NVIDIA A100 SXM4 80 GB vs NVIDIA Tesla V100 SXM3 32 GB
Processeur graphique
| Nom du GPU | GA100 | GV100 |
|---|---|---|
| Architecture | Ampere | Volta |
| Fonderie | TSMC | TSMC |
| Taille du processus | 7 nm | 12 nm |
| Transistors | 54,200 million | 21,100 million |
| Taille des matrices | 826 mm² | 815 mm² |
Carte graphique
| Date de publication | Nov 16th, 2020 | Mar 27th, 2018 |
|---|---|---|
| Génération | Tesla | Tesla |
| Production | Active | End-of-life |
| Bus interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
Vitesse clock
| Base clock | 1275 MHz | 1290 MHz |
|---|---|---|
| Boost clock | 1410 MHz | 1530 MHz |
| Mémoire clock | 1593 MHz 3.2 Gbps effective | 876 MHz 1752 Mbps effective |
Mémoire
| Taille de la mémoire | 80 GB | 32 GB |
|---|---|---|
| Type de mémoire | HBM2e | HBM2 |
| Bus mémoire | 5120 bit | 4096 bit |
| Bande passante | 2,039 GB/s | 897.0 GB/s |
Render Config
| Shading units | 6912 | 5120 |
|---|---|---|
| TMUs | 432 | 320 |
| ROPs | 160 | 128 |
| Comptage SM | 108 | 80 |
| Tensor cores | 432 | 640 |
| Cache L1 | 192 KB (per SM) | 128 KB (per SM) |
| Cache L2 | 40 MB | 6 MB |
Performance théorique
| Taux de pixel | 225.6 GPixel/s | 195.8 GPixel/s |
|---|---|---|
| Taux de texture | 609.1 GTexel/s | 489.6 GTexel/s |
| FP16 (half) performance | 77.97 TFLOPS (4:1) | 31.33 TFLOPS (2:1) |
| FP32 (float) performance | 19.49 TFLOPS | 15.67 TFLOPS |
| FP64 (double) performance | 9.746 TFLOPS (1:2) | 7.834 TFLOPS (1:2) |
Board Design
| Taille Slot | IGP | Dual-slot |
|---|---|---|
| TDP | 400 W | 250 W |
| Suggestions pour le PSU | 800 W | 600 W |
| Sorties | No outputs | No outputs |
| Connecteurs de puissance | None | None |
Caractéristiques graphiques
| DirectX | — | 12 (12_1) |
|---|---|---|
| OpenGL | — | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | — | 1.2 |
| CUDA | 8.0 | 7.0 |
| Shader model | — | 6.6 |
