NVIDIA GeForce GT 630 Rev. 2 vs NVIDIA GRID A100B
Processeur graphique
| Nom du GPU | GK208 | GA100 |
|---|---|---|
| GPU variant | GK208-301-A1 | — |
| Architecture | Kepler 2.0 | Ampere |
| Fonderie | TSMC | TSMC |
| Taille du processus | 28 nm | 7 nm |
| Transistors | 1,020 million | 54,200 million |
| Taille des matrices | 87 mm² | 826 mm² |
Carte graphique
| Date de publication | May 29th, 2013 | May 14th, 2020 |
|---|---|---|
| Génération | GeForce 600 | GRID |
| Production | End-of-life | Active |
| Bus interface | PCIe 2.0 x8 | PCIe 4.0 x16 |
| Prédécesseur | GeForce 500 | — |
| Successeur | GeForce 700 | — |
Vitesse clock
| GPU clock | 902 MHz | — |
|---|---|---|
| Mémoire clock | 900 MHz 1800 Mbps effective | 1215 MHz 2.4 Gbps effective |
| Base clock | — | 900 MHz |
| Boost clock | — | 1005 MHz |
Mémoire
| Taille de la mémoire | 2 GB | 48 GB |
|---|---|---|
| Type de mémoire | DDR3 | HBM2E |
| Bus mémoire | 64 bit | 6144 bit |
| Bande passante | 14.40 GB/s | 1,866 GB/s |
Render Config
| Shading units | 384 | 6912 |
|---|---|---|
| TMUs | 32 | 432 |
| ROPs | 8 | 192 |
| Comptage SMX | 2 | — |
| Cache L1 | 16 KB (per SMX) | 192 KB (per SM) |
| Cache L2 | 512 KB | 48 MB |
| Comptage SM | — | 108 |
| Tensor cores | — | 432 |
Performance théorique
| Taux de pixel | 7.216 GPixel/s | 193.0 GPixel/s |
|---|---|---|
| Taux de texture | 28.86 GTexel/s | 434.2 GTexel/s |
| FP32 (float) performance | 692.7 GFLOPS | 13.89 TFLOPS |
| FP64 (double) performance | 28.86 GFLOPS (1:24) | 6.947 TFLOPS (1:2) |
| FP16 (half) performance | — | 55.57 TFLOPS (4:1) |
Board Design
| Taille Slot | Single-slot | IGP |
|---|---|---|
| Longueur | 145 mm 5.7 inches | — |
| TDP | 25 W | 400 W |
| Suggestions pour le PSU | 200 W | 800 W |
| Sorties | 1x DVI1x HDMI1x VGA | No outputs |
| Connecteurs de puissance | None | None |
| Board number | P2132 | — |
Caractéristiques graphiques
| DirectX | 12 (11_0) | — |
|---|---|---|
| OpenGL | 4.6 | — |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.1 | — |
| CUDA | 3.5 | 8.0 |
| Shader model | 5.1 | — |
