Intel Celeron 3867U vs Apple M2 Max vs Apple M2 Pro 10-Core

Intel Celeron 3867U

The Intel Celeron 3865U is an ULV (ultra low voltage) dual-core SoC based on the Kaby-Lake architecture and has been launched in the first quarter of 2017. The CPU can be found in ultrabooks as well as normal notebooks. In addition to two CPU cores clocked at 1.8 GHz (no Turbo Boost, no HyperThreading), the chip also integrates an HD Graphics 610 GPU and a dual-channel DDR4-2133/DDR3L-1600 memory controller. The SoC is manufactured using a 14 nm process with FinFET transistors.

Compared to the similar Celeron 3865, the 3867 offers a different cTDP-down option (12.5 versus 10 Watt).

Architecture

Intel basically uses the same micro architecture compared to Skylake, so the per-MHz performance does not differ. The manufacturer only reworked the Speed Shift technology for faster dynamic adjustments of voltages and clocks, and the improved 14nm process allows much higher frequencies combined with better efficiency than before.

Performance

Due to the missing Turbo Boost and the low clock speeds, especially the single thread performance is very limited which results in a lower performance even for lower demanding tasks. The performance should be noticeably slower than the Celeron 3965 which offers 400 MHz higher clocked CPU cores. Therefore, the CPU is only suited for entry level tasks like office, web surfing and multimedia.

Graphics

The integrated graphics unit called HD Graphics 610 (similar to the HD Graphics 510) represents the "GT1" version of the Kaby Lake GPU (Intel Gen. 9). Its 12 Execution Units, also called EUs, are clocked at 300 - 900 MHz and offer a performance somewhat below the older HD Graphics 4400. Only a few games of 2015 can be played smoothly in lowest settings.

Power Consumption

Specified at a TDP of 15 W (including CPU, GPU and memory controller), the CPU is best suited for small notebooks and ultrabooks (11-inches and above). Optionally, the TDP can be lowered to 10 watts (cTDP down), reducing both heat dissipation and performance and allowing even more compact designs.

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.

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.