CODEWITHSUNDEEP
arm
learning_dude
learning_dude

Reputation: 1050

Explanation of the arm cortex a/r/m numbering convention

I've been looking around some web sources, but I can not find the meaning of the numbers after the processor type of the ARM family. For example Cortex-A53, I know it refers to the application family, hence the A, the 5 might refer that it contains MMU(not sure though), but the 3 I have no idea...can you please provide an explanation or sources?

Upvotes: 3

Views: 1302

Answers (1)

solidpixel
solidpixel

Reputation: 12119

For the Cortex-A processors there are three major sub-groups which are worth knowing about:

Cortex-A3x => smaller cores, mostly designed for embedded systems and low-cost mobile.

Cortex-A5x => "LITTLE" cores in the Arm big.LITTLE / DynamIQ heterogeneous compute architecture (so lower peak performance than the "big" cores, but better energy efficiency).

Cortex-A7x => "big" cores in the Arm big.LITTLE / DynamIQ heterogeneous compute architecture (so higher peak performance than the "LITTLE" cores, but lower energy efficiency).

Within each those groups the bigger value of "x" will be the newer CPU cores, which nearly always have both improved energy efficiency and peak performance than the lower numbered ones within that group.

The specific numbers don't have specific decode for "has an MMU" or anything like that (unless you go back a long time - some of the early ARM7 and ARM9 CPU names did).

For Cortex-M and R, they don't really have the same tiers - in general bigger number = bigger and faster core with more recent ISA extensions to add new capabilities.

The only significant banding that exists is the Cortex-R5x series (which is ARMv8-R architecture including 64-bit support, where as the single digit R cores are all 32-bit Armv7 cores).

Upvotes: 4

Related Questions