Quantcast
[ 3 / biz / cgl / ck / diy / fa / g / ic / jp / lit / sci / tg / vr / vt ] [ index / top / reports / report a bug ] [ 4plebs / archived.moe / rbt ]

/vt/ is now archived.Become a Patron!

/g/ - Technology


View post   

[ Toggle deleted replies ]
File: 1.96 MB, 320x180, multicore processing.webm [View same] [iqdb] [saucenao] [google] [report]
58518901 No.58518901 [Reply] [Original] [archived.moe] [rbt]

Is "2600k will last forever" just a meme? If CPUs have improved 10% each generation since 2600k, wouldn't a 7700k be quite a bit better and not just marginally?

>> No.58518943

>>58518901
No because no germanium

>> No.58518951

>>58518901
>If CPUs have improved 10% each generation since 2600k,

The majority of performance gains since sandy have been due to higher stock clocks

>> No.58519003

>>58518951
1990's
>All that matters is clock speed

2000's
>Yo dawg cores are all that matters

2010's
>We were only pretending. Clock speed is best.

>> No.58519052

>>58519003
>1990's
>>All that matters is clock speed

>2000's
>>Yo dawg cores are all that matters

https://www.youtube.com/watch?v=tPBtXUUeFK0

>> No.58519078

>>58519003
multi core is great, if devs actually bother optimizing for it.

Unfortunately most are too lazy and we get shit that throttles CPU0 and doesn't touch the other cores.

>> No.58519184

>>58519003
Multicore is still great for tasks that can't be parallelized efficiently on a GPU but for more than a single core.

>> No.58519189

>>58518901
If you overclock them it becomes minimal.

>> No.58519198

>>58519078
When the consumer dual cores came out I remember all this talk about tools that automatically allowed a program to use multiple cores. What happened to this stuff?

>> No.58519218

>>58518901
>>58518951
You're looking at a 20-25% improvement if you upgrade from a 2600k at stock speeds. Still not worth it.
>>58519198
It was a pipe dream. Never happened.

>> No.58519237

>>58518901
In games the difference is only between 0-10% mostly and in some titles 20% at best in fps.

>> No.58519240

>>58519078
have you acctually tried multi threading your programs? shit is still too complicated imo

>> No.58519260

>>58519078
>>58519240
It needs to be implemented on the level of the engine / runtime and done automatically. Devs will never do it consistently.

>> No.58519272

>>58518951
Sandybride overclocks higher than skylake but we've seen like 20% improvement in IPC. Not much at all, obviously. Seems like Kaby finally overclocks higher than sandy again.

>> No.58519284

>>58519218
my 2600k shits itself when I push it past 4ghz. Unlucky batch I guess.

Meanwhile I hear 7700k easily goes 5ghz+. That would be a significant improvement.

Is DDR4 just a meme too? I remember reading that memory speed didn't really mean jack shit.

Of course there's the added benefit of the new USB 3.1 gen 2 speeds, as well as the M.2 SSDs and that new shit Intel is cooking up called Optane.

>> No.58519288

>>58519003
We are currently entering the era of cores, the APIs know it, the manufacturers know it, the devs know it
Clock speed only became relevant recently because that "means" that zen will beat all of Intel so suddenly clock speed is all that matters
Once zen loses relevance the fight will be on for cores, I could see 6 or 8 cores becoming completely normal within 2-3 years. THEN zen will be relevant

>> No.58519296

>>58519189
is that comparing overclock to overclock or overclock to stock?

>> No.58519388

You'll see a 25%+ increase

2nd gen i7 is about equal to a 6th gen i5 in multi and an 4th gen i5 in single and quad

>> No.58519391

>>58519284
>DDR4 just a meme

DDR4 is only relevant because it allows higher density memory for the same cost, meaning we'll see 16-32gb ram become commonplace (unless they artificially keep prices high because consumers are stupid and will buy it anyway).

>> No.58519392

>>58519296
Overclock to overclock, sandy bridge overclocks better than skylake

>> No.58519449

I've been agonizing over whether or not I should upgrade my i7 950. I've got it overclocked to 4.2ghz but I feel like I could probably get better performance with a new CPU at the same speed.

>> No.58519476

>>58519449
according to ppl itt, you're looking at 25% performance increase minimum. Seems worth it to me, but I've got money burning a hole in my pocket.

>> No.58519510

>>58518901
>If CPUs have improved 10% each generation since 2600k
They haven't. Even if you include the fact that Kaby Lake will clock around 300 MHz higher than Sandy Bridge, the overall performance increase will be around 30-35%. Nowhere near enough to justify the massive cost of these chips.

Hopefully AMD will change that because you (a) won't have to buy a top-tier "K" chip for overclocking, (b) you won't have to buy a top-tier "Z" series motherboard for overclocking, and (c) AMD are always more competitive on price anyway.

>> No.58519582
File: 39 KB, 362x363, 1347201661343.jpg [View same] [iqdb] [saucenao] [google] [report]
58519582

>>58519510
>Hopefully AMD will change that

>> No.58519642

>>58519078
>Unfortunately most are too lazy and we get shit that throttles CPU0 and doesn't touch the other cores.

t. templeos

>> No.58519881

>>58519510
Actually you will need to buy a special Z board to overclock well, it's actually called z370
Also Lisa said they no longer want to be the budget option, they want to be Intels competitor in both quality and more or less price. She said "we don't want to do what Intel is doing" but she also said she doesn't want to be the low prices brand

>> No.58519888

>>58519642
GOD SUPPORTS MULTITHREADING

>> No.58519964
File: 767 KB, 700x700, 1483217732813.png [View same] [iqdb] [saucenao] [google] [report]
58519964

>>58519888
trips confirm

>> No.58520072

I say fuck you and ride on my first gen i7

>> No.58520172

>>58519881
No, 3 of the 4 AM4 chipsets support overclocking.

Their chips will be priced competitively. I'm not expecting the 8-core to be the same price as the i7-7700K, that's ridiculous, but I think the 6-cores will be competing at that level, and the 4-cores around i5 level. As long as their IPC is close they should be a much better performance per dollar option.

>> No.58520183
File: 61 KB, 1468x826, AMD-AM4-Update-CES-2017-01.png [View same] [iqdb] [saucenao] [google] [report]
58520183

>>58519881
Not really true, the CPUs are unlocked, and the CPU can increase the boost tact if it is still within its power/temperature curve.

For usual overclocking you need one of the better chipsets (X370, B350, X300) instead of the basic A320/A300 chipsets, and the mainboard must support it.

>> No.58520212

>>58520172
The IPC is the same on both the 6700k and 6800k but two cores adds $500. This market is relatively successful. If AMD entered a market that is already buying $800 6-cores, with a direct competitor to the $800 6-core, they're not gonna let that opportunity pass them up

>> No.58520269

>>58520212
Technically the i7-6700K has 3-5% higher IPC compared to the i7-6800K but, yes, more or less the same. However, the i7-6800K is nowhere near $500 more than the i7-6700K. In the UK, it's not even £100 more.

There'll have to be a 6-core Ryzen chip at the same price point as the i7-6800K at the very least. Even if that's true, the AM4 platform will be a lot cheaper than the X99 one.

>> No.58520308

>>58519198
Whatever could be extracted, already was. Current cpus do what is a technological equivalent of black magic to use as much resources as possible. The same goes for compilers. However proper parallelisation cannot happen on such a low level unless you are willing to accept compile times in hours or days.

Moreover - prevailing model of programming is branchy, side-effect laden object oriented one. With functional programming without side effects you could expect some level of parallelisation.

>> No.58520368

>>58519260
Not necessarily. However this requires a change in the prevailing programming paradigm. Moreover - there are no 'brainless' methods of getting parallelism because 99% of devs are either under pressure to deliver, are under-educated or are just plain dumb.

Being buried under miles of legacy code does not help either.

However, we are slowly bumping onto IPC and clock walls, so threading and later numa-aware throughput processing is the way to go.

>> No.58520405
File: 219 KB, 1920x1081, sandy bridge.png [View same] [iqdb] [saucenao] [google] [report]
58520405

why upgrade when there is LITERALLY no practical benefit

sure if you're building a new PC right now get the newest one, but no point in upgrading when the gains are shit

>> No.58520465

>>58520405
This, pretty much.

Call me when intel releases a chip stock clocked at 8ghz

>> No.58520474

>>58518901
>>58518943
No because jews not in oven.

>> No.58520509

>>58520183
>Overclockin
>g

>> No.58520520

>>58520405
oy vey.
buy new cpu every year, goy.

>> No.58520532
File: 137 KB, 960x960, image.jpg [View same] [iqdb] [saucenao] [google] [report]
58520532

>>58520465
If the CPU die was over 1.5 inches long, that would be bottlenecked by the speed of light

>> No.58520546

>>58520532
I disagree.

>> No.58520559

>>58520546
300,000,000 m/s
Cycling at 8,000,000,000 times a second, light/electricity could only go 1.5" per cycle

>> No.58520573

>>58520559
And that's free radiation, electricity is even slower running through a medium like silicon

>> No.58520580

>>58520559
So make it smaller.

>> No.58520611
File: 155 KB, 640x932, image.jpg [View same] [iqdb] [saucenao] [google] [report]
58520611

>>58520580
But smaller dies plus higher clocks get way too hot way too fast, even for very cooled circuits. Plus the actual electromagnetic limitation we have, we just can't go much smaller without electrons having unstable and unpredictable paths
Quantum computing a great step forward, we don't need high clocks when we have trinary code

>> No.58520632

>>58518901
a stock 6700k is about as powerful as my 4.7ghz overclocked 3930k (which has two more cores)

6700k or 7700k would stomp the shit out of sandy vag no matter how far you overclock it

>> No.58520633

>>58520465
Not exactly stock...
http://www.tomshardware.com/news/Overclock-Intel-Celeron-TiN-CPU,9509.html

>> No.58520634

>>58520611
>But smaller dies plus higher clocks get way too hot way too fast, even for very cooled circuits. Plus the actual electromagnetic limitation we have, we just can't go much smaller without electrons having unstable and unpredictable paths
Just use superconductor junctions instead of transistors and we good to go, new ceiling should be >500ghz.

>> No.58520672

>>58520633
>he first heated the celeron CPU to over 200°
Baking your CPU for better overclocks confirmed

>> No.58520697
File: 50 KB, 800x733, image.jpg [View same] [iqdb] [saucenao] [google] [report]
58520697

>>58520634
>500GHz
>half a millimeter wide CPU die, under perfect conditions
I'd love to see the heatspreader on that one

>> No.58520738

>>58520697
Well look until we get room temperature superconductors it would need to basically be housed in a tank of liquid helium so cooling wouldn't be a problem.
But also superconductors don't really give off much heat when you force electricity through them so it won't be that much of a problem anyway, which is what permits the high speed.

>> No.58520898

>>58520738
It would still be a half a millimeter CPU die, which would be nuts to try to manufacture, regardless of whether or not a system to run that stable could exist

>> No.58520913

>>58520898
Welp, as I said it would be the ceiling. Lots of ground to cover before that.

>> No.58520961

>>58520913
I wonder how big the 10Nm dies of Ice Lake will be
If cooling remains a shrinking issue maybe we'll see some serious clocks in 2018

>> No.58520978

>>58519003
IPC is king and always has been

clockspeed and moar coarz has always been an artificial way of improving IPC

>> No.58520981
File: 3.05 MB, 4128x2322, 20151230_232521_3.jpg [View same] [iqdb] [saucenao] [google] [report]
58520981

>>58520961

Did someone say serious clocks?

>> No.58521054

>>58520981
Is that even Y2K17 compliant

>> No.58521096

>>58520981
what are those called?

>> No.58521106
File: 1.57 MB, 4128x2322, 20170101_003326.jpg [View same] [iqdb] [saucenao] [google] [report]
58521106

>>58521054

No, I had to upgrade.

>>58521096

Nixie tubes.

>> No.58521132

>>58521106
Why is the color wrong in that image?

>> No.58521134
File: 844 KB, 800x786, 1484380472395.gif [View same] [iqdb] [saucenao] [google] [report]
58521134

Government already has the next 20 generations of processor locked away in secret labs and in the Utah data center. Civilians won't see that technology until next century desu

>> No.58521207
File: 2.77 MB, 4128x2322, 20160920_202252.jpg [View same] [iqdb] [saucenao] [google] [report]
58521207

>>58521132

That's because those are VFDs and not true nixie tubes like the other picture. Vacuum Fluorescent Displays work with... well fluorescents while nixie tubes work with neon gas. One glows greenish blue, the other orangish red.

>> No.58521264

>>58521207
>VFDs
>neon gas
Aren't these illegal in the US?

>> No.58521291

>>58520978
>IPC is king and always has been
>clockspeed and moar coarz has always been an artificial way of improving IPC
Actually the real main factor is effective computation per unit of time.

>> No.58521309

>>58519218
>pipe dream
>pipe
HAH I get jt

>> No.58521314

>>58520978
But it's not possible to increase IPC for some highly serial operations. It will always be 1 per clock at best.

>> No.58521341
File: 1.04 MB, 2322x4128, 20160906_173648.jpg [View same] [iqdb] [saucenao] [google] [report]
58521341

>>58521264

>VFDs or neon gas being illegal

m8, I own firearms, do you really think they would ban gas tubes? Also these would be illegal as well.

>> No.58521355

>>58521341
Yeah but you cannot host OpenBSD


so long...

>> No.58521396

>>58521264
>aren't those illegal in the US?
Maybe you are thinking of the incandescent light bulbs that used to go in light fixtures and lamps.

>> No.58521423

>>58518901
>5% IPC gain on ivy
>5% IPC gain on haswell
>5% IPC gain at most on skylake
>1% IPC gain on kaby lake
>this adds up to 116.920125% total gain
so in other words, to match the IPC of the latest chips, you need to overclock your sandy bridge chip to the clock speed of the equivelent kaby lake chip + 16.920125% of the kaby lake chips clock speed

assuming im not braindead, that means a 3.40 GHz 2600k can match a 4.2 GHz 7700k by being overclocked to 4.911 GHz, a rather significant overclock, but not impossible. meanwhile the 7700k can at best overclock to 5 GHz, just a 200 MHz different from its maximum turbo boost, and a 800 MHz difference from its stock clock, in exchange for greater voltage wear on the silicon.

>> No.58521445

>>58521264
>Aren't these illegal in the US?
If so a lot of your advertising signs would be scrapped.

>> No.58521474

>>58520405
I really want to upgrade but I got realllllyyy lucky with a 2600k that I've had overclocked at 4.6 for years now. Hopefully Zen isn't shut.

>> No.58521511

>>58519260
>Just automatically make the programs parallel

So you have no idea how it works? Good to know.

>> No.58521570

>>58521423
>116.920125%
11.6920125%

>> No.58521599

the only reason to upgrade from 2600k is to 4790k which has overclocking and vt-d.

> 2600 vt-d
> 2600k overclocking
> ???
> sheckles!!!

>> No.58521678

>>58521474
Mmm I've got my 2500k overclocked at 4.4ghz
Honestly it goes alright. If it doesn't die soon I'd probably be more inclined to upgrade my graphics card.

>> No.58521798

>>58521570
good point, what i meant was to say that kaby lake has 116.920125% IPC of sandy bridge, or 16.920125% over sandy. that said, how did you get that number?

>> No.58521942

>>58520368
>numa-aware throughput processing
huh?

>>58520532
>upper boundaries of physics are starting to become the limiting factor
what a time to be alive

>> No.58521945

>>58520532
Electrons only move 1/3 the speed of light

>> No.58522071

>>58521945
generally or in silicon?

>> No.58522089

>>58521798
They don't even have that much increase, since most of the time they increased clocks, not the IPC.

>> No.58522157

>>58518901
Indium Antimonide.
Chalcogenide

Look that shit up /g
Intel is going to rock the world in the near future

Chips with laser beams and shit

AMD and Nvidia will be dead

Micron is in on this too

They've been milking us for years

The payoff is coming soon

The patents are up in 5 years.


You heard it here first

>> No.58522203

>>58518901
so morning of owl endorses AMD? sign me in!

>> No.58522320

>>58522089
my understanding is that was the rough IPC gain figures

>> No.58522338

>>58521355
what

>> No.58523106

>>58521945
electrons move a lot fucking slower than that (drift velocity), although they can convey changing electric fields at decently large fractions of c (velocity of propagation).

>>58520532
CPUs are already bottlenecked by propagation speeds. the few fractions of mm distance between an integer execution pipeline and the far edge of an adjacent L1D cache is already a hugely limiting factor in core designs. I.e., bigger caches take more clocks just to access the needed cells, which causes more clocks for read delays, which makes scheduling and mispredict handling harder, and so on...

>> No.58523187

>>58520405
Gains are not just for FPS, depending on what games you play a lot of CPU load is calculation for game aspects rather than just rendering the display.

I'm looking forward to a range of games to run better when I make my replacement/upgrade move in the spring.

>> No.58523391

>>58519078
After a certain point with "optimising for many cores" it becomes more practical to offload processes to a gpu.
The kind of work a CPU tends to get stuck with is the messier stuff that doesn't scale well for multicore which GPUs excel at.

>> No.58523405

>>58518901
Improved according to what criteria?

Because, according to the following source, not only the architecture performance across all generations in between increased only about 20%, it even regressed in many cases.

http://www.hardocp.com/article/2017/01/13/kaby_lake_7700k_vs_sandy_bridge_2600k_ipc_review

>> No.58523455

>>58518901
> If CPUs have improved 10% each generation since 2600k
[citation needed]

>> No.58524057

>>58523106
Both of these.

Electrons themselves travel on the order of a meter per second, or meters per seconds. It's slower than a normal walking pace, if I remember correctly. But the propagation happens at nearly light speed.

Imagine you have a hose filled with water; if you push a plunger in at one end, the water itself doesn't move very fast. But, the water at the other end starts moving almost instantaneously because the whole hose is filled. Basically the same thing with electrons in wires.

>CPUs are already bottlenecked by propagation speeds.
Not just propagation speeds. The signals moving around in a CPU have been, for quite a few years now, bound by transmission line physics. The frequencies of operation hit a point where the physical dimensions of the core amount to large fractions of the signal wavelengths, which is when signals start operating more like waves than currents and you have to deal with reflection and mismatched impedances.

t. unemployed EE grad who's never actually worked in the field

>> No.58524115

>>58519240
>#pragma omp parallel for
It's one line for basic shit and a couple more for anything else. Kill yourself please.

>> No.58524144

>>58518901
they don't really improve 10% they just jack up the stock clock and say it's 10% better leaving out that they speeds are stock

>> No.58524197

>>58523187
>Gains are not just for FPS, depending on what games you play a lot of CPU load is calculation for game aspects rather than just rendering the display.
This this this this this.

Graphics are easy to max out as long as you have a functioning CPU; just drop a 1080 in there and it'll run anything you want at whatever settings you pick.

It's when you get into complex situations that the CPU becomes a determining factor not of frame rate, but sim speed. In an FPS this doesn't ever become an issue; you have 8-32 people running around a map shooting at each other with hitscan weapons. In an RTS this becomes a biiiiiig issue.

Take Supreme Commander, for instance. A game released a decade ago. Sure you can max out the graphics and run it at 200fps with even a modest gaming computer today, but when you have a 4 player match and each guy is controlling an army of 400-1000 units, each of which is firing multiple projectiles per second, all of which are actually modeled and tracked in 3D space in real time, even a 6950X is going to have to slow down the speed of simulation.

If all you play is CS:GO, sure, spending more than about $100 on a CPU is retarded.

If you play just about any strategy games or do any kind of video/audio/photo editing (or stuff like Matlab) then your CPU is a major concern.

>> No.58524289

>>58523405
>http://www.hardocp.com/article/2017/01/13/kaby_lake_7700k_vs_sandy_bridge_2600k_ipc_review
>6 years later, and we only have ~20% better performance
Shit. Moore's Law really is dying.

However,
>it even regressed in many cases
The 7700K was faster in every single benchmark, I think you were looking at the ones showing the *time* it took to perform an operation; the 7700K had a smaller bar because it went faster. They should've shown those with a different bar graph to more clearly differentiate that smaller bar = faster.

>> No.58524392

>>58524057
>of a meter per second
Even less. According to the wikipedia page on drift velocity electrons in a 2mm diameter copper wire at 1amp move at about 2.3x10^-5m/s or 0.000023 m/s
You'd be lucky to get a meter in 12hrs.

>> No.58524423

>>58524392
Sumbitch, my knawledge is slipping. I didn't think they moved that slow.

>> No.58524425

>>58524289
Thanks for pointing this out. I was careless and got carried away by their increase/decrease statements in the comments following up to the graphs.

>> No.58524439

>>58524423
>Sumbitch, my knawledge is slipping. I didn't think they moved that slow.
If you think about it the amount of energy you'd need to accelerate all those electrons up to 1m/s would be pretty high.

>> No.58524462

>>58519240
Functional programming doesn't suffer from this problem.

>> No.58524498
File: 132 KB, 1363x648, 1080.jpg [View same] [iqdb] [saucenao] [google] [report]
58524498

This may be the right thread to ask.

I bought a 1080 a few days ago to replace my amd 280x.

While I see that I can up my visuals to the limits on games like WoW I still notice frame drops to 55-53 in Dalaran. Is my cpu bottlenecking??

My 2500k is overclocked to 4.5.

>> No.58524511

>>58524439
>If you think about it the amount of energy you'd need to accelerate all those electrons up to 1m/s would be pretty high.
Erm, what I mean by this is that, despite electrons being very light, you're not moving them through a vacuum; you're forcing them toward/through a fairly densely packed mass of other electrons which naturally repel each other and are attracted to the atom they're bound with. You gotta get that electron through a lot of atoms for it to pass 1m, and doing that in a second is going to require some serious pushing.

>> No.58524523

>>58524289
Post-silicon era is upon us.

>> No.58524629

>>58524498
seems like it. wow is cpu heavy anyways, what you are experiencing has been noted by people with $1500 rigs

>> No.58524630

>>58524498
Interesting. My bet is it's an issue with WoW's optimization, not your system. I've never heard of it being a CPU-hungry game.

>>58524511
Right. As I read into it more (it's all coming back to me now...) you have to also keep in mind that the electrons don't take the shortest path, they simply go wherever there is space. So while current might be flowing due south, the electron is going to be jumping east and west and up and down as it's shoved through the conductor. I'm glad this stuff is interesting again, I had the problem in school of since you "have" to learn it, it isn't fun.

>>58524523
Aye. Honestly these next few years are going to be exciting, not just in processors or even computing in general, but human development, for better or worse. Automated driving, 3D XPoint memory from Intel and Micron, renewable power including grid-scale storage, direct gene modification, Donald Trump being president (fucking kek), and globalization with automation being a major factor in the transition of our labor economy from the currently-fucked status to total upheaval.

It's certainly going to be exciting. I'm pretty stoked.

>> No.58524645

>>58524630
>I've never heard of it being a CPU-hungry game.
aaaaand >>58524629

I take it back. I never played wow so my experience was limited to reading shitposts on /v/.

>> No.58524668

>>58524630
>I've never heard of it being a CPU-hungry game.
This has not been my experience at all
it's probably just written very poorly

>> No.58524690

>>58524645
I meant it depends on single core performance, if that makes sense. wow isn't, from my understanding, been optimised for multi cores. kinda like Skyrim

>> No.58524728

at this rate my 3570k @ 4.5 will last me another 2 years

>> No.58524732
File: 251 KB, 480x800, Screenshot_2017-01-16-23-25-58.png [View same] [iqdb] [saucenao] [google] [report]
58524732

>>58524690
this

>> No.58524746

>>58524728
hard to say, Murphy's law

>> No.58524748

>>58524732
lol wut

>> No.58524807

3770k+2133MHz RAM is almost the same as 4790k, and maybe 5% slower than a brand new 7700k

>> No.58524826
File: 23 KB, 650x300, attilla i7.png [View same] [iqdb] [saucenao] [google] [report]
58524826

>>58524197
You're still vastly overstating it tho

Take Total War: Attilla. This is the kind of strategy game you describe with thousands of units on screen each with their own animation and projectiles flying aroung and shit.

newest shit is still not any better than a 2600k

face it, intlel hasn't made any gains since sandy bridge. and why should they when AMD hasn't put out anything worthwhile in 5 years. this is direct proof that without competition the market stagnates

>> No.58524846
File: 23 KB, 650x250, alien isolation i7.png [View same] [iqdb] [saucenao] [google] [report]
58524846

>>58524826
here's more proof that older processors will not "bottleneck" you and that the gains between the generations is very small

http://www.anandtech.com/show/9483/intel-skylake-review-6700k-6600k-ddr4-ddr3-ipc-6th-generation/16

gonna dump them all.

>> No.58524847

>>58524732
>>58524690
So, best way to get better FPS in WoW/ other mmos?

>> No.58524854
File: 24 KB, 650x300, shadow of mordor i7.png [View same] [iqdb] [saucenao] [google] [report]
58524854

>>58524846

>> No.58524865
File: 24 KB, 650x300, grid autosport i7.png [View same] [iqdb] [saucenao] [google] [report]
58524865

>>58524854
only real gains that I could find but look at the frames, it's so far above 60 that it doesn't even matter

>> No.58524931

>>58524847
hard to say, it's all about how well it's optimized. I run ffxiv with max settings on a 860k amd cpu @4.3, 8gb of ram, and a r9 380 4gb. and get 60fps. on wow it's from 40-55fps

>> No.58524978

>>58524826
Hold on hold on hold on anon.

You're right: unless you're running an extremely low-end CPU with an extremely high-end GPU, the processor is essentially a non-issue when it comes to graphical frame rate.

However, the issue I was talking about is simulation speed. The game will still render everything at 90fps with no dips in frame rate, BUT one second of "in game time" might take 3 seconds to simulate because the engine simply can't keep up. I'm not sure how CPU intensive the Total War series is (I'd assume quite a bit) but for games like Supreme Commander which are, by design, processor intensive, your choice of CPU is very important.

I'm trying to think of an analogy. Imagine you're watching a video of a soldier walking in 1080p at 60fps. When the sim speed gets cut because your CPU is bottlenecking, you're still watching a 1080p, 60fps video of the soldier walking, but it's now running in slow motion because the game engine can't keep up with all the calculations in real time.

>> No.58524997

>>58524978
I understand what you're saying but like you said the number of games that would matter in are very small

Dwarf fortress would probably benefit but only once you start getting really into the late game

>> No.58525006

>>58524978
total war murders my 860k, I get around 25-30 fps

>> No.58525494

>>58521942
>>numa-aware throughput processing
>huh?

NUMA - Non Uniform Memory Architecture. Look it up. It essentially requires division of a program into as many independant parts with minimal interactions between them. It takes some extra skilled people to program that.

>> No.58525544
File: 334 KB, 1280x720, tpf.jpg [View same] [iqdb] [saucenao] [google] [report]
58525544

>>58524197
This.

I play pic related. Apart from it being poorly programmed, it brings my PC ( OCed 5820k ) to its knees. It is a game about motherfucking trains.

It also simulates about 20k people chosing their travel targets, cargo flowing between industries, cities grow and upwards of 1000 vehicles running around.

>> No.58525867

>>58518901
>If CPUs have improved 10% each generation since 2600k, wouldn't a 7700k be quite a bit better and not just marginally?
maybe for gaymes, most other stuff not really when you're just going to run the same applications using the same old algorithms and working with the same old data you were already working with on a 2600k

practical gains are far less for the vast majority of use cases

>> No.58526475

>>58525544
Another perfect example of this would have to be Cities Skylines. Terribly optimized and also brings any system to its knees, no matter how beefy the system is.

>> No.58526522
File: 19 KB, 403x402, received_1381259288591741.png [View same] [iqdb] [saucenao] [google] [report]
58526522

>>58518901
Im running a i7 2700k mostly on par with the current gen i5

>> No.58526590

WHY DOES ARMA 3 RUN LIKE SHIT ON ALMOST ANY PC

>> No.58526632

>>58526590
Because its custom engine has shit performance optimization hth

>> No.58526637
File: 3.15 MB, 1920x1080, snapshot_21.10_[2016.07.28_03.58.57].png [View same] [iqdb] [saucenao] [google] [report]
58526637

>>58518901
>4core sandy bagoo

>> No.58526660

>>58526632
WHO ALLOWED THIS AND WHY


THE GAME IS SO FUN BUT IS RUINED BY SHIT FPS, RUBBER BANDING, AND MEMORY ERRORS


HOW IS IT 2017 AND WE ARE STILL HAVING ISSUES LIKE THIS ON A PC EXCLUSIVE TITLE


CAPS LOCK IS CRUISE CONTROL FOR COOL

>> No.58526687

>>58526590

Because instead of making a competent game engine, Bohemia Interactive just shat out a heap of garbage and wanked off Dean Hall.

>> No.58526765

>>58526660
BIS is gonna release a 64bit update for the game soon, so maybe check it out again when that hits. And also, If you play in singleplayer and sort out your draw distance and shit right, you'll get a perfectly fine fps, the reason you get bad fps in multiplayer is a combination of gamemodes with a shitload of scripts, and your fps being tied to the servers fps :(

>> No.58526866
File: 142 KB, 1163x342, f2.jpg [View same] [iqdb] [saucenao] [google] [report]
58526866

>>58519078
Yeah, it's not that simple. You can't just flip the parallelize button and have it go faster. In order to build scalable systems, you not only have to really understand data-structures and protocols, but you also need to understand the minutiae your target processors memory model. If you don't, going wide can actually hurt you once the contention kicks in.

>> No.58528389

>>58526522
I get 2450 and 8500 on my 6600k, so no it's not.

>> No.58528561

>>58520978
You're an idiot. Increasing the clock does nothing to instructions per clock (IPC). In fact some of the ways chips are built to improve clockspeed reduce what they can do in one cycle of the clock.

What really matters is instructions/time. More cores, better IPC per core, higher clockspeed, and tricks like hyperthreading to reduce wasted resources can all help.

>> No.58528589

>>58521207
Nixie tubes use filaments like an incandescent light you mong.

>> No.58529709

>>58519391
>>58519284

In games we are seeing memory bottleneck them every now and then, but it's becoming more common.

In reality, if you aren't trying to push everything to the max, memory is good enough so long as its there, some games its a 20-30% difference between the base ram and max.

>> No.58529770

>>58519003
I'm writing a concurrent BVH builder right now (for a real time ray tracer) and the heaviest part of the algorithm scales perfectly linearly with the amount of cores.

Give me all the cores. I can handle 'em. I'll make them sweat. I'm close to fully utilizing every single core.

>> No.58529838

>>58519881
yea, they dont want to be 'well its shit but its all i can afford'

what they want to be is 'hey, amd is the better option' and as of now 'oh look, they are cheaper to boot'

at least this is how I take it after fury had a price range between 550$ and 1000$ and decided on 650, remember, no 980ti at this point, nvidia price matched amd after getting wind of the fury, seeing raw specs, and getting scared, and if you think they did not price match it, do you really think that nvidia, the company that did founders editions, would have chose to put a barely cut titan x at 650$ if they didn't think 'oh shit, amd is going to bring a hammer down'

that said, amd is either price matching the i7 or 500$, as they stated at ces these are their price points, 'one brings the price of performance down, one changes the industry'

they know what they are pricing it at, them showing the 8/16 paired with a 6700k was indication enough but still speculation, if they go 500$ after saying price matching is still on the table they would be retarded as its horrible pr, something amd doesn't need more of.

>> No.58529849

Consumer workloads haven't increased with CPUs. Even if you waited for 3 generations so you could get "30%" improvement, it wouldn't matter since most consumer workloads are single threaded and clock speeds haven't increased enough over an overclocked older chip.

>> No.58529858

>>58520212
>>58520172
amd already said price matching an i7 is still on the table for price range with 500$ being the other option.

>> No.58529871

>>58519476
no, he is looking at closer to 80% uplift, sandybridge beyond is looking at jack shit overall.

>> No.58530273

>>58524630
>>58524511
Electrons hitch rides through atoms, they're not radiating through anything

>> No.58530814

>>58524931
mmo's will never run well
even everquest, which use to run on a pentium 2, in the same zones that have not changed, bring a modern pc to its knees.

>> No.58530844

>>58526660
on the fun portion, the game requires the use of the entire keyboard to play, the devs cant into good design to save their goddamn lives, there is no excuse for requiring that god damn much.

>> No.58530850
File: 343 KB, 514x433, 1482434777427.png [View same] [iqdb] [saucenao] [google] [report]
58530850

>>58520405
>GPU bottlenecked benchmark
fuck outta here. stop spreading literal bullshit nigger

>> No.58531650

>>58518901
To me, future proofing (i.e., but the best consumer i7 available at the time) is a waste because even if the performance is "fine" years later, there are other aspects that might make a user want to upgrade, such as faster RAM, power efficiency, or connections (PCIe 3 or 4 or m.2)

>> No.58533243 [DELETED] 

>>58531650
I think now is a good time (almost, waiting for ryzen) to buy a new CPU and motherboard, since DDR4 is still kinda new and should be supported for years to come.

>> No.58534094

I have i7 2600k, been running at 4.5 its whole life, machines around 7 years old give or take. I have a 770 4gb from a few years back in there now, runs most stuff ok. But from reading this thread its actually worth me just upgrading to a 970+ or something and i should be sorted for another few years? I dont feel like blowing £2000 for a new setup anytime soon

>> No.58534184

>>58534094
not until its dead desu

>> No.58534215
File: 27 KB, 571x425, 1467304686811.jpg [View same] [iqdb] [saucenao] [google] [report]
58534215

>>58521341

>tfw you keep catching your neighbor shitposting on 4chan

>> No.58534650

>>58534094
If your 770 is chugging, you can get a 970/1060/470/480.

But personally I'd wait until either Volta from NVIDIA or Vega from AMD

>> No.58534730

>>58534650
yeah this is what i want todo, to be honest i never thought about it since i assumed there would be such a bottleneck with my 2600k and original mobo , guess i bought into the wrong knowledge, or lack of it

>> No.58534817

>>58530850
>have IPS monitor
>2500k at stock gets over 60fps
Why should I upgrade my cpu again?

>> No.58534838

>>58534730
Your CPU is fine (won't bottleneck any gfx card at reasonable gfx settings), and you could consider a jump to a higher res, like 1440p.

>> No.58534856

>>58534817
Not really, the minimums are far below 60, which is what matters. You can turn down a few settings (shadows and draw dist) to keep a locked 60

>> No.58534889

>>58534838
Its been a great work horse and flawless overclocker for me for sure.

thanks for the info dude, ill invest in a new gfx card powerhouse and see how i do

>> No.58535034
File: 2.00 MB, 360x202, 18vh1a.gif [View same] [iqdb] [saucenao] [google] [report]
58535034

>>58528589

>filaments

Not truly. Filaments use resistance of a metal to produce the glow, this is exciting nearby neon gas to cause the glow. Numitrons (pic related) are filaments. The smaller, segmented ones are numitrons which are filaments.

>>58534215

FUCK OFF MIKE

>> No.58535073
File: 35 KB, 500x386, 1400969401784.jpg [View same] [iqdb] [saucenao] [google] [report]
58535073

>>58518901
I got 4.5 GHz stable on a 3570K, and that's on air cooling. CPU-Z gives me 108% performance on single thread versus a 6600K. Granted the 6600K isn't overclocked, but going for a 6600 means new motherboard and possibly new RAM.

This thing is good for another 3 years at least, unless Intel pulls their finger out of their asshole and does something incredible.

>> No.58535175

>>58535073
What incentive is there for intel to develop something amazing when they can fuck around and release the absolute minimum improvement because AMD are incompetent?

I genuinely hope Ryzen doesn't turn out to be bulldozer 2.0 solely because it might force intel to either drop prices or produce something worth upgrading to

>> No.58535407

>>58535175
Once upon a time there was a rumor that Apple would start making Macbooks with ARM chips, but ever since then they decided to release the iPad pro instead.

Heard another one that some company somewhere was working on building some retardedly powerful ARM chip that was basically scaling ARM up to x86 levels of TDP. Again all just hearsay.

Intel doesn't even need to focus on massive improvements because the High-performance market has been cornered by GPUs and other HPC silicon for highly parallel workloads like machine learning etc. and Datacentres will continue buying whatever they put out, and if it's not enough they'll just buy more chips because they can just scale them out, because they're buying at such ridiculous volumes anyway.

I've never been a fan of AMD but if Ryzen gets it right, no, better than right then I'd switch. I don't want the most ludicrously powerful chip, just a well-engineered efficient one, which Intel has always seemed to have.

>> No.58535557

>>58535175
Intel have already put hyper threading in the pentium chips in a not so subtle response to ryzen, thus shutting AMD's FX line out of the budget CPU market more or less. They did this knowing full well it would butcher their i3 sales, but I guess they figured it was worth it to cut AMD off.

Intel are concerned, and if Ryzen delivered the goods, they will react, and it will be glorious for the consumer. IF their 4/6/8 cores beat intel at every price point (150,250,350,500$), then I can definitely see intel hyperthreading their i5's too, and possibly even unlocking all SKU's next generation.

Remember that the process shrink from 10nm is going pretty badly for Intel, and it means their tick tock cycle is dead, they could be in a deep rut development wise at the moment, and this would allow AMD to make up some serious ground, IFFFF Ryzen delivers.

>> No.58535925

>>58524978
Bro get the supcom limiter removal, apparently the game slows down regardless how hard your CPU is being pushed

>> No.58537028

>>58518901
Nothing lasts forever, even the cold november rain.

>> No.58537389

the 5820k was made 3 years ago and still outperforms the 7700k.
>Fucking KEK

>> No.58537776

>>58518901
>10% increase
this gen is 1% better than the 6th gen

>> No.58537800

>>58530273
>Electrons hitch rides through atoms, they're not radiating through anything
Right and the atoms just move through the circuit huehuehue

>> No.58538373

>>58535073
>108%

>> No.58538527

CPUS HAVE BEEN STAGNANT AS FUCK OUTSIDE OF A FEW VIRTUALIZATION FEATURES LIKE IOMMU

OCED I7 920S ARE STILL GOOD ENOUGH FOR MOSTLY EVERYTHING

>>
Name (leave empty)
Comment (leave empty)
Name
E-mail
Subject
Comment
Password [?]Password used for file deletion.
Captcha
Action