https://www.techpowerup.com/231536/ amd-ryzen-machine-crashe

holy shit they fucked up the architecture design lmao

>>59515927
>What do I do with my new CPU?
Be disappointed in AMD, then sell it and buy Intel like any sane person would've done in the first place.

File: amd-into-the-trash.jpg (410KB, 2445x1375px) Image search: [Google]

410KB, 2445x1375px

>>59515927
>What do I do with my new CPU?

Put it where all AMD products belong

https://www.bit-tech.net/news/hardware/2017/03/21/amd-ryzen-fma3-fix-promise/1

Holy shit fuck AMD

Competition is for suckers.\
Brand loyalty is where it's at baby.
All hail Intel and their i7 CPUs.

https://www.extremetech.com/computing/220953-skylake-bug-causes-intel-chips-to-freeze-in-complex-workloads

skylake meme was just hype?

>>59515927
Looks like Ryzen is trash, developer can't even be bothered to make architecture specific binaries.

>FMA3
desu nothing of actual value, it's like the Skylake TSX fuckup, except that apparently AMD has a fix for it unlike Intel
And Zen is completely new, Skylake wasn't

>>59516032
flops(the application in question) only supports up to Haswell

>>59515983
DELET DIS

>>59516034
>>FMA3
>desu nothing of actual value, it's like the Skylake TSX fuckup, except that apparently AMD has a fix for it unlike Intel
>And Zen is completely new, Skylake wasn't

Yep. Nothing to see here, Intel fanboys grasping for anything they can while sane folks move on and buy Ryzen

>AMD says fixed next AGESA update

Wow its fucking nothing, you might an argument if it needed a new stepping, but nope, just microcde.

File: ryzen-cpu-value.png (26KB, 773x371px) Image search: [Google]

26KB, 773x371px

>>59516061
Ryzen is a horrible CPU and not just because of all the bugs

>The issue with Flops was found and fixed in the beginning of february.
>The current µcode version dates to 01/27/2017, so the fix is obviously not included yet (due to the time required for validation).
>Flops is only affected when the SMT is enabled, so disabling the SMT can be used as a temporary work-around (until the actual fix arrives).

http://forum.hwbot.org/showpost.php?p=480922&postcount=30

Intel fanboys grasping at straws.

>>59516089

It's not horrible. It's got many use cases . Sure it's not the cheapest , but it's not slow.

>>59515927
>only happens on windows
install gentoo

File: a57ee0bc939b.jpg (290KB, 2040x3160px) Image search: [Google]

290KB, 2040x3160px

>>59515983

>>59516120
>but it's not slow
It's slower than cheaper Intel offerings in 99% of normal use cases

>with separate binaries for each major x64 architecture (eg: Bulldozer, Sandy Bridge, Haswell, Skylake, etc.), and as such the GitHub repository does not have a "Zen" specific binary.

>highly customized build which is specifically designed for different architectures at asm level doesnt work correctly on a processor its not designed for.

Fucking idiots.

File: x265-2.png (582KB, 600x600px) Image search: [Google]

582KB, 600x600px

>>59516089
Daily reminder than the $1,000+ i7-5960X OC'd to 4.4GHz with an aftermarket cooler could barely beat the $320 R7 1700 OC'd to 4 GHz WITH THE FUCKING STOCK HEATSINK.

AMD surpassed my expectations, Haswell single thread performance at a low cost.

I will definitely buying a 1500 to upgrade from my i3 6100. You fan boys and shills have no power.

>>59516195
>AMD has just barely managed to catch up with Broadwell-level IPC
Meanwhile Intel has higher IPC and chips that actually have overclocking headroom, unlike Ryzen

>Specific bug that can only be used by running very specific code in VM
>AMD says it will be fixed next update
Kek Intel fanboys will find anything to try and claim that AMD is dead
Ryzen really triggered them I guess

>>59515927
even the comments btfo your shitpost..

File: 1478940400794.jpg (113KB, 500x500px) Image search: [Google]

113KB, 500x500px

>>59515927
>Haswell TSX
>Sandy Bridge E VT-d
>Intel Atom's (pre-baytrail) poor FPU performance

oh and here you go
http://www.intel.com/content/dam/www/public/us/en/documents/specification-updates/4th-gen-core-family-desktop-specification-update.pdf
go to page 23

They both do it, it will be patched in a microcode update
its nothing.

>>59516235
>m-muh single-threaded performance

>>59516294
Like it or not, the majority of everyday workloads is still highly dependent on single-threaded performance

File: 1468186575554.gif (3MB, 322x178px) Image search: [Google]

3MB, 322x178px

>>59516089
>$175 i3
>best value
nice graph you thick fuck

File: RyzenRiseoftheTombRaider1080pVeryHighPreset.png (12KB, 800x600px) Image search: [Google]

12KB, 800x600px

>>59516310
>source: my ass
also see pic related :^)

>>59515927
Already fixed in microcode, and you probably know that.
Shitposting with false info hasn't been fun for a decade now.

Or should I just spam all 141 Skylake errata again?
Maybe the over 200 X99 platform errata?
>>59427843

>>59516492
It's only ok when Intel does it

>>59515927
>>59515983
https://www.techpowerup.com/229594/intels-skylake-and-kaby-lake-based-systems-vulnerable-to-usb-exploit

>>59515927

retards like you really piss me off
educate yourself on the subject of cpu bugs before you post
https://www-ssl.intel.com/content/dam/www/public/us/en/documents/specification-updates/4th-gen-core-family-desktop-specification-update.pdf
>no fix
>no fix


it's time for you to stop posting

>>59516462
A poorly optimised anomaly

>>59516857
Didn't seem very poorly optimized to Intelfags when it was running faster on 7700k on launch day.

Expecting hardware to be complete bug free is as foolish as expecting software to be completely bug free. Even the best minds cannot make something absolutely perfect.

File: 45ture.png (15KB, 441x173px) Image search: [Google]

15KB, 441x173px

>>59515927
Old news, already fixed. Fuck off.

File: 1467480674285.jpg (50KB, 676x720px) Image search: [Google]

50KB, 676x720px

>>59516462
Using your cpu for gpu benching but not disregarding the fact that when it comes to cpu vs cup benches the 7700 sucks ass for its price. lulz and keks

>>59516492
lmao, all saved

>>59517092
>too stupid to read the chart
kys

>>59516857
>It's only okay if optimization suits my brand

I'm really tempted to buy a Ryzen because of muh rendering speeds, but I really don't want to deal with the instability memes.

>>59517666
Buy an ASRock or Gigabyte mobo and you'll be mostly fine. You can also install Windows 7 instead of 10, since there're drivers for it. You need WSUSOffline if you want to install updates on Win7, though, because MS blocked updates for people running Windows 7 on Kaby Lake/Zen CPUs.

File: 1490088228195.jpg (20KB, 492x468px) Image search: [Google]

20KB, 492x468px

>>59515927
>>59516089
>An important point to note here is that this little known benchmark has been tailored by its developer to be highly specific to the CPU micro-architecture, with separate binaries for each major x64 architecture (eg: Bulldozer, Sandy Bridge, Haswell, Skylake, etc.), and as such the GitHub repository does not have a "Zen" specific binary.

Fucking shills i swear.
UPDATE YOUR FUCKING GRAPHS

>>59516857
>WAHHHH, IT BENEFITS AMD SO IT MUST BE EXCLUDED
Fucking shills i swear

File: 1490071744222.png (170KB, 1448x1302px) Image search: [Google]

170KB, 1448x1302px

>>59516089
>Gaymang benchmarks

Daily remind that this is /g/, and not /v/. Too all misplaced, please go back.

>>>/v/

Is there any reason why people don't do benchmarks with ordinary rendering software like sony vegas?

>>59516089
Kill yourself.

>>59518202
Because it's shit. Linpack was supposed to be the standard everyone was gonna use but then faggots like passmark and geekbench fucked everything up.

>>59515927

Already fixed, faggot