Apple's A15 is a 5nm SoC with two performance CPU cores and four efficiency cores, a 16-core Neural Engine capable of 15.8 trillion operations/second, and more
Context & Ripple Effects
The A15's spec sheet is the latest step in a design lineage Apple has been building since the A10 Fusion introduced the split of high-performance and high-efficiency cores in 2016, and which the seven-core-GPU A12X pushed further at 7nm in 2018. What makes this generation different is what the numbers emphasize: a 16-core Neural Engine rated at 15.8 trillion operations per second sits front and center.
The timing matters because Apple broke its own pattern around this launch — for the first time it reported no headline CPU gains for the A15, which SemiAnalysis linked to an exodus of Apple silicon engineers to Nuvia and Rivos. The subsequent independent review bore that out: efficiency improved substantially, but speed gains over the A14 ranged only from 2.5% to 37% depending on workload.
First-order effects
- iPhone 13-series buyers get a chip whose gains are concentrated in efficiency and on-device neural throughput (15.8 TOPS) rather than raw CPU speed — a first in Apple's own reporting.
- Apple's silicon roadmap visibly reweights toward the Neural Engine, making on-device AI throughput the flagship metric where CPU generational claims used to be.
Second-order effects
- Nuvia and Rivos, the destinations named in the engineer-exodus reporting, gain exactly the Apple-trained heterogeneous-core expertise needed to attack the same performance-per-watt territory, tightening the market for senior SoC talent.
- With CPU deltas shrinking to workload-dependent percentages, competitors' phone chips are forced to compete on neural-engine TOPS and battery life instead of clock-speed comparisons.
Third-order effects
- If the pattern holds, mobile silicon differentiation migrates structurally from CPU generations to integrated AI compute — the direction Apple itself later confirmed by shipping the M5 with a Neural Accelerator built into every GPU core.
- A sustained talent drain from Apple's chip team would make silicon engineering a contested labor market rather than a proprietary moat, spreading big-little-plus-NPU design competence across more vendors.
The trend: Mobile SoC competition is pivoting from annual CPU-speed claims to efficiency and on-device neural throughput, while the engineers who built that playbook become the industry's most contested resource.