The Ice Lake Benchmark Preview: Inside Intel's 10nm
by Dr. Ian Cutress on August 1, 2019 9:00 AM EST- Posted in
- CPUs
- Intel
- GPUs
- 10nm
- Core
- Ice Lake
- Cannon Lake
- Sunny Cove
- 10th Gen Core
System Results (15W)
When testing a laptop system, there are various angles to consider on how to test: either user experience benchmarks, that are mostly single threaded and give a good boost to how systems implement a deal of turbo, or sustained benchmarks that test how the system performs when you push it. Intel has gone out of its way to emphasise the former for the next generation of mobile CPUs: they would prefer that reviewers stick to very user experience-like tests, rather than say, rendering programs. The problem there is that outside a number of canned benchmarks, it can be difficult. Users, and especially creators, that typically spend a lot on a premium device, might actually be doing sustained benchmarks.
Given the time that we had to test, we were actually limited in what we could arrange.
On AVX-512, the Ice Lake part destroys the competition.
These last two tests are typically our more memory sensitive tests, and the LPDDR4X-3733 really does win out over the LPDDR3-2133 in the other systems.
Facebook
Twitter
RSS
261 Comments
View All Comments
Ian Cutress - Thursday, August 1, 2019 - link
I'm encouraging the behaviour. I've been on at Intel to do something like this for a while. I'm giving credit where credit is due. As always with events like this companies like Intel have PR saying they want to do something, and the legal side of the equation resisting. If we get more opportunities like this in the future, it helps us provide a richer content base in advance of a product launch - people get to prepare in case they're in the mood for a purchase.Also, tell me if you say the same things on our Qualcomm QRD testing. Please.
brakdoo - Thursday, August 1, 2019 - link
You are just trying to get an edge over other sites but you are just being played.It's the same BS with Qualcomm and their mmWave BS that has been spread by sites like this. Now 5G is just sub-6 and the only important part is massive MIMO
brakdoo - Thursday, August 1, 2019 - link
"and are for the best part thermally unconstrained"Just wait for the real release and do real testing. Don't you think Intel can release SPEC and Cinebench benchmarks themselves?
They just want you to do cheap advertisement months in advance.
Ian Cutress - Thursday, August 1, 2019 - link
We do our own validation of the platform to remove as much Intel involvement as possible. Also, if Intel went ahead and provided a system that performed vastly different, when it comes time to testing the actual systems, we'll be beating them over the head with the data and making a big stink. Everyone would.The question is, do you trust AnandTech to accurately and fairly test a reference system as if it were an OEM sample? So far your answers would seem to suggest no.
brakdoo - Thursday, August 1, 2019 - link
What I'm asking myself: Did we really learn something new from this piece? Not really would be my answer.Intel explained most of it before and we have seen enough leaks of the XPS 13 2-in-1 and the HP Spectre. Even Geekbench showed us that these CPUs have roughly the speed of 8565u on average (higher IPC, lower freq).
A journalist should always have a professional distance to these companies. This type of conflict of interest used to be most prominent in automobile magazines but the tech/PC companies are stepping up their marketing game.
Moizy - Thursday, August 1, 2019 - link
Dude. Before release, before we would have to wait for products on shelves, Ian got a chance to go inside Intel and test and upcoming product. And he wasn't handed benchmark results, he wasn't told what to report, he was allowed to run largely independently his own standardized benchmark suite. So now, 3-6 months before laptops will be available, we have a preview of what performance will look like. I learned a ton from Ian's preview article, and from this benchmarking piece. I'm not an Intel fan, I'm an industry fan, and this was awesome. Please take your toxicity elsewhere, or better yet, cure yourself of it.Ian, you're a good sport to participate in the comments section, but please don't let "brakdoo" or others pull you down. This was stellar work that I truly appreciate, as I'm sure most readers here do. I come to Anandtech specifically because of the high capabilities, understanding, and integrity of its writers and editors. Have been doing so for over 10 years. Please keep it up.
Dennis Travis - Thursday, August 1, 2019 - link
Well said Moizy. I was about the post the same basic thing. Good job Ian.eastcoast_pete - Thursday, August 1, 2019 - link
+1 on that comment. If company X let's you take a close first look AND bring your own tools I.e. test suite, Ian (and Andrei) would be fools not to take company X up on that offer. Yes, of course Intel has an agenda here, as does any other business, but we know that. In this case, I suspect that Intel wanted to show that Ice Lake actually exists and all parts are working, including the iGPU, unlike Whiskey Lake.MrSpadge - Thursday, August 1, 2019 - link
Well said Moizy, I totally agree! And would like to add: "haters gonna hate!"PreacherEddie - Thursday, August 1, 2019 - link
+1