Nom du GPU | Aldebaran | NV18 |
---|---|---|
GPU variant | Aldebaran XT | — |
Architecture | CDNA 2.0 | Celsius |
Fonderie | TSMC | TSMC |
Taille du processus | 6 nm | 150 nm |
Transistors | 58,200 million | 29 million |
Taille des matrices | unknown | 65 mm² |
Date de publication | Nov 8th, 2021 | Nov 12th, 2002 |
---|---|---|
Génération | Radeon Instinct | Quadro4 XGL |
Production | unknown | End-of-life |
Bus interface | PCIe 4.0 x16 | AGP 8x |
Critiques | — | 26 in our database |
Base clock | 1000 MHz | — |
---|---|---|
Boost clock | 1700 MHz | — |
Mémoire clock | 1600 MHz 3.2 Gbps effective | 200 MHz 400 Mbps effective |
GPU clock | — | 300 MHz |
Taille de la mémoire | 128 GB | 64 MB |
---|---|---|
Type de mémoire | HBM2E | DDR |
Bus mémoire | 8192 bit | 128 bit |
Bande passante | 3,277 GB/s | 6.400 GB/s |
Shading units | 14080 | — |
---|---|---|
TMUs | 880 | 4 |
ROPs | 0 | 4 |
Compute units | 220 | — |
Cache L1 | 16 KB (per CU) | — |
Cache L2 | 16 MB | — |
gpu.details.mcm | 2 | — |
Pixel shaders | — | 2 |
Vertex shaders | — | 0 |
Taux de pixel | 0 MPixel/s | 1.200 GPixel/s |
---|---|---|
Taux de texture | 1,496 GTexel/s | 1.200 GTexel/s |
FP16 (half) performance | 383.0 TFLOPS (8:1) | — |
FP32 (float) performance | 47.87 TFLOPS | — |
FP64 (double) performance | 47.87 TFLOPS (1:1) | — |
Taille Slot | Dual-slot | Single-slot |
---|---|---|
Longueur | 267 mm 10.5 inches | — |
Taille | 111 mm 4.4 inches | — |
TDP | 500 W | unknown |
Suggestions pour le PSU | 900 W | 200 W |
Sorties | No outputs | 1x LFH60 |
Connecteurs de puissance | 2x 8-pin | None |
DirectX | — | 7.0 |
---|---|---|
OpenGL | — | 1.5 |
OpenCL | 3.0 | — |
Vulkan | — | — |
Shader model | — | — |
Pixel shader | — | 1.1 |
Vertex shader | — | 1.1 |