Friday, January 12th 2018
Intel Releases CPU Benchmarks with Meltdown and Spectre Mitigations
It's safe to say that there's one thing that you don't mess around with, and that's performance. Enthusiasts don't spend hundreds of dollars on a processor to watch it underperform. Given the complicated nature of the Meltdown and Spectre vulnerabilities, Microsoft's so-called mitigations were bound to have an impact on processor performance. The million dollar question was: Just how much? The initial estimate was somewhere around 30%, but Intel, being optimistic as usual, expected the performance impact to be insignificant for the average user. They recently provided some preliminary benchmark results that looked quite convincing too. Well, let's take a look at their findings, shall we?
Intel measured the mitgations' impact on CPU performance using their 6th, 7th, and 8th Generation Intel Core processors but, more specifically, the i7-6700K, i7-7920HQ, i7-8650U, and i7-8700K. The preferred operating system used in the majority of the benchmarks was Windows 10, however, Windows 7 also made a brief appearance. Intel chose four key benchmarks for their testing. SYSmark 2014 SE evaluated CPU performance on an enterprise level simulating office productivity, data and financial analysis, and media creation. PC Mark 10, on the other hand, tested performance in real-world usage employing different workloads like web browsing, video conferencing, application start-up time, spreadsheets, writing, and digital content creation. 3DMark Sky Diver assessed CPU performance in a DirectX 11 gaming scenario. Lastly, WebXPRT 2015 measured system performance using six HTML5- and JavaScript-based workloads which include photo enhancement, organize album, stock option pricing, local notes, sales graphs, and explore DNA sequencing.The SYSmark 2014 SE overall results showed a moderate decrease in CPU performance between 6% to 8% with the i7-6700K the being the most affected. System responsiveness took the biggest hit with performance dropping up to 21% on the i7-6700K. The Responsiveness scenario tested activities like application launches, application installation, web browsing with many tabs open, file copies, photo manipulation, and multi-tasking - all of which are heavily influenced by the type of storage. So, don't let that i7-6700K with the hard drive result fool you. PCMark 10 registered penalties in the range of 3% to 4% with the i7-7920HQ being least affected. We weren't surprised to see that the mitigations didn't affect gaming performance in 3DMark Sky Diver, since we had already done our own tests in 21 different games. Results from WebXPRT 2015 reveal performance drops between 5% to 10%.
Intel measured the mitgations' impact on CPU performance using their 6th, 7th, and 8th Generation Intel Core processors but, more specifically, the i7-6700K, i7-7920HQ, i7-8650U, and i7-8700K. The preferred operating system used in the majority of the benchmarks was Windows 10, however, Windows 7 also made a brief appearance. Intel chose four key benchmarks for their testing. SYSmark 2014 SE evaluated CPU performance on an enterprise level simulating office productivity, data and financial analysis, and media creation. PC Mark 10, on the other hand, tested performance in real-world usage employing different workloads like web browsing, video conferencing, application start-up time, spreadsheets, writing, and digital content creation. 3DMark Sky Diver assessed CPU performance in a DirectX 11 gaming scenario. Lastly, WebXPRT 2015 measured system performance using six HTML5- and JavaScript-based workloads which include photo enhancement, organize album, stock option pricing, local notes, sales graphs, and explore DNA sequencing.The SYSmark 2014 SE overall results showed a moderate decrease in CPU performance between 6% to 8% with the i7-6700K the being the most affected. System responsiveness took the biggest hit with performance dropping up to 21% on the i7-6700K. The Responsiveness scenario tested activities like application launches, application installation, web browsing with many tabs open, file copies, photo manipulation, and multi-tasking - all of which are heavily influenced by the type of storage. So, don't let that i7-6700K with the hard drive result fool you. PCMark 10 registered penalties in the range of 3% to 4% with the i7-7920HQ being least affected. We weren't surprised to see that the mitigations didn't affect gaming performance in 3DMark Sky Diver, since we had already done our own tests in 21 different games. Results from WebXPRT 2015 reveal performance drops between 5% to 10%.
56 Comments on Intel Releases CPU Benchmarks with Meltdown and Spectre Mitigations
They kept quiet about it because that is exactly what you are supposed to do in this situation. Why do you think Google didn't alert the world when they discovered it? Because when you know there is a security flaw that affects almost every computer in the world, you don't alert the world about it, you secretly work to fix it. If you alert the world about it, you let the malicious people know the flaw exists and those people instantly start looking for a way to exploit it.
This is definitely not a case of Intel doing nothing about the security flaw for the 6 months since they found out about it, and then just quickly whipping up a fix in the two weeks since the news about it broke. You don't figure out fixes like this to major hardware flaws in two weeks. They did not choose to ignore it, they were working on fixing it in secret, because that is exactly what you are supposed to do in this situation.
And at the same time, you don't put a major product release on hold just because it has a security flaw in it that is extremely complex to exploit, is basically unknown to anyone other than Google and other processor manufacturers, and has existed for decades.
(a) This was intentionally (designed) that way
(b) Getting one up on your competitor was more important than securing your chips, talking about meltdown here
So beyond what we know, Intel is at least responsible for grossly neglecting the impact meltdown could've had on current & past gen processors. I can speculate as to whether they should be punished for keeping us all in dark, especially those who bought Intel chips in the last year, but there's ongoing lawsuits & they may set a precedent as to where the future course of action would be in such matters. This is a first for most of us, so let's see what happens from here.
www.techspot.com/news/72729-amd-confirms-chips-vulnerable-spectre-rolling-out-fixes.html
oh and AMD knew about these as well before launching Threadripper and EPYC heck even Ryzen mobile.... stop looking at this thing as a "Intel only" problem it spans through the whole damn industry.
Yes, releasing Coffee Lake with a known vulnerability was a rotten thing to do. Unless they knew at the time it's fixable by the time the vulnerability is publicly disclosed. (But again is something we have no evidence of.)
Curious to see the results on a i5 or HT disabled i3 and i7
IMHO, HT is their trick, look at this, only Hyperthreaded CPUs, and only highly optimized multithreaded Benchmarks ..
Instead for whatever reason they decided to pull it in to 2017 knowing full well thay would have to issue microcode updates later. It was likey to respond to Ryzen and up the core count. My guess is that if they would have launched now like originally planned they would have sold even more and being able to advertise as faster and more secure.
Tech people may be understanding about what Intel has done but look at the average jury. Do you think they will buy Intel's defense that they had no choice but to release Coffee Lake anyway?
Just because Intel shouldn't delay a product launch and just because Intel couldn't have predicted the flaw beforehand, it doesn't explain away their scummy/scammy actions since they found out.
Plus, I don't even think people understand what this exploit does. I think people think that it allows any program to just read any memory space it wants and will allow hackers to access all of your data. That isn't the case. From what I've read, the exploit isn't really targetable. Mean, that someone using the exploit can't decide what data to access, it is very random what data the exploit will spit out. It is also extremely slow to access data using the exploit. I believe in the best case, the people working on the exploit got about 2KB/s or reading random data from RAM.
So the jury isn't going to even hear that Intel had no choice but to release Coffee Lake, they are going to hear that when Coffee Lake was released the vulnerability was considered a low risk. So Intel, and AMD, and nVidia, all didn't consider the threat a high enough risk to delay the release of products. I don't believe Intel knew at all until near the end of the patch process what, if any, performance impact fixing this flaw would have. Especially on the consumer side, which don't run a lot of programs the heavily rely on SE.
Heck, when the news first broke, we had people guessing 30%+. Now we are seeing actual numbers largely in the single digit %s. And if they continue to refine the fix, those performance hits might even get lower as time goes on.
Damn son, I've gotta get me one of those monitors too! I was always gimped on low space on my desk. This candle like monitor it would be perfect ;)
All their actions over the course of last year, once attributed to supposed competition from AMD, make much more sense in the context of an industry-wide scandal hitting them when they'd be normally content to launch a new mainstream i7 line. Intel was scummy. Just say it. Acknowledge it. You can even say that no one should expect anything different from a company than to do a new product launch in the midst of an upcoming scandal if you like, but it's scummy no matter how you slice it.
"In general, our experience is that Variant 1 and Variant 3 mitigations have minimal performance impact, while Variant 2 remediation, including OS and microcode, has a performance impact.
Here is the summary of what we have found so far:
With Windows 10 on newer silicon (2016-era PCs with Skylake, Kabylake or newer CPU), benchmarks show single-digit slowdowns, but we don’t expect most users to notice a change because these percentages are reflected in milliseconds.
With Windows 10 on older silicon (2015-era PCs with Haswell or older CPU), some benchmarks show more significant slowdowns, and we expect that some users will notice a decrease in system performance.
With Windows 8 and Windows 7 on older silicon (2015-era PCs with Haswell or older CPU), we expect most users to notice a decrease in system performance.
For context, on newer CPUs such as on Skylake and beyond, Intel has refined the instructions used to disable branch speculation to be more specific to indirect branches, reducing the overall performance penalty of the Spectre mitigation. Older versions of Windows have a larger performance impact because Windows 7 and Windows 8 have more user-kernel transitions because of legacy design decisions, such as all font rendering taking place in the kernel."
Source: cloudblogs.microsoft.com/microsoftsecure/2018/01/09/understanding-the-performance-impact-of-spectre-and-meltdown-mitigations-on-windows-systems/