NVIDIA GeForce GTX 560 Ti 448 vs NVIDIA GRID A100A
Processeur graphique
| Nom du GPU | GF110 | GA100 |
|---|---|---|
| GPU variant | GF110-270-A1 | — |
| Architecture | Fermi 2.0 | Ampere |
| Fonderie | TSMC | TSMC |
| Taille du processus | 40 nm | 7 nm |
| Transistors | 3,000 million | 54,200 million |
| Taille des matrices | 520 mm² | 826 mm² |
Carte graphique
| Date de publication | Nov 29th, 2011 | May 14th, 2020 |
|---|---|---|
| Génération | GeForce 500 | GRID |
| Production | End-of-life | Active |
| Prix de lancement | 289 USD | — |
| Bus interface | PCIe 2.0 x16 | PCIe 4.0 x16 |
| Critiques | 36 in our database | — |
| Prédécesseur | GeForce 400 | — |
| Successeur | GeForce 600 | — |
Vitesse clock
| GPU clock | 732 MHz | — |
|---|---|---|
| Shader clock | 1464 MHz | — |
| Mémoire clock | 950 MHz 3.8 Gbps effective | 1215 MHz 2.4 Gbps effective |
| Base clock | — | 900 MHz |
| Boost clock | — | 1005 MHz |
Mémoire
| Taille de la mémoire | 1280 MB | 48 GB |
|---|---|---|
| Type de mémoire | GDDR5 | HBM2E |
| Bus mémoire | 320 bit | 6144 bit |
| Bande passante | 152.0 GB/s | 1,866 GB/s |
Render Config
| Shading units | 448 | 6912 |
|---|---|---|
| TMUs | 56 | 432 |
| ROPs | 40 | 192 |
| Comptage SM | 14 | 108 |
| Cache L1 | 64 KB (per SM) | 192 KB (per SM) |
| Cache L2 | 640 KB | 48 MB |
| Tensor cores | — | 432 |
Performance théorique
| Taux de pixel | 20.50 GPixel/s | 193.0 GPixel/s |
|---|---|---|
| Taux de texture | 40.99 GTexel/s | 434.2 GTexel/s |
| FP32 (float) performance | 1,312 GFLOPS | 13.89 TFLOPS |
| FP64 (double) performance | 164.0 GFLOPS (1:8) | 6.947 TFLOPS (1:2) |
| FP16 (half) performance | — | 55.57 TFLOPS (4:1) |
Board Design
| Taille Slot | Dual-slot | IGP |
|---|---|---|
| Longueur | 267 mm 10.5 inches | — |
| TDP | 210 W | 400 W |
| Suggestions pour le PSU | 550 W | 800 W |
| Sorties | 2x DVI1x mini-HDMI | No outputs |
| Connecteurs de puissance | 2x 6-pin | None |
| Board number | P1263 | — |
Caractéristiques graphiques
| DirectX | 12 (11_0) | — |
|---|---|---|
| OpenGL | 4.6 | — |
| OpenCL | 1.1 | 3.0 |
| Vulkan | — | — |
| CUDA | 2.0 | 8.0 |
| Shader model | 5.1 | — |
