[a / b / c / d / e / f / g / gif / h / hr / k / m / o / p / r / s / t / u / v / vg / vm / vmg / vr / vrpg / vst / w / wg] [i / ic] [r9k / s4s / vip / qa] [cm / hm / lgbt / y] [3 / aco / adv / an / bant / biz / cgl / ck / co / diy / fa / fit / gd / hc / his / int / jp / lit / mlp / mu / n / news / out / po / pol / pw / qst / sci / soc / sp / tg / toy / trv / tv / vp / vt / wsg / wsr / x / xs] [Settings] [Search] [Mobile] [Home]
Board
Settings Mobile Home
/g/ - Technology


Thread archived.
You cannot reply anymore.


[Advertise on 4chan]


File: 1920px-ARMCortexA57A53.jpg (763 KB, 1920x1272)
763 KB
763 KB JPG
ARM VS X86
Who wins /g/??

I have seen a lot of ni/g/gers on here shill for ARM lately but they never seem to explain why or come with evidence that it is better than x86
>>
>>100163943
Doesn't matter. Even if your computer was suddenly a thousand times faster and more energy efficient it would take no time at all for software to get a thousand times slower and for chip makers to push the max benchmark performance out of their chips resulting in a thousand times more power consumption.
People are just excited for change because it'd be a cool new toy but for 99% of all programmers it's just a matter of changing a few config settings at compile time and providing one more binary.
>>
File: 7945hx.png (13 KB, 597x107)
13 KB
13 KB PNG
>>100163943
>So is it a better Architecture or what?
not really
best x86 is on par with best arm
phone socs are just tightly integrated with miniscule idle usages so they get very good battery but to perform like x86 they need same power like x86
>>
>>100163943
Yes, ARM is RISC and x86 is CISC. Complexity is bad.
>>
>>100163943
RISC vs CISC has been irrelevant since 1995 when the transistor budget became large enough to make x86's complication relatively minor and irrelevant.

The difference is there are only 2 companies designing their own x64 cores while there are half a dozen designing their own ARM cores. More competition suggests ARM will win in the end.
>>
>>100163943
In short:

x86 = freedom

ARM = communism

The latter is primarily being force fed to the masses so that they eventually pay money to rent an x86 computer over the internet thus only the wealthy elite will be in possession of freedom computers I guess. See geforce now.
>>
>>100164088
Imagine thinking modern ARM is even remotly "reduced".
>>
>>100163943
Mx wins at two workloads compared to the best x86 laptops.
- playing Big Buck Bunny on a loop.
- restricting the power consumption of high spec configurations

A good 7840U laptop has about the same efficiency when shitposting as a normal M2. A good 7945HX laptop has has about the same efficiency running Cinebench MT as a M2 Max. M3 is better, but that's mostly process advantage.

What 7945HX systems can't do well is stay efficient while shitposting. Is that the difference of ARM to x86? Unlikely, more likely everything around it.
>>
>>100163943
RISC V beats ARM beats x86
>>
>>100163943
I hope arm solely because i am sick and tired of intel and amd and want them both to die
>>
File: 1693097673935626.png (1.58 MB, 1001x1007)
1.58 MB
1.58 MB PNG
>>100163943
The X86, of course, has, when you want software running faster on the ARM CPU, you need to compile it, especially for this specific CPU. Otherwise, X86 will win every time.

This is something you uneducated faggots won't understand.

Deploying same binary for different types of ARM CPUs, results in a drastic performance degradation.

And this is the only reason MacOS has the only viable software ecosystem for its ARM-based M series.

So you see, effectively, the X86 CPUs will dominate the market for the next few decades.
>>
File: 1581481597624.jpg (74 KB, 310x310)
74 KB
74 KB JPG
>>100163943
You go with ARM if you play geekbench alot
>>
yes, Risc-v or power isa for Trve freedom
>>
I like the fact they generally have less Builtin cpu bugs/exploits
>>
ARM is good when you want to watch tiktok for 10 hours a day
x86 is good when you have some heavy lifting to do
>>
>>100163943
RiscV, if Huawei is betting the house on it, it's the future.
>>
>>100163943
>ut they never seem to explain why or come with evidence that it is better than x86
> coping ipedophile hasn't seen the thousands of screenshots of apple's m-series being destroyed by x86
L
M
A
O

>>100164036
> muh power consumption
nobody gives a fucking shit about power consumption, nigger. people give a shit about performance. now match performance between x86 and ARM, you dumb coon.
>>
>>100165552
>nobody gives a fucking shit about power consumption

t.nigger who never leaves the basement
>>
>>100165608
He is right you know?
Performance first, temps second
I measure in FPS faggot not in °C

There is a reason why we only see ARM in Phones and tablets and x86 in PC's
>>
>>100163943
X86 will eventually fase out of the market, all major tech companies are in the process of or already producing arm based SoCs
>>
>>100165515
I agree, but it's not huawei that is controlling the chinese market, there will be a Cambrian explosion of consumer electronics brands flooding all markets with 7 nm and 5nm arm based first made by smic and designed by the likes of rockship (they already took odominate sbc mini computer market), they will not go into risc-v after investing heavily on making arm SoCs
>>
Arm wins
>>100165552
if power consumption means noise, then yeah most people care
>>
>>100165552
>nobody gives a fucking shit about power consumption, nigger. people give a shit about performance.
It's seems kinda significant.
I jumped back into this computer shit after tuning out for a decade, to build a couple low-power workstation / home servers. Most stuff I looked at wasn't much better than an Apple M1, but were double the power draw, or more.
>>
Itanium is genuinely a better architecture than either but implementations were subpar. The early ones were too static and dependent on magic compilers which didn't materialize while the later dynamic itaniums were too late and no one cared that they finally fixed ia64, especially not Intel
>>
>>100163943
RISC-V is inevitable.
>ARM VS X86
Both are irrelevant in the face of RISC-V.
>>
>>100164485
> Laughs in VGF2P8AFFINEINVQB
>>
>>100164032
*Laughs in AI*
>>
>>100164088
>>100164605
>>100164639
>>100165515
Based.
>>100164197
Unjustified complexity is still inherently bad.
>>100164393
>x86 = freedom
>ARM = communism
Both are proprietary, you need a license.
RISC-V is freedom; everybody gets a free license.
With RISC-V, Free Market rules apply.
>>100164485
The R in ARM still stands for RISC. ARM has rid of cruft several times in the past, breaking binary compatibility.
ARM remains an order of magnitude simpler than x86.
I still prefer MIPS and RISC-V, they're much simpler and do not lose anything for it.
>>
>>100163943
RISC-V64
>>
>>100166324
>ARM remains an order of magnitude simpler than x86.
>ARM ISA reference manual: 12,000 pages
>x86 ISA reference manual: 5000 pages
So much simpler.
>>
>>100166976
takes a person with a very high iq to understand those 5,000 pages.
>>
>>100166976
ARM having more extensive documentation despite being a simpler ISA might have something to do with Intel documentation targeting programmers, whereas ARM's targets both programmers and digital designers.
Are you so feeble-minded as to not realize? Do you need us to hold your hand to this extent?



[Advertise on 4chan]

Delete Post: [File Only] Style:
[Disable Mobile View / Use Desktop Site]

[Enable Mobile View / Use Mobile Site]

All trademarks and copyrights on this page are owned by their respective parties. Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.