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
Section by Andrei Frumusanu
SPEC2017 and SPEC2006 Results (15W)
SPEC2017 and SPEC2006 is a series of standardized tests used to probe the overall performance between different systems, different architectures, different microarchitectures, and setups. The code has to be compiled, and then the results can be submitted to an online database for comparsion. It covers a range of integer and floating point workloads, and can be very optimized for each CPU, so it is important to check how the benchmarks are being compiled and run.
We run the tests in a harness built through Windows Subsystem for Linux, developed by our own Andrei Frumusanu. WSL has some odd quirks, with one test not running due to a WSL fixed stack size, but for like-for-like testing is good enough. SPEC2006 is deprecated in favor of 2017, but remains an interesting comparison point in our data. Because our scores aren’t official submissions, as per SPEC guidelines we have to declare them as internal estimates from our part.
For compilers, we use LLVM both for C/C++ and Fortan tests, and for Fortran we’re using the Flang compiler. The rationale of using LLVM over GCC is better cross-platform comparisons to platforms that have only have LLVM support and future articles where we’ll investigate this aspect more. We’re not considering closed-sourced compilers such as MSVC or ICC.
clang version 8.0.0-svn350067-1~exp1+0~20181226174230.701~1.gbp6019f2 (trunk)
clang version 7.0.1 (ssh://git@github.com/flang-compiler/flang-driver.git
24bd54da5c41af04838bbe7b68f830840d47fc03)-Ofast -fomit-frame-pointer
-march=x86-64
-mtune=core-avx2
-mfma -mavx -mavx2
Our compiler flags are straightforward, with basic –Ofast and relevant ISA switches to allow for AVX2 instructions. Despite ICL supporting AVX-512, we have not currently implemented it, as it requires a much greater level of finesse with instruction packing. The best AVX-512 software uses hand-crafted intrinsics to provide the instructions, as per our 3PDM AVX-512 test later in the review.
For these comparisons, we will be picking out CPUs from across our dataset to provide context. Some of these might be higher power processors, it should be noted.
SPECint2006
Amongst SPECint2006, the one benchmark that really stands out beyond all the rest is the 473.astar. Here the new Sunny Cove core is showcasing some exceptional IPC gains, nearly doubling the performance over the 8550U even though it’s clocked 100MHz lower. The benchmark is extremely branch misprediction sensitive, and the only conclusion we can get to rationalise this increase is that the new branch predictors on Sunny Cove are doing an outstanding job and represent a massive improvement over Skylake.
456.hmmer and 464.h264ref are very execution bound and have the highest actual instructions per clock metrics in this suite. Here it’s very possible that Sunny Cove’s vastly increased out-of-order window is able to extract a lot more ILP out of the program and thus gain significant increases in IPC. It’s impressive that the 3.9GHz core here manages to match and outpace the 9900K’s 5GHz Skylake core.
Other benchmarks here which are limited by other µarch characteristics have various increases depending on the workload. Sunny Cove doubled L2 cache should certainly help with workloads like 403.gcc and others. However because we’re also memory latency limited on this platform the increases aren’t quite as large as we’d expect from a desktop variant of ICL.
In SPECfp2006, Sunny Cove’s wider out-of-order window can again be seen in tests such as 453.povray as the core is posting some impressive gains over the 8550U at similar clocks. 470.lbm is also instruction window as well as data store heavy – the core’s doubled store bandwidth here certainly helps it.
Overall in SPEC2006, the new i7-1065G7 beats a similarly clocked i7-8550U by a hefty 29% in the int suite and 34% in the fp suite. Of course this performance gap will be a lot smaller against 9th gen mobile H-parts at higher clocks, but these are also higher TDP products.
The 1065G7 comes quite close to the fastest desktop parts, however it’s likely it’ll need a desktop memory subsystem in order to catch up in total peak absolute performance.
Performance per clock increases on the new Sunny Cove architecture are outstandingly good. IPC increases against the mobile Skylake are 33 and 38% in the integer and fp suites, though we also have to keep in d mind these figures go beyond just the Sunny Cove architecture and also include improvements through the new LPDDR4X memory controllers.
Against a 9900K, although apples and oranges, we’re seeing 13% and 14% IPC increases. These figures likely would be higher on an eventual desktop Sunny Cove part.
SPEC2017
The SPEC2017 results look similar to the 2006 ones. Against the 8550U, we’re seeing grand performance uplifts, just shy of the best desktop processors.
Here the IPC increase also look extremely solid. In the SPECin2017 suite the Ice Lake part achieves a 14% increase over the 9900K, however we also see a very impressive 21% increase in the fp suite.
Overall in the 2017 suite, we’re seeing a 19% increase in IPC over the 9900K, which roughly matches Intel’s advertised metric of 18% IPC increase.
Facebook
Twitter
RSS
261 Comments
View All Comments
Phynaz - Saturday, August 3, 2019 - link
And it’s “than” not “then”. Perhaps your lack of grammar is part of your problem.Korguz - Saturday, August 3, 2019 - link
um ya ok sure.. anything you say...HStewart - Thursday, August 1, 2019 - link
Is useless to argue with AMD fans - they first state that 10nm is old fashion and that claims of 30% is based on 2015 Sky Lake cpus and when they find out it based on 8th generation they don't believe and then state G{U is not good enough. And that AVX 512 does not matter, bug Siggraph 2019 is going to change that.But people forget about the past, yes AMD did it 64 bit back in the older days when nobody care much about greater than 4G memory. They build memory management and we had the frequency wars with Pentium 4 days - but Intel came back with I Series and change ever. Past is be repeated again. But this time is the core wars but Ice Lake is beginning of iSeries like in those days.
Please keep in mind this is only the low power cpus that Intel has release - it only the top of iceburg.
HStewart - Thursday, August 1, 2019 - link
"G{U is not good enough. And that AVX 512 does not matter, bug Siggraph 2019"I wish we could edit, I am older so my eyes are not as good
"GPU is not good enough. And that AVX 512 does not matter, but SigGraph 2019"
Korguz - Thursday, August 1, 2019 - link
and its just a useless to argue with intel fans, right HStewart ?? you know 1st hand about that, as you are well known now to praise intel any chance you get, and seemingly forget the negative things intel has one over the years, especially the ones that cost intel a few billion dollars...HStewart - Friday, August 2, 2019 - link
Lets just keep Intel articles to Intel only and AMD articles to AMD only - not of this fan boy BS, I support Intel primary because the AMD fans are so rude to Intel supports and I will never support them because of that. I do change, I use to support only Apple and hated Android - but I change on that one primary because I saw that Apple was not changing it UI and that they require developer tools on Mac's. I not actually Intel fan, Intel user and Intel developer - that is different. I have 30 years development experience.jospoortvliet - Friday, August 2, 2019 - link
You know, nobody cares about your ‘support’. If you mean your support to help intel - it merely serves to make it look pathetic. If you have nothing intelligent to offer besides your ‘support’, whichever brand or product it is to benefit, you better just stay out of the conversation as that would improve its average quality substantially.I’m sure there are sites where comments from brand- supporting fans are appreciated. I sure as hell don’t read the comments here for that reason but to get insights and your comments just serve to make that harder as i need to weed through countless pointless conversations which involve you ‘supporting’ intel by lowering the collective intelligence of all readers here. Do everyone a favor and leave.
Korguz - Friday, August 2, 2019 - link
your are hilarious HStewart, maybe you should take your OWN advice for once.. oh wait.. you CAN'T cause you cant deal with the fact that intel isnt doing as good as it was before zen came out. when you stop with the intel fanboy BS, then maybe the rest of us will as well. no, you support intel cause you are a fanatic when it comes to them. " I not actually Intel fan " BS complete BS, and you have proved over AND over again, you are an intel fan.30 years of experience ?? BS, you dont know the DIFFERENCE between WATTS and VOLTS, and you KEEP spelling architeCture WRONG
Qasar - Friday, August 2, 2019 - link
" they first state that 10nm is old fashion and that claims of 30% is based on 2015 Sky Lake cpus and when they find out it based on 8th generation they don't believe " who is they ?? to be fair HStewart, most of intels iGP, were best suited for any thing that isnt games that arent played on facebook, or games that are a few years old, and office work. but looks like intel is trying to improve that :-)" yes AMD did it 64 bit back in the older days when nobody care much about greater than 4G memory " i can remember a few people wanting to be able to use more then 4 gigs of ram in their comps, with out having to go to server platforms, i was one of them, and a few of my friends did too.
" Please keep in mind this is only the low power cpus that Intel has release " from what i have read, seems like this is all intel can do with their current 10nm process right now, looks like intel, like with the desktop, thinks quad cores are " good enough ", cause if it isnt, why are these only quad core ? why not up the ante to 6 cores ? i guess, like the desk top, we have to wait to see if amd will do this...
RSAUser - Friday, August 2, 2019 - link
AVX512 really doesn't matter as I would find it strange for people to run such workloads on their laptops rather than on dedicated machines with way more processing power.For the common man, AVX512 does nothing though, but we can argue that most of the performance improvements don't really matter, I'm still using a device 5 years old with an i7 4720HQ and I feel no need to upgrade, only thing I am let down by is the graphics card (960M).
Intel will have a hard time convincing people to upgrade for this stuff before their machines basically keel over.