2005 Called they want their list of bragging rights back. Oh and hypertransport is mostly technology that AMD bought from Digital along with parts of the Alpha team. They get some credit for bringing their version to market first, but it's hardly like they came up with the idea for Hypertransport out of thin air. As for x86-64, AMD brought it to market first, but Intel had internal builds of 64 bit enabled X86 chips around for some time, which is why they could bolt it onto the P4 and not require a brand new microarchitecture.
Of course, what people forget most about x86-64 is that Microsoft was the big proponent of a 64 bit x86 chip since it meant they could start moving into larger scale data server applications. The irony is that EPIC, for all the hate it gets in this website, is dominated by Linux and other UNIX derivatives where MS is almost completely absent.
I don't think BD is a failure because it can't beat Sandy Bridge in every benchmark. I think it's a failure because it is a *massive* (2 BILLION transistor) chip with very large (315 mm^2) die and a LARGE power envelope that still doesn't beat a 2600K even with higher clockspeeds and at using highly multithreaded code where BD is supposed to be superior.
If AMD had come out with a chip that had the same performance as BD but was much smaller and more power efficient (basically the chip that AMD promised rather than the one they delivered) then I'd be calling this a big success.
As it stands, AMD is not even *price* competitive with BD unless they slash prices even further. They are trying to sell the cut-down 6 core BD for the exact same price as the 6 core Phenom II that we have already seen beats the 8 core FX in a decent number of benchmarks! The 8 core FX is more expensive than a 2500K, but the 2500K wins in most benchmarks that people really care about in this price range (games) *and* uses a whole lot less power to boot.
buy a 6 core Phenom II, overclock it, and pray that AMD can stay around long enough to fix this mess.
Go check the techreport review and look at the price/performance chart: The 2500K has slightly higher performance, lower price, and *much* better energy efficiency.
I feel bad for AMD's engineers. I *don't* feel bad for the marketing hype machine that has been relying on "geek-cred" from sites like Slashdot and the usual David vs. Goliath myth to get unearned praise. If Intel had come out with Bulldozer instead of AMD, we'd be calling this Prescott version 2.0.
Phoronix has issues because the guy running it likes to oversensationalize and hyperbolize to get traffic and ad revenue... which is to say it's exactly like Slashdot with the difference being that Phoronix actually does some useful work and there are valuable facts that Phoronix discovers.
The (multiple) kernel power bugs are a very real problem affecting a large number of Linux users and Phoronix helped to shine a light on the issue and at least get the word out about work-arounds. I don't hang on everything that Phoronix publishes, but dismissing it just shows that you want to remain wilfully ignorant about real issues surrounding Linux so that you can appear 'l33t' to your friends.
P.S. --> Since Slashdot formatting is whack, the above results should show the 1.7 Ghz P4 with a 382 Mflop Linpack score when "optimized" compared to Nvidia's published results of 309 Mflops.
Mathematically, the P4 has a 70% clockspeed advantage with only a 23.6% performance advantage, but remember how crappy the IPC on the old P4 was, and remember that the P4 is a single core CPU vs. Quad Cores for Nvidia.
OK, the idea behind ARM is that it is "fast enough" for desktop and notebook PCs. Well, if that's the case, then a P4 is also "fast enough" and you should consider not buying anything newer.
Why am I saying that? Let's look at one benchmark that *is* multi-core ready and that Nvidia kindly ran on the upcoming Kal-El quad-core systems: Linpack.
Now I know Linpack is not a perfect benchmark, but it does do a decent job of showing off number-crunching power and it is multi-core capable and there are results from a wide range of architectures.
I'm going to assume that Nvidia will go out of its way to make sure the code is optimized for benchmarks that it posts as part of a marketing push.
So a QUAD CORE Arm architecture is still lagging behind a P4, and while the P4 has a clock speed advantage, it's a lot smaller than is justified by the difference in performance considering the Nvidia chip has 4 cores compared to a single-core P4.
Now, I'm not saying that Kal-El won't be awesome for use on tablets and smaller devices, but on a desktop or even a notebook, don't go around expecting miraculous performance.
Holy crap! Van Drashek has come to Slashdot! He even has a 5 digit UID! You keep working on whatever quasi-functional AI program that spews out all that crap is! One of these decades you might be able to spew out a halfway coherent troll post.
The first few posts might be trollish but look at the original article. It's a puff-piece wrapping AMD in the open source flag as a paragon of virtue when the truth is far less rosy.
AMD enjoys a (largely unearned) reputation on Slashdot as being the scrappy underdogs who want to save the world for Open Source or something like that. People forget that AMD is (or was) a multi-billion company that has no problems with getting patents, cozying up with Microsoft (see Jerry Sanders testifying in favour of MS at the anti-trust trial... ironic), or locking up its IP in the video card area. Sure they dump partial sets of documentation several months after releasing a new card, but with that level of support I have no reason to upgrade from a 3 year old Nvidia card since the shiny new AMD card won't work any better.
I *want* AMD to have real open source drivers that give great support for their hardware... basically what Intel already does right now. However, congratulating AMD and holding them up as superior to everyone else when they are not is not the right way to accomplish this goal.
Aside from the fact that you are completely wrong, I was waiting for you to say how horrible the US is and how we need to be more like Europe.... (where first to file has been the rule for decades).
Then I was waiting for you to say that first to file was dreamed up by evil Republicans who hate other countries to cheat the world of innovation.... by applying the exact same rules to the US that are used in most of the rest of the world.
I eagerly await the conclusion of your hilariously wrong, yet sadly modded +5 post.
The exact same slashbots who are screaming about how unfair it is that teachers can friend students on Facebook will be the same ones screaming at the top of their lungs about Big Brother and the police state violating "privacy" rights when some stupid student posts pictures of himself committing a crime and the teacher reports it to the cops.....
It's all part of the I want all of my "rights" without ever having any consequences to my actions philosophy of Slashdot.
Please inform me where I can go to use the patented Intel time travelling technology Haha an anti-Intel snarky comment on Slashdot... way to speak truth to power. What's funny is that if I actually told you I had a time machine in 2010 that could bring you the fastest CPU available from AMD at the end of 2011 and you only had to pay a few hundred bucks for my service, you'd probably jump at the chance... which is exactly what Intel effectively did with Gulftown.....
There's no evidence to indicate that AMD's "mainline" $200 CPU will be much better than the existing "mainline" $200 2500K that's out right now... Just because Intel offers chips at a higher range than AMD doesn't mean that AMD automatically beats Intel at everything below the highest range. When the 2500K first came out it was priced lower than AMD chips that were substantially slower... AMD "corrected" the price to performance ratio by slashing its own prices, which didn't do too much to help its profitability.
You may laugh but think of it this way... if that $1000 Gulftown CPU from March of 2010 can still beat an 8 core Bulldozer that comes out 19 months later, then you would only have to realize a marginal benefit of about $1.75 per day to make it economically worth your while to have bought the "overpriced" Gulftown chip. (that includes the cost from Intel motherboards that tend to be more expensive and the extra RAM for a triple-channel configuration). Nevermind the fact that 6-core chips have been sold for $600 for some time as well. I can think of a bunch of professional applications that can easily show a $1.75 / day benefit from the extra cores. Maybe not for playing games, but for a lot of real applications.
Bulldozer should beat the consumer-level SB chips at perfectly threaded integer benchmarks, but it remains a very open question if it will be able to beat the almost 2 year old Gulftowns at the same tasks, and it is an almost foregone conclusion that it won't beat the 6 core SB-E chips at those tasks. Factor into account the 315 mm^2 die size of EVERY Bulldozer (not just the 8 core ones, but the cheap 4 core ones too since AMD only has 1 die design) and the immaturity of AMD's 32nm process and things could be expensive for AMD on the desktop. That's why it makes sense to ship the server chips first where AMD has some hope of getting higher ASPs.
What are you talking about? Curren Opterons have a 2 chip MCM module (see the AMD fanboys squirm over that after they denigrated Intel for doing it first). Each chip in the module has a 2-channel memory controller that isn't any different from the ones on the desktop Phenoms. Manwhile, Intel has been selling single chip solutions with 4 memory channels since 2009, with lower end models having 3 channels (Intel also had a "real" 8 core CPU out before Bulldozer despite AMD's marketing claims that they invented the number 8). If you ever look at a real memory benchmark, there are no problems whatsoever with either the three or four channel models. I'd be REAL careful bragging about AMD's supposed prowess with memory controllers since the early rumors about Bulldozer are that AMD has had a very difficult time getting BD's memory controller working as fast as existing Phenoms, much less destroying Intel. Also, you are denigrating Intel for having higher clock speeds when AMD's main strategy for BD is to push the clocks into the stratosphere, slap on massive caches, and pray... sounds like somebody is "copying" the P4 in that regard.
Ivy Bridge can't compete with ARM... but similarly, ARM can't compete with Ivy Bridge either. IB will have its biggest advantage in thinner-lighter notebooks (Macbook Air & the new Ultrabooks being put out by lots of different vendors). The projected power envelope is about 17 watts which is much much higher than even the tablet-level ARM chips. At the same time, its performance will destroy anything that ARM will have in the next 5 years (the newest ARM chips that are coming out next year are just barely approaching the earlier core 2 chips, and usually require more core & multithreading to get there). In a notebook sized device, the 17 watt power envelope is fine and should give very nice battery life in a lightweight system.
Intel's biggest competitor isn't AMD, it's ARM, or more accurately the various ARM licensees. Intel does have an big advantage in that it can put out one easy to use reference platform instead of the plethora of semi-compatible ARM implementations floating around right now. Also, the Atom has been a second-class citizen that hasn't been good enough to compete in ARM's market, but the noise coming out of Intel is that this is changing and Intel may finally be getting serious about making a solid version of Atom that can at least compete well in tablets, and eventually work down to higher-end smartphones. I'm not sure Intel wants to even try to compete in the low-end phone market since the profits there aren't all that great to begin with.
Oh and before you say that Malda & crew will do a deep code analysis of the 1.3 branch and fixit themselves:
1. They're STILL RUNNING 1.3!!
2. Slashcode... QED.
This is why we don't see ground cars with four rubber wheels! Damn the practicalities, no company could establish a respectable monopoly through patent lawfare.
This is just a plot by Bush Cheney & Big Oil to destroy the world!! Now hurry up with the organic hempseed paint so I can finish my sign protesting Nuclear power plants and solar power plants that despoil Nature's beauty and wind turbines that spoil the views of multimillionares in Nantucket!! We won't save the world until China produces everything because there's no pollution in China!
Yeah... let's see here. Massive earthquake that kills more than 18,000 people in Japan leading to Fukushima (where nobody died due to the meltdown) is incontrovertible proof that capitalism is a complete failure. Meanwhile, a single lightning strike leading to a derailment is an act of God beyond anyone's possible comprehension and China is perfect. Thanks for clearing that up for us.
1500Km from an Apple store? You just used metric there! That means your not in the U.S. and according to the standard Slashdot groupthink, the second you leave the U.S. every single person in the whole world has a 20 gigabit Internet connection with no data caps that you can pay for with spare change you found in your couch. Therefore, this shouldn't be a problem for you at all, since Slashdot groupthink defines reality.
Slashdot Mirror
2005 Called they want their list of bragging rights back. Oh and hypertransport is mostly technology that AMD bought from Digital along with parts of the Alpha team. They get some credit for bringing their version to market first, but it's hardly like they came up with the idea for Hypertransport out of thin air. As for x86-64, AMD brought it to market first, but Intel had internal builds of 64 bit enabled X86 chips around for some time, which is why they could bolt it onto the P4 and not require a brand new microarchitecture.
Of course, what people forget most about x86-64 is that Microsoft was the big proponent of a 64 bit x86 chip since it meant they could start moving into larger scale data server applications. The irony is that EPIC, for all the hate it gets in this website, is dominated by Linux and other UNIX derivatives where MS is almost completely absent.
I don't think BD is a failure because it can't beat Sandy Bridge in every benchmark. I think it's a failure because it is a *massive* (2 BILLION transistor) chip with very large (315 mm^2) die and a LARGE power envelope that still doesn't beat a 2600K even with higher clockspeeds and at using highly multithreaded code where BD is supposed to be superior.
If AMD had come out with a chip that had the same performance as BD but was much smaller and more power efficient (basically the chip that AMD promised rather than the one they delivered) then I'd be calling this a big success.
As it stands, AMD is not even *price* competitive with BD unless they slash prices even further. They are trying to sell the cut-down 6 core BD for the exact same price as the 6 core Phenom II that we have already seen beats the 8 core FX in a decent number of benchmarks! The 8 core FX is more expensive than a 2500K, but the 2500K wins in most benchmarks that people really care about in this price range (games) *and* uses a whole lot less power to boot.
buy a 6 core Phenom II, overclock it, and pray that AMD can stay around long enough to fix this mess.
Go check the techreport review and look at the price/performance chart: The 2500K has slightly higher performance, lower price, and *much* better energy efficiency.
Go look at the LKML where you'll see Linus & Ingo Molnar calling out AMD for design flaws in Bulldozer's cache that AMD wants to paper-over with kludgy software workarounds in the kernel: http://us.generation-nt.com/answer/patch-x86-amd-correct-f15h-ic-aliasing-issue-help-204200361.html
I feel bad for AMD's engineers. I *don't* feel bad for the marketing hype machine that has been relying on "geek-cred" from sites like Slashdot and the usual David vs. Goliath myth to get unearned praise. If Intel had come out with Bulldozer instead of AMD, we'd be calling this Prescott version 2.0.
Phoronix has issues because the guy running it likes to oversensationalize and hyperbolize to get traffic and ad revenue... which is to say it's exactly like Slashdot with the difference being that Phoronix actually does some useful work and there are valuable facts that Phoronix discovers.
The (multiple) kernel power bugs are a very real problem affecting a large number of Linux users and Phoronix helped to shine a light on the issue and at least get the word out about work-arounds. I don't hang on everything that Phoronix publishes, but dismissing it just shows that you want to remain wilfully ignorant about real issues surrounding Linux so that you can appear 'l33t' to your friends.
P.S. --> Since Slashdot formatting is whack, the above results should show the 1.7 Ghz P4 with a 382 Mflop Linpack score when "optimized" compared to Nvidia's published results of 309 Mflops.
Mathematically, the P4 has a 70% clockspeed advantage with only a 23.6% performance advantage, but remember how crappy the IPC on the old P4 was, and remember that the P4 is a single core CPU vs. Quad Cores for Nvidia.
OK, the idea behind ARM is that it is "fast enough" for desktop and notebook PCs. Well, if that's the case, then a P4 is also "fast enough" and you should consider not buying anything newer.
Why am I saying that? Let's look at one benchmark that *is* multi-core ready and that Nvidia kindly ran on the upcoming Kal-El quad-core systems: Linpack.
Now I know Linpack is not a perfect benchmark, but it does do a decent job of showing off number-crunching power and it is multi-core capable and there are results from a wide range of architectures.
Here's a result from a 1.7 Ghz P4 system (see: http://www.roylongbottom.org.uk/linpack%20results.htm)
CPU Mhz Opt (MFlops) Non-Opt (MFlops)
Pentium 4 1700 382.00 131.59
I think (but I'm not sure) that Opt means optimized (such as using SSE) and non-Opt is a minimal x86 implementation with no optimizations.
Now, here are Nvidia's results for its not-yet-on-the-market Kal-El Quad Core ARM at 1.0 Ghz:
Multi-threaded Linpack: 309 Mflops
See: http://www.xbitlabs.com/news/mobile/display/20110921142759_Nvidia_Unwraps_Performance_Benchmarks_of_Tegra_3_Kal_El.html
I'm going to assume that Nvidia will go out of its way to make sure the code is optimized for benchmarks that it posts as part of a marketing push.
So a QUAD CORE Arm architecture is still lagging behind a P4, and while the P4 has a clock speed advantage, it's a lot smaller than is justified by the difference in performance considering the Nvidia chip has 4 cores compared to a single-core P4.
Now, I'm not saying that Kal-El won't be awesome for use on tablets and smaller devices, but on a desktop or even a notebook, don't go around expecting miraculous performance.
Holy crap! Van Drashek has come to Slashdot! He even has a 5 digit UID! You keep working on whatever quasi-functional AI program that spews out all that crap is! One of these decades you might be able to spew out a halfway coherent troll post.
The first few posts might be trollish but look at the original article. It's a puff-piece wrapping AMD in the open source flag as a paragon of virtue when the truth is far less rosy.
AMD enjoys a (largely unearned) reputation on Slashdot as being the scrappy underdogs who want to save the world for Open Source or something like that. People forget that AMD is (or was) a multi-billion company that has no problems with getting patents, cozying up with Microsoft (see Jerry Sanders testifying in favour of MS at the anti-trust trial... ironic), or locking up its IP in the video card area. Sure they dump partial sets of documentation several months after releasing a new card, but with that level of support I have no reason to upgrade from a 3 year old Nvidia card since the shiny new AMD card won't work any better.
I *want* AMD to have real open source drivers that give great support for their hardware... basically what Intel already does right now. However, congratulating AMD and holding them up as superior to everyone else when they are not is not the right way to accomplish this goal.
Aside from the fact that you are completely wrong, I was waiting for you to say how horrible the US is and how we need to be more like Europe.... (where first to file has been the rule for decades).
Then I was waiting for you to say that first to file was dreamed up by evil Republicans who hate other countries to cheat the world of innovation.... by applying the exact same rules to the US that are used in most of the rest of the world.
I eagerly await the conclusion of your hilariously wrong, yet sadly modded +5 post.
The exact same slashbots who are screaming about how unfair it is that teachers can friend students on Facebook will be the same ones screaming at the top of their lungs about Big Brother and the police state violating "privacy" rights when some stupid student posts pictures of himself committing a crime and the teacher reports it to the cops.....
It's all part of the I want all of my "rights" without ever having any consequences to my actions philosophy of Slashdot.
Please inform me where I can go to use the patented Intel time travelling technology Haha an anti-Intel snarky comment on Slashdot... way to speak truth to power. What's funny is that if I actually told you I had a time machine in 2010 that could bring you the fastest CPU available from AMD at the end of 2011 and you only had to pay a few hundred bucks for my service, you'd probably jump at the chance... which is exactly what Intel effectively did with Gulftown.....
There's no evidence to indicate that AMD's "mainline" $200 CPU will be much better than the existing "mainline" $200 2500K that's out right now... Just because Intel offers chips at a higher range than AMD doesn't mean that AMD automatically beats Intel at everything below the highest range. When the 2500K first came out it was priced lower than AMD chips that were substantially slower... AMD "corrected" the price to performance ratio by slashing its own prices, which didn't do too much to help its profitability.
You may laugh but think of it this way... if that $1000 Gulftown CPU from March of 2010 can still beat an 8 core Bulldozer that comes out 19 months later, then you would only have to realize a marginal benefit of about $1.75 per day to make it economically worth your while to have bought the "overpriced" Gulftown chip. (that includes the cost from Intel motherboards that tend to be more expensive and the extra RAM for a triple-channel configuration). Nevermind the fact that 6-core chips have been sold for $600 for some time as well. I can think of a bunch of professional applications that can easily show a $1.75 / day benefit from the extra cores. Maybe not for playing games, but for a lot of real applications.
Bulldozer should beat the consumer-level SB chips at perfectly threaded integer benchmarks, but it remains a very open question if it will be able to beat the almost 2 year old Gulftowns at the same tasks, and it is an almost foregone conclusion that it won't beat the 6 core SB-E chips at those tasks. Factor into account the 315 mm^2 die size of EVERY Bulldozer (not just the 8 core ones, but the cheap 4 core ones too since AMD only has 1 die design) and the immaturity of AMD's 32nm process and things could be expensive for AMD on the desktop. That's why it makes sense to ship the server chips first where AMD has some hope of getting higher ASPs.
What are you talking about? Curren Opterons have a 2 chip MCM module (see the AMD fanboys squirm over that after they denigrated Intel for doing it first). Each chip in the module has a 2-channel memory controller that isn't any different from the ones on the desktop Phenoms. Manwhile, Intel has been selling single chip solutions with 4 memory channels since 2009, with lower end models having 3 channels (Intel also had a "real" 8 core CPU out before Bulldozer despite AMD's marketing claims that they invented the number 8). If you ever look at a real memory benchmark, there are no problems whatsoever with either the three or four channel models. I'd be REAL careful bragging about AMD's supposed prowess with memory controllers since the early rumors about Bulldozer are that AMD has had a very difficult time getting BD's memory controller working as fast as existing Phenoms, much less destroying Intel. Also, you are denigrating Intel for having higher clock speeds when AMD's main strategy for BD is to push the clocks into the stratosphere, slap on massive caches, and pray... sounds like somebody is "copying" the P4 in that regard.
Of course this gets modded up even though Xeons have had more memory bandwidth than Opterons for over 3 years....
Ivy Bridge can't compete with ARM... but similarly, ARM can't compete with Ivy Bridge either. IB will have its biggest advantage in thinner-lighter notebooks (Macbook Air & the new Ultrabooks being put out by lots of different vendors). The projected power envelope is about 17 watts which is much much higher than even the tablet-level ARM chips. At the same time, its performance will destroy anything that ARM will have in the next 5 years (the newest ARM chips that are coming out next year are just barely approaching the earlier core 2 chips, and usually require more core & multithreading to get there). In a notebook sized device, the 17 watt power envelope is fine and should give very nice battery life in a lightweight system.
Intel's biggest competitor isn't AMD, it's ARM, or more accurately the various ARM licensees. Intel does have an big advantage in that it can put out one easy to use reference platform instead of the plethora of semi-compatible ARM implementations floating around right now. Also, the Atom has been a second-class citizen that hasn't been good enough to compete in ARM's market, but the noise coming out of Intel is that this is changing and Intel may finally be getting serious about making a solid version of Atom that can at least compete well in tablets, and eventually work down to higher-end smartphones. I'm not sure Intel wants to even try to compete in the low-end phone market since the profits there aren't all that great to begin with.
The first way: Haha, these skiddies didn't have what it takes to effectively hide their cracking.
The second way: Skiddies were able to crack kernel.org using automated cracking tools just Windows, no evil genius required.
Oh and before you say that Malda & crew will do a deep code analysis of the 1.3 branch and fixit themselves:
1. They're STILL RUNNING 1.3!!
2. Slashcode... QED.
All versions in the 1.3 and 2.0 lines are said to be vulnerable to attack. The group no longer supports the older Apache 1.3.
Since Slashdot is still stuck in the late '90's with a thin veneer of bad javascript, over apache 1.3 it's vulnerable... and no patch either.
This is why we don't see ground cars with four rubber wheels! Damn the practicalities, no company could establish a respectable monopoly through patent lawfare.
California --> There's your problem right there.
This is just a plot by Bush Cheney & Big Oil to destroy the world!! Now hurry up with the organic hempseed paint so I can finish my sign protesting Nuclear power plants and solar power plants that despoil Nature's beauty and wind turbines that spoil the views of multimillionares in Nantucket!! We won't save the world until China produces everything because there's no pollution in China!
Yeah... let's see here. Massive earthquake that kills more than 18,000 people in Japan leading to Fukushima (where nobody died due to the meltdown) is incontrovertible proof that capitalism is a complete failure. Meanwhile, a single lightning strike leading to a derailment is an act of God beyond anyone's possible comprehension and China is perfect. Thanks for clearing that up for us.
You religious wingnut! Everyone knows the Dinosaurs went extinct because climate change caused by the the Bush Tax Cuts and Big Oil!
- A Student from San Francisco
1500Km from an Apple store? You just used metric there! That means your not in the U.S. and according to the standard Slashdot groupthink, the second you leave the U.S. every single person in the whole world has a 20 gigabit Internet connection with no data caps that you can pay for with spare change you found in your couch. Therefore, this shouldn't be a problem for you at all, since Slashdot groupthink defines reality.