Apple M1 GPU (8-core) vs Apple M2 GPU (8-core)
25
out 100
VS
30
out 100
Compared 2 processors: Apple M1 GPU (8-core), vs Apple M2 GPU (8-core). Below are specs, tests, pros and cons for each device
Review
Games
Performance in DirectX, OpenCL, Vulkan
AI/ML
AI workload testing
Professional Apps
3D modeling, video editing, rendering
Energy Efficiency
Power usage in various scenarios
Tests & specs
Specs & test comparisonBenchmarks
| Solar Bay | 6311 | n/a |
| Background Blur | 38.3 frames/s | 58.7 frames/s |
| Face Detection | 23 frames/s | 35.2 frames/s |
| Horizon Detection | 0.76 Gpix/sec | 1.1 Gpix/sec |
| Edge Detection | 1.33 Gpix/sec | 1.82 Gpix/sec |
| Gaussian Blur | 0.87 Gpix/sec | 1.2 Gpix/sec |
| Feature Matching | 0.27 Gpix/sec | 0.37 Gpix/sec |
| Stereo Matching | 69.9 Gpix/sec | 96 Gpix/sec |
| Particle Physics | 2766.4 fps | 3825.9 fps |
| API | OpenCL | OpenCL |
| Aztec Ruins (Normal) | n/a | 296.7 fps |
| Car Chase | n/a | 231.3 fps |
| Manhattan 3.1.1 (1440p) | n/a | 178.6 fps |
| T-Rex | n/a | 935.1 fps |
| ALU 2 | n/a | 404.2 fps |
| Driver Overhead 2 | n/a | 445 fps |
| API | n/a | Metal |
| OS | n/a | OS X |
| Image Classification (SP) | 1400 | n/a |
| Image Segmentation (HP) | 2280 | n/a |
| Horizon Detection | 3402 | n/a |
| Face Detection (HP) | 5638 | n/a |
| Pose Estimation (Q) | 12027 | n/a |
| Text Classification (SP) | 2324 | n/a |
| Machine Translation (HP) | 4296 | n/a |
| Object Detection (SP) | 1530 | n/a |
| Depth Estimation (Q) | 7675 | n/a |
| Style Transfer (SP) | 17293 | n/a |
| Framework | Core ML | n/a |
| Backend | CPU | n/a |
Tech Specs
Specs & test comparisonGeneral Info
| Manufacturer | Apple | Apple |
| Build | Integrated | Integrated |
| Announced | November, 20, 2020 | June, 6, 2022 |
| Form Factor | Laptop use | Laptop use |
| Use case | Professional | Professional |
| Segment | Mid-range | Mid-range |
| Architecture | Apple M GPU | Apple M GPU |
GPU
| GPU Frequency | 450 MHz | 500 MHz |
| Boost GPU Frequency | 1278 MHz | 1398 MHz |
| Shader Units | 1024 | 1024 |
| TMUs | 64 | 64 |
| ROPs | 32 | 32 |
| Execution Units | 128 | 128 |
| Ray Tracing Cores | No | n/a |
| Instructions per Clock | 2 IPC | 2 IPC |
Performance
| Pixel Fill Rate | 41 Gpix/sec | 45 Gpix/sec |
| Texture Fill Rate | 82 GTex/s | 89 GTex/s |
| FLOPS | 2.6 TFLOPS | 2.9 TFLOPS |
Process
| Interface | Custom | Custom |
| TGP | 15 W | 15 W |
| Process | Intel | TSMC |
| Process tech. | 5 nm | 5 nm |
| Max temperature | 94 °C | 94 °C |
| Transistor count | 11.6 billion | 11.6 billion |
Memory
| Interface | System Shared | System Shared |
| Memory Frequency | 4266 MHz | 6400 MHz |
| Bus | 128 bit | 128 bit |
| ECC support | No | No |
| Effective Memory Speed | 8532 MB/s | 12800 MB/s |
Max Throughput
API
| Ray Tracing | No | No |
| DLSS | No | No |
Results
No clear favorite identified yet; updates may follow as new data arrives.
Survey
Total Votes: 0
