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
Gaming Results (15W and 25W)
One of the biggest changes to the Ice Lake design is in the integrated graphics – Intel is now giving more focus and more die area to graphics, something it has arguably been neglecting for several years now. With Ice Lake, we move to a Gen11 graphics architecture, which is almost like the previous Gen9.5 but now with added support for variable rate shading (VRS), moving from 24 EUs to 64 EUs, and memory support up from LPDDR3-2133 to LPDDR4X-3733.
World of Tanks is a very CPU driven benchmark, and having the extra frequency of the 25W processor does help here. We're getting a sizeable uplift from Whiskey Lake, due to the extra EUs and memory frequency.
Our Final Fantasy test seemed to regress in 25W mode, although still within the noise. This test is still GPU bound, so adding the extra TDP to the CPU didn't actually help much. However, comparing to the Whiskey Lake integrated graphics, we've got over a 2x speedup.
Similarly with Civilization, with what is normally our 'IGP' settings, we are still GPU limited here.
One of Intel's newest features is Variable Rate Shading.
If developers add the option, soon to be an easy checkbox in Unity and Unreal, the game can decide to control the rate at which it shades pixels, from calculating every pixel down using one result across a 4x4 grid, to save compute power. Currently the only way to test this is with the 3DMark functional demo.
The new VRS test in 3DMark is designed as a feature test to show the potential uplift effect from enabling variable rate shading within a game. In both 15W and 25W modes, the data saw a good uplift, and we seemed to get more out of the 25W mode than the 15W mode.
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