Intel's Future Chips: News, Rumours & Reviews

[juanrga]

No, what needs to end is you making everyone believe that Intel is not affected by it and everything is OK.

LOL. This post from mine can be found in this thread:

Let us summarize this shocking news:

1. There are a huge security problem split into three known variants. Those variants are collected into two codenames: Spectre and Meltdown.
2. Spectre attack is confirmed to affect CPUs from AMD, ARM, and Intel. This is very serious. There are no patches available and maybe never will be and new hardware will be required.
3. Meltdown attack is confirmed to affect CPUs from Intel. The situation with AMD and ARM CPUs "is unclear".

So I state clearly that Intel is affected. It is other people which still pretends this is an Intel-only problem and that AMD is not affected.

You just provided justification that the patches indeed do not affect AMD and Intel equally, yet you've been stating over and over and over that watching Intel's performance take a deep dive is absolutely comparable to what AMD might suffer, which is obviously not true.

Just the contrary. Since I know that the patches don't affect equally, I have debunked the FUD that Intel is more affected because it is being patched for Meltdown+Spectre, whereas AMD is being patched only for Spectre. As example I provided a server benchmark where a EPYC server patched only for Spectre suffer a larger performance drop than a Xeon Gold server patched for both Meltdown and Spectre.

And keep in mind these are day-1 patches. These measurements are not "final" either.

I have state that and I quoted Linus thoughts about this.

 

[goldstone77]

AMD has finally admitted it is affected by and stock is dropping.

Clearly Intel's stock price is dropping(~$5), and AMD's is rising(~$2). AMD's 1% stock drop today isn't significant, and it's already heading back up. Intel stock has lost all it gained in the last month, and still declining.

 

[juanrga]

Actually, until there is proof to the contrary Intel is affected more by these patches. How many servers are exclusively using Intel products? Meltdown takes one system call and maps it into 7. That alone is more overhead than AMD since AMD isn't affected by Meltdown. Also, reports now show there is a lot of system instability after the patches, and servers are have to reboot much more often.
I showed the 2 tests form phoronix.com greatest differences in performance between Intel and AMD on patch 4.14 here
http://www.tomshardware.com/forum/id-3609004/cpu-security-vulnerabilities-information/page-5.html#20585746
This clearly shows intel has a much bigger hit to performance out of all the tests vs. AMDs.

Reddis is a data structure server. And your own graphic show that EPYC is affected by 24% whereas Xeon Gold is affected by only 6%.

The Meltdown & Spectre thread is littered with various services reporting ~30% or greater CPU utilization after the patches on Intel products. We have yet to see any reports from any services of severe CPU utilization from AMD systems, but Intel we have several.

http://www.tomshardware.com/forum/id-3609004/cpu-security-vulnerabilities-information/page-5.html#20585463

http://www.tomshardware.com/forum/id-3609004/cpu-security-vulnerabilities-information/page-4.html#20576594

http://www.tomshardware.com/forum/id-3609004/cpu-security-vulnerabilities-information/page-4.html#20576623
Until we have even one definitive report you are just speculating against synthetic benchmarks, which you leave out the one showing Intel is having the most significant performance loss. I find this rather convenient since you are arguing in favor of Intel. The fact that we don't even have one service reporting about AMD performance issues, and multiple reports of Intel's performance issues that constitutes a greater problem for Intel. And this would make their enterprise customers at the very least consider other options like AMD or ARM.

Do you mean that significant benchmark where EPYC suffers a bigger performance loss than Xeon?

Also, as mentioned before, some reports about performance impact of Meltdown are incorrect, because the actual slowdown is generated by the Spectre patch. I mentioned explicitly the case with Amazon AWS. And I quoted Linus stating that it was not Meltdown...

 

[juanrga]

AMD has finally admitted it is affected by and stock is dropping.

Clearly Intel's stock price is dropping(~$5), and AMD's is rising(~$2). AMD's 1% stock drop today isn't significant, and it's already heading back up. Intel stock has lost all it gained in the last month, and still declining.

Both graphs show that AMD is loosing more: 1.07% vs 0.64--0.71%.

Also I did refer to this

https://www.cnbc.com/2018/01/11/amd-stock-drops-3-percent-after-the-company-says-its-chips-are-affected-by-security-flaw.html

https://seekingalpha.com/news/3322506-amd-drops-acknowledging-vulnerability-spectre-flaw

 

[goldstone77]

Yeah, but Juan 1% fluctuation isn't a big deal. The news is hardly having an impact, and isn't really worth the mention to be honest as the comparison shows. Stocks and gain and lose 1% or more daily depending on volatility, and AMD doesn't need much of an excuse to move up and down given it's low market cap. In comparison Intel's 1% fluctuation and volatility is more significant given it's higher market cap and stable stock price trend!

 

[juanrga]

Yeah, but Juan 1% fluctuation isn't a big deal. The news is hardly having an impact, and isn't really worth the mention to be honest as the comparison shows. Stocks and gain and lose 1% or more daily depending on volatility, and AMD doesn't need much of an excuse to move up and down given it's low market cap. In comparison Intel's 1% fluctuation and volatility is more significant given it's higher market cap and stable stock price trend!

Check the links. The drop wasn't 1%.

 

[aldaia]

New Intel AMT Vulnerability found.
Intel AMT Security Issue Lets Attackers Bypass Login Credentials in Corporate Laptops
https://www.theregister.co.uk/2018/01/12/intel_amt_insecure/
http://www.tomshardware.co.uk/intel-amt-bitlocker-bios-bypass,news-57714.html

 

[goldstone77]

Yeah, but Juan 1% fluctuation isn't a big deal. The news is hardly having an impact, and isn't really worth the mention to be honest as the comparison shows. Stocks and gain and lose 1% or more daily depending on volatility, and AMD doesn't need much of an excuse to move up and down given it's low market cap. In comparison Intel's 1% fluctuation and volatility is more significant given it's higher market cap and stable stock price trend!

Check the links. The drop wasn't 1%.

I see what you are talking about now. If you google the 1 year stock price, this is typical nature for AMD stock to make big swings on speculation. This news was being used to incite volatile swings in AMD stock, which any little comment in the press has done. This was probably the most short lived that I've seen not withstanding 24 hours closing at 12.02 (0.99%), and yesterday's close was 12.14. But look at the story though, it's not saying anything AMD hasn't already admitted too. The only difference is they are publically saying they are mitigating variant 2, where we already know they have been implementing it in linux since last Friday. This story is being used as an attempt to cause volatility to make profit. Similar to a pump and dump scam.
http://www.tomshardware.com/forum/id-3609004/cpu-security-vulnerabilities-information/page-3.html#20566795

 

[juanrga]

Intel started shipping 10nm chips

http://www.tomshardware.com/news/intel-ces-10nm-processor,36289.html

Confirmed it is mobile.

Harlan Sur

Got it, got it, okay. Let's talk about next generation, back at the Q3 earnings call BK said that the team would start shipping their first 10 nanometer processor by end of 2017 followed by initial ramp in the first half of this year. Maybe you can give us an update there, did the team execute to what they said they were going to do?

Gregory M. Bryant

Yeah, we did it, actually I will confirm that for you today. We expect[ed] our first 10 nanometer Cannon Lake parts before the end of the year, before the end of the year. And just like we said we are going to do that in our October call which is what you are referring to. And we did exactly what we said we would do and we are still on track for that.

So 10nm desktop by end of 2018?

 

[goldstone77]

Yeah, this statement doesn't instill confidence, and it might have something to do with being lied to for years now... The whole repeating himself at the end... Intel needs to fire BK, he has to be the worst CEO Intel has ever had. All he does is come up with excuses or deflecting comments. They need someone motivated like Nvidia's CEO. BK at CES shows a laid back old man who likes playing with drones...

We expect[ed] our first 10 nanometer Cannon Lake parts before the end of the year, before the end of the year.

 

[8350rocks]

https://www.computerbase.de/2018-01/meltdown-spectre-amd-intel-benchmarks/

Computerbase.de results for intel processors post windows patch, and Ryzen is compared.

They used a 7700K in WinX and 2500K in Win7 and WinX, Ryzen 1800X was WinX as well.

TL;DR:7700K loses minimum of 3% across the board in performance, 2500K loses closer to 10% in WinX, 15% in Win7, and Ryzen loses nothing in any category. The benchmarks also include games for examples.

 

[juanrga]

https://www.computerbase.de/2018-01/meltdown-spectre-amd-intel-benchmarks/

Computerbase.de results for intel processors post windows patch, and Ryzen is compared.

They used a 7700K in WinX and 2500K in Win7 and WinX, Ryzen 1800X was WinX as well.

TL;DR:7700K loses minimum of 3% across the board in performance, 2500K loses closer to 10% in WinX, 15% in Win7, and Ryzen loses nothing in any category. The benchmarks also include games for examples.

That review is already mentioned in the specific thread about Meltdown and Spectre

http://www.tomshardware.co.uk/forum/id-3609004/cpu-security-vulnerabilities-information/page-5.html

The 7700k (full patched) loses 1--2% in applications. 2% in FPS; 8% in 99% framerate. All games results at 720p.

The 2500k loses 0--1% in applications. 0% in FPS; (4% in W7). 5% in 99% framerate (12% in W7). All games results at 720p.

Ryzen "loses nothing" because performance-affecting fix wasn't enabled this round:

This is currently synonymous for the countermeasures for Specter 2, because BIOS updates with new microcode for AMD does not exist, the manufacturer has only started on Friday with the release of the code. These countermeasures are therefore not yet armed in the operating system despite Patch.

 

[goldstone77]

https://www.computerbase.de/2018-01/meltdown-spectre-amd-intel-benchmarks/

Computerbase.de results for intel processors post windows patch, and Ryzen is compared.

They used a 7700K in WinX and 2500K in Win7 and WinX, Ryzen 1800X was WinX as well.

TL;DR:7700K loses minimum of 3% across the board in performance, 2500K loses closer to 10% in WinX, 15% in Win7, and Ryzen loses nothing in any category. The benchmarks also include games for examples.

That review is already mentioned in the specific thread about Meltdown and Spectre

http://www.tomshardware.co.uk/forum/id-3609004/cpu-security-vulnerabilities-information/page-5.html

The 7700k (full patched) loses 1--2% in applications. 2% in FPS; 8% in 99% framerate. All games results at 720p.

The 2500k loses 0--1% in applications. 0% in FPS; (4% in W7). 5% in 99% framerate (12% in W7). All games results at 720p.

Ryzen "loses nothing" because performance-affecting fix wasn't enabled this round:

This is currently synonymous for the countermeasures for Specter 2, because BIOS updates with new microcode for AMD does not exist, the manufacturer has only started on Friday with the release of the code. These countermeasures are therefore not yet armed in the operating system despite Patch.

It's also worth mentioning the impact on solid state devices.

On the power of a separately built in-system Samsung SSD 960 Pro (test) , the active melt-down patch has the negative impact already proven with Coffee Lake on randomly reading and writing 4K files with one thread: up to six percent in performance loss ,

With Specter-Fix the data throughput drops
On the other hand, the countermeasures for Specter prove to be much more serious: The SSD loses more than 40 percent throughput in the random reading and writing of small blocks via a thread - reproducible.

 

[juanrga]

The real impact on SSD is coming from the Spectre-fix, which is worth to mention affects virtually any modern CPU: AMD, Apple, ARM, Fujitsu, IBM, Intel, NVIDIA,...

 

[-Fran-]

The real impact on SSD is coming from the Spectre-fix, which is worth to mention affects virtually any modern CPU: AMD, Apple, ARM, Fujitsu, IBM, Intel, NVIDIA,...

And again you're mixing all of them in the same bag.

 

[juanrga]

The real impact on SSD is coming from the Spectre-fix, which is worth to mention affects virtually any modern CPU: AMD, Apple, ARM, Fujitsu, IBM, Intel, NVIDIA,...

And again you're mixing all of them in the same bag.

All them are affected by Spectre.

 

[-Fran-]

The real impact on SSD is coming from the Spectre-fix, which is worth to mention affects virtually any modern CPU: AMD, Apple, ARM, Fujitsu, IBM, Intel, NVIDIA,...

And again you're mixing all of them in the same bag.

All them are affected differently by Spectre.

FIFY.

 

[juanrga]

The real impact on SSD is coming from the Spectre-fix, which is worth to mention affects virtually any modern CPU: AMD, Apple, ARM, Fujitsu, IBM, Intel, NVIDIA,...

And again you're mixing all of them in the same bag.

All them are affected differently by Spectre.

FIFY.

No one claimed that all are affected exactly the same. In fact even different CPUs from the same vendor are affected differently. Piledriver is affected differently than Zen. Kabylake is affected differently than Sandy.

 

[YoAndy]

The real impact on SSD is coming from the Spectre-fix, which is worth to mention affects virtually any modern CPU: AMD, Apple, ARM, Fujitsu, IBM, Intel, NVIDIA,...

And again you're mixing all of them in the same bag.

All them are affected differently by Spectre.

FIFY.

No one claimed that all are affected exactly the same. In fact even different CPUs from the same vendor are affected differently. Piledriver is affected differently than Zen. Kabylake is affected differently than Sandy.

At least Intel didn't say we have "near zero risk" :lol:

 

[8350rocks]

The real impact on SSD is coming from the Spectre-fix, which is worth to mention affects virtually any modern CPU: AMD, Apple, ARM, Fujitsu, IBM, Intel, NVIDIA,...

And again you're mixing all of them in the same bag.

All them are affected differently by Spectre.

FIFY.

No one claimed that all are affected exactly the same. In fact even different CPUs from the same vendor are affected differently. Piledriver is affected differently than Zen. Kabylake is affected differently than Sandy.

At least Intel didn't say we have "near zero risk" :lol:

Then there is media like this: https://mybroadband.co.za/news/security/245183-amd-faces-lawsuit-over-spectre-vulnerability.html

Almost makes you wonder how much Intel paid for that advertising.

 

[juanrga]

The real impact on SSD is coming from the Spectre-fix, which is worth to mention affects virtually any modern CPU: AMD, Apple, ARM, Fujitsu, IBM, Intel, NVIDIA,...

And again you're mixing all of them in the same bag.

All them are affected differently by Spectre.

FIFY.

No one claimed that all are affected exactly the same. In fact even different CPUs from the same vendor are affected differently. Piledriver is affected differently than Zen. Kabylake is affected differently than Sandy.

At least Intel didn't say we have "near zero risk" :lol:

Then there is media like this: https://mybroadband.co.za/news/security/245183-amd-faces-lawsuit-over-spectre-vulnerability.html

Almost makes you wonder how much Intel paid for that advertising.

So when sites publish news about lawsuits filled against Intel, it is advertising paid by AMD? LOL

 

[-Fran-]

So when sites publish news about lawsuits filled against Intel, it is advertising paid by AMD? LOL

It's better to get paid than being a free shill pill.

EDIT: Typos.

 

[juanrga]

So when sites publish news about lawsuits filled against Intel, it is advertising paid by AMD? LOL

It's better to get paid than being a free shill pill.

I know some Intel haters would pay only to get something bad about Intel published.

 

[YoAndy]

So when sites publish news about lawsuits filled against Intel, it is advertising paid by AMD? LOL

It's better to get paid than being a free shill pill.

I know some Intel haters would pay only to get something bad about Intel published.

This always happens when people start taking sides

 

[goldstone77]

You two are ridiculous, Intel owns ~90% of the market, and you have conspiracy theories that others are plotting against Intel. Especially given Intel's rocky unethical past. It's comical how blind some people can be....