Nom du GPU | NV28 | GV10B |
---|---|---|
GPU variant | NV28M A1 | — |
Architecture | Kelvin | Volta |
Fonderie | TSMC | TSMC |
Taille du processus | 150 nm | 12 nm |
Transistors | 36 million | 9,000 million |
Taille des matrices | 101 mm² | 350 mm² |
Date de publication | Mar 15th, 2003 | — |
---|---|---|
Génération | GeForce 4 Ti | — |
Production | End-of-life | — |
Bus interface | AGP 8x | — |
Prédécesseur | GeForce 4 MX | — |
Successeur | GeForce FX | — |
GPU clock | 300 MHz | — |
---|---|---|
Mémoire clock | 325 MHz 650 Mbps effective | System Shared |
Base clock | — | 854 MHz |
Boost clock | — | 1377 MHz |
Taille de la mémoire | 128 MB | System Shared |
---|---|---|
Type de mémoire | DDR | System Shared |
Bus mémoire | 128 bit | System Shared |
Bande passante | 10.40 GB/s | System Dependent |
Pixel shaders | 4 | — |
---|---|---|
Vertex shaders | 2 | — |
TMUs | 8 | 24 |
ROPs | 4 | 16 |
Shading units | — | 384 |
Comptage SM | — | 6 |
Tensor cores | — | 48 |
Cache L1 | — | 128 KB (per SM) |
Cache L2 | — | 256 KB |
Taux de pixel | 1.200 GPixel/s | 22.03 GPixel/s |
---|---|---|
Vertex rate | 150.0 MVertices/s | — |
Taux de texture | 2.400 GTexel/s | 33.05 GTexel/s |
FP16 (half) performance | — | 2.115 TFLOPS (2:1) |
FP32 (float) performance | — | 1,058 GFLOPS |
FP64 (double) performance | — | 528.8 GFLOPS (1:2) |
Taille Slot | Single-slot | IGP |
---|---|---|
Longueur | 216 mm 8.5 inches | 70 mm 2.8 inches |
TDP | unknown | 15 W |
Suggestions pour le PSU | 200 W | — |
Sorties | 1x DVI1x VGA1x S-Video | No outputs |
Connecteurs de puissance | None | — |
Taille | — | 45 mm 1.8 inches |
DirectX | 8.1 | 12 (12_1) |
---|---|---|
OpenGL | 1.5 | 4.6 |
OpenCL | — | 1.2 |
Vulkan | — | 1.2 |
Pixel shader | 1.3 | — |
Vertex shader | 1.1 | — |
CUDA | — | 7.2 |
Shader model | — | 6.4 |
Date de publication | — | May 14th, 2020 |
---|---|---|
Génération | — | Tegra |
Production | — | End-of-life |
Prix de lancement | — | 399 USD |
Bus interface | — | IGP |