AMD Radeon HD 7650A vs NVIDIA GeForce RTX 2080
Processeur graphique
| Nom du GPU | Onega | TU104 |
|---|---|---|
| Architecture | TeraScale 2 | Turing |
| Fonderie | TSMC | TSMC |
| Taille du processus | 40 nm | 12 nm |
| Transistors | 716 million | 13,600 million |
| Taille des matrices | 118 mm² | 545 mm² |
| GPU variant | — | TU104-400A-A1 |
Graphiques mobiles
| Date de publication | Jan 5th, 2012 | — |
|---|---|---|
| Génération | All-In-One (HD 7000) | — |
| Production | End-of-life | — |
| Bus interface | MXM-A (3.0) | — |
Vitesse clock
| GPU clock | 600 MHz | — |
|---|---|---|
| Mémoire clock | 900 MHz 1800 Mbps effective | 1750 MHz 14 Gbps effective |
| Base clock | — | 1515 MHz |
| Boost clock | — | 1710 MHz |
Mémoire
| Taille de la mémoire | 1024 MB | 8 GB |
|---|---|---|
| Type de mémoire | DDR3 | GDDR6 |
| Bus mémoire | 128 bit | 256 bit |
| Bande passante | 28.80 GB/s | 448.0 GB/s |
Render Config
| Shading units | 480 | 2944 |
|---|---|---|
| TMUs | 24 | 184 |
| ROPs | 8 | 64 |
| Compute units | 6 | — |
| Cache L1 | 8 KB (per CU) | 64 KB (per SM) |
| Cache L2 | 256 KB | 4 MB |
| Comptage SM | — | 46 |
| Tensor cores | — | 368 |
| RT cores | — | 46 |
Performance théorique
| Taux de pixel | 4.800 GPixel/s | 109.4 GPixel/s |
|---|---|---|
| Taux de texture | 14.40 GTexel/s | 314.6 GTexel/s |
| FP32 (float) performance | 576.0 GFLOPS | 10.07 TFLOPS |
| FP16 (half) performance | — | 20.14 TFLOPS (2:1) |
| FP64 (double) performance | — | 314.6 GFLOPS (1:32) |
Board Design
| Taille Slot | MXM Module | Dual-slot |
|---|---|---|
| TDP | 33 W | 215 W |
| Sorties | No outputs | 1x HDMI3x DisplayPort1x USB Type-C |
| Longueur | — | 267 mm 10.5 inches |
| Taille | — | 116 mm 4.6 inches |
| Taille | — | 35 mm 1.4 inches |
| Suggestions pour le PSU | — | 550 W |
| Connecteurs de puissance | — | 1x 6-pin + 1x 8-pin |
| Board number | — | PG180 SKU 2 |
Caractéristiques graphiques
| DirectX | 11.2 (11_0) | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | 4.4 | 4.6 |
| OpenCL | 1.2 | 3.0 |
| Vulkan | — | 1.2 |
| Shader model | 5.0 | 6.6 |
| CUDA | — | 7.5 |
AUTRES CARACTÉRISTIQUES
Carte graphique
| Date de publication | — | Sep 20th, 2018 |
|---|---|---|
| Génération | — | GeForce 20 |
| Prédécesseur | — | GeForce 10 |
| Production | — | Active |
| Prix de lancement | — | 699 USD |
| Prix courant | — | Amazon / Newegg |
| Bus interface | — | PCIe 3.0 x16 |
| Critiques | — | 66 in our database |
| Successeur | — | GeForce 30 |
