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

Due to resource constraints, /g/ and /tg/ will no longer be archived or available. Other archivers continue to archive these boards.Become a Patron!

/g/ - Technology

View post   

[ Toggle deleted replies ]
File: 18 KB, 403x402, CPU-Z.png [View same] [iqdb] [saucenao] [google] [report]
61740874 No.61740874 [Reply] [Original] [archived.moe] [rbt]

Why does a $500 flagship AMD CPU from 2017 have worse single-threaded performance than a $320 Intel CPU from 2011?

>> No.61740923

heil hitler

>> No.61740975

Um, threadripper is their flagship, try again sweaty.

>> No.61740992

>ryzen beats the competition in cpu-z benchmark
>cpu-z update released
>this is no longer true

>> No.61741014

Why does a $999 flagship AMD CPU from 2017 have worse single-threaded performance than a $320 Intel CPU from 2011?

>> No.61741026

Why does a $1700 flagship Intel CPU from 2016 have worse single-threaded performance than a $320 Intel CPU from 2011?

>> No.61741049

Why are you comparing an overclocked CPU with a not overclocked CPU?

Ryzen at 4Ghz has the same single thread performance as Sandy Bridge at 5Ghz

>> No.61741090 [DELETED] 

Lets think about this for a second.

Hardware that has 16 cores and 32 threads might be optimized for using 32 threads rather than just one alone.

Have you considered that?

>> No.61741109
File: 55 KB, 806x402, 5ghz.png [View same] [iqdb] [saucenao] [google] [report]

Show me a Rypoo at 4GHz even coming close to this score. Go ahead, I'll wait.

>> No.61741121

>>61740874 (OP)
Lets think about this for a second.

Hardware+Software that has 16 cores and 32 threads might be optimized for using 32 threads rather than just one alone.

Have you considered that? Ditto for 32 cores.

>> No.61741124
File: 17 KB, 407x404, 2011 vs 2017.png [View same] [iqdb] [saucenao] [google] [report]

>this is what Intel calls progress

>> No.61741140


>> No.61741148

op and Intel btfo

>> No.61741160

>4.7GHz vs 3.8GHz

An overclocked 7600K scores nearly 600 points single thread.

>> No.61741165

is single threaded performance even important now?

>> No.61741194

that's 27% improvement in 6 years

4.06% improvement per year
4.89% per processor generation

>> No.61741195

nobody fucking cares
Ryzen fucked Intel's anus whether you like it or not

>> No.61741236


reminder cpuz adjusted their scoring because ryzen was too good.

>> No.61741249


don't pretend like your CPU is stock fag

>> No.61741256

>"P-P-P-Poozen can d-do that t-too!"
>Prove it then.
>"Benchmarks don't even matter Poozen is the best!"

AMDrones everybody!

Yesssssssss, it's all a big conspiracy to mask Poozen's amazing performance! All benchmarks and real world applications have been bought by Intel and the Jewish Global Conspiracy, otherwise you'd see Poozen on top, because the performance is there. Honest. :^)

>> No.61741261
File: 13 KB, 403x402, 47.png [View same] [iqdb] [saucenao] [google] [report]


lmao 5Ghz is worse than my 4 core i5

>> No.61741285
File: 16 KB, 399x398, Capture.png [View same] [iqdb] [saucenao] [google] [report]

The 7770K is a beast..
Anyone got a 7600K to compared against my [email protected]?

>> No.61741290

>Intel CPU from 2015 beats Intel CPU from 2011

Really made me think.

Still worse multithreaded performance though. Imagine falling for the i5 meme.

>> No.61741365
File: 63 KB, 946x862, 2500k vs 1700.png [View same] [iqdb] [saucenao] [google] [report]

4% difference single threaded
+175% multithreaded performance

>> No.61741370

Because GPU-Z got gimped with an update when Ryzen outperformed Intel. GPU-Z confiormed for Intel shill or got paid.

>> No.61741399
File: 8 KB, 225x225, jhffikufy.jpg [View same] [iqdb] [saucenao] [google] [report]


>> No.61741429
File: 12 KB, 501x504, merchant.gif [View same] [iqdb] [saucenao] [google] [report]


>> No.61741438

>It's all da jooz fault!!!


>> No.61741504
File: 22 KB, 407x404, Screenshot 2017-08-05 03.14.39.png [View same] [iqdb] [saucenao] [google] [report]

The CPU-Z scores are weird

>> No.61741559

who the fuck still use 2011 processor??

get a fucking job man!!

>> No.61742138

It's using dated instructions so more CPUs can bench on it.
If we used something like AVX2 the older CPUs would crawl or not manage to bench at all.

>> No.61742237

what the fuck is wrong with you

>> No.61742256

>literally calling facts /pol/
are you a parody of yourself? they straight up changed the algorithm for CPU-Z because ryzen could fit the entire benchmark in cache and it was "unfairly overperforming"

but no tell me more about the raycism and how it triggers you

>> No.61742291

How the hell are you supposed to compare against a "reference" 1800X when the performance of Zen CPUs seems to rely entirely on RAM speed and timings?

>> No.61742363

I have a 2400 i5 and it doesn't bottleneck me and works perfectly at 3.4GHz. I'd rather add $250 to GPU savings instead of 5fps gains CPU

>> No.61742558

>we found out that their ALUs executed this unexpected sequence in a much more efficient way so we removed it from the test
not even hiding it kek
hurr durr this particular part of our synthetic benchmark is irrelevant, but the rest of the score totally is!

>> No.61742610
File: 162 KB, 633x900, 1489103005792.png [View same] [iqdb] [saucenao] [google] [report]


>> No.61742712

You're mentally ill.

>> No.61742759

The (((update))) was a success.


>> No.61742780

oy vey

>> No.61742786
File: 76 KB, 417x413, CPUZ.jpg [View same] [iqdb] [saucenao] [google] [report]

Guys, aren't the modern CPUs supposed to be 10 times faster than my ancient shit by now?

>> No.61742831
File: 16 KB, 403x402, cpuz_2017-08-05_12-45-33.png [View same] [iqdb] [saucenao] [google] [report]

Not sure.. why does my $200 AMD cpu come so close to to this $1000 Intel CPU from 2014?

>> No.61742888


Yeah but having lots of cache is an unfair advantage because efsyvghdgfjn trnfmkbmurvtydfnverdstbwts!!

>> No.61744578

>almost 30% higher than Intel Skylake
>We reviewed many software and synthetics benchmarks without being able to find a single case where such a performance boost occurs. We're now convinced that this special case is very unlikely to happen in real-world applications. Our new algorithm described below does not exhibit this behaviour.
It's not like this explanation doesn't make any sense, though. Zen doesn't exhibit 30% better single-thread performance than Skylake in any real-world test.

That being said, though, it does imply that their benchmarking methodology consists in trying to develop a benchmark that matches some perceived real-world performance, which is problematic.

>> No.61745365

It really is a terrible benchmark tacked on to an info tool. Don't know why anyone uses it except to troll. Which is probably what the OP is doing here.

>> No.61745392

why does a $9000 xeon from 2017 have worse single thread performance than a highly overclocked $320 intel CPU from 2011?

>> No.61745657

Also disabled HT

>> No.61745997

AMD is a joke

>> No.61746033
File: 232 KB, 800x449, intel ceo yells at clouds.png [View same] [iqdb] [saucenao] [google] [report]

Get back in the cuckcage, Brian.

Name (leave empty)
Comment (leave empty)
Password [?]Password used for file deletion.