SPEC CPU - Single-Threaded Performance

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 comparison. 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 10.0.0
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. We decided to build our SPEC binaries on AVX2, which puts a limit on Haswell as how old we can go before the testing will fall over. This also means we don’t have AVX512 binaries, primarily because in order to get the best performance, the AVX-512 intrinsic should be packed by a proper expert, as with our AVX-512 benchmark.

To note, the requirements for the SPEC licence state that any benchmark results from SPEC have to be labelled ‘estimated’ until they are verified on the SPEC website as a meaningful representation of the expected performance. This is most often done by the big companies and OEMs to showcase performance to customers, however is quite over the top for what we do as reviewers.

Single-threaded performance of TGL-H shouldn’t be drastically different from that of TGL-U, however there’s a few factors which can come into play and affect the results: The i9-11980HK TGL-H system has a 200MHz higher boost frequency compared to the i7-1185G7, and a single core now has access to up to 24MB of L3 instead of just 12MB.

SPECint2017 Rate-1 Estimated Scores

In SPECint2017, the one results which stands out the most if 502.gcc_r where the TGL-H processor lands in at +16% ahead of TGL-U, undoubtedly due to the increased L3 size of the new chip.

Generally speaking, the new TGL-H chip outperforms its brethren and AMD competitors in almost all tests.

SPECfp2017 Rate-1 Estimated Scores

In the SPECfp2017 suite, we also see general small improvements across the board. The 549.fotonik3d_r test sees a regression which is a bit odd, but I think is related to the LPDDR4 vs DDR4 discrepancy in the systems which I’ll get back to in the next page where we’ll see more multi-threaded results related to this.

SPEC2017 Rate-1 Estimated Total

From an overall single-threaded performance standpoint, the TGL-H i9-11980HK adds in around +3.5-7% on top of what we saw on the i7-1185G7, which lands it amongst the best performing systems – not only amongst laptop CPUs, but all CPUs. The performance lead against AMD’s strongest mobile CPU, the 5980HS is even a little higher than against the i7-1185G7, but loses out against AMD’s best desktop CPU, and of course Apple M1 CPU and SoC used in the latest Macbooks. This latter comparison is apples-to-apples in terms of compiler settings, and is impressive given it does it at around 1/3rd of the package power under single-threaded scenarios.

CPU Tests: Core-to-Core and Cache Latency SPEC CPU - Multi-Threaded Performance
POST A COMMENT

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...
    Reply
  • 5j3rul3 - Monday, May 17, 2021 - link

    It's a big step to intel
    M1 and Ryzen 5000 are powerful, Intel need more pros to getting the leading performance
    Reply
  • 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. Reply
  • Exotica - Monday, May 17, 2021 - link

    Yields may have been the primary concern. Reply
  • 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. Reply
  • 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.
    Reply
  • 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. Reply
  • 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. Reply
  • 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. Reply
  • 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.
    Reply

Log in

Don't have an account? Sign up now