VS
Google Tensor vs Apple M4 Max (16-CPU 40-GPU)
Última actualización:
|
Wischen
|
Google Tensor | Apple M4 Max (16-CPU 40-GPU) |
|---|---|---|
| Familia | Google Tensor (5) | Apple M series (38) |
| Grupo de CPU | Google Tensor (1) | Apple M4 (7) |
| Arquitectura | G1 | M4 |
| Tecnologia | 5 nm | 3 nm |
| Segmento | Smartphone / Tablet | Notebook |
| Enchufe | ||
| Predecesor | Apple M3 Max (16-CPU 40-GPU) | |
| Sucesor | Google Tensor G2 | Apple M5 Max (18-CPU 40-GPU) |
|
Wischen
|
Google Tensor | Apple M4 Max (16-CPU 40-GPU) |
|---|---|---|
| CPU Nùcleos / Threads | 8 / 8 | 16 / 16 |
| Hyperthreading / SMT | ✗ | ✗ |
| Arquitectura central | hybrid (Prime / big.LITTLE) | hybrid (big.LITTLE) |
| Core Cluster 1: | 2x Cortex-X1 2,80 GHz |
12x Donan P-Core 1,26 - 4,51 GHz |
| Core Cluster 2: | 2x Cortex-A76 2,25 GHz |
4x Donan E-Core 1,02 - 2,59 GHz |
| Core Cluster 3: | 4x Cortex-A55 1,80 GHz |
|
| L2-Cache | 8,00 MB | 52,00 MB |
| L3-Cache | ||
| Overclocking | ✗ | ✗ |
|
Wischen
|
Google Tensor | Apple M4 Max (16-CPU 40-GPU) |
|---|---|---|
| nombre GPU | ARM Mali-G78 MP20 | Apple M4 Max (40 Core) |
| Frecuencia GPU | 0,76 GHz | 0,39 - 1,58 GHz |
| CUs / Shader | 20 / 320 | 640 / 5120 |
| Raytracing | ✗ | ✓ |
| Max. visualizaciones | 1 | 3 |
| Max. GPU Memoria | 96 GB | |
| Tecnologia | 5 nm | 3 nm |
| Fecha de lanzamiento | Q4/2021 | Q4/2024 |
|
Wischen
|
Google Tensor | Apple M4 Max (16-CPU 40-GPU) |
|---|---|---|
| Hardware de IA | Google Tensor AI | Apple Neural Engine |
| especificaciones de IA | Google Edge TPU @ 1.6 TOPS | 16 Neural cores @ 38 TOPS |
| NPU + CPU + iGPU |
|
Wischen
|
Google Tensor | Apple M4 Max (16-CPU 40-GPU) |
|---|---|---|
| Memoria | LPDDR5-5500 (53,0 GB/s) | LPDDR5X-8533 (546,0 GB/s) |
| Max. Memoria | 12 GB | 128 GB |
| Canales de memoria | 2 | 8 |
| ECC | No | No |
| PCIe | 5.0 | |
| PCIe Banda ancha |
|
Wischen
|
Google Tensor | Apple M4 Max (16-CPU 40-GPU) |
|---|---|---|
| TDP | 10 W | 90 W |
| TDP (PL2) | ||
| TDP up | ||
| TDP down | ||
| T. junction max. | 100 °C |
|
Wischen
|
Google Tensor | Apple M4 Max (16-CPU 40-GPU) |
|---|---|---|
| Diseño de chips | Desconocido | Monolítico |
| AES-NI | ✗ | ✓ |
| Sistemas operativos | Android | macOS, iPadOS |
| Conjunto de instrucciones | Armv8-A (64 bit) | Armv9.2-A (64 bit) |
| Extensiones ISA | Rosetta 2 x86-Emulation, AVX2, SME | |
| Fecha de lanzamiento | Q4/2021 | Q4/2024 |
| Precio de lanzamiento | ||
| Documentos |