WAwalterbell·Sep 12, 2026Submission
Apple GPU Microarchitecture (2022)
2 points · Open discussionphilipturner
metal-benchmarks
Metal2023–2026
philipturner / metal-benchmarks
metal-benchmarks
Apple GPU microarchitecture
4Distinct people
5Mentions
0Explicit recommenders
636GitHub stars
What to know before exploring
What it is
Apple GPU microarchitecture
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by year5 dated mentions
Observed mentions: 2023-02-20 15:27:17 UTC to 2026-09-12 15:10:51 UTC.
* An incomplete calendar period is marked with an outlined bar. Its count is not directly comparable with a full period.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| 2023 | 2023-01-01 00:00:00 UTC | 2024-01-01 00:00:00 UTC | 1 | 0 | 1 |
| 2024 | 2024-01-01 00:00:00 UTC | 2025-01-01 00:00:00 UTC | 3 | 2 | 1 |
| 2025 | 2025-01-01 00:00:00 UTC | 2026-01-01 00:00:00 UTC | 0 | 0 | 0 |
| 2026 (partial) | 2026-01-01 00:00:00 UTC | 2027-01-01 00:00:00 UTC | 1 | 1 | 0 |
What Hacker News says
5 sourcesMetal-benchmarks: Apple GPU microarchitecture
50 points · Open discussionHere's my quick take.
A top of the line Zen core is a powerful CPU with wide SIMD (AVX-512 is 16 lanes of 32 bit quantities), significant superscalar parallelism (capable of issuing approximately 4 SIMD operations per clock), and a high clock rate (over 5GHz). There isn't a lot of confusion about what constitutes a "core," though multithreading can inflate the "thread" count. See [1] for a detailed analysis of the Zen 5 line.
A single Granite Ridge core has peak 32 bit multiply-add performance of about 730 GFLOPS.
Nvidia, by contrast, uses the marketing term "core" to refer to a single SIMD lane. Their GPUs are organized as 32 SIMD lanes grouped into each "warp," and 4 warps grouped into a Streaming Multiprocessor (SM). CPU and GPU architectures can't be directly compared, but just going by peak floating point performance, the most compar
Read the rest
able granularity to a CPU core is the SM. A warp is in some ways more powerful than a CPU core (generally wider SIMD, larger register file, more local SRAM, better latency hiding) but in other ways less (much less superscalar parallelism, lower clock, around 2.5GHz). A 4090 has 128 SMs, which is a lot and goes a long way to explaining why a GPU has so much throughput. A 1080, by contrast, has 20 SMs - still a goodly number but not mind-meltingly bigger than a high end CPU. See the Nvidia Ada whitepaper [2] for an extremely detailed breakdown of 4090 specs (among other things).
A single Nvidia 4090 "core" has peak 32 bit multiply-add performance of about 5 GFLOPS, while an SM has 640 GFLOPS.
I don't know anybody who counts tensor cores by core count, as the capacity of a "core" varies pretty widely by generation. It's almost certainly best just to compare TFLOPS - also a bit of a slippery concept, as that depends on the precision and also whether the application can make use of the sparsity feature.
I'll also note that not all GPU vendors follow Nvidia's lead in counting individual SIMD lanes as "cores." Apple Silicon, by contrast, uses "core" to refer to a grouping of 128 SIMD lanes, similar to an Nvidia SM. A top of the line M2 Ultra contains 76 such cores, for 9728 SIMD lanes. I found Philip Turner's Metal benchmarks [3] useful for understanding the quantitative similarities and differences between Apple, AMD, and Nvidia GPUs.
[1]: http://www.numberworld.org/blogs/2024_8_7_zen5_avx512_teardo...
[2]: https://images.nvidia.com/aem-dam/Solutions/Data-Center/l4/n...
[3]: https://github.com/philipturner/metal-benchmarks
These chipsandcheese articles are fantastic, they really go into depth.
Last week I had occasion to dig deeply into the microarchitecture of the Apple M1 and M2 GPUs (which are very similar to the A series on mobile). I found the metal-benchmarks[1] repo to be very useful, and, relevant to this article, it contains a comparison to the RDNA generations. From that it appears that GPU microarchitectures are starting to converge, even if terminology is not. The standard configuration these days seems to be blocks of 128 threads (WGP's in AMD terminology, "cores" in Apple), organized into 4 SIMDs. Resources like workgroup memory (LDS in AMD lingo) are shared among each of these 128-blocks.
The linked repo also has links to other resources, including the incredible work being done by the Asahi Linux people to reverse engineer M1 and deliver wor
Read the rest
king open source GPU drivers.
[1]: https://github.com/philipturner/metal-benchmarks