|
Surely one of the biggest problems with IE6 is not that it sucked in one way or another, but that it helped proliferate a million proprietary piece of poo poo ActiveX controls, which probably locks many a person into using old poo poo today. Also a great vector for spyware! ActiveX is older than that, I guess, but I'm still going with blaming IE6's continued support of this and other IE only controls as being a barrier to alternative browsers in many situations for so long. HalloKitty fucked around with this message at 23:44 on Oct 20, 2011 |
# ? Oct 20, 2011 23:42 |
|
|
# ? May 9, 2024 10:37 |
|
AMD Roadmap Discussion: Let's talk about IE6 instead
|
# ? Oct 20, 2011 23:52 |
|
At this point, I guess IE6 is probably slightly less disappointing
|
# ? Oct 20, 2011 23:54 |
|
Agreed posted:Intel -needs- AMD. If Intel becomes an effective monopoly, nobody wins. I can only imagine the fallout from Intel getting busted up like Ma Bell, jesus. Why would you think the current administration or the next for that matter would bust them up? The last few administrations have been incredibly pro big business/mega corp and have allowed massive consolidation in many areas. They didn't even bust up the banks after they helped to trash the economy, hell they made them bigger as part of a "solution". They sure haven't broken up MS either. I'd really be surprised if they did anything if AMD essentially torpedoes itself with a bad product or something.
|
# ? Oct 20, 2011 23:59 |
|
Obama visited the Intel Oregon facilities and Intel's CEO is on his jobs council. I don't think the administration views Intel as a big evil monopoly that needs to be broken up sans AMD
|
# ? Oct 21, 2011 00:14 |
|
PC LOAD LETTER posted:Why would you think the current administration or the next for that matter would bust them up? The last few administrations have been incredibly pro big business/mega corp and have allowed massive consolidation in many areas. They didn't even bust up the banks after they helped to trash the economy, hell they made them bigger as part of a "solution". They sure haven't broken up MS either. Yep, I think some people think that the US Government still has the anti-monopoly views that it had back in the early 20th century. The Government has learnt to leave the corporations well alone these days (I mean Microsoft manage to easily survive attacks against it about monopolising the OS market)
|
# ? Oct 21, 2011 00:59 |
|
HalloKitty posted:At this point, I guess IE6 is probably slightly less disappointing There's your thread title. At this point I've lost all interest in BD. Time to look forward to their next iteration of the processor.
|
# ? Oct 21, 2011 01:03 |
|
How would you even break up Intel? Not let the desktop and laptop cpu teams talk to each other?
|
# ? Oct 21, 2011 02:53 |
|
trandorian posted:How would you even break up Intel? Not let the desktop and laptop cpu teams talk to each other? I'm guessing they'd break the GPU and chipset side of the business off into separate companies if they really wanted to. Not sure if even that would really make sense in the long run though given the trend to integrate everything onto a single die for power savings, to reduce the size, and cost reductions.
|
# ? Oct 21, 2011 03:06 |
|
trandorian posted:How would you even break up Intel? Not let the desktop and laptop cpu teams talk to each other? You could try and split their chipset/graphics/nic/wireless divisions off, but that's not going to get you much.
|
# ? Oct 21, 2011 03:06 |
|
Intel is a huge company. They have fabs, ram (that's how they started out before they did processors), flash, cpus, and a whole bunch of miscellaneous stuff. It's not like they only do CPUs. Imagine if Intel's fabs got split off Global Foundries style so other people could use their process. Longinus00 fucked around with this message at 05:07 on Oct 21, 2011 |
# ? Oct 21, 2011 03:13 |
|
Splitting the chipset business off from CPU makes no sense but that might just be my bias speaking.
|
# ? Oct 21, 2011 04:11 |
|
trandorian posted:How would you even break up Intel? Not let the desktop and laptop cpu teams talk to each other? Better question: why would you gently caress with a company that has the majority of institutional knowledge when it comes to computer hardware (from the process level up to software) and the world literally runs on their hardware and innovations? The Intel Architecture Labs developed PCI, AGP, amongst many other contributions. In fact, a lot of their research was shut down prematurely because they were beginning to compete with Microsoft. That's a bit sensationalist though, on a more sane note, if there was some busting going on I assume it'd be split along the line of business units.
|
# ? Oct 21, 2011 04:20 |
|
movax posted:Better question: why would you gently caress with a company that has the majority of institutional knowledge when it comes to computer hardware (from the process level up to software) and the world literally runs on their hardware and innovations? Is it really even necessary? They paid huge fines and settlements to AMD over their anti-competitive behavior. Pretty sure AMD's only recent fiscal year in the black was because of that. Is there any evidence that they are still actively pursuing anti-competitive practices? Their prices are pretty fair considering they ARE delivering the best product.
|
# ? Oct 21, 2011 05:13 |
|
Nostrum posted:Is it really even necessary? They paid huge fines and settlements to AMD over their anti-competitive behavior. Pretty sure AMD's only recent fiscal year in the black was because of that. Is there any evidence that they are still actively pursuing anti-competitive practices? Their prices are pretty fair considering they ARE delivering the best product. I dunno if there is any current concern over their current business practices, but I think what people are "worried" about is when/if they get a virtual monopoly on a gigantic market because their products are the only one available/worth buying. The barrier of entry for a new competitor into the x86-processor market would be almost insurmountable, I think.
|
# ? Oct 21, 2011 05:24 |
|
HalloKitty posted:Surely one of the biggest problems with IE6 is not that it sucked in one way or another, but that it helped proliferate a million proprietary piece of poo poo ActiveX controls, which probably locks many a person into using old poo poo today. Also a great vector for spyware! IE6 is so reviled because millions of business machines where all trapped on windows2000 with nothing but IE6 available, which made IE6 a embarrassingly, frustratingly huge presence on the net. Its horrible standards support became an issue because web developers were stuck supporting IE6 which was completely broke by that point in comparison to every other browser, including the newer versions of IE. I knew a guy working at facebook years ago around the time of their big redesign, which included massive amounts of AJAX/dynamic content, and he had an aneurism dealing with IE6. Facebook was so huge as an at work time waster that a massive amount of their traffic was on IE6, so that meant developing an IE6 compatable version of the site. Apparently it took months of additional work. Nothing was smelling of roses back in the original IE6 days, but a lot of the real hate comes from the fact everyone was stuck supporting it a good half decade past the point it should have been.
|
# ? Oct 21, 2011 11:29 |
|
Juriko posted:IE6 is so reviled because millions of business machines where all trapped on windows2000 with nothing but IE6 available Of course, I forgot about it that. I can't see any reason why Microsoft left it like that. I guess they just shrugged and said Windows 2000 is unsupported. Are there really frameworks in XP that make IE7/8 possible that couldn't have been ported to Windows 2000? We have the same situation now with XP and IE8, so there's a small chance we'll run into exactly the same problem down the line. That said, it seems Windows 7 has a relatively decent adoption rate now. Although I'm sure there enough business that won't ever budge. Edit: hold on a minute, this derail is going too far. Bulldozer. They're working on a new stepping. Then again, it's fairly obvious that they'll be trying to improve it as they go along. They've got a lot of improving to do.. HalloKitty fucked around with this message at 12:20 on Oct 21, 2011 |
# ? Oct 21, 2011 12:15 |
|
Agreed posted:I hate to ask, but... How's that stock looking? It's actually up almost 4% today. I need it to get back to 6 dollars (up another buck?) to break even, though.
|
# ? Oct 21, 2011 15:38 |
|
The Linux kernel patch has been benchmarked http://openbenchmarking.org/result/1110200-AR-BULLDOZER41
|
# ? Oct 21, 2011 15:41 |
|
movax posted:Better question: why would you gently caress with a company that has the majority of institutional knowledge when it comes to computer hardware (from the process level up to software) and the world literally runs on their hardware and innovations? ARM might want a word with you on that one...
|
# ? Oct 21, 2011 15:54 |
|
Its funny reading all the reviews on Newegg about these processors. Its like they all drank the cool-aid. You just want to smack all of them and say WTF is wrong with you people. But then you realize that it just does not matter.
|
# ? Oct 21, 2011 16:18 |
|
WhyteRyce posted:The Linux kernel patch has been benchmarked Am I misreading something or does this patch do literally nothing
|
# ? Oct 21, 2011 16:49 |
|
MeramJert posted:Am I misreading something or does this patch do literally nothing That's how I read it! That's just sad as all hell. Come on, generic computing god, give AMD a break! At least throw them like... a measurable improvement.
|
# ? Oct 21, 2011 17:02 |
|
feedmegin posted:ARM might want a word with you on that one... ARM's nowhere near close enough yet. How many ARM servers on the internet and private networks (banking, etc) versus x86 servers, or even mainframes and SPARC? How many ARM machines in your ATMs, at government offices, in the military, and so on versus x86? A very big part of the reason that Intel would be under scrutiny if AMD went out of business is that so much of the world relies on x86 CPUs.
|
# ? Oct 21, 2011 17:28 |
|
feedmegin posted:ARM might want a word with you on that one... Yea, providing a soft IP core. That's totally the entire stack.
|
# ? Oct 21, 2011 17:30 |
|
Windows 8 is supposed to run on ARM, right? That could legitimize it further, considering that ARM and related processors do power a number of consumer devices. But it's not especially germane to the discussion; as others have pointed out, the chances of Intel getting broken up even if AMD torpedoes completely are pretty loving unlikely given where they're headquartered at. Fined a bunch by the EU, maybe. But AMD probably isn't going to torpedo completely. If they can get Bulldozer to stop being a total loving albatross, that would be great, maybe that one patch sucked and didn't do anything but we know for a fact they have fabrication issues with their process. That can be fixed, maybe. Bulldozer is getting a second stepping, which isn't exactly the worst thing for a processor, that happened really quickly with Sandy Bridge too. They've got enough information on broad usage scenarios and failure conditions that they might be able to pull it into a moderately less loving miserable state, at least. My idea of "push the K10.5 harder!" probably isn't going to happen... So the realistic option left seems "try and make Bulldozer not gently caress the dog!" and good luck with that, sincerely. Otherwise, I doubt they're going to just implode. Maybe end up back in the old pre-K6 days again, making second-rate "compatible" hardware, and certainly not the industry-revolutionizing opportunists they got to be for awhile... But there will always be space to do it cheaper and good enough. They can probably just do that if it's all that's left for them to do. Then hope Intel fucks up again somehow and they get another chance.
|
# ? Oct 21, 2011 17:45 |
|
Agreed posted:Windows 8 is supposed to run on ARM, right? That could legitimize it further, considering that ARM and related processors do power a number of consumer devices.. It could, but the necessity of recompiling everything means that you don't get the legacy app support that allows movement to it the way x86-64 did or even the way various expansions to the instruction set since the original 8086/8088 did. Not to mention there's an awful lot of x86 devices that don't run Windows. And even in Windows, look how much a of a problem it was for many businesses and people that 64 bit Windows no longer ran 16 bit applications native.
|
# ? Oct 21, 2011 18:00 |
|
Don't count ARM out, it's easy to talk about the wide installed base of legacy x86 machines, but every smartphone and nearly every tablet sold today is ARM and that's a lot of momentum. Remember also that webapps are the rule today, so it's highly unlikely that your average user even has any x86 code they couldn't work around if they wanted to. When ARM Cortex A15 products come out next year we'll see ARM chips with performance around the same as desktop Core 2 Duos, which could really bite a chunk out of Intel's low-end market.
|
# ? Oct 21, 2011 20:30 |
|
After reading through benchmarks and this thread, my question is "What benefits or spiffy technology are actually in Bulldozer?" I mean, in two years after they get 5 Ghz in the core design going to be where they get a lot of money out of it, or something? Is there any value here as a processor?
|
# ? Oct 22, 2011 15:09 |
|
trandorian posted:It could, but the necessity of recompiling everything means that you don't get the legacy app support that allows movement to it the way x86-64 did or even the way various expansions to the instruction set since the original 8086/8088 did. Not to mention there's an awful lot of x86 devices that don't run Windows.
|
# ? Oct 22, 2011 15:27 |
|
Combat Pretzel posted:I wouldn't be surprised if someone came up with a assembly level recompiler...After all, only the APIs need to be there, not the CPU architecture per se. What do APIs have to do with assembly?
|
# ? Oct 23, 2011 01:44 |
|
Longinus00 posted:What do APIs have to do with assembly? Rosetta on OS X dynamically recompiles PowerPC binaries to x86 and IIRC in the process replaces calls into PowerPC libraries with equivalent x86 ones if they exist. (I could be talking out of my rear end here, but I'm pretty sure I read that ) Presumably an x86 emulator for Windows on ARM, if one were to exist, could do the same thing for a performance increase. The point doesn't really matter though since Microsoft has explicitly said they won't include an emulator. You either compile your native code for both platforms or use .NET. (Plus it would probably be really hard to pull off effectively, given all the stupid API tricks relying on undocumented behavior that Win32 programmers like to do.)
|
# ? Oct 23, 2011 02:44 |
|
Arsten posted:After reading through benchmarks and this thread, my question is "What benefits or spiffy technology are actually in Bulldozer?" What benefits to the consumer from bulldozer? Questionable benefits at best. Maybe the release inspired intel to announce their next generation of processor, or maybe they are just carrying on the same anyway. Further on down the track bulldozer will probably be beneficial. The design has a lot more room for development so it will allow for some considerable improvements. This probably will just result it reasonable cheap cpus on the bottom end of the market. That said I bought a new laptop yesterday with an i3-2310M. AMDs bulldozer inspired that purchase.
|
# ? Oct 23, 2011 23:04 |
|
Arsten posted:After reading through benchmarks and this thread, my question is "What benefits or spiffy technology are actually in Bulldozer?" edit: actually misread that chart. It only shows performance per watt, its possible then that AMD may not be able to improve total performance much at all then but knows they can lower the power draw, which is nice but still leaves them screwed with BD. That probably means they won't be able to catch up to or beat Nehalem, which by then will be almost a 5 yr old core and likely phased out, until 2013. Excavator will probably bring them up to SB levels of performance by 2014, if they meet their performance goals of course, but by then Intel will have moved on to a better core as well. Then you have to consider the process lead Intel has as well...and yea things are looking grim for AMD. More so then ever before. Unless they can pull of some miracles in a redesign with a new chip its looking doubtful if AMD can ever catch up to Intel again. edit2: AFAIK even with all those new instructions it still loses to SB and Nehalem much less SB, at least on recompiled linux benches that were posted on RWT. There is something wrong with BD's FPU too. On paper it should be great, I used to be pretty gung ho about BD reading that stuff, but again the implementation is screwed up. That isn't to say BD doesn't get a nice speed up with recompiled apps, making it faster than PhenomII is an improvement, it just still isn't good enough. \/\/\/\/\/ edit3: of course nearly no one will recompile their apps for BD either, so its pointless talking about that seriously anyways.\/\/\/\/ PC LOAD LETTER fucked around with this message at 04:30 on Oct 24, 2011 |
# ? Oct 24, 2011 02:34 |
|
To be fair Bulldozer DOES implement a lot of enhancements to the x86 instruction set, including SSE4, AVX, SSE5 (FMA4, CVT, XOP), and AES-NI. This allows it to reach and exceed the capabilities of Sandy Bridge. If you have an application that supports any of these extensions you can get vastly improved performance from Bulldozer, though the only extension that's likely going to make a difference in people's lives right now is AES encryption/decryption acceleration, which can be a HUGE deal if you use full disk encryption. FMA4 is a floating-point Fused Multiply-Add which allows three values to be multiplied and added together in a single step, with the result stored in a fourth value (a+b*c=d). Doing it in a single step means you only round once, improving accuracy as well as performance. This can enable some really interesting, high-performance applications. Of course, since only Bulldozer supports this and Intel's implementations is incompatible (FMA3, where the result has to be written to one of the original values you used) it's probably not going to be supported in anything people actually use. And of course, since in the actual real world Bulldozer is just plain slow, even these advances aren't going to be much help to anyone, but it's nice that they exist.
|
# ? Oct 24, 2011 03:12 |
|
Arsten posted:After reading through benchmarks and this thread, my question is "What benefits or spiffy technology are actually in Bulldozer?" It doesn't do much good for desktop users, but the uncore is loaded with features that may make more compelling in servers. It had better, considering how freaking huge it is - the uncore by itself is almost as large as a quad-core Sandy Bridge chip. I've not seen much coverage on it, but there is this SemiAccurate article on it.
|
# ? Oct 24, 2011 05:18 |
|
AES-NI is a nice point, I'll grant you... but Sandy Bridge and Westmere already have AES-NI. Still, there might be a certain price point at which Bulldozer makes sense for an encrypted file server on a budget, or something.
|
# ? Oct 24, 2011 11:11 |
|
That certain price point will surely be offset by the higher power bill.
|
# ? Oct 24, 2011 11:40 |
|
So I did a little back of the envelope math, and I'm thinking that two Bulldozer modules minus the L3 cache might work well as an APU. The L3 cache seems to use up about a quarter of the die area in total, cutting off two of the modules will do slightly less than cut the chip in half, since the northbridge/IO area can't be reduced. Say the resulting chip has about 40% of the die area, or ~126mm^2. Llano is 228mm^2 and about half the die is graphics, so say 114mm^2. Add these together and you have a ~240mm^2 chip, which is only slightly bigger than Llano, and the CPU performance would probably be rather competitive compared to the slow Llano cores (in the tasks Llano is used for). The real question is whether you can cram two Bulldozer modules and graphics onto a single die and have enough power budget left over for meaningful clockspeeds, but I think this might not be unreasonable. Looking at Legion Hardware's benchmarks of the FX-4170 (4.2Ghz) vs the Phenom II X4 980 BE (3.7Ghz) with the same TDP, the Bulldozer doesn't do too badly in apps that aren't well-threaded and actually has 25W lower total power usage. There was some mention by AMD that Bulldozer isn't as badly affected by the loss of L3 on the desktop as the STARS core was, but this may be BS.
|
# ? Oct 24, 2011 13:47 |
|
|
# ? May 9, 2024 10:37 |
|
But then why did they blow all that die space for all that cache if it had little impact on performance and consumed so much more power? Doesn't seem to add up.
|
# ? Oct 24, 2011 13:56 |