AMD Radeon Pro W5500 vs NVIDIA Tesla M40
Processeur graphique
| Nom du GPU | Navi 14 | GM200 |
|---|---|---|
| GPU variant | Navi 14 PRO XL | GM200-895-A1 |
| Architecture | RDNA 1.0 | Maxwell 2.0 |
| Fonderie | TSMC | TSMC |
| Taille du processus | 7 nm | 28 nm |
| Transistors | 6,400 million | 8,000 million |
| Taille des matrices | 158 mm² | 601 mm² |
Carte graphique
| Date de publication | Feb 10th, 2020 | Nov 10th, 2015 |
|---|---|---|
| Génération | Radeon Pro | Tesla |
| Production | Active | End-of-life |
| Prix de lancement | 399 USD | — |
| Bus interface | PCIe 4.0 x8 | PCIe 3.0 x16 |
Vitesse clock
| Base clock | 1744 MHz | 948 MHz |
|---|---|---|
| Boost clock | 1855 MHz | 1112 MHz |
| Mémoire clock | 1750 MHz 14 Gbps effective | 1502 MHz 6 Gbps effective |
Mémoire
| Taille de la mémoire | 8 GB | 12 GB |
|---|---|---|
| Type de mémoire | GDDR6 | GDDR5 |
| Bus mémoire | 128 bit | 384 bit |
| Bande passante | 224.0 GB/s | 288.4 GB/s |
Render Config
| Shading units | 1408 | 3072 |
|---|---|---|
| TMUs | 88 | 192 |
| ROPs | 32 | 96 |
| Compute units | 22 | — |
| Cache L2 | 2 MB | 3 MB |
| Comptage SMM | — | 24 |
| Cache L1 | — | 48 KB (per SMM) |
Performance théorique
| Taux de pixel | 59.36 GPixel/s | 106.8 GPixel/s |
|---|---|---|
| Taux de texture | 163.2 GTexel/s | 213.5 GTexel/s |
| FP16 (half) performance | 10.45 TFLOPS (2:1) | — |
| FP32 (float) performance | 5.224 TFLOPS | 6.832 TFLOPS |
| FP64 (double) performance | 326.5 GFLOPS (1:16) | 213.5 GFLOPS (1:32) |
Board Design
| Taille Slot | Single-slot | Dual-slot |
|---|---|---|
| Longueur | 241 mm 9.5 inches | 267 mm 10.5 inches |
| Taille | 111 mm 4.4 inches | — |
| TDP | 125 W | 250 W |
| Suggestions pour le PSU | 300 W | 600 W |
| Sorties | 4x DisplayPort | No outputs |
| Connecteurs de puissance | 1x 6-pin | 1x 6-pin + 1x 8-pin |
| Board number | D325-87 | PG600 SKU 202 |
Caractéristiques graphiques
| DirectX | 12 (12_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.1 |
| Shader model | 6.5 | 6.4 |
| CUDA | — | 5.2 |
