Overclock.net - An Overclocking Community

Overclock.net - An Overclocking Community (https://www.overclock.net/forum/)
-   Hardware News (https://www.overclock.net/forum/225-hardware-news/)
-   -   [Tom's Hardware] Intel Brings Its Own Benchmark to Refute AMD's '2X' EPYC Claim (https://www.overclock.net/forum/225-hardware-news/1726782-toms-hardware-intel-brings-its-own-benchmark-refute-amds-2x-epyc-claim.html)

WannaBeOCer 05-31-2019 10:22 AM

[Tom's Hardware] Intel Brings Its Own Benchmark to Refute AMD's '2X' EPYC Claim
 
1 Attachment(s)
Source: https://www.tomshardware.com/news/in...eon,39544.html

Quote:

Intel is firing back at AMD CEO Lisa Su's Computex claims that the company's upcoming 7nm EPYC Rome data center processors are twice as fast as Intel's Xeon Scalable 8280 processors in a popular benchmark. But Intel says that AMD didn't configure its Intel test system correctly, and also didn't use the most relevant processors for comparison testing. Now Team Blue has released benchmarks to back its claims.

But Intel doesn't want to just be more competitive. It wants to prove that it will continue to lead even after AMD's 7nm Rome processors come to market. To that effect, Intel also included test results with its Xeon Platinum 9000-series (Cascade Lake-AP) that come armed with as many as 56 cores, 112 threads, and 12 memory channels crammed into a package that dissipates up to 400W. These new behemoths, which are essentially two Skylake-SP CPUs in a single socket, only come in OEM servers, so they aren't available on their own like AMD's Rome chips will be.

AMD did use a different compiler for its EPYC setup than it did for the Intel system, but that's expected. Intel's tuning did expose greater performance from its chips than AMD did, but that appears to be because AMD didn't use the optimizations. Intel's optimizations are available publicly on its website, meaning that AMD either wasn't aware of the optimizations or chose not to use them. Aside from the lack of optimizing the competitors' platform, which may be unintentional, it doesn't appear that AMD went out of the way to skew its test results.

tpi2007 05-31-2019 10:47 AM

So, they're saying:

1. "We don't lose by that much.";
2. "And when compared against the upcoming 2S 48C/96T system that's a non upgradeable, soldered to the board special OEM order we expect to tie (up to 1.5% higher) with a much more power hungry setup.";
3. "And if we dial it up to 11, our 2x400w 2S 56C/112T system that is also the same OEM affair can be up to 23% faster.".

I get why they have to say this, but the outcome is a little embarrassing.

rdr09 05-31-2019 10:53 AM

Is there a benchmark that will uncover which gets exploited the most?:)

looniam 05-31-2019 11:21 AM

in a totally unrelated note:


Hwgeek 05-31-2019 11:43 AM

Quote:

Originally Posted by tpi2007 (Post 27986970)
So, they're saying:

1. "We don't lose by that much.";
2. "And when compared against the upcoming 2S 48C/96T system that's a non upgradeable, soldered to the board special OEM order we expect to tie (up to 1.5% higher) with a much more power hungry setup.";
3. "And if we dial it up to 11, our 2x400w 2S 56C/112T system that is also the same OEM affair can be up to 23% faster.".

I get why they have to say this, but the outcome is a little embarrassing.

Funny part is that 2x400w 2S 56C/112T is actually 4s 28C to match 2s Rome :-).

Intel just made a bet that they could just invest in Fabs and keep continuing down-scaling their same monolithic design to make more CPU's per wafer, but 10nm showed them that they can't make good yields with their massive 28c design and they are stuck trying to fix the 10nm processes till this days, if they made a choice to move to chiplet design then they could compete AMD's Servers cheap more easily.
.

tpi2007 05-31-2019 12:03 PM

Quote:

Originally Posted by Hwgeek (Post 27987060)
Funny part is that 2x400w 2S 56C/112T is actually 4s 28C to match 2s Rome :-).

Intel just made a bet that they could just invest in Fabs and keep continuing down-scaling their same monolithic design to make more CPU's per wafer, but 10nm showed them that they can't make good yields with their massive 28c design and they are stuck trying to fix the 10nm processes till this days, if they made a choice to move to chiplet design then they could compete AMD's Servers cheap more easily.
.


Their response reminds me of Monty Python's dead parrot sketch, here in adapted form:

Quote:

Spoiler!


startekee 05-31-2019 12:08 PM

I am confused. Is this saying that Intel's 56c setup is faster than AMD's 64c?

WannaBeOCer 05-31-2019 12:28 PM

Quote:

Originally Posted by startekee (Post 27987100)
I am confused. Is this saying that Intel's 56c setup is faster than AMD's 64c?

With optimizations which probably Rome would also benefit from when looking at Zen's performance when running Clear Linux. Maybe in a few years we'll be able to see an optimized AMD distro.

https://www.phoronix.com/scan.php?pa...ux-10way&num=4

"Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel."

Hwgeek 05-31-2019 12:40 PM

Quote:

Originally Posted by tpi2007 (Post 27987094)
Their response reminds me of Monty Python's dead parrot sketch, here in adapted form:

You killed me with that, ROFL!.

cssorkinman 05-31-2019 12:41 PM

Wow things are really getting bad if Intel is complaining about a compiler that favors AMD..... ;)

NightAntilli 05-31-2019 01:24 PM

Damage control and nothing more.

magnek 05-31-2019 06:04 PM

Karma is a female dog

And also Intel is a giant hypocrite, but I'm sure you all knew that.

opt33 05-31-2019 07:03 PM

I bet posting picks up when ryzen 7nm gets released as many long term intel users like myself will be new to amd mobo/cpu/ocing hence reading/posting again from necessity and from finally having something interesting to talk about. It also may be a little annoying switching/relearning AMD, but necessary after Intel management followed the Charlie Sheen plan of how to stay on top.

CJRhoades 05-31-2019 07:10 PM

So when Intel glues together two $10k CPUs and makes a giant one that isn't socketed and is only available in OEM servers, they achieve 23% higher performance at the cost of 60% higher power. I'm not sure why they would want to point that out to anyone. Seems like a very roundabout way to say they're still losing. Anandtech estimates those Xeon 9282's run $25k+ and I'm sure AMD would be happy to sell you the top Rome SKU for a quarter of that.

The Robot 05-31-2019 09:03 PM

Emergency Edition and fact manipulation. Intel never changes.

rluker5 06-02-2019 10:19 AM

Quote:

Originally Posted by dagget3450 (Post 27987656)
Is that before or after you disable hyper threading?

I don't have untrusted guests running vms on my computers so I don't have to worry about them jumping from their hyperthread to mine.

Hwgeek 06-02-2019 10:26 AM

GL to intel when 64C TR will be out, it's safe to assume that new TR MB with upgraded VRM could offer near 8X9900K raw performance with PBO active ~500W.

Wishmaker 06-02-2019 01:39 PM

AMD fanboys are the saltiest you can find.
When E6600 came out you were in denial for 12 months.
Now this chip is not even launched and praise AMD for being victorious.

This industry works in cycles and once AMD is on top, INTEL will take out the big guns.

Speaking of benchmark manipulation, when NVIDIA was haxing and AMD came out with proof that they were, y'all praised your lord and saviour AMD.
When INTEL tries to clarify the situation and show that AMD's numbers were not entirely correct, INTEL is playing dirty again.

Its that time of the year when I retire from OCN because of the super toxicity when it comes to AMD fanboyz.

Hwgeek 06-02-2019 02:04 PM

Quote:

Originally Posted by Wishmaker (Post 27988970)
This industry works in cycles and once AMD is on top, INTEL will take out the big guns.


Yes - this is the key for good progress in development and innovation, unlike past decade that Intel had monopoly with ~90%+ and stopped the progress, now we see how much can change just in 2 years if there is a competition.
Lets hope for healthy competitions for many years to come, we all gonna benefit from that.

bmaxa 06-02-2019 02:13 PM

yes, with AMD out of the game we saw stagnation and degradation. That is how things work without competition.

opt33 06-02-2019 02:16 PM

I built ~ 20 computers in past 20 years, never touched an AMD mobo, cpu, or gpu, ryzen 7nm will be my first. While I dont understand cheering for a piece of equipment, if I did im not sure buying only intel and nvidia for 20 yrs qualifies me as an AMD fanboy. But any company that has a monopoly (intel on high end) is going to exploit consumers, it is business 101... look at pharmacies and non-generic drugs. When the competition (AMD in this case), despite lower resources and R&D comes from behind and provides a cheaper, competitive high end product and without penny pitching ie using solder tim, etc, I think that win for the consumer in bringing better products at a lower price is worth cheering about. Im a fan of quality products at competitive prices, monopolies do not supply competition.

maltamonk 06-02-2019 02:23 PM

Quote:

Originally Posted by opt33 (Post 27989002)
I built ~ 20 computers in past 20 years, never touched an AMD mobo, cpu, or gpu, ryzen 7nm will be my first. While I dont understand cheering for a piece of equipment, if I did im not sure buying only intel and nvidia for 20 yrs qualifies me as an AMD fanboy. But any company that has a monopoly (intel on high end) is going to exploit consumers, it is business 101... look at pharmacies and non-generic drugs. When the competition (AMD in this case), despite lower resources and R&D comes from behind and provides a cheaper, competitive high end product and without penny pitching ie using solder tim, etc, I think that win for the consumer in bringing better products at a lower price is worth cheering about. Im a fan of quality products at competitive prices, monopolies do not supply competition.

Wow you missed out on some good hardware. On the CPU/mobo...you'd have to go back a ways, but on the GPU front 7970, 290x, and ofc mid/low end gpu's.

m4fox90 06-02-2019 03:53 PM

Quote:

Originally Posted by Wishmaker (Post 27988970)
AMD fanboys are the saltiest you can find.
When E6600 came out you were in denial for 12 months.
Now this chip is not even launched and praise AMD for being victorious.

This industry works in cycles and once AMD is on top, INTEL will take out the big guns.

Speaking of benchmark manipulation, when NVIDIA was haxing and AMD came out with proof that they were, y'all praised your lord and saviour AMD.
When INTEL tries to clarify the situation and show that AMD's numbers were not entirely correct, INTEL is playing dirty again.

Its that time of the year when I retire from OCN because of the super toxicity when it comes to AMD fanboyz.

You're right about one thing, there's definitely some toxicity.

philhalo66 06-02-2019 04:03 PM

Quote:

Originally Posted by Wishmaker (Post 27988970)
AMD fanboys are the saltiest you can find.
When E6600 came out you were in denial for 12 months.
Now this chip is not even launched and praise AMD for being victorious.

This industry works in cycles and once AMD is on top, INTEL will take out the big guns.

Speaking of benchmark manipulation, when NVIDIA was haxing and AMD came out with proof that they were, y'all praised your lord and saviour AMD.
When INTEL tries to clarify the situation and show that AMD's numbers were not entirely correct, INTEL is playing dirty again.

Its that time of the year when I retire from OCN because of the super toxicity when it comes to AMD fanboyz.

no worse than intel fanboys, that goes both ways, Intel fanboys are far worse they use personal attacks when you criticize their purchases.

magnek 06-02-2019 11:42 PM

Quote:

Originally Posted by Wishmaker (Post 27988970)
AMD fanboys are the saltiest you can find.
When E6600 came out you were in denial for 12 months.
Now this chip is not even launched and praise AMD for being victorious.

This industry works in cycles and once AMD is on top, INTEL will take out the big guns.

Speaking of benchmark manipulation, when NVIDIA was haxing and AMD came out with proof that they were, y'all praised your lord and saviour AMD.
When INTEL tries to clarify the situation and show that AMD's numbers were not entirely correct, INTEL is playing dirty again.

Its that time of the year when I retire from OCN because of the super toxicity when it comes to AMD fanboyz.

Replace AMD with Intel, E6600 with P4 (EE) and the same also rings true.

Kpjoslee 06-03-2019 12:36 AM

Quote:

Originally Posted by philhalo66 (Post 27989096)
no worse than intel fanboys, that goes both ways, Intel fanboys are far worse they use personal attacks when you criticize their purchases.

Well, you will get personal attacks if you criticize their purchase lol. Make criticisms on products, not their purchases.

ToTheSun! 06-03-2019 01:36 AM

Quote:

Originally Posted by NihilOC (Post 27987536)
crackpot conspiracy theorists that hijack every privacy or security thread rambling about how they personally just run an airgapped abacus rather than rely on M$ Windoze spyware.

That made me chuckle heartily.

Ghilly 06-03-2019 05:13 AM

Quote:

Originally Posted by NihilOC (Post 27987536)
Honestly, from the perspective of someone that is slowly visiting this site less and less, what is killing the site is every thread being filled with "Intel fanboy" or "AMD fanboy" namecalling. That and crackpot conspiracy theorists that hijack every privacy or security thread rambling about how they personally just run an airgapped abacus rather than rely on M$ Windoze spyware.

People just don't find that interesting, at this point I don't see it changing however and I suspect the user base will just slowly die out as people find other news aggregators. Overclock.net is also more than likely facing reasonable competition from the declining interest in overclocking, and the rise of more general purpose competing services like Google News.

This is the reason for me also - the whole Amdz is da best /Intel is da best and Im the new Alan Turing garbage attitude that covers this site is so boring

mothergoose729 06-03-2019 01:50 PM

Quote:

Originally Posted by rluker5 (Post 27988872)
I don't have untrusted guests running vms on my computers so I don't have to worry about them jumping from their hyperthread to mine.

Do you host your server with Amazon AWS? No... lots of other people do.

bmgjet 06-03-2019 02:56 PM

I remember when the shoe was on the other foot and intel claiming Cine bench is the most accurate benchmark there is and disabling there AMD lock out in the complier was cheating.

KyadCK 06-04-2019 10:39 AM

Quote:

Originally Posted by Defoler (Post 27990740)
And Rome is 8 chips of 8 cores. It is not a true 64/128 the same as you bash intel for not being true 56/112.
But hey, it's AMD, we should ignore that and only bash intel. AMD are sacred ground.

That would be true of EPYC, but not EPYC 2.

EPYC and Intel's new 56-core are literally several complete discrete dies connected by inter-die communications (IF and UPI). EPYC 2 is chiplets. Significant difference, especially at the NUMA level that everyone gave EPYC grief for.

ryan92084 06-07-2019 02:47 AM

Agreed. If you don't like reading a certain company's news then just don't open the thread? I really don't see the issue with bringing in more news.


All times are GMT -7. The time now is 07:41 PM.

Powered by vBulletin® Copyright ©2000 - 2019, Jelsoft Enterprises Ltd.

User Alert System provided by Advanced User Tagging (Pro) - vBulletin Mods & Addons Copyright © 2019 DragonByte Technologies Ltd.
vBulletin Security provided by vBSecurity (Pro) - vBulletin Mods & Addons Copyright © 2019 DragonByte Technologies Ltd.

vBulletin Optimisation provided by vB Optimise (Pro) - vBulletin Mods & Addons Copyright © 2019 DragonByte Technologies Ltd.