AMD Radeon Pro Duo vs NVIDIA Tesla V100S PCIe 32 GB
Grafikprozessor
| GPU Name | Capsaicin | GV100 |
|---|---|---|
| GPU Variante | Capsaicin XT | — |
| Architektur | GCN 3.0 | Volta |
| Hersteller | TSMC | TSMC |
| Prozessgröße | 28 nm | 12 nm |
| Transistoren | 8,900 million | 21,100 million |
| Chipgröße | 596 mm² | 815 mm² |
Grafikkarte
| Veröffentlichungsdatum | Apr 26th, 2016 | Nov 26th, 2019 |
|---|---|---|
| Generation | Radeon Pro | Tesla |
| Produktion | End-of-life | End-of-life |
| Originalpreis | 1,499 USD | — |
| Businterface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Reviews | 6 in our database | — |
Takt-Geschwindigkeiten
| GPU-Taktung | 1000 MHz | — |
|---|---|---|
| Speicher-Taktung | 500 MHz 1000 Mbps effective | 1106 MHz 2.2 Gbps effective |
| Basis-Taktfrequenz | — | 1245 MHz |
| Boost-Takt | — | 1597 MHz |
Speicher
| Speichergröße | 4 GB | 32 GB |
|---|---|---|
| Speichertyp | HBM | HBM2 |
| Speicherbus | 4096 bit | 4096 bit |
| Bandbreite | 512.0 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 | 2 MB | 6 MB |
| Anzahl SM | — | 80 |
| Tensor Cores | — | 640 |
Theoretische Leistung
| Pixelrate | 64.00 GPixel/s | 204.4 GPixel/s |
|---|---|---|
| Texturrate | 256.0 GTexel/s | 511.0 GTexel/s |
| FP16 (half) Leistung | 8.192 TFLOPS (1:1) | 32.71 TFLOPS (2:1) |
| FP32 (float) Leistung | 8.192 TFLOPS | 16.35 TFLOPS |
| FP64 (double) Leistung | 512.0 GFLOPS (1:16) | 8.177 TFLOPS (1:2) |
Boarddesign
| Steckplatzbreite | Dual-slot | Dual-slot |
|---|---|---|
| Länge | 277 mm 10.9 inches | — |
| Breite | 111 mm 4.4 inches | — |
| TDP | 350 W | 250 W |
| Vorgeschlagenes Netzteil | 750 W | 600 W |
| Ausgabe | 1x HDMI3x DisplayPort | No outputs |
| Stromverbindung | 3x 8-pin | 2x 8-pin |
| Board-Nummer | C888-37 | PG500 |
Grafik-Features
| DirectX | 12 (12_0) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| Shader-Modell | 6.0 | 6.6 |
| CUDA | — | 7.0 |
