ATI Radeon HD 5670 640SP Edition vs NVIDIA GRID RTX T10-4
Grafikprozessor
| GPU Name | Juniper | TU102 |
|---|---|---|
| GPU Variante | Juniper CE | TU102-875-A1 |
| Architektur | TeraScale 2 | Turing |
| Hersteller | TSMC | TSMC |
| Prozessgröße | 40 nm | 12 nm |
| Transistoren | 1,040 million | 18,600 million |
| Chipgröße | 166 mm² | 754 mm² |
Grafikkarte
| Veröffentlichungsdatum | Jul 18th, 2010 | Unknown |
|---|---|---|
| Generation | Evergreen | GRID |
| Produktion | End-of-life | Active |
| Originalpreis | 119 USD | — |
| Businterface | PCIe 2.0 x16 | PCIe 3.0 x16 |
| Reviews | 83 in our database | — |
| Vorgänger | Radeon R700 | — |
| Nachfolger | Northern Islands | — |
Takt-Geschwindigkeiten
| GPU-Taktung | 750 MHz | — |
|---|---|---|
| Speicher-Taktung | 1000 MHz 4 Gbps effective | 1750 MHz 14 Gbps effective |
| Basis-Taktfrequenz | — | 1065 MHz |
| Boost-Takt | — | 1395 MHz |
Speicher
| Speichergröße | 512 MB | 4 GB |
|---|---|---|
| Speichertyp | GDDR5 | GDDR6 |
| Speicherbus | 128 bit | 384 bit |
| Bandbreite | 64.00 GB/s | 672.0 GB/s |
Render-Konfiguration
| Shading-Einheiten | 640 | 4608 |
|---|---|---|
| TMUs | 32 | 288 |
| ROPs | 8 | 96 |
| Compute Units | 8 | — |
| Cache L1 | 8 KB (per CU) | 64 KB (per SM) |
| Cache L2 | 256 KB | 6 MB |
| Anzahl SM | — | 72 |
| Tensor Cores | — | 576 |
| RT-Kerne | — | 72 |
Theoretische Leistung
| Pixelrate | 6.000 GPixel/s | 133.9 GPixel/s |
|---|---|---|
| Texturrate | 24.00 GTexel/s | 401.8 GTexel/s |
| FP32 (float) Leistung | 960.0 GFLOPS | 12.86 TFLOPS |
| FP16 (half) Leistung | — | 25.71 TFLOPS (2:1) |
| FP64 (double) Leistung | — | 401.8 GFLOPS (1:32) |
Boarddesign
| Steckplatzbreite | Single-slot | Dual-slot |
|---|---|---|
| Länge | 168 mm 6.6 inches | 267 mm 10.5 inches |
| TDP | 64 W | 260 W |
| Vorgeschlagenes Netzteil | 250 W | 600 W |
| Ausgabe | 1x DVI1x HDMI1x DisplayPort | No outputs |
| Stromverbindung | None | 1x 6-pin + 1x 8-pin |
| Board-Nummer | C099 | PG150 SKU 215 |
Grafik-Features
| DirectX | 11.2 (11_0) | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | 4.4 | 4.6 |
| OpenCL | 1.2 | 3.0 |
| Vulkan | — | 1.2 |
| Shader-Modell | 5.0 | 6.6 |
| CUDA | — | 7.5 |
