NVIDIA A100 PCIe vs NVIDIA Quadro4 380 XGL
Processeur graphique
| Nom du GPU | GA100 | NV18 |
|---|---|---|
| Architecture | Ampere | Celsius |
| Fonderie | TSMC | TSMC |
| Taille du processus | 7 nm | 150 nm |
| Transistors | 54,200 million | 29 million |
| Taille des matrices | 826 mm² | 65 mm² |
Carte graphique
| Date de publication | Jun 22nd, 2020 | Nov 12th, 2002 |
|---|---|---|
| Génération | Tesla | Quadro4 XGL |
| Production | Active | End-of-life |
| Bus interface | PCIe 4.0 x16 | AGP 8x |
| Critiques | — | 26 in our database |
Vitesse clock
| GPU clock | 1410 MHz | 275 MHz |
|---|---|---|
| Mémoire clock | 1215 MHz 2.4 Gbps effective | 256 MHz 512 Mbps effective |
| Base clock | 765 MHz | — |
| Boost clock | 1410 MHz | — |
Mémoire
| Taille de la mémoire | 40 GB | 128 MB |
|---|---|---|
| Type de mémoire | HBM2E | DDR |
| Bus mémoire | 5120 bit | 128 bit |
| Bande passante | 1,555 GB/s | 8.192 GB/s |
Render Config
| Shading units | 6912 | — |
|---|---|---|
| TMUs | 432 | 4 |
| ROPs | 160 | 4 |
| Comptage SM | 108 | — |
| Tensor cores | 432 | — |
| Cache L1 | 192 KB (per SM) | — |
| Cache L2 | 40 MB | — |
| Pixel shaders | — | 2 |
| Vertex shaders | — | 0 |
Performance théorique
| Taux de pixel | 225.6 GPixel/s | 1.100 GPixel/s |
|---|---|---|
| Taux de texture | 609.1 GTexel/s | 1.100 GTexel/s |
| FP16 (half) performance | 77.97 TFLOPS (4:1) | — |
| FP32 (float) performance | 19.49 TFLOPS | — |
| FP64 (double) performance | 9.746 TFLOPS (1:2) | — |
Board Design
| Taille Slot | Dual-slot | Single-slot |
|---|---|---|
| Longueur | 267 mm 10.5 inches | — |
| TDP | 250 W | unknown |
| Suggestions pour le PSU | 600 W | 200 W |
| Sorties | No outputs | 1x DVI1x VGA1x S-Video |
| Connecteurs de puissance | 8-pin EPS | None |
| Board number | P1001 SKU 200 | — |
Caractéristiques graphiques
| DirectX | — | 7.0 |
|---|---|---|
| OpenGL | — | 1.5 |
| OpenCL | 3.0 | — |
| Vulkan | — | — |
| CUDA | 8.0 | — |
| Shader model | — | — |
| Pixel shader | — | 1.1 |
| Vertex shader | — | 1.1 |
