|
MeramJert posted:There is absolutely no way getting a 2500k will only cost you $50-$100 more than an Athlon II x4 system It'll get you the processor, at least. 
|
#
¿
Apr 1, 2011 13:58
|
|
|
|
| # ¿ Apr 28, 2024 07:55 |
|
|
Combat Pretzel posted:Dual CPU crew represent! What up, symmetric multiprocessing buddy?  I used a year of allowance and job earnings in high school to buy an A7M266-D fitted with one Athlon MP Palomino 1800+ (1.53 GHz). Got the second processor a month later for my birthday.  Later I watercooled them because I was a dumb teenager. But the experience cured me of ridiculous builds forever. It was a drat sight better than my T-Bird on that super-flaky A7A266 with both PC133 and DDR SDRAM support. Goes to show: always find reviews that cover stability, 'cause that thing hosed itself once every two weeks and I did two RMAs before giving up on it. Factory Factory fucked around with this message at 16:12 on Apr 10, 2011 |
|
#
¿
Apr 10, 2011 13:04
|
|
|
Is that the top 4-core or comparing 8-core to the i7-2600K's 4-core? AMD seems to be going all-in on multithreaded performance if that's an 8 vs. 4 comparison. Then again, that would mirror their graphics strategies. It'll kinda suck when 6/8-core Sandy Bridge E parts come out. Poor AMD 
|
|
#
¿
May 4, 2011 20:56
|
|
|
Higher clock speeds on the lower-core processors, maybe?
|
|
#
¿
May 20, 2011 23:26
|
|
|
Alereon posted:To be fair, it isn't directly comparable to desktop-class cards because of the reduced memory bandwidth. Llano has 29.8GB/sec shared between the CPU cores and GPU, desktop cards (those intended for 3D) have at least 64GB/sec. The lower-end cards intended for HTPC and video applications do have as little as 28.8GB/sec though, so Llano will easily mean videocards are only necessary for gaming. Actually, video cards aren't anywhere near as bandwidth-intensive as their interconnects suggest. Everything below a dual-GPU card actually loses only a handful percent of their performance scaling all the way down to a PCIe x4 connect. Also, PCIe 2.0 x16 only runs at 8 GB/s (500 MB/s per lane times 16 lanes). You might be thinking gigabits. VVVV Ahh, derp.  'kay.
Factory Factory fucked around with this message at 20:05 on May 21, 2011 |
|
#
¿
May 21, 2011 19:55
|
|
|
I dunno how kosher it is to repeat this, but Star War Sex Parrot gave an offhand comment in the System Building thread about being both really disappointed with Bulldozer and bound by NDA about the subject. Also mentioned was how it seemed nice for workstations and servers, but otherwise was not impressive. I'm thinking the FPU design backfired - the half-as-many-as-cores, double-wide, bifurcating thing just doesn't sound like it would really hold up to the floating-point-strong Intel Core processors. I was optimistic for BD, but ever since I heard about its design, I felt like it was pushing the Phenom "more cores" strategy out too far. Rather than being designed for today's (or even tomorrow's) most pressing processing needs, the chips are designed toward some highly-parallelized vision of software years from now, putting power in the wrong places compared to what most people usually wait on their processors for now.
|
|
#
¿
May 30, 2011 12:00
|
|
|
Maybe nVidia will rethink declining to design an x86 CPU? Or maybe AMD will take this as a good prompt to go on a hiring binge and build something new in a relatively short time. Hell, maybe even call back to the team featured in The Soul of a New Machine and grab a whole bunch of novice graduates to... well, no. AMD has their GPUs and a sufficient CPU for budget uses. This isn't make-or-break for them.
|
|
#
¿
Jun 24, 2011 18:38
|
|
|
This is why good review sites will actually load up some apps and games and time a standardized task that mimics real-world use.
|
|
#
¿
Jun 24, 2011 22:29
|
|
|
fishmech posted:And what that means is Windows on ARM will barely have any software. If it's the same OS and the same APIs, isn't it just a question of some guy (possibly at Microsoft) writing and selling an ARM compiler to set as a target alongside the x86 compiler? As long as the software doesn't use any assembly code, at least.
|
|
#
¿
Jun 26, 2011 00:47
|
|
|
Yeah but... Yeah, okay. But those didn't really have major market penetration, whereas a Windows 8 tablet or ultraportable notebook might. It's kind of a chicken-or-egg question, though. Without apps, such devices will never get good penetration. Also, stop making me remember my iPaq.
|
|
#
¿
Jun 26, 2011 03:33
|
|
|
Bob Morales posted:If they can offer 80% of the performance for 30% of the price (like the X6 compared to the i7) then that's good enough Intel's been doing that, too. The $1000 hexacore Nehalem i7 is matched by the quad-core Sandy Bridge i7 in most tasks (and that's just at stock clocks), and it costs $300. Granted, the top-end Phenom II x6 is down to ~$200 now, but still. Intel seriously closed the price gap and has monstrous performers for chips.
|
|
#
¿
Jun 30, 2011 22:03
|
|
|
What I don't understand is how the chip can slot between the i7-2600K and the i7-990X. In all but a very few tasks, they are neck and neck, with the 2600K winning on per-thread tasks and the 990X winning on heavily multithreaded/floating point tasks. Where does the FX-8130p fit in, exactly?
|
|
#
¿
Jul 13, 2011 06:44
|
|
|
FFS, it's not even out yet. Stop having a sperg contest. According to Wikipedia, the L3 is shared between all cores, but none of the currently-known (i.e. possibly old and outdated) SKUs will have less than 8 MB of L3 cache. L2 cache is paired with the Bulldozer modules and is slated to be 1 MB/core regardless of number of cores.
|
|
#
¿
Aug 23, 2011 02:08
|
|
|
Maxwell Adams posted:That page says there are two kinds of FX-8120, the only difference being the TDP. That seems a bit weird. TDP is actually important for Turbo Core purposes. If Bulldozer works like the A-series APU, then the TDP will provide an upper thermal and electrical limit for per-core overclocking, and it will not be possible to override or ignore this limit like with Turbo Boost on Intel CPUs. I'm guessing it will be configurable, ultimately, as AMD usually caters to enthusiasts that way, but for stock performance it can make quite the difference. E: Just looked it up, TDP will be configurable, and you can set a maximum TDP for automatic reclocking as an alternative to manual overclocking.
|
|
#
¿
Sep 3, 2011 03:09
|
|
|
Alereon posted:Their benchmarks are also against the i7 980X on the Intel side, and while that's a hex-core, it's not terribly competitive with the Sandy Bridge quad cores in most applications, especially gaming. Well, "not competitive" tends to mean "equal performance for 4-5x the price", so this if this is accurate, it ends up meaning a good price/performance match for Sandy Bridge CPUs. From an enthusiast standpoint, which platform becomes the platform to buy depends on use-specific benchmarks, motherboard prices, and average overclocking performance. These FX chips are already being clocked fairly high, and AMD is claiming 5 GHz+ on air, but Sandy Bridge chips can do 5 GHz+ on air, too... if you get REALLY lucky in the chip lottery. It still remains to be seen whether there's as much headroom on the average FX chip as on the average i5-2500K.
|
|
#
¿
Sep 24, 2011 21:47
|
|
|
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.
|
|
#
¿
Oct 2, 2011 04:22
|
|
|
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
|
|
|
They could also just stop selling the 2600K.
|
|
#
¿
Oct 11, 2011 22:10
|
|
|
Tom's Hardware: http://www.tomshardware.com/reviews/fx-8150-zambezi-bulldozer-990fx,3043.html Engadget has some useless "Hey, lookit these marketing slides!" drivel. E: As I'm reading, it seems that all of the FX CPUs are the same silicon, just with Bulldozer modules turned off? Jesus, way to leverage your lovely fabs. Factory Factory fucked around with this message at 05:18 on Oct 12, 2011 |
|
#
¿
Oct 12, 2011 05:11
|
|
|
Also, it does indeed look like there will be process scheduling issues in Windows analogous to Hyperthreading inefficiencies, and though Microsoft is on the case, that there will be some time before they are resolved. As such, all benchmarks we see (which I haven't even gotten to yet, personally) will be filling threads inefficiently. e: Single-threaded performance   All turbo and power saving disabled, for the record. Factory Factory fucked around with this message at 05:34 on Oct 12, 2011 |
|
#
¿
Oct 12, 2011 05:25
|
|
|
That said, I'm getting to the benchmarks (finally) in Tom's review, and the multicore performance really is pretty good. Even hobbled by whatever inefficiencies may be from the module-not-cores architecture, the FX-8150 is holding up extremely well in content creation apps. Sometimes it's the out-and-out winner between the 2600K, 2500K, and 1100T, sometimes it's in between those, and sometimes... Well, okay, sometimes it's outperformed by a quad-core Phenom II. Still, my expectations have been minimized sufficiently that this is slightly impressing me.
|
|
#
¿
Oct 12, 2011 05:59
|
|
|
MeramJert posted:Well, you did pick the single worst performing benchmark. It's not like the single-threaded performance really is as bad as this across all of them. True, but it's still disappointing from a desktop use point of view. That said, it turns out that Windows 8 Dev Preview has all the "treat modules as modules, not cores" code in it, so the FX-8150 actually makes up a little ground in lightly-threaded games on Windows 8 instead of Win 7, plus it saves power. Alereon posted:I would consider an 8-core processor that can't quite equal a quad-core to be a pretty serious failure. The HardOCP Cinebench numbers show Bulldozer BARELY beating a Phenom II X6, and losing slightly to the i7 2600K. Things are a bit better for POVRay, but I'd definitely say that multi-threaded performnace is far below expectations. I never really expected per-core performance to be good, but I at least thought it would win pretty handily in heavily multi-threaded integer workloads, and that is definitively not the case. I would have also hoped that per-thread floating point performance would go up over Phenom II, but instead it seems to have dropped, pretty seriously when you consider that Bulldozer has a 200-500Mhz clock speed advantage, depending on how effective Turbo Core is. On one hand, yes, you are absolutely right. Compared to where Bulldozer should be given the state of technology and its competition, both in-house and out, it's disappointing. That said, there are some usage profiles where, if you want to buy $200-$300 of CPU, Bulldozer can stand and deliver. It's not a total shut-out. I'm the guy in a prison camp thrilled about being beaten only six days a week instead of daily, here. Factory Factory fucked around with this message at 06:28 on Oct 12, 2011 |
|
#
¿
Oct 12, 2011 06:19
|
|
|
Agreed posted:I think the whole thing is pretty ridiculous but what kills it completely is the power draw, what the gently caress is up with such an absolutely massive difference in power draw under load compared to Intel? More transistors, more voltage (power draw increases with the square of voltage). And probably something else going on, because I wrote this whole effortpost based on P=CV2f assuming C (capacitance) was constant given changes in V and f, and while the Intel CPUs in [H]'s overclocked power consumption results jived to a first approximation, the FX used a ton more power overclocked than using that formula would suggest.
|
|
#
¿
Oct 12, 2011 18:26
|
|
|
Spiderdrake posted:Which benchmark best represents what servers need or will do with Bulldozer? It honestly depends on the workload. If all of the cores are loaded well, it could perform like the best benchmarks and have reasonable performance/watt at stock clocks (albeit not as good as Intel). If anything goes wrong, it starts sucking ducks.
|
|
#
¿
Oct 13, 2011 04:39
|
|
|
notwithoutmyanus posted:I note that windows 7 and 8 don't show a substantial difference, yet read all this stuff about scheduler problems, etc, which were mentioned on the last page. 10% free performance in lightly-threaded applications is pretty substantial and reasonable, all things considered. It's not like the modules are as un-core-like as Hyperthreading, which duplicates only floating point execute units. The BD modules are really really close to being two cores, so scheduler inefficiency isn't gonna hit them THAT hard.
|
|
#
¿
Oct 13, 2011 19:45
|
|
|
angrytech posted:God drat it why do I feel like I'll end up going from Athlon64 -> Piledriver based on the name alone. http://www.10stripe.com/articles/where-do-they-get-their-codenames.php http://en.wikipedia.org/wiki/List_of_Intel_codenames I'd lmgtfy it, but 
|
|
#
¿
Oct 28, 2011 05:11
|
|
|
They're just a bystander. Skynet was built on TSMC's 28nm process.
|
|
#
¿
Nov 22, 2011 13:30
|
|
|
Y'know, one thing that's been bugging my uninformed-about-chip-fab self about Bulldozer has been AMD's recommended overclocking voltages. In [H]'s Bulldozer review, it quoted AMD as saying to overclock by setting a Vcore from 1.4 to 1.55 V. It took a little re-evaluation, but Intel recommended a top voltage of 1.38 V for their 32nm processors. Is AMD's process different, or are overclocked Bulldozer chips going to burn out faster than a fart in a frat house?
|
|
#
¿
Nov 22, 2011 15:46
|
|
|
Shaocaholica posted:This is not a bad thing IMO. These people will spread their wacky logic to others in their circle of friends and family and hopefully game developers won't be so shy to actually leverage their engines against more cores. Its a catch-22 which needs these people to push things forward. Thing is, quad-core CPUs are by no means universal: link. About as many Steam users are still using dual-core CPUs as are using quad-cores. Folks with 8-core BD CPUs will be long, long, long in waiting for their market segment to have enough representation for 4 vs. 8 threads to be worth a programmer's time.
|
|
#
¿
Nov 25, 2011 17:13
|
|
|
A couple years ago, just before I graduated, I happened across an AMD engineer alum who was recruiting at my school's electrical and computer engineering program. He was packing up but was glad to give the elevator version of his recruiting pitch and flip through the Powerpoint a bit. I noted AMD's GPU strategy of competing with what were, in essence, highly scaleable midrange parts, and I asked if a similar strategy was going to come into the CPU market and help bridge the (ca. 2008) performance gap with Intel. Or if they would push harder on the low-end market and try to usurp mass-market computing. The guy just... shut down. Like, his eyes kinda went vacant, he said that AMD didn't see its processors as second best, and the conversation, which had been fairly lively as these things go, just ended. In retrospect, that was a lot more meaningful than I thought at the time.
|
|
#
¿
Nov 30, 2011 03:38
|
|
|
Hold on, wait, what? AMD is entering the DDR3 SDRAM market. Is this not a big deal or did it completely slip this thread by?
|
|
#
¿
Nov 30, 2011 15:29
|
|
|
Faceless Clock posted:That's just with Llano. Sandy Bridge doesn't see much benefit from faster RAM. Part of the point here is that AMD makes and sells Llano and not Sandy Bridge. And adding faster RAM to Llano improves its value vs. Sandy Bridge solutions.
|
|
#
¿
Nov 30, 2011 23:33
|
|
|
It's the bee's knees for low-priced laptops. It's really driven down the price of Intel stuff to compete with it, too. Desktops? Eh.
|
|
#
¿
Dec 6, 2011 00:57
|
|
|
I do a full HTPC because I actually don't have a huge transcoded media archive. I spend most of my storage on documents and media I create and backups of my PCs, and all my video stuff is live/recorded cable TV, streaming from YouTube and Hulu, and physical disks. It would actually be more of a pain in the rear end to convert everything over to STB-playable stuff than just deal with the four different player softwares and web browser - all of which work great, they just aren't centralized. And I'd need more, expensive storage to boot. It's an E350 mini-ITX box, and I love it.
|
|
#
¿
Dec 6, 2011 05:46
|
|
|
Blu-Rays, DVDs, YouTube, Hulu, and a CableCard TV tuner with DVR functionality in one device. v v
|
|
#
¿
Dec 6, 2011 06:40
|
|
|
For what it's worth, the fan on my ASRock E350 board may be tiny and lovely, but it's not loud.
|
|
#
¿
Dec 6, 2011 07:30
|
|
|
That was incredibly disappointing.
|
|
#
¿
Dec 7, 2011 10:43
|
|
|
AMD has been pretty good about that within HD 5000 and HD 6000, as long as you don't try to compare them to each other. The gradations aren't regular, but a higher number does indeed mean it is better.
|
|
#
¿
Dec 16, 2011 02:14
|
|
|
A 6990 is essentially two core-unlocked 6950s in SLI. It's quite a bit more quick than 30% faster than a 6970. So a 7970 is still not going to directly compete with that monster even if the 30% faster thing is accurate.
|
|
#
¿
Dec 16, 2011 23:11
|
|
|
|
| # ¿ Apr 28, 2024 07:55 |
|
|
Oh, Lord, they're copying the K from Intel. Still, if the secondhand marketing mumbo-jumbo is correct, they both look like very attractive alternatives to an i3 at that price.
|
|
#
¿
Dec 17, 2011 08:07
|
|