AMD Ryzen 5 7645HX vs Apple M2 Pro 10-Core

AMD Ryzen 5 7645HX

The AMD Ryzen 5 7645HX is a fast high-end laptop processor of the Dragon Range series. It offers 6 cores based on the Zen 4 architecture that supports hyperthreading (12 threads). The cores clock from 4 (base) up to 5 GHz (single core boost).

The performance of the R5 7645HX should be significantly higher than the fastest 6-core CPU of the Ryzen 6000 mobile series the Ryzen 5 6600H. Especially single threaded performance should be very good thanks to the new Zen 4 cores and relatively high clock speeds. This means even the old Ryzen 9 6980HX (also 5 GHz, but Zen 3) should be slightly slower in single threaded workloads.

The Dragon Range series still uses a chiplet design with two CCD-clusters (each with 8 possible cores, the 7645HX only uses one CCD with 6 of the 8 cores) in 5nm and an IO-die (including the memory controller and the Radeon 610M iGPU) in 6nm. The chip integrates 4x USB 3.2 Gen2 (10 Gbps) ports (no USB4), 28 PCIe 5.0 lanes (for GPU and SSDs) and a dual-channel DDR5-5200 memory controller.

The R5 7645HX is rated at a TDP of 55 Watt and can be configured up to 75 Watt (cTDP).

Apple M2 Pro 10-Core

The Apple M2 Pro 10-Core is a System on a Chip (SoC) from Apple that is found in the early 2023 MacBook Pro 14 and Mac Mini entry level models. It offers 10 of the 12 cores available in the chip divided in six performance cores (P-cores) and four power-efficiency cores (E-cores). The E-cores clock with up to 3.4 GHz, the P-Cores up to 3.7 GHz (mostly 3.3 GHz in multi-threaded workloads and 3.4 GHz in single threaded).

The big cores (codename Avalanche) offer 192 KB instruction cache, 128 KB data cache, and 36 MB shared L2 cache (up from 24 MB in the M1 Pro). The four efficiency cores (codename Blizzard) are a lot smaller and offer only 128 KB instruction cache, 64 KB data cache, and 4 MB shared cache. CPU and GPU can both use the 24 MB SLC (System Level Cache). 

The unified memory (16 or 32 GB LPDDR5-6400) next to the chip is connected by a 256 Bit memory controller (200 GB/s bandwidth) and can be used by the GPU and CPU.

The performance of the M2 Pro 10-Core should be similar to the old M1 Pro with all 10 cores. The multi-threaded performance should be slower, as the M2 10-core has two p-cores less (and 2 e-cores more) but the single-threaded performance should be better due to the faster clock speed and architectural improvements. The old M1 Pro 8-core should be noticeably slower.

The integrated graphics card in the M1 Pro 10-core offers all 16 of the 19 cores.

Furthermore, the SoC integrates a fast 16 core neural engine (faster than M1 Pro), a secure enclave (e.g., for encryption), a unified memory architecture, Thunderbolt 4 controller, an ISP, and media de- and encoders (including ProRes).

The M2 Pro is manufactured in 5 nm at TSMC (second generation) and integrates 40 billion transistors.