Intel 11th Generation Core Tiger Lake-H Performance Review: Fast and Power Hungry
by Brett Howse & Andrei Frumusanu on May 17, 2021 9:00 AM EST- Posted in
- CPUs
- Intel
- 10nm
- Willow Cove
- SuperFin
- 11th Gen
- Tiger Lake-H
CPU Tests: Synthetic
Most of the people in our industry have a love/hate relationship when it comes to synthetic tests. On the one hand, they’re often good for quick summaries of performance and are easy to use, but most of the time the tests aren’t related to any real software. Synthetic tests are often very good at burrowing down to a specific set of instructions and maximizing the performance out of those. Due to requests from a number of our readers, we have the following synthetic tests.
Linux OpenSSL Speed: SHA256
One of our readers reached out in early 2020 and stated that he was interested in looking at OpenSSL hashing rates in Linux. Luckily OpenSSL in Linux has a function called ‘speed’ that allows the user to determine how fast the system is for any given hashing algorithm, as well as signing and verifying messages.
OpenSSL offers a lot of algorithms to choose from, and based on a quick Twitter poll, we narrowed it down to the following:
- rsa2048 sign and rsa2048 verify
- sha256 at 8K block size
- md5 at 8K block size
For each of these tests, we run them in single thread and multithreaded mode. All the graphs are in our benchmark database, Bench, and we use the sha256 results in published reviews.
GeekBench 5: Link
As a common tool for cross-platform testing between mobile, PC, and Mac, GeekBench is an ultimate exercise in synthetic testing across a range of algorithms looking for peak throughput. Tests include encryption, compression, fast Fourier transform, memory operations, n-body physics, matrix operations, histogram manipulation, and HTML parsing.
Unfortunately we are not going to include the Intel GB5 results in this review, although you can find them inside our benchmark database. The reason behind this is down to AVX512 acceleration of GB5's AES test - this causes a substantial performance difference in single threaded workloads that thus sub-test completely skews any of Intel's results to the point of literal absurdity. AES is not that important of a real-world workload, so the fact that it obscures the rest of GB5's subtests makes overall score comparisons to Intel CPUs with AVX512 installed irrelevant to draw any conclusions. This is also important for future comparisons of Intel CPUs, such as Rocket Lake, which will have AVX512 installed. Users should ask to see the sub-test scores, or a version of GB5 where the AES test is removed.
To clarify the point on AES. The Core i9-10900K scores 1878 in the AES test, while 1185G7 scores 4149. While we're not necessarily against the use of accelerators especially given that the future is going to be based on how many and how efficient these accelerators work (we can argue whether AVX-512 is efficient compared to dedicated silicon), the issue stems from a combi-test like GeekBench in which it condenses several different (around 20) tests into a single number from which conclusions are meant to be drawn. If one test gets accelerated enough to skew the end result, then rather than being a representation of a set of tests, that one single test becomes the conclusion at the behest of the others, and it's at that point the test should be removed and put on its own. GeekBench 4 had memory tests that were removed for Geekbench 5 for similar reasons, and should there be a sixth GeekBench iteraction, our recommendation is that the cryptography is removed for similar reasons. There are 100s of cryptography algorithms to optimize for, but in the event where a popular tests focuses on a single algorithm, that then becomes an optimization target and becomes meaningless when the broader ecosystem overwhelmingly uses other cryptography algorithms.
229 Comments
View All Comments
Spunjji - Thursday, May 20, 2021 - link
He measured the power consumption, you pillock. It's right there in the review. Nice work getting your FUD on the front page though, round of applause for gondaft.If Tiger Lake H will be better in "the right chassis", Intel really should have thought of that when they supplied this one. As things stand, it's clear that this chassis wasn't causing the CPU to throttle at 45W, so the only way it would perform better is in a chassis that allows for 65W - at which point you'd find AMD's CPUs performing better, too...
5j3rul3 - Monday, May 17, 2021 - link
It's a big step to intelM1 and Ryzen 5000 are powerful, Intel need more pros to getting the leading performance
mode_13h - Monday, May 17, 2021 - link
This is definitely what Rocket Lake should've been. If they just put this chip in a desktop package, so it could be run with a desktop power budget and cooling, it'd sure be a lot more interesting than it is inside a laptop.Exotica - Monday, May 17, 2021 - link
Yields may have been the primary concern.mode_13h - Monday, May 17, 2021 - link
I get why they didn't do it, but it's clear to me this chip really wants to be a desktop CPU.whatthe123 - Monday, May 17, 2021 - link
it's probably more that they've tweaked their 10nm to hit high boost at the cost of efficiency. I think they increased their gate pitch with "superfin" so you end up with more performance scaling but also more power use. considering how far behind their desktop chips are compared to 7nm chips from AMD they may just be crippling efficiency across the board to get performance parity while their fabs lag behind. they don't seem to have high hopes for 10nm considering their target for market leadership is 2024 with 7nm.laptop users generally stick with bursty operations or video games and in both cases raw throughput isn't as much of a concern. average user would probably not notice or even benefit from the high ST burst performance, but anyone planning on using it professionally would probably be better off with cezanne.
Spunjji - Tuesday, May 18, 2021 - link
It would certainly be able to stretch its legs better there. It would be interesting to see whether it could handle running those higher boost clocks across more cores with a higher TDP. Guess we'll find out with Alder Lake.Lucky Stripes 99 - Monday, May 17, 2021 - link
I thought the same. This chip in a mini-STX case with a desktop cooler would make a great portable system. However, if it is having thermal issues with a full-size workstation laptop, it'll likely struggle in the smallest of SFF cases like the NUC.Azix - Monday, May 17, 2021 - link
the laptop doesn't look that that big. A nuc would have more vertical space for the cooling for example. It would also be easier to throw that heat out.mode_13h - Monday, May 17, 2021 - link
Uh, the mini-STX NUCs don't really have much space. Everything is packed in pretty tightly. Furthermore, they usually top out at 28 W.For Coffee Lake, Intel made a larger system they called a "NUC", but I think they had actual Nvidia graphics cards in them and were bigger than a lot of mini-PCs.