AMD Radeon R7 260 vs NVIDIA Tesla C2075
Processeur graphique
| Nom du GPU | Bonaire | GF110 |
|---|---|---|
| GPU variant | Bonaire PRO | GF110-351-A1 |
| Architecture | GCN 2.0 | Fermi 2.0 |
| Fonderie | TSMC | TSMC |
| Taille du processus | 28 nm | 40 nm |
| Transistors | 2,080 million | 3,000 million |
| Taille des matrices | 160 mm² | 520 mm² |
Carte graphique
| Date de publication | Dec 17th, 2013 | Jul 25th, 2011 |
|---|---|---|
| Génération | Volcanic Islands | Tesla |
| Production | End-of-life | End-of-life |
| Prix de lancement | 109 USD | — |
| Bus interface | PCIe 3.0 x16 | PCIe 2.0 x16 |
| Critiques | 10 in our database | — |
| Prédécesseur | Sea Islands | — |
| Successeur | Pirate Islands | — |
Vitesse clock
| GPU clock | 1000 MHz | 574 MHz |
|---|---|---|
| Mémoire clock | 1500 MHz 6 Gbps effective | 783 MHz 3.1 Gbps effective |
| Shader clock | — | 1147 MHz |
Mémoire
| Taille de la mémoire | 2 GB | 6 GB |
|---|---|---|
| Type de mémoire | GDDR5 | GDDR5 |
| Bus mémoire | 128 bit | 384 bit |
| Bande passante | 96.00 GB/s | 150.3 GB/s |
Render Config
| Shading units | 768 | 448 |
|---|---|---|
| TMUs | 48 | 56 |
| ROPs | 16 | 48 |
| Compute units | 12 | — |
| Cache L1 | 16 KB (per CU) | 64 KB (per SM) |
| Cache L2 | 256 KB | 768 KB |
| Comptage SM | — | 14 |
Performance théorique
| Taux de pixel | 16.00 GPixel/s | 16.07 GPixel/s |
|---|---|---|
| Taux de texture | 48.00 GTexel/s | 32.14 GTexel/s |
| FP32 (float) performance | 1.536 TFLOPS | 1,028 GFLOPS |
| FP64 (double) performance | 96.00 GFLOPS (1:16) | 513.9 GFLOPS (1:2) |
Board Design
| Taille Slot | Dual-slot | Dual-slot |
|---|---|---|
| Longueur | 170 mm 6.7 inches | 248 mm 9.8 inches |
| TDP | 95 W | 247 W |
| Suggestions pour le PSU | 250 W | 550 W |
| Sorties | 1x DVI1x HDMI1x DisplayPort | 1x DVI |
| Connecteurs de puissance | 1x 6-pin | 1x 6-pin + 1x 8-pin |
| Board number | C582 | P1030 |
Caractéristiques graphiques
| DirectX | 12 (12_0) | 12 (11_0) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 1.1 |
| Vulkan | 1.2 | — |
| Shader model | 6.3 | 5.1 |
| CUDA | — | 2.0 |
