Apple M1 Ultra GPU (64-core) vs Apple A18 Pro GPU
46
out 100
VS
28
out 100
Compared 2 processors: Apple M1 Ultra GPU (64-core), vs Apple A18 Pro GPU. 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 | n/a | 7273 |
| Background Blur | 157.3 frames/s | n/a |
| Face Detection | 108.7 frames/s | n/a |
| Horizon Detection | 5.07 Gpix/sec | n/a |
| Edge Detection | 10.7 Gpix/sec | n/a |
| Gaussian Blur | 6.59 Gpix/sec | n/a |
| Feature Matching | 0.73 Gpix/sec | n/a |
| Stereo Matching | 293.4 Gpix/sec | n/a |
| Particle Physics | 14154.4 fps | n/a |
| API | OpenCL | n/a |
| Aztec Ruins (Normal) | 727.9 fps | n/a |
| Car Chase | 438.5 fps | n/a |
| Manhattan 3.1.1 (1440p) | 884.3 fps | n/a |
| T-Rex | 2706.8 fps | n/a |
| ALU 2 | 2120.6 fps | n/a |
| Driver Overhead 2 | 478.9 fps | n/a |
| API | Metal | n/a |
| OS | OS X | n/a |
| Image Classification (SP) | n/a | 3264 |
| Image Segmentation (HP) | n/a | 4550 |
| Horizon Detection | n/a | 6705 |
| Face Detection (HP) | n/a | 11770 |
| Pose Estimation (Q) | n/a | 15548 |
| Text Classification (SP) | n/a | 3678 |
| Machine Translation (HP) | n/a | 5678 |
| Object Detection (SP) | n/a | 3360 |
| Depth Estimation (Q) | n/a | 13468 |
| Style Transfer (SP) | n/a | 31541 |
| Framework | n/a | Core ML |
| Backend | n/a | GPU |
Tech Specs
Specs & test comparisonGeneral Info
| Manufacturer | Apple | Apple |
| Build | Integrated | Integrated |
| Announced | March, 8, 2022 | September, 9, 2024 |
| Form Factor | Laptop use | Laptop use |
| Use case | Professional | Universal |
| Segment | High-end | Mid-range |
| Architecture | Apple M GPU | Apple M GPU |
| Codename | Custom | Custom |
GPU
| GPU Frequency | 450 MHz | n/a |
| Boost GPU Frequency | 1296 MHz | 1490 MHz |
| Shader Units | 8192 | 768 |
| TMUs | 512 | 40 |
| ROPs | 256 | n/a |
| Execution Units | 1024 | 128 |
| Instructions per Clock | 2 IPC | 2 IPC |
Performance
| Pixel Fill Rate | 332 Gpix/sec | n/a |
| Texture Fill Rate | 664 GTex/s | 60 GTex/s |
| FLOPS | 21.2 TFLOPS | 2.3 TFLOPS |
Process
| Interface | Custom | Custom |
| TGP | 120 W | n/a |
| Process | TSMC | TSMC |
| Process tech. | 5 nm | 3 nm |
| Max temperature | 94 °C | n/a |
| Transistor count | 92.8 billion | n/a |
Memory
| Interface | System Shared | System Shared |
| Memory Frequency | 6400 MHz | 7500 MHz |
| Bus | 1024 bit | 128 bit |
| ECC support | No | No |
| Effective Memory Speed | 12800 MB/s | n/a |
Max Throughput
API
| Ray Tracing | No | Yes |
| DLSS | No | No |
Results
After analyzing the data, we consider Apple M1 Ultra GPU (64-core) the clear winner in this comparison.
Survey
Total Votes: 0
