|
Craptacular! posted:I think this time next year will be time for the Sandy/Ivy people to finally upgrade to something. AMD and Intel are getting into a war and the winner is nerds. I don't know if I can wait that long. I'm thinking it might be 8700K time come Christmas. Locked SB i7 is not good enough.
|
# ¿ Nov 21, 2017 02:37 |
|
|
# ¿ May 21, 2024 03:19 |
|
Paul MaudDib posted:Yeah AMD is just shipping people new chips off the line now, the boxes are no longer getting opened and tested. But the chips off the line actually stand a chance of passing now, whereas before week 25/week 30 they have a near-100% failure rate, so you shouldn't feel bad about getting it replaced. Odds are very good your old CPU had the issue, just be sure to test your replacement too. I wonder if the pile of returned ones is getting mixed up with the pile of R5s and that's why we're seeing R5s showing up once in a whilej with 8C/16T. They're actually just repainted segfaulting R7s and when someone gets a segfault they're forced to choose between RMAing it and losing two cores or just not using the thing for compiling eight kernels at once.
|
# ¿ Nov 23, 2017 09:43 |
|
Measly Twerp posted:Phoronix is kind of a garbage fire, he loves stirring up drama any time Lennart Poettering farts. The benchmarking is really what redeems that site, but only just because that's often full of flaws and is of questionable use anyway. Phoronix is the perfect benchmarking/etc site for your stereotypical Linux Uber Alles type PC master race nerd. The benchmarks mean poo poo when comparing to any other platform for myriad reasons so naturally they look really good on Linux systems. Dude knows exactly what he's doing and somehow manages to sustain the site and I guess himself off it.
|
# ¿ Nov 25, 2017 00:09 |
|
NewFatMike posted:I'm on the bus so I can't check out the video in the article, but: Those are the kind of numbers we saw in "leaks" before Ryzen was officially announced, just with 50% more cores. WCCFTech editors are looking at those and going "come on, guys, at least make your rumours believable."
|
# ¿ Dec 10, 2017 02:39 |
|
I'd buy a guaranteed 4.5 GHz 8C/16T Ryzen1.5 part for sure. Anything above that would be icing on the cake.
|
# ¿ Dec 10, 2017 12:37 |
|
Has anyone seen any benchmarks of the impact on heavily parallel loads on post-update Windows on Zen? I know we've seen gaming loads but I haven't seen anything for server and workstation type loads.
|
# ¿ Jan 4, 2018 03:48 |
|
Xae posted:The real gain, at least for gaming, will be if they can get the single core boost up higher. One of the reasons why Coffee Lake does so well on gaming is that it will boost one core up +1GHz. And as a bonus, it doesn't take a whole lot of extra juice at all to get all core +1 GHz.
|
# ¿ Jan 9, 2018 02:22 |
|
Rastor posted:Better switch to a 486, just to be safe They can pry my 68030 from my cold, dead hands.
|
# ¿ Jan 9, 2018 19:56 |
|
GRINDCORE MEGGIDO posted:AMD CPU and Platfrom Discussion: No meltdowns here Yes please
|
# ¿ Jan 10, 2018 19:15 |
|
SamDabbers posted:I got an R7 1700 at launch and paid $110 for 16GB (2x8GB) of DDR4-2933, which I thought was expensive at the time. How much higher will it go before prices get back to reasonable levels again? I really want to upgrade to 32GB, but definitely can't justify it at these prices, even though my machine has started swapping at times when working with multiple VMs. It's never going back down. Welcome to the idiot hellfucker dimension where the cost of building a PC is going back to 1980s levels.
|
# ¿ Jan 26, 2018 19:44 |
|
SamDabbers posted:
Brilliant post/avatar combo. And Truga has a good point. China's put on the Bubbles glasses and is saying "something's a bit fucky here, boys", which in and of itself is a bit fucky. Who knows what that's going to do about chip prices.
|
# ¿ Jan 26, 2018 19:55 |
|
The gently caress is with some of those Linux distributions just being horrendous at some things compared to the others? Is library choice and performance across different distros so wildly different that you actually in some cases have to pick which distro you want to use specifically based on how poo poo your preferred one will perform in it? God drat. No wonder Linux people still try to dunk on Windows like the past 20 years haven't happened. Modern Linux is a complete shitshow of platform fragmentation and modern Windows is a stable operating system that works out of the box e: Also gently caress Adored, dude is seriously like an Alex Jones wannabe who wishes he could be Linus Sebastian.
|
# ¿ Jan 28, 2018 13:17 |
|
BangersInMyKnickers posted:XTU is still maintained. I use it to dial in stable clocks and then just manually set those values in bios so they're persistent and not dependent on some janky software suite XTU actually does its OCs as a lightweight system service so they get applied when Windows boots and doesn't need the big ugly software to be open at all. Pretty sure they're applied well before logon.
|
# ¿ Feb 8, 2018 23:06 |
|
That is all kinds of cool. Do they just include a little return envelope and plastic sheath or something to drop the chip in?
|
# ¿ Feb 17, 2018 00:22 |
|
Novo posted:Is there a go-to Threadripper motherboard for people wanting to run Linux and do GPU passthrough? I heard they updated the Taichi? Buy an ASUS board for the features, put it in a case that has no big ugly plexiglas window on the side, never need to look at the motherboard, ???, profit?
|
# ¿ Feb 22, 2018 21:42 |
|
Khorne posted:It's what happens in 2020 and beyond that is probably bad for intel. I think "we literally cannot shrink the node anymore" is bad for everyone. Intel especially, but no one wins when quantum mechanics punches your engineers in the soft spots.
|
# ¿ Mar 8, 2018 03:29 |
|
Paul MaudDib posted:snip I do not believe the blockchain security researcher in those tweets is involved in any capacity in a 24-hour-disclosure-period massive CPU security bug fest that is in any way real
|
# ¿ Mar 13, 2018 22:10 |
|
Should I know who Gadi Evron is?
|
# ¿ Mar 14, 2018 04:57 |
|
You know, I thought you just had this hate-boner for AMD you just couldn't resist playing with in public, but Christ your posting is terrible.
|
# ¿ Mar 14, 2018 10:19 |
|
I was really hoping for the exploits to be bullshit. Not for any sort of "lol nice meltdown intel xdddd" fanboyism, but because I was honestly hoping CTS Labs was just some lovely stock manipulation scam. That is a preferable alternative to some rowdy shits getting away with 24 hour disclosure on firmware level privilege escalation vulnerabilities.
|
# ¿ Mar 20, 2018 23:45 |
|
Except the Steves revolutionized an industry, and these guys are just smug cunts looking for the quick buck. fakeedit: so actually that fits Jobs pretty well
|
# ¿ Mar 21, 2018 00:12 |
|
Alpha Mayo posted:So an attacker with kernel level access to the system can do kernel level things with it? I still don't see the exploit. You can also flash a corrupted Intel Management Engine into the BIOS and brick an Intel computer or permenantly change configuration settings most people aren't even aware of, is that also an "exploit"? Mmyep. I would not be surprised if chunks of their PoC is copy/pasted from the Zen BIOS and Kernel Developer's Guide. Obituary indeed.
|
# ¿ Mar 21, 2018 02:10 |
|
I'm still not concerned about the exploit that requires already having methods to completely pwn the machine. It's a neat exploit, and yes it lets you gently caress with the firmware, but it still requires you to find some way to be on the other side of the airtight hatchway. At that point you've already lost. This is just a deeper level of "you've lost".
|
# ¿ Mar 22, 2018 21:25 |
|
Yeah, you wouldn't save anything. You wouldn't even free up any pipelines by dropping MMX, since it shares a pipeline and register file with the x87 FPU.
|
# ¿ Mar 23, 2018 07:04 |
|
SwissArmyDruid posted:....NGC could be referring to any number of things, none of which are good. I choose to believe they're making an obscure joke about nebulae instead of "you ain't seeing a GCN replacement until 2023, suckaaaaaaz"
|
# ¿ Mar 24, 2018 07:05 |
|
The actual answer is "Source is a pile of crap engine that still has code from Quake 1 in core places".
|
# ¿ Mar 29, 2018 20:39 |
|
Khorne posted:Why do you have to blame it on Q1 code? Q1 movement code, for example, is far better than source's. The Q1 code is not necessarily the problem. The problem is that it's an engine that has parts dating back to 1995 and has been incrementally updated and rebranded over the course of 23 years. The whole thing was designed and built long before modern x86 SoCs and n-core hyperthreaded x86-on-RISC CPUs, and four thousand core vector processors as graphics cards. Incremental work was built in a dozen different eras of CPU and GPU philosophy. It is entirely unsurprising that it runs incredibly weirdly and not well at all.
|
# ¿ Mar 29, 2018 20:47 |
|
AMD's back in the extreme WTF lead it seems. Good on them!
|
# ¿ Apr 21, 2018 10:58 |
|
StoreMI Is just fakeraid storage tiering, yeah.
|
# ¿ Apr 21, 2018 22:40 |
|
VirtualBox gets fixes on Windows. Not so much other platforms.
|
# ¿ Apr 23, 2018 20:44 |
|
I really want to know what the roadmap is for a Zen based successor to the G-series embedded SoCs is like, myself.
|
# ¿ May 3, 2018 20:38 |
|
A gargantuan number of PCIe SSDs.
|
# ¿ May 10, 2018 03:14 |
|
IIRC there are POWER and SPARC chips with 8-way SMT. 2-way has only been the standard for x86 because consumer applications haven't been in a position to gain any dramatic performance increases from anything more until now. Possibly even now.
|
# ¿ May 17, 2018 08:25 |
|
EmpyreanFlux posted:Rome wasn't built on one die. Hoooooly poo poo.
|
# ¿ Nov 7, 2018 19:16 |
|
Bloody Antlers posted:I wonder how feasible it would be to move most AVX units to some kind of math co-processor socket. Ideally there would be some units on package for the average user, but if you have workloads that lean hard on AVX, you could trade a little bit of latency for not having the central processor thermal throttle. Hello friend I would like to introduce you to something called a graphics processing unit
|
# ¿ Dec 19, 2018 06:50 |
|
Crotch Fruit posted:I agree video game programmers can be pretty lazy sometimes, and I think that games will not take advantage of multiple cores any time soon, but I believe that is only because so many PCs out there are still just dual core machines and I believe PC gaming, or even just PC ownership, is becoming a dying trend. Source your quotes
|
# ¿ Jan 8, 2019 20:53 |
|
NewFatMike posted:COMING FOR THE CROWN You know I had to Su it to 'em
|
# ¿ Jan 9, 2019 18:28 |
|
Malloc Voidstar posted:https://www.anandtech.com/show/13829/amd-ryzen-3rd-generation-zen-2-pcie-4-eight-core ok google how do i get rid of an erection at work
|
# ¿ Jan 9, 2019 19:17 |
|
Don't engage and/or quote Paul
|
# ¿ Jan 28, 2019 20:14 |
|
|
# ¿ May 21, 2024 03:19 |
|
aluminumonkey posted:So you guys are saying I shouldn't have picked up a Ryzen 2700 (same price as the 2600x with a RTX 2080? You're fine as long as you're not trying to explicitly find niche graphics settings in modern games that would expose CPU bottlenecks, like setting everything to 900p low.
|
# ¿ Jan 28, 2019 21:51 |