ATI Radeon HD 4770 vs NVIDIA GRID M3-3020
Processeur graphique
| Nom du GPU | RV740 | GM107 |
|---|---|---|
| GPU variant | RV740 XT (215-0727019) | — |
| Architecture | TeraScale | Maxwell |
| Fonderie | TSMC | TSMC |
| Taille du processus | 40 nm | 28 nm |
| Transistors | 826 million | 1,870 million |
| Taille des matrices | 137 mm² | 148 mm² |
Carte graphique
| Date de publication | Apr 28th, 2009 | May 18th, 2016 |
|---|---|---|
| Génération | Radeon R700 | GRID |
| Production | End-of-life | End-of-life |
| Prix de lancement | 109 USD | — |
| Bus interface | PCIe 2.0 x16 | PCIe 3.0 x16 |
| Critiques | 82 in our database | — |
| Prédécesseur | Radeon R600 | — |
| Successeur | Evergreen | — |
Vitesse clock
| GPU clock | 750 MHz | — |
|---|---|---|
| Mémoire clock | 800 MHz 3.2 Gbps effective | 1300 MHz 5.2 Gbps effective |
| Base clock | — | 1033 MHz |
| Boost clock | — | 1306 MHz |
Mémoire
| Taille de la mémoire | 512 MB | 4 GB |
|---|---|---|
| Type de mémoire | GDDR5 | GDDR5 |
| Bus mémoire | 128 bit | 128 bit |
| Bande passante | 51.20 GB/s | 83.20 GB/s |
Render Config
| Shading units | 640 | 640 |
|---|---|---|
| TMUs | 32 | 40 |
| ROPs | 16 | 16 |
| Compute units | 8 | — |
| Cache L1 | 16 KB (per CU) | 64 KB (per SMM) |
| Cache L2 | 128 KB | 2 MB |
| Comptage SMM | — | 5 |
Performance théorique
| Taux de pixel | 12.00 GPixel/s | 20.90 GPixel/s |
|---|---|---|
| Taux de texture | 24.00 GTexel/s | 52.24 GTexel/s |
| FP32 (float) performance | 960.0 GFLOPS | 1.672 TFLOPS |
| FP64 (double) performance | 192.0 GFLOPS (1:5) | 52.24 GFLOPS (1:32) |
Board Design
| Taille Slot | Dual-slot | Dual-slot |
|---|---|---|
| Longueur | 203 mm 8 inches | 267 mm 10.5 inches |
| TDP | 80 W | unknown |
| Suggestions pour le PSU | 250 W | 200 W |
| Sorties | 2x DVI1x S-Video | No outputs |
| Connecteurs de puissance | 1x 6-pin | 1x 8-pin |
| Board number | B743 | — |
Caractéristiques graphiques
| DirectX | 10.1 (10_1) | 12 (11_0) |
|---|---|---|
| OpenGL | 3.3 | 4.6 |
| OpenCL | 1.1 | 3.0 |
| Vulkan | — | 1.1 |
| Shader model | 4.1 | 5.1 |
| CUDA | — | 5.0 |
