[jchw]

Hmm, I don't fully agree. There are a whole lot of embarassingly parallel processes that people interested in many core workstations are interested in; compiling large C++ codebases for example tends to scale very well since each translation unit is independent. This is still going to not quite give you linear scaling so it's definitely still valuable to know what that looks like.

[wtallis]

Geekbench is not intended for benchmarking large workstations. Look at how the web site actually describes the benchmark. It's for phones and laptops and similar devices. A test mode that uses a machine in a way that is only relevant to high-end workstation or server use would be actively harmful to the suitability of Geekbench for its intended audience of consumer hardware and consumer users.

[aurareturn]

No idea why you're downvoted. Geekbench's focus is consumer workloads. In consumer workloads, having 20 cores or more is nearly useless. Most normal people will not need more than 8 in 2026. You're better off with a few fast cores over many slow cores.

Geekbench isn't a server CPU benchmark that stresses 128 core CPUs.

[jchw]

I dunno why people are downvoting at all. I don't get what nerve this is striking so hard.

The real truth is that if consumers don't benefit from knowing how well multicore workloads scale, then they can just look only at the single-core score. Skewing it on purpose by including things that genuinely only use ~1 core doesn't seem to serve to add value but only obfuscate the truth about how well a CPU is able to scale on multicore workloads, which does matter sometimes (like with modern video games.)

Yes this means that 128 core Xeon servers will maybe look especially good, but idk, what consumer hardware has 128 cores? Consumers are not considering a Mac Mini versus a fucking NVIDIA Vera rack, you know?

I fully accept that you could view it either way, but if you're going to have a multicore score at all, in my opinion, it may as well actually show you what multicore workloads look like. It is OK that consumers can't necessarily understand how this translates. If all they ever do is single core workloads, they will never have any benefit to looking at the multicore workload score for any Geekbench score on any Geekbench version, because otherwise the multicore score overstates the performance, whereas if they were to look at a version that has multicore including ~single threaded workloads, it would understate the multicore scaling.

Benchmarks are necessarily imperfect no matter how you shake it. For example, it is impossible for a general compute benchmark to show how much better the UX of two cores is over having just one core that is a bit faster.

Though, now that I say all of this, I get the strange feeling the nerve it's striking is fanboyism. What else would make people care this much, but perhaps the hardware vendor they are fans of showing up higher in the numbers? Well it ain't me. I couldn't care less how Apple and AMD and Intel compare in the Geekbench scores. Could be wrong, but somehow this just feels like a good bet.

[aurareturn]

Given that Geekbench is a consumer workload benchmark, it makes sense to factor in Amdahl's Law. Period.

Now the question is whether having a 3rd CPU score for embarrassingly parallel work makes sense for Geekbench. It probably does since many professionals also use Geekbench nowadays.

[adrian_b]

Amdahl's law is one thing, and an inefficient implementation of a concurrent program is another thing.

We do not know how much of the bad scaling of Geekbench 6 was due to Amdahl's law and how much was caused by an inept implementation.

Moreover, Amdahl's law is really important only for very short computational tasks, i.e. which do not need more than a few seconds or minutes for completion.

The bigger is the job that must be accomplished, the more likely it is that it can be reorganized in a way that tends to be embarassingly parallel, so that Amdahl's law has little importance.

So for jobs as big that they need hours, days or weeks to be completed by a computer, if they are well planned it is frequent to reach scaling factors not much lower than the number of available cores, even if that may be much more difficult to achieve for short jobs.

[wmf]

If they had an embarrassingly parallel test, Intel would be exclusively promoting that misleading number just like they do with Cinebench. Let's not create even more totally unrepresentative benchmarks.

[aurareturn]

I don't think Intel and AMD promote Cinebench as they used to back in the 2017-2023. Cinebnech 2024 actually heavily favors Apple.

[jchw]

> Given that Geekbench is a consumer workload benchmark, it makes sense to factor in Amdahl's Law. Period.

To be honest, they are factoring in Amdahl's law, because they're actually not only including embarrassingly parallel workloads, they're just not including ones where the speedup factor is roughly 0. Frankly I should have acknowledged this in my initial response.

> Now the question is whether having a 3rd CPU score for embarrassingly parallel work makes sense for Geekbench. It probably does since many professionals also use Geekbench nowadays.

Including workloads that are almost entirely single-threaded does not tell you anything about the "multi-core" performance of the processor. It just biases the multi-core score to be lower, period.

It is true that even without that, the multi-core score will still be biased towards the rough average speedup factor of all of the workloads combined, but that's just the nature of an aggregate benchmark. If you wanted to know how it would perform on a specific task, you'd need a specific benchmark anyways. If they've done a good job, the multi-core scores should still be useful for comparison across processors for your average multi-core workload.

I think two things are true:

- If consumers almost only ever use single threaded workloads, then the multi-core score will always be misleading to them if it is anything above what the single core score is. They should be paying more attention to the single-core score.

- If consumers do have multi-threaded workloads, then a multi-core score that averages in a bunch of tasks with no multi-core speedup will also not be representative for them, as it will understate the performance benefits they can see.

If you wanted a more useful third number it would be a weighted overall score, but what is the objectively correct weight between single and multi-core? Even for consumers this is a challenging number to come up with.

But I know one thing: it is almost certainly not whatever weight you just happen to wind up with by just arbitrarily including whatever number of single-threaded tasks your benchmark happens to have in a multi-core benchmark score.

[jchw]

Well, apparently they must not agree.

[sroussey]

In that case, just assume linear scaling? You only need pay attention to a single core.

[osti]

You can use geekbench 5 in that case. But given that they deprecated that, it might be harder to compare to others.