NVIDIA GeForce 8600M GS vs NVIDIA Quadro RTX 3000 Max-Q
Processeur graphique
| Nom du GPU | G86 | TU106 |
|---|---|---|
| GPU variant | G86-770-A2 | — |
| Architecture | Tesla | Turing |
| Fonderie | TSMC | TSMC |
| Taille du processus | 80 nm | 12 nm |
| Transistors | 210 million | 10,800 million |
| Taille des matrices | 127 mm² | 445 mm² |
Graphiques mobiles
| Date de publication | May 1st, 2007 | May 27th, 2019 |
|---|---|---|
| Génération | GeForce 8M (8000M) | Quadro Mobile (Tx000) |
| Production | End-of-life | Active |
| Bus interface | MXM-II | PCIe 3.0 x16 |
| Prédécesseur | GeForce Go 7 | — |
| Successeur | GeForce 9M | — |
Vitesse clock
| GPU clock | 450 MHz | — |
|---|---|---|
| Shader clock | 900 MHz | — |
| Mémoire clock | 400 MHz 800 Mbps effective | 1500 MHz 12 Gbps effective |
| Base clock | — | 600 MHz |
| Boost clock | — | 1215 MHz |
Mémoire
| Taille de la mémoire | 512 MB | 6 GB |
|---|---|---|
| Type de mémoire | DDR2 | GDDR6 |
| Bus mémoire | 128 bit | 192 bit |
| Bande passante | 12.80 GB/s | 288.0 GB/s |
Render Config
| Shading units | 16 | 1920 |
|---|---|---|
| TMUs | 8 | 120 |
| ROPs | 4 | 64 |
| Comptage SM | 1 | 30 |
| Cache L2 | 32 KB | 3 MB |
| Tensor cores | — | 240 |
| RT cores | — | 30 |
| Cache L1 | — | 64 KB (per SM) |
Performance théorique
| Taux de pixel | 1.800 GPixel/s | 77.76 GPixel/s |
|---|---|---|
| Taux de texture | 3.600 GTexel/s | 145.8 GTexel/s |
| FP32 (float) performance | 28.80 GFLOPS | 4.666 TFLOPS |
| FP16 (half) performance | — | 9.331 TFLOPS (2:1) |
| FP64 (double) performance | — | 145.8 GFLOPS (1:32) |
Board Design
| Taille Slot | MXM Module | IGP |
|---|---|---|
| TDP | 20 W | 60 W |
| Sorties | No outputs | No outputs |
| Connecteurs de puissance | — | None |
Caractéristiques graphiques
| DirectX | 11.1 (10_0) | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | 3.3 | 4.6 |
| OpenCL | 1.1 | 3.0 |
| Vulkan | — | 1.2 |
| CUDA | 1.1 | 7.5 |
| Shader model | 4.0 | 6.6 |
