AMD Radeon Pro WX 9100 vs NVIDIA Tesla V100S PCIe 32 GB
Grafikprozessor
| GPU Name | Vega 10 | GV100 |
|---|---|---|
| GPU Variante | Vega 10 XT (215-0894200) | — |
| Architektur | GCN 5.0 | Volta |
| Hersteller | GlobalFoundries | TSMC |
| Prozessgröße | 14 nm | 12 nm |
| Transistoren | 12,500 million | 21,100 million |
| Chipgröße | 495 mm² | 815 mm² |
Grafikkarte
| Veröffentlichungsdatum | Jul 10th, 2017 | Nov 26th, 2019 |
|---|---|---|
| Generation | Radeon Pro | Tesla |
| Produktion | Active | End-of-life |
| Originalpreis | 1,599 USD | — |
| Businterface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Takt-Geschwindigkeiten
| Basis-Taktfrequenz | 1200 MHz | 1245 MHz |
|---|---|---|
| Boost-Takt | 1500 MHz | 1597 MHz |
| Speicher-Taktung | 945 MHz 1890 Mbps effective | 1106 MHz 2.2 Gbps effective |
Speicher
| Speichergröße | 16 GB | 32 GB |
|---|---|---|
| Speichertyp | HBM2 | HBM2 |
| Speicherbus | 2048 bit | 4096 bit |
| Bandbreite | 483.8 GB/s | 1,133 GB/s |
Render-Konfiguration
| Shading-Einheiten | 4096 | 5120 |
|---|---|---|
| TMUs | 256 | 320 |
| ROPs | 64 | 128 |
| Compute Units | 64 | — |
| Cache L1 | 16 KB (per CU) | 128 KB (per SM) |
| Cache L2 | 4 MB | 6 MB |
| Anzahl SM | — | 80 |
| Tensor Cores | — | 640 |
Theoretische Leistung
| Pixelrate | 96.00 GPixel/s | 204.4 GPixel/s |
|---|---|---|
| Texturrate | 384.0 GTexel/s | 511.0 GTexel/s |
| FP16 (half) Leistung | 24.58 TFLOPS (2:1) | 32.71 TFLOPS (2:1) |
| FP32 (float) Leistung | 12.29 TFLOPS | 16.35 TFLOPS |
| FP64 (double) Leistung | 768.0 GFLOPS (1:16) | 8.177 TFLOPS (1:2) |
Boarddesign
| Steckplatzbreite | Dual-slot | Dual-slot |
|---|---|---|
| Länge | 267 mm 10.5 inches | — |
| Breite | 111 mm 4.4 inches | — |
| TDP | 230 W | 250 W |
| Vorgeschlagenes Netzteil | 550 W | 600 W |
| Ausgabe | 6x mini-DisplayPort | No outputs |
| Stromverbindung | 1x 6-pin + 1x 8-pin | 2x 8-pin |
| Board-Nummer | D051 | PG500 |
Grafik-Features
| DirectX | 12 (12_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| Shader-Modell | 6.4 | 6.6 |
| CUDA | — | 7.0 |
