NVIDIA A100 PCIe vs NVIDIA Quadro4 900 XGL
Grafikprozessor
| GPU Name | GA100 | NV25 |
|---|---|---|
| Architektur | Ampere | Kelvin |
| Hersteller | TSMC | TSMC |
| Prozessgröße | 7 nm | 150 nm |
| Transistoren | 54,200 million | 63 million |
| Chipgröße | 826 mm² | 142 mm² |
| GPU Variante | — | NV25 GL |
Grafikkarte
| Veröffentlichungsdatum | Jun 22nd, 2020 | Feb 19th, 2002 |
|---|---|---|
| Generation | Tesla | Quadro4 XGL |
| Produktion | Active | End-of-life |
| Businterface | PCIe 4.0 x16 | AGP 4x |
| Reviews | — | 26 in our database |
Takt-Geschwindigkeiten
| GPU-Taktung | 1410 MHz | 300 MHz |
|---|---|---|
| Speicher-Taktung | 1215 MHz 2.4 Gbps effective | 325 MHz 650 Mbps effective |
| Basis-Taktfrequenz | 765 MHz | — |
| Boost-Takt | 1410 MHz | — |
Speicher
| Speichergröße | 40 GB | 128 MB |
|---|---|---|
| Speichertyp | HBM2E | DDR |
| Speicherbus | 5120 bit | 128 bit |
| Bandbreite | 1,555 GB/s | 10.40 GB/s |
Render-Konfiguration
| Shading-Einheiten | 6912 | — |
|---|---|---|
| TMUs | 432 | 8 |
| ROPs | 160 | 8 |
| Anzahl SM | 108 | — |
| Tensor Cores | 432 | — |
| Cache L1 | 192 KB (per SM) | — |
| Cache L2 | 40 MB | — |
| Pixelshader | — | 4 |
| Vertex-Shader | — | 2 |
Theoretische Leistung
| Pixelrate | 225.6 GPixel/s | 2.400 GPixel/s |
|---|---|---|
| Texturrate | 609.1 GTexel/s | 2.400 GTexel/s |
| FP16 (half) Leistung | 77.97 TFLOPS (4:1) | — |
| FP32 (float) Leistung | 19.49 TFLOPS | — |
| FP64 (double) Leistung | 9.746 TFLOPS (1:2) | — |
| Vertex-Rate | — | 150.0 MVertices/s |
Boarddesign
| Steckplatzbreite | Dual-slot | Single-slot |
|---|---|---|
| Länge | 267 mm 10.5 inches | — |
| TDP | 250 W | unknown |
| Vorgeschlagenes Netzteil | 600 W | 200 W |
| Ausgabe | No outputs | 2x DVI1x S-Video |
| Stromverbindung | 8-pin EPS | None |
| Board-Nummer | P1001 SKU 200 | — |
Grafik-Features
| DirectX | — | 8.1 |
|---|---|---|
| OpenGL | — | 1.5 |
| OpenCL | 3.0 | — |
| Vulkan | — | — |
| CUDA | 8.0 | — |
| Shader-Modell | — | — |
| Pixelshader | — | 1.3 |
| Vertex-Shader | — | 1.1 |
