|
Desperate attempt to draw traffic to a site? Or legitimate excitement?quote:I'm sitting in on a press briefing for AMD Bulldozer right now, and while everything is embargoed, I will say this: If you're building a gaming PC, this is going to be the way to go. I won't be surprised if this delivers all the performance you need for games (and then some) at a very competitive price point compared to Intel. And sufficient performance for modern games usually means sufficient performance for most other desktop tasks. I'm kind of excited to see what the G34 Bulldozer variants will deliver. I'll likely be working on a G34-based refresh for one of our server boards soon and having some Bulldozer action to toss in (and the lower TDP) will be awesome. Have they said what SB this mates with yet?
|
#
?
Oct 6, 2011 15:54
|
|
|
|
| # ? May 10, 2024 14:17 |
|
|
Reads like the first one. But I'm all for unexpected good news. Companies usually don't sit on it after crowing in the early stages about how profound an improvement it's going to be. Getting quieter and quieter closer to release with bad things happening --> jump out with confetti and a sign saying "Gotcha!" while your stockholders go all "et tu" on you for ruining that portion of their portfolio?
|
|
#
?
Oct 6, 2011 16:09
|
|
|
Sufficient gaming performance doesn't require an i5/i7 - most current games are still playable on a 2/3/4 core Athlon 2. I'll eat one of my socks if these upcoming benchmarks actually outpace Intel's current line, though.
|
|
#
?
Oct 6, 2011 16:50
|
|
|
Civil posted:Sufficient gaming performance doesn't require an i5/i7 - most current games are still playable on a 2/3/4 core Athlon 2. I'll eat one of my socks if these upcoming benchmarks actually outpace Intel's current line, though. Yeah, the fact they phrased it that way made me worry too.
|
|
#
?
Oct 6, 2011 16:55
|
|
|
trandorian posted:Yeah, the fact they phrased it that way made me worry too. The way they talked up the value proposition against Intel, too. I do like the "Please add us to your rotation guys! Please!!" movax posted:Desperate attempt to draw traffic to a site? Best comment from the link quote:Cool! Very excited for the NDA lift. Sadly, I put my computer fund into AMD stock, so I'm not sure if I'm going to be able to afford a new computer Computer nerds playing at being daytraders 
WhyteRyce fucked around with this message at 17:02 on Oct 6, 2011 |
|
#
?
Oct 6, 2011 16:58
|
|
|
PCM NL leaked benchmarks: http://www.overclock.net/rumors-unconfirmed-articles/1134704-pcm-leaked-dutch-fx-8150-review.html Summary: Cinebench 11.5 FX-8150 = 6.01 2600K = 6.73 2500K = 5.73 Dirt 3 - 1080p HD5970 FX-8150 = 105 avg, 75 min i7-965 = 93 avg, 71 min Far Cry 2 - 1080p DX10 max FX-8150 = 111 avg, 23 min i7-965 = 126 avg, 75.2 min Mafia 2 FX-8150 = 68.3 avg i7-965 = 76 avg Power consumption - full load FX-8150 = 120W Overclocking 5GHz, 1.47V Edit: Link fixed. Thanks Movax! freeforumuser fucked around with this message at 17:41 on Oct 6, 2011 |
|
#
?
Oct 6, 2011 17:27
|
|
|
freeforumuser posted:PCM NL leaked benchmarks: Fixed Link Module architecture reminds me a bit of what the Xenon can do, in terms of having 3 cores but each being 2-way SMT capable. Benchies look good; not many people are going to really need more than four cores but the price point is nice and it can at least play in the same field as Intel now. movax fucked around with this message at 17:43 on Oct 6, 2011 |
|
#
?
Oct 6, 2011 17:39
|
|
|
Didn't we already know BD would be behind the highest-end of the last-gen i7's in gaming and single-thread stuff? I'd like to see the #'s for Cinebench, single CPU
|
|
#
?
Oct 6, 2011 18:00
|
|
|
Bob Morales posted:Didn't we already know BD would be behind the highest-end of the last-gen i7's in gaming and single-thread stuff? There's Cinebench 10 in there: 2600K = 5800 FX-8150 = 4024 Single threaded IPC = (5800 / 3800MHz) / (4024 / 4200MHz) = SB has 1.6x better IPC per clock than BD. That's really sad. Actually I think thats even worse than Phenom II. freeforumuser fucked around with this message at 18:08 on Oct 6, 2011 |
|
#
?
Oct 6, 2011 18:02
|
|
|
freeforumuser posted:Far Cry 2 - 1080p DX10 max This is just confusing, how can the FPS vary by almost 90 for the AMD chip while the Intel chip only varies by 51?
|
|
#
?
Oct 6, 2011 20:09
|
|
|
Now I want to see the benches of it running at 5ghz comparing to the intel line up
|
|
#
?
Oct 6, 2011 20:31
|
|
|
trandorian posted:This is just confusing, how can the FPS vary by almost 90 for the AMD chip while the Intel chip only varies by 51?
|
|
#
?
Oct 6, 2011 20:32
|
|
|
I wonder if it has any way of keeping two floating point threads from being assigned to the same module? There were cases back in the day when HyperThreading reduced performance significantly, and it seems like there could be situations where you get similar problems on Bulldozer.
|
|
#
?
Oct 6, 2011 22:58
|
|
|
I'm not sure if that will be an issue. With hyperthreading, that problem has been largely solved at the OS level at this point. It's quite possible that will be a trivial fix with BD chips.
|
|
#
?
Oct 6, 2011 23:02
|
|
|
Factory Factory posted:All this time I've taken IPC to refer to Instructions Per Clock (which Intel is also kicking AMD's butt with). The More You Know. When concerning CPU performance, it does mean Instructions Per Clock. While a fast CPU (and especially fast/efficient core/socket interconnects) may speed up Inter-Process Communication, it is mainly a software implementation issue and a not a metric for CPU speed. Unless there are benchmarks showing a marked performance advantage for Intel vs. AMD in Inter-Process Communication, which is independent of other characteristics of the CPUs (such as memory, cache or integer performance), I think Agreed is confused.
|
|
#
?
Oct 7, 2011 16:51
|
|
|
gemuse posted:When concerning CPU performance, it does mean Instructions Per Clock. While a fast CPU (and especially fast/efficient core/socket interconnects) may speed up Inter-Process Communication, it is mainly a software implementation issue and a not a metric for CPU speed. Unless there are benchmarks showing a marked performance advantage for Intel vs. AMD in Inter-Process Communication, which is independent of other characteristics of the CPUs (such as memory, cache or integer performance), I think Agreed is confused. That's a definite possibility, though I was under the impression (could be wrong!) that there's a significant factor in the actual instruction sets/microarchitecture in terms of how they can be utilized by operating systems. E.g AMD's K10 vs. Bulldozer, and Sandy Bridge. K10: Superscalar, out-of-order execution, 32-way set associative L3 victim cache, 32-byte instruction prefetching Bulldozer: Shared L3 cache, multithreading, multicore, integrated memory controller Sandy Bridge: Simultaneous multithreading, multicore, integrated memory controller, L1/L2/L3 cache. 2 threads per core. compare that to Intel's post-Netburst return to the P6 style with the Core architecture - 4 issues wide, ditched hyperthreading and introduced macro-ops, increase to 64 KB L1 cache/core split between L1 data and L1 instruction. I thought all that would have a pretty significant impact on Inter-Process Communication because of the fairly dramatic differences in how the microarchitecture structures execution. But if I'm wrong, tell me so, always happy to learn.
|
|
#
?
Oct 7, 2011 18:01
|
|
|
I was a bit hasty, some parts of the microarchitecture can have a large impact on some IPC performance, such as the speed of execution of instructions that support locking primitives such as CMPXCHG, which has IIRC indeed seen some performance gains in later Intel CPUs. Benchmarking CMPXCHG and similar can give you some indication of the CPU's IPC performance, but since there a some types of IPC of which does not necessarily depend on hardware support, it will only be limited to measuring just a subset of possible IPC mechanisms. And in any case, it will tell you nothing of the general performance characteristics of the CPU. A CPU that has fantastic lock performance can sucks at everything else and vice versa. IPC meaning Inter-Process Communication here of course  A fast CPU will probably be pretty fast at IPC as well, but as said, it's not a metric like Instructions Per Clock (which has it's own problems).
|
|
#
?
Oct 7, 2011 21:47
|
|
|
FX-4110 Quad-core @ 4.2GHz leaks from China @ xtremesystems.org It doesn't take much effort to Google current Phenom II scores for comparison. Superpi Worse than 965BE (20.529 vs 18.252 secs) 3dmark Vantage CPU Worse than 965BE (10664 vs 11395) W-Prime: Much worse than 965BE (17.191s vs 10.764s) 7-Zip compression Worse than 975 BE (11387 vs 12547) 7-Zip decompression Worse than 975 BE (12701 vs 14294) Cinebench Single-threaded: Worse than 975 BE (1.03 vs 1.09), BTW this is the same score reported by the 8150 @ 4.2GHz PCM NL leak. Multi-threaded: Much worse than 975 BE (3.31 vs 4.27) What is this I don't even. How can AMD make a new quad-core that loses to their previous generation quads clocked 600-800 MHz slower? This is a trainwreck of epic proportions. freeforumuser fucked around with this message at 13:31 on Oct 8, 2011 |
|
#
?
Oct 8, 2011 13:11
|
|
|
A quad-core Bulldozer should be compared to a dual-core Phenom II. Each Bulldozer module contains two integer cores and a floating point unit, so a "quad-core" Bulldozer is only two modules.
|
|
#
?
Oct 8, 2011 13:54
|
|
|
We knew that, but still, they either need to go back to the drawing board and re-market it as core = module as opposed to module = 2 cores, otherwise this is just a flat out embarrassment..
|
|
#
?
Oct 8, 2011 14:34
|
|
|
The cat is out of the bag now, with a legit Romanian hardware review site doing a FX-8150 preview: http://lab501.ro/procesoare-chipseturi/amd-fx-8150-bulldozer-preview/14 tl;dr version: Loses heavily in everything to 2600K, except Handbrake it comes within 1% of 2600K. BD isn't going to find itself in the SH/SC recommendation thread anytime soon.
|
|
#
?
Oct 9, 2011 05:36
|
|
|
How does the first Bulldozer review describe performance? "Downright tragic." If those numbers are anywhere near what the platform should be producing, AMD is hosed. It's simply not performing worth a drat in multi-threaded applications, and that should be its strong-suit. The fact that in some tests it's even losing to a Phenom II leaves me at a loss for words.
|
|
#
?
Oct 9, 2011 06:01
|
|
|
Really surprising considering the HardOCP guy alluded to buyers being happy with BD if they overclock. If these numbers are close to being remotely true then that JFAMD guy will never be able to show his face on boards again after all his "these aren't official benches and should be regarded as fake!" talk the past two months in response to "leaks"
|
|
#
?
Oct 9, 2011 06:06
|
|
|
Alereon posted:How does the first Bulldozer review describe performance? "Downright tragic." Yeah, this is just incredibly bad news. I am still waiting for Anandtech to get their hands on it, but it's looking more and more like AMD is delivering this product effectively stillborn. Meanwhile, tick, tock, tick, tock, tick, tock... Edit: I can't believe how miserable the floating point performance is. How in the gently caress can they put in two flexible 128-bit floating point hardware units per module and get results that are so deflated? And its overclocking seems to be "about as good as Sandy Bridge for clock rate" with worse performance and ungodly power draw. Intel's improvements to hyperthreading, optimizations for its usage, and processing efficiency mean they're wiping their asses with Bulldozer's floating point performance, which of anything, ANYTHING it should be able to dominate at, should be that. Some kind of absolutely tragic mistakes and bad decisions and poor guesses and rotten luck combined here, the modules thing appears to just totally screwed. I was concerned about the way their new execution process might look when the gaming benches suggested that AMD has much wilder variance when intensive processing that involves more guesswork in the pipeline starts going on, but this really underlines that their module idea is a rotten egg. This is just poo poo. They must have spent a lot of time trying to make this into something worthwhile but it's just more disappointment and they can't afford that. I dread the opening of trading if this information is generally out by Monday. God drat. Again, I am still waiting for official stuff, but silence from AMD is absolutely deafening at this point given the nature of the information coming out. Fuuuuuuck. Agreed fucked around with this message at 06:37 on Oct 9, 2011 |
|
#
?
Oct 9, 2011 06:25
|
|
|
Man, this is beyond pathetic. AMD really has no hope of regaining any lost ground. Especially considering windows 8 is coming soon, and it will run on ARM, the old battle of Intel vs AMD will just become irrelevant. It's going to be Intel vs ARM. No one in their right mind is going to buy this lovely loving processor.
|
|
#
?
Oct 9, 2011 11:01
|
|
|
hootimus posted:Man, this is beyond pathetic. AMD really has no hope of regaining any lost ground. Especially considering windows 8 is coming soon, and it will run on ARM, the old battle of Intel vs AMD will just become irrelevant. It's going to be Intel vs ARM. No one in their right mind is going to buy this lovely loving processor. Intel vs. ARM isn't even a battle. Intel laptops can run for 7 hours (Macbook Air, Macbook Pro) or more time (netbooks) all while having way more computing power to hand than any ARM chip. The latest, most cutting edge, 8 core ARM chips are on par, performance wise, with a Core 2 Duo from 2006, and take just as much power to do that as said Core 2 Duo chips did. Cost more too. It would take a radical change in a lot of things to get comparable performance for everyday non-trivial Windows applications on the ARM platform, and if things actually started getting close, Intel could simply license ARM themselves and start cranking them out again.
|
|
#
?
Oct 9, 2011 11:07
|
|
|
Well what I mean is, Intel wants to compete in the mobile device world (phones and tablets) and they couldn't give a poo poo about AMD. With Win 8 supporting ARM, that will give Intel extra incentive to compete, because every Win 8 tablet or phone with an ARM inside is a lost sale for Intel. I could be wrong, Win 8 on ARM could be total poo poo, in which case Intel would not care. But I think it's going to become a big deal for them and for consumers in general.
|
|
#
?
Oct 9, 2011 11:17
|
|
|
trandorian posted:Intel vs. ARM isn't even a battle. Intel laptops can run for 7 hours (Macbook Air, Macbook Pro) or more time (netbooks) all while having way more computing power to hand than any ARM chip. The reality is that with the move to an out-of-order architecture in the Cortex A9, ARM processors became performance competitive, especially with low-power x86 designs like the Atom. With the move to the Cortex A15, per-core performance rises to a level that begins to be adequate for desktop workloads. When paired with a current-generation mobile GPU you have performance that's better than a 360/PS3, meaning even gaming isn't outside the realm of possibility. When you consider whether such a system would be usably fast, remember that people were happy to buy Atom netbooks and nettops with a tiny fraction of the raw CPU power and no ability to play video or do 3D, but an ARM processor can do all that AND is unencumbered by a legacy x86 Windows codebase. We're not going to see ARM beating Core i5s for desktop performance benchmarks, but i3s might be within reach, and with a fraction of the power usage. Edit: I should note that it's hard to directly compare a mobile processor built on a low-power manufacturing process to a desktop one built on a high-performance process, much less processors with vastly different CPU architectures. If ARM decided to directly attack the desktop market, they'd probably design a processor to be built on a high-performance process and scale to high clockspeeds. This is a lot of work and will take a long time, so it's likely that they'll just attack the periphery of the market with Cortex A15, where Intel/AMD's performance isn't required. Keep an eye on nVidia though, they have a project to develop a high-performance ARM processor using Code Morphing Technology they licensed from Transmeta. Code Morphing was originally used to try to run x86 code faster and more efficiently on a special processor custom-designed for the purpose, the Transmeta Crusoe. nVidia licensed it with the goal of making x86 programs run on their ARM processors, but Intel sued to put the kibosh on that. Instead, nVidia will go back to Transmeta's roots and try to use Code Morphing to run ARM code on a custom-designed CPU even faster/more efficiently than it would on an ARM CPU. Alereon fucked around with this message at 12:41 on Oct 9, 2011 |
|
#
?
Oct 9, 2011 12:27
|
|
|
freeforumuser posted:The cat is out of the bag now, with a legit Romanian hardware review site doing a FX-8150 preview: Oh man that is a complete slaughter, what a disappointment.
|
|
#
?
Oct 9, 2011 17:01
|
|
|
Oh dear. I still want proper reviews, but nothing we've seen is good. Edit: Just skimmed through and looked at all the images in that preview. Dear god. Worse than the 2600k all round, whilst using more power. Advertised as 8 core, yet is crapped on by a 4 core with HT. (Yes, I understand why they call it 8, and why it isn't in truth). I don't know what AMD can do now. This architecture is a dead end. drat. Bulldozer? More like a plastic toy shovel.. HalloKitty fucked around with this message at 13:10 on Oct 10, 2011 |
|
#
?
Oct 9, 2011 17:18
|
|
|
If Bulldozer is doing this poorly on the desktop, I can't imagine what kind of trouble they're having with Virgo and Comal. Comal will be especially difficult because its a mobile platform that needs its power profile kept within lower limits than a desktop. At the very least, they need them to match Lynx and Sabine or they're going to be an even tougher sell than Bulldozer. Especially since this coming year's Fusion lineup will be using Bulldozer cores for mainstream APUs with Bobcat-based APUs for low-power applications and no announced K10-based APUs in the pipeline.
|
|
#
?
Oct 10, 2011 22:17
|
|
|
Agreed posted:Again, I am still waiting for official stuff, but silence from AMD is absolutely deafening at this point given the nature of the information coming out. Fuuuuuuck. Yea, them being silent plus all the delays is what finally made me give up on BD. In theory the chip sounds like it should be pretty good while having a smaller die size but it looks like AMD hosed up their implementation. Usually when any of these tech companies have something good they "leak" info. like a sieve. When they gently caress up they get as quiet as a mouse and then start pimping the next product. AMD is being very quiet on BD but is happily hyping up Piledriver (improved BD) for next year.
|
|
#
?
Oct 11, 2011 00:41
|
|
|
If Bulldozer matches an 2500k in terms of performance and price, is that enough?
|
|
#
?
Oct 11, 2011 06:17
|
|
|
Ragingsheep posted:If Bulldozer matches an 2500k in terms of performance and price, is that enough? I don't think so; the 2500K was essentially completed a year ago, if not longer. Several revisions of the chip have been taped out, the chipsets for it are mature and Intel is busy at work getting Ivy Bridge ready for mass product; 22nm ES silicon is already at the majority of ISVs, and that product will only exceed Sandy Bridge performance with no regressions (ideally) as well as correcting some Sandy Bridge errata. I think AMD has to provide a very compelling budget-conscious processor, an area they have historically dominated in (hell I picked an Athlon II for my server build several years ago because the equivalent Intel hardware was a good $150+ more and delivered less performance). Delivering a comparable product is good, but it is not so good when you're always racing to catch up and your competitor has the resources to put out an immediate successor to the chip you're trying to compete with, as well as being a full generation ahead with physical silicon of their next generation architecture.
|
|
#
?
Oct 11, 2011 06:35
|
|
|
Ragingsheep posted:If Bulldozer matches an 2500k in terms of performance and price, is that enough? Not really, because by current numbers, it's using a LOT more power to do less. Unless the price is significantly less, you'd have to an AMD fanboy to buy AMD chips for mass desktops (power concerns) or your gaming desktop (limits your GPU performance, as well as sucking down more power, meaning the thing will be a drat space heater combined with the GPU). I think Brazos is the only thing AMD has going right now, which isn't saying a huge amount. Having a chip that's marginally better than Atom in all ways is a low-end space to play in. HalloKitty fucked around with this message at 07:55 on Oct 11, 2011 |
|
#
?
Oct 11, 2011 07:51
|
|
|
Not to mention that 2500k's overclock like beasts out of hell and are getting a price cut the moment the bulldozer chips come out. You are also guaranteed an upgrade path if you really need it to the ivy bridge models. Bulldozer is too little too late for AMD.
|
|
#
?
Oct 11, 2011 20:07
|
|
|
My Llano chipset's got some interesting performance. It's a laptop A6, and for some reason, it's possible to overclock/undervolt the thing. The 1.4ghz/2.2ghz turbo seems incredibly generous, the Tj. Max is 115c according to querying it using CoreTemp (which may be wrong, I'm not really trying this yet, personally.) It'd be rather interesting if they kept going with the low cost stuff in laptops, as this was the best thing I could find under $600 or so. I'm wondering if they could release unlock codes like the i3 ones to enable a system to run at 1.6/2.4 or something like that. It seems like the combination of graphics and CPU is doing really well in low-end mobile gaming, even if the higher end CPUs are doing terribly. I'm wondering if the way they're doing production is to just have really generous testing to minimize the number of unacceptable chips.
|
|
#
?
Oct 11, 2011 20:26
|
|
|
Cao Ni Ma posted:Not to mention that 2500k's overclock like beasts out of hell and are getting a price cut the moment the bulldozer chips come out. You are also guaranteed an upgrade path if you really need it to the ivy bridge models. I thought Intel didn't cut prices of their chips. But yeah, AMD is getting a serious black eye off this one. I hope it doesn't mean the beginning of the end. Intel needs a competitor.
|
|
#
?
Oct 11, 2011 20:28
|
|
|
Civil posted:I thought Intel didn't cut prices of their chips. But yeah, AMD is getting a serious black eye off this one. I hope it doesn't mean the beginning of the end. Intel needs a competitor. They've announced a 2700K which will take the price spot of the 2600K, should just be a binned 2600K if I understand it correctly but that would trickle down.
|
|
#
?
Oct 11, 2011 20:55
|
|
|
|
| # ? May 10, 2024 14:17 |
|
|
Civil posted:I thought Intel didn't cut prices of their chips. But yeah, AMD is getting a serious black eye off this one. I hope it doesn't mean the beginning of the end. Intel needs a competitor. The 2700k will replace the 2600k so the 2600k will get a natural price cut. I'd guess they'll lower the price of the rest of the chips to compensate as well but there's a chance Intel wont do it cause lack of competition etc.
|
|
#
?
Oct 11, 2011 20:57
|
|