ATI Radeon HD 5770 X2 vs NVIDIA GeForce GTS 450 OEM
Processeur graphique
| Nom du GPU | Juniper | GF106 |
|---|---|---|
| GPU variant | Juniper XT (215-0754013) | GF106-250-KB-A1 |
| Architecture | TeraScale 2 | Fermi |
| Fonderie | TSMC | TSMC |
| Taille du processus | 40 nm | 40 nm |
| Transistors | 1,040 million | 1,170 million |
| Taille des matrices | 166 mm² | 238 mm² |
Carte graphique
| Date de publication | Oct 13th, 2010 | Oct 11th, 2010 |
|---|---|---|
| Génération | Evergreen | GeForce 400 |
| Production | End-of-life | End-of-life |
| Bus interface | PCIe 2.0 x16 | PCIe 2.0 x16 |
| Critiques | 142 in our database | 80 in our database |
| Prédécesseur | Radeon R700 | GeForce 200 |
| Successeur | Northern Islands | GeForce 500 |
Vitesse clock
| GPU clock | 850 MHz | 790 MHz |
|---|---|---|
| Mémoire clock | 1200 MHz 4.8 Gbps effective | 1000 MHz 4 Gbps effective |
| Shader clock | — | 1580 MHz |
Mémoire
| Taille de la mémoire | 1024 MB | 1536 MB |
|---|---|---|
| Type de mémoire | GDDR5 | GDDR5 |
| Bus mémoire | 128 bit | 192 bit |
| Bande passante | 76.80 GB/s | 96.00 GB/s |
Render Config
| Shading units | 800 | 144 |
|---|---|---|
| TMUs | 40 | 24 |
| ROPs | 16 | 24 |
| Compute units | 10 | — |
| Cache L1 | 8 KB (per CU) | 64 KB (per SM) |
| Cache L2 | 256 KB | 384 KB |
| Comptage SM | — | 3 |
Performance théorique
| Taux de pixel | 13.60 GPixel/s | 4.740 GPixel/s |
|---|---|---|
| Taux de texture | 34.00 GTexel/s | 18.96 GTexel/s |
| FP32 (float) performance | 1,360 GFLOPS | 455.0 GFLOPS |
| FP64 (double) performance | — | 37.92 GFLOPS (1:12) |
Board Design
| Taille Slot | Dual-slot | Dual-slot |
|---|---|---|
| TDP | unknown | 106 W |
| Suggestions pour le PSU | 200 W | 300 W |
| Sorties | 2x DVI1x HDMI1x DisplayPort | 2x DVI1x mini-HDMI |
| Longueur | — | 210 mm 8.3 inches |
| Connecteurs de puissance | — | 1x 6-pin |
| Board number | — | P1060 |
Caractéristiques graphiques
| DirectX | 11.2 (11_0) | 12 (11_0) |
|---|---|---|
| OpenGL | 4.4 | 4.6 |
| OpenCL | 1.2 | 1.1 |
| Vulkan | — | — |
| Shader model | 5.0 | 5.1 |
| CUDA | — | 2.1 |
