Apple M2 Max vs Google Tensor vs Apple M2 Pro

Apple M2 Max

The Apple M2 Max is a System on a Chip (SoC) from Apple that is found in the early 2023 MacBook Pro 14 and 16-inch models. It offers all 12 CPU cores available in the chip divided in eight 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 49 MB SLC (System Level Cache). 

The unified memory (32, 64, or 96 GB LPDDR5-6400) next to the chip is connected by a 512 Bit memory controller (400 GB/s bandwidth) and can be used by the GPU and CPU.

The CPU performance should be quite similar to the M2 Pro as only the higher memory bandwidth and bigger L3 cache could make a difference for some workloads.

The integrated graphics card in the M1 Max offers a 30-core GPU or a GPU with all 38 cores.

Furthermore, the SoC integrates a fast 16 core neural engine (faster than M1 Max), 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 Max is manufactured in 5 nm at TSMC (second generation) and integrates 40 billion transistors. The power consumption of the CPU part is up to 36 Watt according to powermetrics. When fully loading the CPU and GPU cores, the chip uses up to 89 Watt and the CPU part is limited to 25 Watt.

Google Tensor

The Google Tensor SoC (G1, first generation) is the first smartphone processor from Google. It is positioned as a high end SoC and focuses on the integrated TPU for efficient AI and ML calculations. The CPU part integrates two fast and big ARM Cortex X1 cores at up to 2.8 GHz. A second cluster integrates 2 mid range Cortex-A76 cores at up to 2.25 GHz. Finally, four small ARM Cortex-A55 cores with up to 1.8 GHz are integrated for efficiency purposes. All cores can access the shared 4 MB L3 cache. 

The successors of the Tensor SoC are the Tensor G2 and G3.

The chip also integrates a Titan M2 security processor and a ARM Mali G78 MP20 GPU. The chip is manufactured in the modern 5nm process.

Apple M2 Pro

The Apple M2 Pro is a System on a Chip (SoC) from Apple that is found in the early 2023 MacBook Pro 14 and 16-inch models. It offers all 12 cores available in the chip divided in eight 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.

Apple states that the M2 Pro has a 25% higher performance than the M1 Pro in Xcode compiling.

The integrated graphics card in the M1 Pro offers all 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.