AMD Radeon R9 FURY X2 vs NVIDIA Tesla V100 PCIe 16 GB
Processeur graphique
| Nom du GPU | Fiji | GV100 |
|---|---|---|
| GPU variant | Fiji XT | — |
| Architecture | GCN 3.0 | Volta |
| Fonderie | TSMC | TSMC |
| Taille du processus | 28 nm | 12 nm |
| Transistors | 8,900 million | 21,100 million |
| Taille des matrices | 596 mm² | 815 mm² |
Carte graphique
| Date de publication | Never Released | Jun 21st, 2017 |
|---|---|---|
| Génération | Pirate Islands | Tesla |
| Production | End-of-life | End-of-life |
| Bus interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Prédécesseur | Volcanic Islands | — |
| Successeur | Arctic Islands | — |
Vitesse clock
| GPU clock | 1050 MHz | — |
|---|---|---|
| Mémoire clock | 500 MHz 1000 Mbps effective | 876 MHz 1752 Mbps effective |
| Base clock | — | 1245 MHz |
| Boost clock | — | 1380 MHz |
Mémoire
| Taille de la mémoire | 4 GB | 16 GB |
|---|---|---|
| Type de mémoire | HBM | HBM2 |
| Bus mémoire | 4096 bit | 4096 bit |
| Bande passante | 512.0 GB/s | 897.0 GB/s |
Render Config
| Shading units | 4096 | 5120 |
|---|---|---|
| TMUs | 256 | 320 |
| ROPs | 64 | 128 |
| Compute units | 64 | — |
| Cache L1 | 16 KB (per CU) | 128 KB (per SM) |
| Cache L2 | 2 MB | 6 MB |
| Comptage SM | — | 80 |
| Tensor cores | — | 640 |
Performance théorique
| Taux de pixel | 67.20 GPixel/s | 176.6 GPixel/s |
|---|---|---|
| Taux de texture | 268.8 GTexel/s | 441.6 GTexel/s |
| FP32 (float) performance | 8.602 TFLOPS | 14.13 TFLOPS |
| FP16 (half) performance | — | 28.26 TFLOPS (2:1) |
| FP64 (double) performance | — | 7.066 TFLOPS (1:2) |
Board Design
| Taille Slot | Dual-slot | Dual-slot |
|---|---|---|
| TDP | unknown | 300 W |
| Suggestions pour le PSU | 200 W | 700 W |
| Sorties | 1x HDMI3x DisplayPort | No outputs |
| Connecteurs de puissance | 2x 8-pin | 2x 8-pin |
| Board number | C883 | PG500 SKU 200 |
Caractéristiques graphiques
| DirectX | 12 (12_0) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| Shader model | 6.3 | 6.6 |
| CUDA | — | 7.0 |