ARM Announces Cortex-A32 As A Tiny, 32-bit ARMv8 CPU

[speculatrix]

we need a 3D scatter graph with X, Y and Z being architecture, performance and power consumption.
actually we probably need five dimensions to show the Arm range, but unfortunately I am not a Time Lord and can't visualise that.

[Marc Guillot]

I'm not sure this is how it works. For example, an A7 (maybe even an A5) can outperform an A8.

If the names are based on a technical perspective, the numbers still make no sense at all. There is no consistency, rhyme, or reason. For example:
* The A15 is effectively the successor to the A9. A15 is faster and more efficient per-core, and is a big leap ahead. Sounds good so far, but...
* The A9 is pretty much just a multi-core A8, yet it's only an increment of 1.
* The A7 is the successor to the A8. It is faster and more efficient per-core, and can be multi-core, yet the number is a "step back".

See that I didn't put the Cortex-A8 in that list, because the Cortex-A8 is a generation older, so it doesn't directly compares.

* The A15 has a smaller L1 cache than the A12 and lacks an L2 cache, yet is "ranked higher". The A15 is overall slower/worse.

Indeed, that's why I didn't put the Cortex-A12 in the list either, but the Cortex-A17. Seeing the improvement they made they decided to rebrand the Cortex-A12 as Cortex-A17 so it shows that is overall a better core than the Cortex-A15.

* To my knowledge, all ARMv8 processors are 64 bit, but the Cortex A32 comes along and is 32 bit.

ARMv8 defines two modes, the 32bits mode is ARMv7 plus several new instructions, and the new 64bits mode. They decided to offer two different very low power cores to their costumers, the Cortex-A35 to be used when you need 64bits and the Cortex-A32 which drops the 64bits mode so is smaller and allows an even lower consumption, to be used for IoT devices that won't need the 64bits OS.

So, the numbers aren't based on total performance and aren't based on technical features. The numbers don't [accurately] represent per-core performance either.

No, you are right, the numbers don't show exactly the total performance. It shows three different metrics : small cores to large cores, low power cores to high power cores, low performance cores to high performance cores. In the same generation all three metrics usually agree (the larger the core, the more consumption and more performance). But a posterior design, like the Cortex-A12, can have improvements that make it smaller but more powerful than the Cortex-A15, so they finally decided to rebrand it as Cortex-A17. The number is just a trade-off of these three metrics.

Although there are some oddities. Between the Cortex-A35 and Cortex-A53 you can see there is a big increase in performance and consumption. But between the Cortex-A53 and Cortex-A57 it doesn't show the big increase they have in performance and consumption (the Cortex-A57 should have better been named Cortex-A67).