|
 https://twitter.com/NVIDIAGeForce/status/895746289589039104
|
#
¿
Aug 11, 2017 02:02
|
|
|
|
| # ¿ May 16, 2024 22:34 |
|
|
wargames posted:Threadripper 8 core does make way more sense then x299 kabylake-x only because pci-e lanes. Also quad channel RAM.
|
|
#
¿
Aug 11, 2017 03:49
|
|
|
I always read techpowerup first and it's almost entirely because of their graphs. Having nice neat charts of performance, performance/W, and performance/$ is something everyone should do.
|
|
#
¿
Aug 15, 2017 01:40
|
|
|
HalloKitty posted:It really didn't. I remember talking to a friend back then and betting ARM would become the next big architecture, even on the desktop, but I never saw the demise of x86, it's just too deeply embedded. It's.. kind of come true. At least ARM is far more successful than Itanium. Explicitly parallel instruction computing design for CPUs just turned out to be a pretty lovely and unworkable solution and would have sucked even without x86 momentum. ARM on the other hand is inherently better but nowhere near enough to overcome said momentum.
|
|
#
¿
Aug 26, 2017 22:57
|
|
|
That's a hell of a build and good overclocking numbers, will probably do something similar with Threadripper 2 and Big Volta sans SLI.
|
|
#
¿
Sep 25, 2017 01:14
|
|
|
jeffreyw posted:I have a question regarding Threadripper. Looking at Puget System's benchmarks of Adobe and CAD suites, Intel's similarly priced 7900X typically matches or keeps up with the 1950X in multithreaded tasks but completely slaughters it when tasks are poorly threaded. Unfortunately, there isn't much to compare with as most reviewers don;t go much further then use Cinebench, don't test professional programs or don't really go into detail what they're actually testing. The 1950X beats the 7900X by a pretty good margin in tasks that scale really well with more cores, it all depends on what tasks and what software you're going to be using. https://www.pcper.com/reviews/Processors/AMD-Ryzen-Threadripper-1950X-and-1920X-Review/Media-Encoding-and-Rendering
|
|
#
¿
Sep 25, 2017 19:29
|
|
|
SlayVus posted:I thought the majority of games running 4k on consoles were all running some kind of rendering trucks like checker board. To get the visual quality they do at 1080p in 4k, I doubt any consoles could do legitimate native 4k. The 1070 barely does 30 fps in Ghost Recon Wildlands and less then 30 in Deus Ex, surprisingly gets ~50 fps in BF1. Console games can be optimized a lot better than PC games since you're always gonna be running one set of hardware, it would probably be better to use a really well optimized game like DOOM as a point of comparison. https://twitter.com/id_aa_carmack/status/436012673243693056?lang=en
|
|
#
¿
Oct 31, 2017 17:05
|
|
|
Seamonster posted:Perhaps not as outright awful as RAM but SSD prices have increased per GB as well. And innovation in terms of drive size has utterly stagnated too. Where the hell are our 4TB drives for ~$800? Innovation hasn't stagnated it's just the supply shortage keeping prices high which makes higher capacities make less sense, things should be better by 2019 sometime when more production capacity is coming online.
|
|
#
¿
Jan 6, 2018 02:38
|
|
|
https://twitter.com/ryanshrout/status/950230588149006336
|
|
#
¿
Jan 8, 2018 06:13
|
|
|
Why are people mad at PCPer?
|
|
#
¿
Jan 27, 2018 00:52
|
|
|
The amount of time he spends dwelling on PCPer taking a dig at his "Con Lake" video on Twitter makes it hard to believe that had no influence on his video, I wish he would have just stuck to the freesync thing because that does sound fishy.
|
|
#
¿
Jan 27, 2018 03:12
|
|
|
I always like TPU for their graphs, pretty solid 1080p gaming improvements and overall right up there with the 8700k, not bad at all. 
|
|
#
¿
Apr 19, 2018 19:37
|
|
|
SamDabbers posted:I can't be the only one who wants to see a workstation-class ARM chip, right? Will ARM always be relegated to low power implementations? No I've really wanted a windows ARM laptop or desktop for a while, I can't even really articulate why I just want one. Maybe it's because I've enjoyed tinkering around with ARM linux SBCs for the past few years. FaustianQ posted:Isn't x86 vs ARM more about whether the stronger x86 cores will lose out to ARMs ability to just leverage a hell of a lot more cores for a given wattage? Well current ARM designs are mostly low-power cores designed for mobile, if you wanted to compete with x86 you'd design an ARM core with a higher TDP. The big question is whether or not ARM offers much of a performance/watt advantage over x86 when scaled up to the level of performance needed for a laptop or desktop. MaxxBot fucked around with this message at 20:38 on Apr 27, 2018 |
|
#
¿
Apr 27, 2018 20:32
|
|
|
Rastor posted:That's the best kind of correct, but the practical effect of doubling transistor count was doubling performance. The reason CPU performance has stalled isn't because transistor counts are stalled, as Subjunctive pointed out other areas like GPUs are still seeing big gains every generation. If you could just keep adding more cores like you can with a GPU we'd still be seeing big gains, but that approach doesn't work for CPUs because you need to balance single and multi-threaded performance. CPU performance gains have stalled because clock speed improvements have stalled and IPC gains are not even close to being linear with increased transistor counts of the individual cores. Basically it comes down to the fact that further increases in single-threaded IPC at this point are really difficult. MaxxBot fucked around with this message at 07:43 on May 6, 2018 |
|
#
¿
May 6, 2018 07:37
|
|
|
MaxxBot fucked around with this message at 19:58 on May 18, 2018 |
|
#
¿
May 18, 2018 19:46
|
|
|
Core wars https://twitter.com/david_schor/status/1004198284515270656?s=19 
MaxxBot fucked around with this message at 04:10 on Jun 6, 2018 |
|
#
¿
Jun 6, 2018 04:07
|
|
|
Devian666 posted:The price of the Epyc chips is pretty drat crazy at the low end so yeah 32 core TR is likely to have an eye bleed price. The multi socket capable EPYCs are pretty expensive but the single socket ones are quite reasonable, there's a 24-core one for $1000.
|
|
#
¿
Jun 6, 2018 06:47
|
|
|
Well Ryzen 2 is gonna have 12-16 cores which is a good balance of moar corez and not having to deal with the NUMA stuff or high cost of TR.
|
|
#
¿
Jun 7, 2018 22:43
|
|
|
https://twitter.com/AMDNews/status/1022235553838903296
|
|
#
¿
Jul 26, 2018 19:13
|
|
|
|
|
#
¿
Jul 30, 2018 19:34
|
|
|
https://twitter.com/Cat_Merc/status/1026191903052767232?s=19
|
|
#
¿
Aug 5, 2018 22:51
|
|
|
Truga posted:I have it on pretty good authority that epyc2 is going to be 8x8 cores and also a +1 something else. Is there anything that +1 thing could be besides a gpu? I've seen the same thing with regards to the 8+1, people seem to think the ninth die is something to do with I/O.
|
|
#
¿
Sep 15, 2018 01:12
|
|
|
Yeah the Apple A12 went with the crazy wide and massive caches approach on the same process and I would assume that Zen 2 would do something like that as well since rumors are not pointing to much in the way of clock speed bumps, that's a guess though. I have not heard any specific rumors about the Zen 2 uarch other than that it will have wider AVX.
MaxxBot fucked around with this message at 16:20 on Oct 17, 2018 |
|
#
¿
Oct 17, 2018 16:14
|
|
|
isndl posted:What do you recommend for scrambling eggs? Can't find Pentium 4s anymore. GTX 480, it has a griddle built right in on top https://www.youtube.com/watch?v=BLdXfFsgvkE MaxxBot fucked around with this message at 18:12 on Nov 12, 2018 |
|
#
¿
Nov 12, 2018 18:09
|
|
|
I remember when Zen 1 came out they claimed that AM4 would last through 2020 so I'd assume yeah unless that's changed.
|
|
#
¿
Nov 12, 2018 18:35
|
|
|
PC LOAD LETTER posted:Or that the price difference isn't worth it for what frequently are unnoticeable performance differences outside of synth benches. Yeah when you include the cost of a CPU cooler it's almost double going from a Ryzen 2600 to a 9600k or a Ryzen 2700X to a 9900k, I wouldn't go for that unless I really wanted 120Hz+ gaming or just had a lot of expendable income. Even with an i5-8400 you're looking at 5% extra 1080p gaming performance for over $100 more cost vs a R5 2600. MaxxBot fucked around with this message at 04:05 on Nov 23, 2018 |
|
#
¿
Nov 23, 2018 03:53
|
|
|
Dr. Fishopolis posted:Are you kidding? It's the first product on a new process, there's miles and miles of improvement to go. I think trying to predict several years ahead in this game is just foolish in general, no way would I have predicted $130 8-core CPUs just a couple years back.
|
|
#
¿
Dec 2, 2018 23:33
|
|
|
The pricing and crazy number of different SKUs and naming schemes is what makes me skeptical as well.
|
|
#
¿
Dec 3, 2018 19:15
|
|
|
I mean the odds are pretty good for a reasonably priced 32-core TR but I don't know about 5GHz.
|
|
#
¿
Dec 3, 2018 21:57
|
|
|
sincx posted:My reason for thinking it's fake is that the photo was obviously of a high resolution monitor, at least 1440p and possibly 4k. I have never seen a >1080p monitor at any accounting, sales, or supply chain worker's desk. Hell, most of them still use 22" 1600x900 Dells. I knew a lady working in supply chain who would have like 100 windows open on her 13" laptop screen until she would get out of RAM errors, a couple nice monitors probably would have doubled her productivity since she would spend like 2 minutes hunting for the desired window.
|
|
#
¿
Dec 4, 2018 04:50
|
|
|
ratbert90 posted:I’m still holding out hope for a 64C/128T 3990wx. I think that’s doable. Just not at 5ghz. Yeah I did embedded Linux stuff at my last job for a few months and I'd start builds before lunch and come back and they'd still be going, Threadripper would have been a godsend.
|
|
#
¿
Dec 13, 2018 18:53
|
|
|
https://twitter.com/fragman1978/status/1073356067596251142?s=19 https://twitter.com/fragman1978/status/1073356715452596225?s=19 Here's some background info on why they're using cobalt. https://semiengineering.com/dealing-with-resistance-in-chips/ MaxxBot fucked around with this message at 01:50 on Dec 14, 2018 |
|
#
¿
Dec 14, 2018 01:31
|
|
|
Yeah if it were done it would probably be in the context of something like this where it could be a chiplet added onto a package with cores, I/O, GPU, FPGA, etc as part of a heterogeneous design. 
|
|
#
¿
Dec 19, 2018 03:46
|
|
|
Yeah things definitely are changing, just like 3-4 years ago people here were still recommending dual cores for some budget gamers and now 4/4 CPUs are starting to have issues in some games. There was definitely no concern from most people at the time I got my 6600k that the lack of hyperthreading would ever limit gaming performance, turns out that thinking was wrong.
MaxxBot fucked around with this message at 06:28 on Jan 5, 2019 |
|
#
¿
Jan 5, 2019 06:24
|
|
|
PC LOAD LETTER posted:Laziness also isn't the issue when talking about programming either. Most of those guys are getting worked pretty hard, to the point of premature burn out sometimes. Its almost always either comes down to development budget or market support when talking about taking advantage of hardware features like more CPU cores or even other stuff like more system RAM and SSD's. Yeah quad cores were the norm for a full decade and taking advantage of a lot of CPU cores is difficult, why put in the effort for something that very few people have? Only in the past couple years has this made sense and we have seen some change.
|
|
#
¿
Jan 9, 2019 07:12
|
|
|
Cygni posted:If they truly can just swap that 3rd chiplet between another 8core cpu chiplet or a GPU chiplet, that is really fuckin cool. The theoretical 16core AM4 design would be wild, but I can't help but feel it would be extremely memory bandwidth constrained with just a dual channel bus? I thought that too but it was pointed out to me that Rome has that ratio of memory channels to cores (64 cores, 8 channels) and if it's not a problem on servers it certainly wouldn't be an issue on desktop. Keep in mind that Zen 2 has massive caches which will help out a bit with bandwidth requirements.
|
|
#
¿
Jan 9, 2019 22:16
|
|
|
The 20CU Navi would need HBM on there as well since it would be hilariously bandwidth constrained by dual channel DDR4.
|
|
#
¿
Jan 10, 2019 01:20
|
|
|
Seeing that some games are already having weird frame time issues with 6/6 CPUs I'd be really wary of buying one, if you just play MMOs and older games though you probably would be fine. https://www.youtube.com/watch?v=F92byoMgptU
|
|
#
¿
Jan 10, 2019 01:41
|
|
|
Here's another pic where the footprint for the second chiplet is clearly visible. https://twitter.com/brianmacocq/status/1083269332338204672?s=19
|
|
#
¿
Jan 10, 2019 09:48
|
|
|
|
| # ¿ May 16, 2024 22:34 |
|
|
I doubt the 8-core Ryzen parts cost as much as a 9900k since that will be the mid range of their lineup, some of the 12 or 16-core parts might.
|
|
#
¿
Jan 24, 2019 21:45
|
|