AMD Radeon Pro WX 9100 vs NVIDIA GeForce RTX 3070 Ti Mobile
Processeur graphique
| Nom du GPU | Vega 10 | GA104 |
|---|---|---|
| GPU variant | Vega 10 XT (215-0894200) | — |
| Architecture | GCN 5.0 | Ampere |
| Fonderie | GlobalFoundries | Samsung |
| Taille du processus | 14 nm | 8 nm |
| Transistors | 12,500 million | 17,400 million |
| Taille des matrices | 495 mm² | 392 mm² |
Carte graphique
| Date de publication | Jul 10th, 2017 | — |
|---|---|---|
| Génération | Radeon Pro | — |
| Production | Active | — |
| Prix de lancement | 1,599 USD | — |
| Bus interface | PCIe 3.0 x16 | — |
Vitesse clock
| Base clock | 1200 MHz | 915 MHz |
|---|---|---|
| Boost clock | 1500 MHz | 1410 MHz |
| Mémoire clock | 945 MHz 1890 Mbps effective | 1750 MHz 14 Gbps effective |
Mémoire
| Taille de la mémoire | 16 GB | 8 GB |
|---|---|---|
| Type de mémoire | HBM2 | GDDR6 |
| Bus mémoire | 2048 bit | 256 bit |
| Bande passante | 483.8 GB/s | 448.0 GB/s |
Render Config
| Shading units | 4096 | 5632 |
|---|---|---|
| TMUs | 256 | 176 |
| ROPs | 64 | 80 |
| Compute units | 64 | — |
| Cache L1 | 16 KB (per CU) | 128 KB (per SM) |
| Cache L2 | 4 MB | 4 MB |
| Comptage SM | — | 44 |
| Tensor cores | — | 176 |
| RT cores | — | 44 |
Performance théorique
| Taux de pixel | 96.00 GPixel/s | 112.8 GPixel/s |
|---|---|---|
| Taux de texture | 384.0 GTexel/s | 248.2 GTexel/s |
| FP16 (half) performance | 24.58 TFLOPS (2:1) | 15.88 TFLOPS (1:1) |
| FP32 (float) performance | 12.29 TFLOPS | 15.88 TFLOPS |
| FP64 (double) performance | 768.0 GFLOPS (1:16) | 248.2 GFLOPS (1:64) |
Board Design
| Taille Slot | Dual-slot | — |
|---|---|---|
| Longueur | 267 mm 10.5 inches | — |
| Taille | 111 mm 4.4 inches | — |
| TDP | 230 W | 115 W |
| Suggestions pour le PSU | 550 W | — |
| Sorties | 6x mini-DisplayPort | No outputs |
| Connecteurs de puissance | 1x 6-pin + 1x 8-pin | None |
| Board number | D051 | — |
Caractéristiques graphiques
| DirectX | 12 (12_1) | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| Shader model | 6.4 | 6.6 |
| CUDA | — | 8.6 |
AUTRES CARACTÉRISTIQUES
Graphiques mobiles
| Date de publication | — | Unknown |
|---|---|---|
| Génération | — | GeForce 30 Mobile |
| Prédécesseur | — | GeForce 20 Mobile |
| Production | — | Unreleased |
| Bus interface | — | PCIe 4.0 x16 |
