Back Original

How did AMD Ryzen get 50% faster in two years?

People still tell me that CPUs are boring. That nothing much happens anymore.

Let us look at AMD Ryzen 7 processors from 2022 to 2024: the 5800X3D (Zen 3), the 7800X3D (Zen 4) and the 9800X3D (Zen 5). They are comparable 8-core chips with 3D V-Cache. I have written about them before, in How stagnant is CPU technology?

On Geekbench 6, performance went up by about 50% in two years.

Geekbench 6 single-core and multi-core scores for Ryzen 7 5800X3D, 7800X3D and 9800X3D

2022 2023 2024
Single-core 2,016 2,426 2,969
Multi-core 11,832 15,508 18,751

The 2024 chip is 47% faster on a single core than the 2022 chip, and 58% faster with all cores.

The clock did not do that. Max boost went from 4.5 GHz to 5.2 GHz, a 15% increase.

Base and max boost frequencies for Ryzen 7 5800X3D, 7800X3D and 9800X3D

2022 2023 2024
Base 3.4 GHz 4.2 GHz 4.7 GHz
Max boost 4.5 GHz 5.0 GHz 5.2 GHz

The number of transistors is way up, by about 50%, from roughly 11 billion to 16 billion. Most of the extra transistors went into the core, not the cache.

Transistor counts for Ryzen 7 5800X3D, 7800X3D and 9800X3D, split into core, I/O and cache

How do you turn extra transistors into extra performance?

You make the core wider, and you give it more to work with. Dispatch width went from a maximum of 6 instructions per cycle to 8. The L2 cache per core doubled, from 512 KB to 1 MB. The L1 data cache went from 32 KB to 48 KB. Integer ALUs went from 4 to 6. The reorder buffer grew from 256 to 448 entries, so the processor can keep more instructions in flight and schedule them better.

Cache sizes, dispatch width, integer ALUs and reorder buffer from Zen 3 to Zen 5

Zen 3 Zen 4 Zen 5
L2 cache per core 512 KB 1 MB 1 MB
L1 data cache 32 KB 32 KB 48 KB
Dispatch width 6 6 8
Integer ALUs 4 4 6
Reorder buffer 256 320 448

For data parallelism (SIMD), Zen 5 is a different machine. Zen 3 and Zen 4 had four 256-bit SIMD arithmetic units. Zen 5 has four 512-bit units. Loads and stores widened the same way: two 512-bit loads per cycle, one 512-bit store.

SIMD arithmetic units, loads per cycle and stores per cycle from Zen 3 to Zen 5

Zen 3 Zen 4 Zen 5
SIMD arithmetic units 4 × 256-bit 4 × 256-bit 4 × 512-bit
Loads per cycle 2 × 256-bit 2 × 256-bit 2 × 512-bit
Stores per cycle 1 × 256-bit 1 × 256-bit 1 × 512-bit

I already made the point that processors are getting wider. This is what that looks like on a desktop chip you can buy.

What about the next step? Zen 6 is arriving. AMD is talking about a 256-core Epyc part (Venice) with a gigabyte of L3 cache. We do not yet know what the desktop cores will look like. It could be wild.

Further reading: AMD’s 256-core Epyc 9996 ‘Venice’ (Tom’s Hardware).