NVIDIA Quadro RTX 3000 Mobile Refresh vs NVIDIA RTX A4000 Mobile
Processeur graphique
| Nom du GPU | TU106 | GA104 |
|---|---|---|
| GPU variant | N19E-Q1-KD-A1 | — |
| Architecture | Turing | Ampere |
| Fonderie | TSMC | Samsung |
| Taille du processus | 12 nm | 8 nm |
| Transistors | 10,800 million | 17,400 million |
| Taille des matrices | 445 mm² | 392 mm² |
Graphiques mobiles
| Date de publication | May 27th, 2019 | Apr 12th, 2021 |
|---|---|---|
| Génération | Quadro Mobile (Tx000) | Quadro Mobile (Ax000) |
| Production | Active | Active |
| Bus interface | PCIe 3.0 x16 | PCIe 4.0 x16 |
Vitesse clock
| Base clock | 945 MHz | 1140 MHz |
|---|---|---|
| Boost clock | 1380 MHz | 1680 MHz |
| Mémoire clock | 1750 MHz 14 Gbps effective | 1500 MHz 12 Gbps effective |
Mémoire
| Taille de la mémoire | 6 GB | 8 GB |
|---|---|---|
| Type de mémoire | GDDR6 | GDDR6 |
| Bus mémoire | 192 bit | 256 bit |
| Bande passante | 336.0 GB/s | 384.0 GB/s |
Render Config
| Shading units | 1920 | 5120 |
|---|---|---|
| TMUs | 120 | 160 |
| ROPs | 64 | 80 |
| Comptage SM | 30 | 40 |
| Tensor cores | 240 | 160 |
| RT cores | 30 | 40 |
| Cache L1 | 64 KB (per SM) | 128 KB (per SM) |
| Cache L2 | 4 MB | 4 MB |
Performance théorique
| Taux de pixel | 88.32 GPixel/s | 134.4 GPixel/s |
|---|---|---|
| Taux de texture | 165.6 GTexel/s | 268.8 GTexel/s |
| FP16 (half) performance | 10.60 TFLOPS (2:1) | 17.20 TFLOPS (1:1) |
| FP32 (float) performance | 5.299 TFLOPS | 17.20 TFLOPS |
| FP64 (double) performance | 165.6 GFLOPS (1:32) | 537.6 GFLOPS (1:32) |
Board Design
| Taille Slot | IGP | — |
|---|---|---|
| TDP | 80 W | 140 W |
| Sorties | No outputs | No outputs |
| Connecteurs de puissance | None | None |
Caractéristiques graphiques
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| CUDA | 7.5 | 8.6 |
| Shader model | 6.6 | 6.6 |
