>2x Intel(R) Xeon(R) Platinum 8180 CPU @ 2.50GHz (28C 56T 3.8GHz, 2.4GHz IMC, 28x 1MB L2, 38.5MB L3) 5989.90Mpix/s
>2x AMD EPYC 7601 32-Core Processor (4N 32C 64T 2.7GHz, 1.33GHz IMC, 32x 512kB L2, 8x 8MB L3) 974.33Mpix/s
THANK YOU BASED INTEL
AYYMD IS FINISHED & BANKRUPT
AYYMDPOORFAGS CONFIRMED ON SUICIDE WATCH
>>60948648
>no source
Into the trash it goes
Is that sandra? Why the fuck is Sandra used on server CPUs? Where are the SPEC2006 tests?
Fake as fuck.
>>60948648
>source: my ass
>>60948794
SPEC isn't done by users, it's done by a committee which publishes quarterly results.
Pretty much the whole reason anyone buying enterprise hardware goes off from SPEC numbers, if hardware is doing worse than expected in some workloads, middle-manager-kun can all blame it on the 'industry benchmark'
http://ranker.sisoftware.net/show_run.php?q=c2ffcee889e8d5e3dbe3d1e0d6f082bf8fa9cca994a482f1ccfc&l=en
AYYMDPOORFAGS UTTERLY ANAL DEVASTATED
>>60948648
>>60948648
>Providing no source
dropped
>>60948849
So it's the same score as 2x 14 core Haswell Xeons?
Makes sense, maybe, if the other CPU wasn't working.
Yet again another pointless benchmark with so much variation.
>>60949048
I took a deeper look into this, the arithmetic performance on 2S platforms for both highend server chips, Intel is literally x2 of AMD, and considering clockspeeds(equal) core counts(AMD) and IPC(Intel), this makes about as much sense as your mom.
So it's likely the other CPU isn't running for whatever reason, else the difference would be within 10%, not 100%
>>60948648
2 x Intel Xeon Platnium 8180 = USD$24,800
2 x AMD EPYC 7601 = USD$8,000 (at best)
Great comparison fuckwit.
>>60948648
I'm gonna run you some baseline numbers (with false precision)
E5-2699v4 can manage Cinebench R15 (Multi-Core) of 3240
( http://www.cpu-monkey.com/en/cpu-intel_xeon_e5_2699_v4-548 )
WCCFTech is reporting a 47% improvement versus that CPU for the EPYC 7601.
Crude math: 3240 x 1.47 = ~4763
( http://wccftech.com/amd-epyc-7000-series-server-cpu-family-specifications-price-performance-leak/ )
Keep in mind, that's a LEAK, and may not be true.
Another leak from WCCFTech shows a benchmark from Dual Platinum 8178. Since it's a Dual Socket was tested, and there is some diminishing returns for going from 1 to 2 CPUs, let's hald that Cinebench score and add 10% to that halved score (compensate for loss marks, maybe give 8180 like results).
Crude math: (6525 / 2) * 1.10 = ~3589
According to the same article, the 8168, one step down, apparently gives better performance on the dual socket, what happens then?
Crude math: (7212 / 2) * 1.10 = ~3967
( http://wccftech.com/intel-28-core-xeon-platinum-8176-8168-xeon-gold-6161-6142-benchmarks/ )
If you desire to continue circlejerking to your unrealistic to buy and use hardware, please consider this leaked Platinum 8168 selling on Taobao right now for just under $4000 USD.
( https://world.taobao.com/item/548238529710.htm?fromSite=main )
( https://world.taobao.com/item/42659072321.htm?fromSite=main / a platinum 8176 for just over USD$3000 )
Let's review. Crude math aside, I need you to step the fuck back and think. Do you even remotely have a purpose for this hardware, or is your brand loyalty blatantly showing? Seems to be the brand loyalty, as we have a thread for a similarly sounding person multiple times a week.
I cannot give you accurate prices for both processors, but I gave one the post before. It's brand loyalty you have, and you need to step back and look at the bigger picture.
If I've made an error in this post, I'll fix it with follow-up post.
/thread
>>60948648
OP serious question, are you retarded? You know you're not supposed to be doing some hardcore gaming on server CPUs with some liquid nitrogen cooling. That Xeon will burn