|
If rumors are true BD will show up in April. Motherboards should be out by then too, but considering the chipset is pretty much a minor refresh of the current ones I'm kinda surprised they aren't out already.
|
#
¿
Jan 17, 2011 01:52
|
|
|
|
| # ¿ Sep 10, 2024 13:02 |
|
|
Stuff like media encoding is what the GPU is supposed to be used for at some point, its the whole APU/Fusion thing they've been talking about for years and years. Looks like the hardware will be there but I dunno about the software.
|
|
#
¿
Jan 21, 2011 12:43
|
|
|
That may be true but that is what AMD seems to have in mind.
|
|
#
¿
Jan 21, 2011 14:12
|
|
|
OK so according to the new CEO desktop BD will be coming in June, servers will be "late" summer. Rumor mill was close but still off by a fair amount then. 5 months though to wait, sheesh AMD.
|
|
#
¿
Jan 21, 2011 18:04
|
|
|
Combat Pretzel posted:Aren't games FP heavy? And what about preprocessing in the graphics drivers?
|
|
#
¿
Jan 22, 2011 03:37
|
|
|
Either they'll beat it somehow in performance (unlikely) or they'll kinda close and sell it for less (way more likely). Still no word on pricing though and all we have for performance is some shady rumors and JF's statement that it'll have higher IPC than PhenomII. Supposed to be some sort of conference AMD is gonna do in late Feb. Should have more info. by then.
|
|
#
¿
Jan 23, 2011 23:51
|
|
|
Yea, whole thing smacks of "something went really wrong but we're not gonna say what". At this point I'm expecting more delays for BD, which is really bad for AMD. e: Also this is apparently fake info. on BD. Hopefully there won't be as many fakes with BD as there was with the 6xxx GPU's. PC LOAD LETTER fucked around with this message at 21:48 on Jan 24, 2011 |
|
#
¿
Jan 24, 2011 14:28
|
|
|
Thread's been dead for a while but then there hasn't been much good info. for a while either. That seems to have changed in the last couple of weeks. We seem to be getting current 8xx chipset based boards that can support BD coming soon, in April. The mobo shown looks like a high end exxtreme version that'll cost probably north of $200, but hopefully they'll have some more sanely priced versions out too. This is kinda old now too but hasn't been brought up. Looks like we can expect some 3.5Ghz 16 thread BD's that'll fit in the same power envelope as current 12 thread Opteron's running at 2.6Ghz or so. Turbo supposedly might add another 500Mhz or more to that, but no word on the power/work load requirements for when/how Turbo kicks in or how many cores will use it at a given speed. Still no word on per clock performance though. e: 9xx is supposed to be a minor refresh of the 8xx chipset, much like how the 8xx chipset was a minor refresh of the 7xx chipset. Best you could hope for is better performance with SSD's and PCIe performance but its not clear if we'll get even that.\/\/\/\/\/ PC LOAD LETTER fucked around with this message at 16:02 on Mar 1, 2011 |
|
#
¿
Mar 1, 2011 14:57
|
|
|
Nothing BD related though there is a nifty quick n' dirty video demo of Llano that was done recently. Will get whipped soundly CPU wise of course by SB, but the video showed it getting around nearly double the fps in games while using around 10-20w less than a 2Ghz quad core SB part. No clue on clockspeed or pricing yet, but its a AthlonII derivative so clocks/performance will likely be similar at least.
|
|
#
¿
Mar 2, 2011 13:57
|
|
|
adorai posted:Not bulldozer, but question relating to the new poo poo from AMD. Per clock, can I expect similar performance between an ontario/zacate/llano platform as I can get from PhenomII/AthlonII? I am considering replacing my fileserver, which is currently a 45W AM2 Athlon x2 1.9GHz. If I can replace this with an APU that consumes only 18W, and not have to worry about performance, it's worth it to me (my office has terrible air flow and it gets warm in there). If it goes well I might even replace my VMware server as well (Athlon X2 2.5GHz) since it rarely caps out. Zacate/Ontario is around 10% slower per clock than AthlonII. Llano will perform nearly the same as AthlonII per clock since its the same core but shrunk down to 32nm. The Llano used in the demo I linked a ways up the page was apparently a 1.8Ghz dual core version FWIW. greasyhands posted:The only time they've ever been "real strong" was due to intel's colossal misstep with the pentium4. Looks like AMD has finalized the shipping date of BD and Llano, so no more rumors, late June (20th) is the shipping date. Given the "FX" branding the chips are getting these will probably be high end expensive parts. Which is both good and bad I guess. Good because AMD has something that may compete with Intel's best, bad because they'll probably price it accordingly. Oh well, they'll still have to contend with the ~$200 i5-2500K somehow so I'm guessing they won't go too crazy with the pricing. PC LOAD LETTER fucked around with this message at 13:55 on Mar 8, 2011 |
|
#
¿
Mar 8, 2011 12:50
|
|
|
Another lil' leak that gives some pretty big hints about how AMD expects BD to perform given its price positioning.
|
|
#
¿
Mar 14, 2011 10:52
|
|
|
Alereon posted:It seems like it's going to come down to how efficient AMD's Turbo Core 2.0 is. . Ryokurin posted:Didn't they admit a few weeks back that Cool'n'Quiet came kind of late in the Athlon64's design phase and as a result they have only been able to do minor improvements, but they were able to make changes to make it better from the start this time?
|
|
#
¿
Mar 15, 2011 00:18
|
|
|
fishmech posted:MORE CORES!* *yes I know there are already a few things out now that support it, but heavy heavy emphasis on few. New instructions usually take quite a few years to become commonplace even if they offer a significant performance advantage, as you well know.
|
|
#
¿
Mar 15, 2011 12:13
|
|
|
They aren't out yet so its possible that may be why they aren't listed for comparison, no prices and such. That being said the socket 1366 CPU's aren't listed either. We'll have to wait and see as usual to know for sure. And some more leaks. If this and the other slide are correct that means we can expect a quad core Llano with 320-400 SP's to sell for around $150-200 for the highest end model. The lower end dual core and 160 SP models will probably go for around $100. Bear in mind you'll need a new socket/mobo (socket FM1) for Llano to work. Still seems like a good deal if this pans out. PC LOAD LETTER fucked around with this message at 18:56 on Mar 16, 2011 |
|
#
¿
Mar 16, 2011 14:34
|
|
|
I know on the very low end prices seem about right for the whole PC new. Sub $400 for a Ontario/Zacate system is pretty close to what they sell for right now for instance. Doing a quick and dirty check online at Tigerdirect and newegg i7 prices for the desktop actually seem to be around $50-100 higher than the $700 cut off on the chart and that is without the monitor. i5 system prices seem to be around $550-700 or so, also without the monitor. i3 systems are about the same price wise as the i5's. Sure there are some deals that will skew things either which way, but I don't think chart is off by much if it is off at all.
|
|
#
¿
Mar 16, 2011 21:01
|
|
|
I think AMD always said that the new socket was to allow for TC2 and some new power savings options, which won't work if you put a BD into a AM3 socket. It was probably always technically possible, after all the north bridge doesn't have the memory controller anymore and the interconnect is somewhat generic now*, but for some reason AMD didn't want to do it. I guess ASUS decided to give it a shot, and you might not care about power savings and TC2 if you're gonna OC the thing anyways. *AMD uses HT as a bus between the North Bridge and CPU, the South Bridge connects to the North Bridge via a PCIe variant IIRC, which is why you can find 7xx chipset AM3 motherboards and 8xx chipset motherboards with the old SB710 South Bridge instead of the newer SB850 one.
|
|
#
¿
Mar 18, 2011 03:19
|
|
|
Yea saw that. Didn't mention them because the test system apparently is configured improperly and/or is buggy beta hardware. 1 benches looked good, others were actually slower than Phenom II's. Doubtful that will reflect the final product since JF-AMD already said BD will be faster per clock than the "Stars" core.
|
|
#
¿
Mar 27, 2011 22:30
|
|
|
Its only for mobo OEM's who already have a SLI licence though, but still nice to have as an option without using the lovely and ooold NF200 chip. Also RWT did about as good as an evaluation as possible on those crappy leaked BD benches, has some good info.
|
|
#
¿
Apr 1, 2011 02:03
|
|
|
Alereon posted:The AMD750 (Irongate) chipset was horribly unstable, mostly because it was the first generation chipset and the first one for the platform.  http://www.active-hardware.com/english/reviews/mainboard/sd11.htm Alereon posted:By the time of the KT133A the Via chipsets actually made for a pretty reasonable platform, as long as you didn't have a Soundblaster Live! card.
|
|
#
¿
Apr 4, 2011 04:40
|
|
|
Not much to talk about right now. Only new info. I've seen is that supposedly BD is now coming out at Computex. So early June. http://wccftech.com/2011/04/09/gigabyte-slide-reveals-amd-bulldozer-launch-date-launched-7th-june-computex-2011/ And yes the 8RDA+ was great. IIRC it had some of the VRM's on the back of the board which was weird and it used a different power supply spec, emphasizing the 3.3v rail, instead of the 5v or 12v rails like most PSU's. Caused it to behave oddly if you had a crappy PSU, but oh man was it good if you had a good one.
|
|
#
¿
Apr 10, 2011 01:05
|
|
|
Faceless Clock posted:Zacate is nice and all but per-clock its barely better than Atom on the CPU side. That has me skeptical. Zacate is a cheap part but come on. Atom wasn't even new tech when it was released. Faceless Clock posted:I think we'll have to consider Bulldozer a relative success if they manage to catch up to Nehalem.
|
|
#
¿
Apr 18, 2011 03:28
|
|
|
BD clocks just got leaked. Base clocks top out around 3.2Ghz and start at 2.4Ghz. The 900Mhz-1Ghz Turbo boost over stock clocks is quite nice, and its likely to be per module too, so 2 instead of 1 core would be boosted. JF has already said that they'll be able to raise the clocks up to 500Mhz on all cores while maintaining stock TDP for at least some models as well. edit: mhzzzzzzz PC LOAD LETTER fucked around with this message at 16:29 on Apr 28, 2011 |
|
#
¿
Apr 27, 2011 14:34
|
|
|
And it looks like BD performance numbers have been leaked. The top BD chip is supposedly as fast as the i7 2600K which is pretty good but we still don't quite know its exact price yet nor how well, if at all, it overclocks. So its possible the i5 2500K or i7 2600K might end up being better buys over all, but still this seems like good news for AMD even if Intel has a big update coming 6 months or so after that.
|
|
#
¿
May 4, 2011 19:22
|
|
|
tijag posted:then what you're seeing is effectively the performance of a 2 module 4 core BD chip being equivalent to a 2600K. Combat Pretzel posted:So in regards to integer performance, the BD should blow the SB out of the water. PC LOAD LETTER fucked around with this message at 05:45 on May 5, 2011 |
|
#
¿
May 5, 2011 05:41
|
|
|
I don't think there are going to be any 3rd party chipsets for AMD's chips this time around. Their in house chipsets aren't perfect but do seem to be good enough that no one tries to compete with them anymore. They could certainly still screw something up though. edit: looks like some specs for some up coming AMD 900 series based motherboards have been leaked as well. No prices but I'm sure you could make a reasonably close WAG on what they'll be based on ASUS's current line up. 
PC LOAD LETTER fucked around with this message at 02:05 on May 6, 2011 |
|
#
¿
May 6, 2011 01:58
|
|
|
Looking at how Intel configured SB (only ~10% performance improvement over Nehalem but around 20% less power usage) my WAG is they're going to emphasize power usage over performance. They already know good and well that most of their CPU's are overpowered for what most people need to do with their computers and they're going to have to compete with ARM in laptops and servers somehow. AMD's, well GF's fab tech is based off of what IBM has IIRC, which is actually part of a whole group of companies working together to share development costs of the process. I don't know what they're planning re: FinFET's either. edit: Kanter at RWT recently did a article on Intel's FinFET's you guys may be interested in. One of the relevant tidbits in it was that GF/IBM were planning on using FinFET's when they get to a 14nm process. They appear to be shooting for a late 2015 launch for that process. I somehow doubt that they'll be able to avoid some delays or even pull that date in earlier so I think it wouldn't be unreasonable to expect a 14nm chip using FinFET's from AMD until early 2016 at best. It'll be interesting to say the least to see how AMD tries to compete when Intel will have such a huge advantage for so long. One option would be to use FD-SOI I guess since that may be available if not now then much sooner than 2015, but Kanter mentions that would increase costs by 10%. AMD has gone the SOI route before though when others wouldn't due to reported cost issues, so we'll have to wait and see... PC LOAD LETTER fucked around with this message at 01:39 on May 9, 2011 |
|
#
¿
May 6, 2011 22:01
|
|
|
Not really no, just some more false benches to troll people. Some mobo manufacturers did mention they'd show some 9xx based mobos at Computex.
|
|
#
¿
May 17, 2011 21:33
|
|
|
Llano mobo details if that is your thing. Looks decent enough even if it is a ECS mobo but no real surprises yet.
|
|
#
¿
May 18, 2011 07:31
|
|
|
Sinestro posted:I know this is pretty I'm sure eventually it'll go into laptops but I don't know when. The June launch is just for desktop and server parts AFAIK. e: more mobo shots. ASUS high end 990FX mobo. Jetway "cheap" 990X mobo. Prices on both unknown but I'd expect the ASUS board to be close to or north of $200, the Jetway board looks like a mid range offering which is uncommon from them. PC LOAD LETTER fucked around with this message at 13:39 on May 19, 2011 |
|
#
¿
May 18, 2011 22:30
|
|
of me, but is BD going on laptops, or is it just Llano?
|
Alereon posted:I'm talking about memory bandwidth, a Radeon HD 6570 has a 128-bit 4Ghz GDDR5 memory bus, but the Radeon HD 6550 is going to have to make do with a 128-bit 1866Mhz DDR3 bus, shared with the CPU.
|
|
#
¿
May 22, 2011 02:26
|
|
|
Tab8715 posted:The hell? This is going in a laptop? edit: Looks like we've got a good leak on BD clocks and prices from ASUS. e2: Looks like we got some prices for some Llano based laptops. In Euros and has a discrete GPU in it too (common place CF in a low to mid range laptop ahoy!) but still it gives you a good idea of what they'll be like in dollars. PC LOAD LETTER fucked around with this message at 14:15 on May 24, 2011 |
|
#
¿
May 23, 2011 05:18
|
|
|
Space Gopher posted:TDP isn't a great way to look at power consumption and battery life any more. It specifies a sustained maximum power draw, but it doesn't give you any information about how the chip performs with lighter loads. Intel's current Sandy Bridge mobile quads have high TDPs, but still get excellent battery life under typical light-usage scenarios like web browsing because they're aggressive about clocking down, sleeping, and even gating off parts of the CPU that aren't in active use. It remains to be seen if AMD can match Intel's progress on that front, but I wouldn't assume that a 45W TDP automatically means poor runtime.
|
|
#
¿
May 25, 2011 02:55
|
|
|
Its a drat shame AMD dropped the ball, again.  They're lucky they have a decent GPU to cram onto a single die with their older cores. Llano will make a good mainstream chip but that is a real disappointment to those of us who were hoping for something more than that.FPU though? I'd be surprised if the FPU was the problem. For what ever reason the problems seem to pop up with the L1 cache, decoders/schedulers with AMD.
|
|
#
¿
May 30, 2011 14:02
|
|
|
That makes lots more sense, especially given the rumors of poor yields and delays from GF's 32nm process.
|
|
#
¿
May 30, 2011 23:28
|
|
|
x86 is pretty IPC limited, IIRC the Athlon had 3 decoders and only averaged around 1.5 IPC thorough put. 4 is already overkill, adding a 5th would be a waste. Resources would probably be better spent on a bigger/faster cache or branch prediction or improving clockspeed. I don't believe memory bandwidth is an issue right now either, almost nothing seems to be limited by it for desktop workloads.
|
|
#
¿
May 31, 2011 03:15
|
|
|
JawnV6 posted:No. Branch prediction is such a dead topic and is never the answer. In my later classes where we had to cook up architectural features, we were explicitly discouraged from doing anything with branch prediction. When you're above 95-97% on most workloads.. who cares? Devian666 posted:For the desktop loads I was referring to typical home desktop loads (which for me means gaming as other tasks don't use much cpu). So your previous post make a lot of sense for HPC or something else perhaps even more niche, but not for common desktop stuff. AMD confirms Sept. date for BD release. Lets hope they actually stick to it this time. PC LOAD LETTER fucked around with this message at 13:11 on Jun 2, 2011 |
|
#
¿
Jun 2, 2011 02:24
|
|
|
Fudzilla has a link on a Llano laptop for less than 600 Euros which suggests to me that Llano based laptops will be priced quite a bit lower than most any SB+discrete GPU alternatives which tend to go for over $700.
|
|
#
¿
Jun 14, 2011 21:17
|
|
|
Alereon posted:and the 360 used the same IBM PowerPC cores from the Cell minus the SPEs. It would be pretty strange and amazing if MS uses a revamped Cell and Sony goes with a BD variant after pimping Cell as the end all be all of the future back when they released the PS3. Its almost a total reversal in each company's design ideology. Alereon posted:On the GPU front, AMD will be powering all three next-generation consoles.  Wow big win for them. I really hope BD is better than rumored to be but it looks like either which way AMD may end up financially sound for the future if for no other reason then all the consoles will be using their hardware or at least liscencing their designs. I guess AMD really nailed the perfect balance between GPGPU support, graphics performance, power usage, and die size (cost).edit: I know and I don't think I said otherwise, but Sony sure thought it would.\/\/\/\/\/\/\/ PC LOAD LETTER fucked around with this message at 03:05 on Jul 8, 2011 |
|
#
¿
Jul 8, 2011 02:40
|
|
|
wicka posted:It's not really strange or amazing that Sony promoted something new and expensive and it turned out not to be the next big thing. They dumped a heap of cash into it as well though IIRC. They seemed pretty serious about pushing it for a while but after a couple of years nothing really came of it outside of the PS3.
|
|
#
¿
Jul 8, 2011 03:06
|
|
|
|
| # ¿ Sep 10, 2024 13:02 |
|
|
Supposedly GCN is big and hot compared to VLIW5/4 5xxx/6xxx GPU's so it won't be put on a APU until another die shrink or 2. No one is really sure about what the 7xxx will be exactly yet but it could very well be VLIW4's last hurrah before GCN shows up in 8xxx cards.
PC LOAD LETTER fucked around with this message at 07:11 on Jul 11, 2011 |
|
#
¿
Jul 11, 2011 07:09
|
|