AMD Radeon RX 550X 640SP vs NVIDIA GeForce GTX 460
Processeur graphique
| Nom du GPU | Baffin | GF104 |
|---|---|---|
| GPU variant | Baffin LE | GF104-300-KB-A1 |
| Architecture | GCN 4.0 | Fermi |
| Fonderie | GlobalFoundries | TSMC |
| Taille du processus | 14 nm | 40 nm |
| Transistors | 3,000 million | 1,950 million |
| Taille des matrices | 123 mm² | 332 mm² |
Carte graphique
| Date de publication | Apr 11th, 2018 | Jul 12th, 2010 |
|---|---|---|
| Génération | Polaris | GeForce 400 |
| Production | Active | End-of-life |
| Bus interface | PCIe 3.0 x8 | PCIe 2.0 x16 |
| Prédécesseur | Polaris | GeForce 200 |
| Successeur | Vega | GeForce 500 |
| Prix de lancement | — | 199 USD |
| Critiques | — | 154 in our database |
Vitesse clock
| Base clock | 1019 MHz | — |
|---|---|---|
| Boost clock | 1071 MHz | — |
| Mémoire clock | 1500 MHz 6 Gbps effective | 900 MHz 3.6 Gbps effective |
| GPU clock | — | 675 MHz |
| Shader clock | — | 1350 MHz |
Mémoire
| Taille de la mémoire | 2 GB | 768 MB |
|---|---|---|
| Type de mémoire | GDDR5 | GDDR5 |
| Bus mémoire | 128 bit | 192 bit |
| Bande passante | 96.00 GB/s | 86.40 GB/s |
Render Config
| Shading units | 640 | 336 |
|---|---|---|
| TMUs | 40 | 56 |
| ROPs | 16 | 24 |
| Compute units | 10 | — |
| Cache L1 | 16 KB (per CU) | 64 KB (per SM) |
| Cache L2 | 1024 KB | 384 KB |
| Comptage SM | — | 7 |
Performance théorique
| Taux de pixel | 17.14 GPixel/s | 9.450 GPixel/s |
|---|---|---|
| Taux de texture | 42.84 GTexel/s | 37.80 GTexel/s |
| FP16 (half) performance | 1,371 GFLOPS (1:1) | — |
| FP32 (float) performance | 1,371 GFLOPS | 907.2 GFLOPS |
| FP64 (double) performance | 85.68 GFLOPS (1:16) | 75.60 GFLOPS (1:12) |
Board Design
| Taille Slot | Dual-slot | Dual-slot |
|---|---|---|
| Longueur | 145 mm 5.7 inches | 210 mm 8.3 inches |
| TDP | 60 W | 160 W |
| Suggestions pour le PSU | 250 W | 450 W |
| Sorties | 1x DVI1x HDMI1x DisplayPort | 2x DVI1x mini-HDMI |
| Connecteurs de puissance | None | — |
| Board number | D090-21 | — |
Caractéristiques graphiques
| DirectX | 12 (12_0) | 12 (11_0) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 1.1 |
| Vulkan | 1.2 | — |
| Shader model | 6.4 | 5.1 |
| CUDA | — | 2.1 |
