AMD Stream Processor vs NVIDIA GRID RTX T10-16
Grafikprozessor
| GPU Name | R580 | TU102 |
|---|---|---|
| GPU Variante | R580 XTX | TU102-875-A1 |
| Architektur | R500 | Turing |
| Hersteller | TSMC | TSMC |
| Prozessgröße | 90 nm | 12 nm |
| Transistoren | 384 million | 18,600 million |
| Chipgröße | 352 mm² | 754 mm² |
Grafikkarte
| Veröffentlichungsdatum | 2006 | Unknown |
|---|---|---|
| Generation | FireStream | GRID |
| Produktion | End-of-life | Active |
| Businterface | PCIe 1.0 x16 | PCIe 3.0 x16 |
Takt-Geschwindigkeiten
| GPU-Taktung | 594 MHz | — |
|---|---|---|
| Speicher-Taktung | 648 MHz 1296 Mbps effective | 1575 MHz 12.6 Gbps effective |
| Basis-Taktfrequenz | — | 1065 MHz |
| Boost-Takt | — | 1395 MHz |
Speicher
| Speichergröße | 1024 MB | 16 GB |
|---|---|---|
| Speichertyp | GDDR3 | GDDR6 |
| Speicherbus | 256 bit | 384 bit |
| Bandbreite | 41.47 GB/s | 604.8 GB/s |
Render-Konfiguration
| Pixelshader | 48 | — |
|---|---|---|
| Vertex-Shader | 8 | — |
| TMUs | 16 | 288 |
| ROPs | 16 | 96 |
| Shading-Einheiten | — | 4608 |
| Anzahl SM | — | 72 |
| Tensor Cores | — | 576 |
| RT-Kerne | — | 72 |
| Cache L1 | — | 64 KB (per SM) |
| Cache L2 | — | 6 MB |
Theoretische Leistung
| Pixelrate | 9.504 GPixel/s | 133.9 GPixel/s |
|---|---|---|
| Vertex-Rate | 1.188 GVertices/s | — |
| Texturrate | 9.504 GTexel/s | 401.8 GTexel/s |
| FP16 (half) Leistung | — | 25.71 TFLOPS (2:1) |
| FP32 (float) Leistung | — | 12.86 TFLOPS |
| FP64 (double) Leistung | — | 401.8 GFLOPS (1:32) |
Boarddesign
| Steckplatzbreite | Dual-slot | Dual-slot |
|---|---|---|
| Länge | 241 mm 9.5 inches | 267 mm 10.5 inches |
| Breite | 111 mm 4.4 inches | — |
| TDP | 165 W | 260 W |
| Vorgeschlagenes Netzteil | 450 W | 600 W |
| Ausgabe | 2x DVI1x S-Video | No outputs |
| Stromverbindung | 1x 6-pin | 1x 6-pin + 1x 8-pin |
| Board-Nummer | — | PG150 SKU 215 |
Grafik-Features
| DirectX | 9.0c (9_3) | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | 2.1 (full) 3.0 (partial) | 4.6 |
| OpenCL | — | 3.0 |
| Vulkan | — | 1.2 |
| Shader-Modell | 3.0 | 6.6 |
| CUDA | — | 7.5 |
