, it could really be something. Once it hit our stride it'd be like open source going against microsoft.
This google search turns up a link "Commentary: Working with Microsoft to plug a big hole" now the funny thing is that this morning the link was called "AMD grabs key security advantage" and that's also in the title bar of the page and in big caption. Interesting how that was replaced with the subtitle that downplays a big win for AMD. I had trouble even finding the link which was obvious this morning. Things that make you go 'hmm.
So the implication is that Intel is only supporting this security feature on enterprise servers (Itanium), while AMD is supporting security on desktops and servers. Combine this with "cool and quiet" in desktop chips, like the mobile chip power saving technology, and 64 bit processing and AMD has quite a value proposition.
So the implication is that Intel is only supporting this security feature on enterprise servers (Itanium), while AMD is supporting security on desktops and servers.
I doubt I will see 128 bit computing in our lifetime, but then again I might live longer than I expect. Why would we need it? The memory addressing situation will take probably over 100 years, if you think of the amount of memory doubling every 2 years, to take up that next 64 bits of address space, that's about 128 years, right?
So, short of some new technology requirements or ram moving much faster (it will probably advance slower) it doesn't sound likely.
One of the things I find really amusing is that everyone is using AMD originated technology except intel. Transmeta Efficeon, Apple's G5, AMD Athlon 64/Opteron, Nvidia Athlon XP chipsets and the Microsoft Xbox all use hypertransport.
That's got to make you think that AMD isn't just the technology follower like they used to be.
I do find that having multiple desktops is extremely helpful and it's a feature I always miss on windows. The key advantage it gives you is saving time when juggling multiple projects and you have to do a context switch between them. You keep them in their seperate desktops and pick up right where you left off. To some degree, you can accomplish the same with multiple monitors.
One of the advantages of the dual monitor setup for a web developer over even a larger single monitor is for testing how something looks at multiple resolutions.
I think it would be useful to have a discussion amongst us (which is more trustworthy than some report by monitor and video card companies) about how useful dual monitor setups are and if it makes a difference if the monitors are CRT or LCD (or even plasma). Yep, some roundup would be cool, a duel of the duals.
Note that for $2800 or so, you can even get 42" plasma screens these days limited to 1024x768 resolution. If someone has one of these, how does it stack up? Seems like it wouldn't be as useful to have such a large screen constrained to that resolution.
Oops I meant it was a dual opteron beating a dual xeon by almost double (which was just a bit above double the opteron's Mhz). All those 2s, I accidently multiplied one. Given the tremendous scaling of these processors, I'm not suprised to hear someone else mention that a dual opteron beat a quad xeon. I imagine thats where the quad part came from.
http://www.aceshardware.com/read.jsp?id=60000253 has a cooling technology that allowed them to overclock to a 2.8 Ghz Athlon FX. It was pretty impressive stuff, especially how well Age of Mythology did, even against the non-shipping P4 Emergency Edition.
I can't wait until theres 64 bit games for this sort of thing. Of course, the first to be released will be Unreal Tournament. Oh yahh!! I know I'll own at least one of the AMD64 computers within the next year!
I'd love to have a new AMD64 for my application server. There were benchmarks on extreme tech showing a 1.6 Ghz dual opteron beating a 2.8 Ghz quad xeon by gigantic margins (almost double). So when these Athlon 64 processors trickle down to the same clocked Opterons, it should start to shake up the server market even more. Especially given upcoming backing from Sun: http://www.theinquirer.net/?article=11772
To REALLY drive my point home, what is the icon for this article?? It's Intel, NOT AMD. So even in their own story, AMD finds itself in Intel's shadow, even when they are about to break into major new territory for a chip meant to be a mainstream desktop. Sure there's Opteron, G5, Alpha, UltraSparc, etc that might be used for desktop, but this will be a whole new ball game for windows. Plus this will be the first really cheap 64 bit high performance Linux machines (within 6 months when prices drop). Even now Opteron has topped the TCP price/performance benchmarks with a MULTI-processor machine beating out a dell single processor. You know multi-processor machines are generally more expensive per processor, so this is remarkable.
I saw an application server benchmark where a dual 1.6 Ghz Opteron did almost twice as good as a dual 2.8 Ghz Xeon, which is at a little more than half the Mhz! Talk about impressive.
The story itself was written with an obvious Intel bias. That's easy to tell for several reasons:
They focus on the FUD: don't buy that Athlon 64
They point to the Intel price roadmap, inferring somehow that Intel will be cheaper
mention of people who thought Athlon 64s would be supreme, as if he really WANTS to say "you're wrong"
Athlon 64 is existing technology and it's kin, the Opteron, was released back in April. So let's talk Intel x86-64 derivatives when they're on the books. It's certainly not why you shouldn't buy an Athlon 64. Go home FUDSTER. Come back when you got something with at least a launch date. Granted I read the Inquirer every day, but your article could have been more balanced.
AMD has always provided a better value at a given performance level and will continue to do so. You can't tell me that if an Intel part has 64 bit and comparable performance that it will be less expensive. So what if a 2.8 Ghz Pentium 4 will be $178. You'll probably have an Athlon 64 3200+ for $150 or less at that point.
Sounds like you're an Intel fanboy as much as I'm an AMD fanboy. If they had cards, I'd be a card carrying fanboy.:) Even if you don't like AMD, you have to admit that they're the only thing standing in the way of higher prices and slower introductions. Otherwise, we'd be talking about our new 1.6 Ghz Pentium 4 with expensive Rambus memory and how FAST it was and how cheap at only $800. I doubt Celeron would have ever existed without competition. So if AMD falls, we will ALL pay for it. Don't forget that Intel is one of those companies like Microsoft that would love to tell YOU, the customer what you can have instead of asking you what you want (like AMD). Granted AMD sometimes has their head up their butt, especially in marketing, but it's very impressive they're surviving where so many have perished. The only real competitor standing out of about 15 in x86! Via and Transmeta don't have any sort of serious presence.
Re:Not an Athlon64, but an Opteron
on
AMD64 Preview
·
· Score: 1
What you're not considering is that there is an Athlon 64 that IS dual channel and that's the FX one. So expect it to be a bit better performance than Opteron because it will likely not require ECC memory.
I started with basic and soon after was doing 1st edition rules. I developed quite an affinity for 1st edition and liked it best. I was not so thrilled with second edition rules. While I tend to be a DM and know the value of game balance, I didn't like all the limits on spells. Unlike most DM's I had no trouble in keeping my players challenged well into high levels, so I didn't need the limits. After all, if you post upper limits on damage, what is the point to being 40th level? I didn't see too much to salvage my opinion of 2nd edition rule book and did what I could to avoid it. In general 2nd edition rules would be the low point of D&D.
I was also reluctant to learn yet another new D&D system, but once I got into 3rd edition rules I felt as if I had all been playing D&D wrong for the last 20 years. Before 3rd edition, I just accepted that this was how it is done. Now I can see that rules we have been using since the begnning of time were needlessly complicated. Like having armor class being the unadjusted roll that is needed to hit, instead of using THACO! Spell resistances and damage resistances are also done well. It's so mush superior to "needs +1 weapon to hit". Breaking down types of AC bonuses and simply explaining that they don't stack. Simple Simple. Classes are more free form now with skills and feats that allow you to customize your character a bit more, even within the boundaries of classes. Somehow I don't even mind the spell limits. It's seems to be a more organic part of the system and not just a band aid, like 2nd edition.
So cleary 3rd edition is by far the best yet. I think the best way I can desribe it is if someone came up with a new keyboard design that rearranged the letters in a way that made more sense and once you got used to it doubled your typing speed.
If we take two points of performance data, we should be able to extropolate hammer performance as far as PR rating.
So if we take the quake score listed and assume that means a 800 mhz clawhammer is a 1600+ and combine that with earlier projections that hammer would be release on Q4 at about 2 Ghz as a 3400+, that gives us the following:
y+ 800x = 1600 y+ 2000x = 3400
Solving the equations gives you: y=400 x=1.5
So clawhammer mhz versus P4 mhz could be along the lines of:
The upcoming mustang athlon will have similarly large caches and I'm sure it will be much cheaper and available at higher speeds. It should also have a 16 way associative cache and will do very well once the SMP motherboards are released in the 2nd half of the year. Even with them cutting prices in half, it is still outrageous for a 700 Mhz chip today.
I don't recall if it was the thunderbird or mustang Athlons, but I do remember that they were going to have 16 way associative cache. Besides the AMD 760MP boards, I think there were also plans by Micron to create multi-processor samurai chipsets with DDR DRAM support.
To answer a couple questions I saw other people post, here is some more info. Duron will use a new motherboard type known as socket A. The chipset support will be coming from ALI and Via. The Via chipset is the KZ133 which is the followup to Via's Slot A chipset, KX133. Many of the board today for slot A use the KX133. ALI is also working on motherboards that will have support for slot A, socket A and DDR that should be released in Q3. For a good site to keep up on AMD, check out www.amdzone.com or www.theregister.com or hardware sites like www.tomshardware.com, www.acesharedware.com, www.ebnews.com And to the guy asking about Cryix, they have out a new chip called the cyrix III (codename was joshua) and it will probably be cheap but is not even close to intel or AMD on performance. It will most likely only be used for things on the scale of a network appliance.
Look at how many trouble Intel has trouble admitting they are wrong and following AMD on something. Intel is so used to AMD copycating them on everything, they don't seem to know how to deal with the shoe being on the other foot.
So far Intel has followed AMD onto DDR memory, after dragging their feet for a year. Now it's happening with 64 bits. Next expect to see it with integrated memory controller, desktop dynamic power management(like quick 'n cool) and hypertransport. I'm sure when they come around the technologies might be similar, but they'll have some other name for it. Hopefully, Intel doesn't try the old Microsoft embrace and extend.
"Apple's CPUs are more popular than IBM's".
Huh?! Apple doesn't make CPUs, IBM makes the CPUs marketed as G5. Where do you think the G5 comes from?? Motorola was the one who made G4 and I believe IBM was still a second source on those. I don't remember the specifics of the arrangement.
The jakarta project (including ant which is now a top level apache project) has spawned a number of projects that are almost de facto in their area like struts, tomcat, cactus and many more.
Struts is an MVC framework that even includes tools to generate javascript validation code. This is a very common method to create a model 2 architecture J2EE site. Tomcat is the standard in open source servlet containers and often refered to as the reference implementation on a JSP and Servlet spec. Cactus is for unit testing J2EE components and is starting to become more popular.
If you intend to program java, then you should visit the Jakarta site.
As for who these people are, there are usually some pages on a project to mention that sort of thing. I'm most familiar with struts and their page for that sort of information is the volunteers page. Ant is already the defacto java build tool. Originally designed as a replacement for make, it's abilities can be extended using java classes.
Jakarta and Apache projects will continue to be a source of innovation, especially within the java world.
Paul Sundling
I've gone to AMD related articles and gotten Intel adds so many times I got used to it. I'm glad to see the opposite happening. I just hope in Q2 they start advertising so that AMD64 really takes off and 64 bit software will become very mainstream. The reason I say Q2 is that this is when the socket shakedown should be over and the windows alternative will be available.
:)
Let's face it. Those of us on slashdot are the ones most likely to be utilizing the new 64 bitness.
Paul
There are a bunch of us techies that know their stuff in computers. The real way to do is to work together and make an employee owned version of a dell.
Here's how we do it:
1. we get a central group together that sets up a distribution center, gets the asian low cost, volume deals and then a JIT supply chain. The center assembles and ships the computers either to customers or our local reps. This entity would have a salary cap on "executives" so that there wouldn't be some big CEO, CFO, etc that takes the company profits. There would be an employee based oversight committee on major changes or those affecting executive salaries. All profits by this main entity would be put towards the business, marketing the main brand or profit sharing. News and technical information would be shared with all members.
2. In local comminities, those like us would be trained / certified to handle PC support. These reps would work somewhat like technical francises.
There would be a shared repository for problems and solutions that would be shared. We'd quickly develop support best practices and our high level of knowledge would enshure customer loyalty. Certain support plans would cost more money.
We'd stick to some standardized PC choices to limit the number of configurations, like just 1 or 2 motherboards for each of the AMD/Intel lines.
Bottom line, if we worked together, it could really be something. Once it hit our stride it'd be like open source going against microsoft.
Here is the link to the google search that turned up the strangely renamed article. I must need sleep, making the same mistake again.
http://news.google.com/news?hl=en&ie=ISO-8859-1&sc oring=d&edition=us&q=amd+overflow&btnG=Search+News
This google search turns up a link "Commentary: Working with Microsoft to plug a big hole"
now the funny thing is that this morning the link was called "AMD grabs key security advantage" and that's also in the title bar of the page and in big caption. Interesting how that was replaced with the subtitle that downplays a big win for AMD. I had trouble even finding the link which was obvious this morning. Things that make you go 'hmm.
AMD grabs key security advantage. The article says it all.
So the implication is that Intel is only supporting this security feature on enterprise servers (Itanium), while AMD is supporting security on desktops and servers. Combine this with "cool and quiet" in desktop chips, like the mobile chip power saving technology, and 64 bit processing and AMD has quite a value proposition.
http://cbs.marketwatch.com/news/story.asp?guid=%7B 605678E9-C043-4B7E-94C7-E693D2BBA696%7D&siteid=goo gle&dist=google
So the implication is that Intel is only supporting this security feature on enterprise servers (Itanium), while AMD is supporting security on desktops and servers.
I doubt I will see 128 bit computing in our lifetime, but then again I might live longer than I expect. Why would we need it? The memory
addressing situation will take probably over 100 years, if you think of the amount of memory doubling every 2 years, to take up that next 64 bits of address space, that's about 128 years, right?
So, short of some new technology requirements or ram moving much faster (it will probably advance slower) it doesn't sound likely.
I think you mean value object instead of view object. Value Object is actually one of the design patterns that's expected fot this sort of use.
One of the things I find really amusing is that everyone is using AMD originated technology except intel. Transmeta Efficeon, Apple's G5, AMD Athlon 64/Opteron, Nvidia Athlon XP chipsets and the Microsoft Xbox all use hypertransport.
That's got to make you think that AMD isn't just the technology follower like they used to be.
I do find that having multiple desktops is extremely helpful and it's a feature I always miss on windows. The key advantage it gives you is saving time when juggling multiple projects and you have to do a context switch between them. You keep them in their seperate desktops and pick up right where you left off. To some degree, you can accomplish the same with multiple monitors.
One of the advantages of the dual monitor setup for a web developer over even a larger single monitor is for testing how something looks at multiple resolutions.
I think it would be useful to have a discussion amongst us (which is more trustworthy than some report by monitor and video card companies) about how useful dual monitor setups are and if it makes a difference if the monitors are CRT or LCD (or even plasma). Yep, some roundup would be cool, a duel of the duals.
Note that for $2800 or so, you can even get 42" plasma screens these days limited to 1024x768 resolution. If someone has one of these, how does it stack up? Seems like it wouldn't be as useful to have such a large screen constrained to that resolution.
Paul Sundling
Oops I meant it was a dual opteron beating a dual xeon by almost double (which was just a bit above double the opteron's Mhz). All those 2s, I accidently multiplied one. Given the tremendous scaling of these processors, I'm not suprised to hear someone else mention that a dual opteron beat a quad xeon. I imagine thats where the quad part came from.
http://www.aceshardware.com/read.jsp?id=60000253
has a cooling technology that allowed them to overclock to a 2.8 Ghz Athlon FX. It was pretty impressive stuff, especially how well Age of Mythology did, even against the non-shipping P4 Emergency Edition.
I can't wait until theres 64 bit games for this sort of thing. Of course, the first to be released will be Unreal Tournament. Oh yahh!! I know I'll own at least one of the AMD64 computers within the next year!
I'd love to have a new AMD64 for my application server. There were benchmarks on extreme tech showing a 1.6 Ghz dual opteron beating a 2.8 Ghz quad xeon by gigantic margins (almost double). So when these Athlon 64 processors trickle down to the same clocked Opterons, it should start to shake up the server market even more. Especially given upcoming backing from Sun:
http://www.theinquirer.net/?article=11772
To REALLY drive my point home, what is the icon for this article?? It's Intel, NOT AMD. So even in their own story, AMD finds itself in Intel's shadow, even when they are about to break into major new territory for a chip meant to be a mainstream desktop. Sure there's Opteron, G5, Alpha, UltraSparc, etc that might be used for desktop, but this will be a whole new ball game for windows. Plus this will be the first really cheap 64 bit high performance Linux machines (within 6 months when prices drop). Even now Opteron has topped the TCP price/performance benchmarks with a MULTI-processor machine beating out a dell single processor. You know multi-processor machines are generally more expensive per processor, so this is remarkable.
I saw an application server benchmark where a dual 1.6 Ghz Opteron did almost twice as good as a dual 2.8 Ghz Xeon, which is at a little more than half the Mhz! Talk about impressive.
yah right, an intel chip that's better and cheaper? :)
Step away from the crack pipe.
That's like expecting to find a SONY that's cheaper and better than an AIWA. Until Joe User knows has even heard of AMD that will never happen.
bias. That's easy to tell for several reasons:
Athlon 64 is existing technology and it's kin, the Opteron, was released back in April. So let's talk Intel x86-64 derivatives when they're on the books. It's certainly not why you shouldn't buy an Athlon 64. Go home FUDSTER. Come back when you got something with at least a launch date. Granted I read the Inquirer every day, but your article could have been more balanced.
AMD has always provided a better value at a given performance level and will continue to do so. You can't tell me that if an Intel part has 64 bit and comparable performance that it will be less expensive. So what if a 2.8 Ghz Pentium 4 will be $178. You'll probably have
an Athlon 64 3200+ for $150 or less at that point.
Sounds like you're an Intel fanboy as much as I'm an AMD fanboy. If they had cards, I'd be a card carrying fanboy.
What you're not considering is that there is an
Athlon 64 that IS dual channel and that's the FX one. So expect it to be a bit better performance than Opteron because it will likely not require ECC memory.
I guess you have to pick a more interesting article on the same topic or know someone. :(
I started with basic and soon after was doing 1st edition rules. I developed quite an affinity for 1st edition and liked it best. I was not so thrilled with second edition rules. While I tend to be a DM and know the value of game balance, I didn't like all the limits on spells. Unlike most DM's I had no trouble in keeping my players challenged well into high levels, so I didn't need the limits. After all, if you post upper limits on damage, what is the point to being 40th level? I didn't see too much to salvage my opinion of 2nd edition rule book and did what I could to avoid it. In general 2nd edition rules would be the low point of D&D.
I was also reluctant to learn yet another new D&D system, but once I got into 3rd edition rules I felt as if I had all been playing D&D wrong for the last 20 years. Before 3rd edition, I just accepted that this was how it is done. Now I can see that rules we have been using since the begnning of time were needlessly complicated. Like having armor class being the unadjusted roll that is needed to hit, instead of using THACO! Spell resistances and damage resistances are also done well. It's so mush superior to "needs +1 weapon to hit". Breaking down types of AC bonuses and simply explaining that they don't stack. Simple Simple. Classes are more free form now with skills and feats that allow you to customize your character a bit more, even within the boundaries of classes. Somehow I don't even mind the spell limits. It's seems to be a more organic part of the system and not just a band aid, like 2nd edition.
So cleary 3rd edition is by far the best yet. I think the best way I can desribe it is if someone came up with a new keyboard design that rearranged the letters in a way that made more sense and once you got used to it doubled your typing speed.
If we take two points of performance data, we
should be able to extropolate hammer performance
as far as PR rating.
So if we take the quake score listed and assume
that means a 800 mhz clawhammer is a 1600+ and
combine that with earlier projections that hammer
would be release on Q4 at about 2 Ghz as a 3400+,
that gives us the following:
y+ 800x = 1600
y+ 2000x = 3400
Solving the equations gives you:
y=400 x=1.5
So clawhammer mhz versus P4 mhz could be along
the lines of:
400 + 1.5 clawhammer mhz = P4 mhz
The upcoming mustang athlon will have similarly large caches and I'm sure it will be much cheaper and available at higher speeds. It should also have a 16 way associative cache and will do very well once the SMP motherboards are released in the 2nd half of the year. Even with them cutting prices in half, it is still outrageous for a 700 Mhz chip today.
I don't recall if it was the thunderbird or mustang Athlons, but I do remember that they were going to have 16 way associative cache. Besides the AMD 760MP boards, I think there were also plans by Micron to create multi-processor samurai chipsets with DDR DRAM support.
To answer a couple questions I saw other people post, here is some more info. Duron will use a new motherboard type known as socket A. The chipset support will be coming from ALI and Via. The Via chipset is the KZ133 which is the followup to Via's Slot A chipset, KX133. Many of the board today for slot A use the KX133. ALI is also working on motherboards that will have support for slot A, socket A and DDR that should be released in Q3. For a good site to keep up on AMD, check out www.amdzone.com or www.theregister.com or hardware sites like www.tomshardware.com, www.acesharedware.com, www.ebnews.com And to the guy asking about Cryix, they have out a new chip called the cyrix III (codename was joshua) and it will probably be cheap but is not even close to intel or AMD on performance. It will most likely only be used for things on the scale of a network appliance.