Nom du GPU | DG1 | GF104 |
---|---|---|
Architecture | Generation 12.1 | Fermi |
Fonderie | Intel | TSMC |
Taille du processus | 10 nm | 40 nm |
Transistors | unknown | 1,950 million |
Taille des matrices | 95 mm² | 332 mm² |
GPU variant | — | GF104-300-KB-A1 |
Date de publication | Oct 31st, 2020 | — |
---|---|---|
Génération | Iris Xe Graphics-M (Tiger Lake) | — |
Production | Active | — |
Bus interface | PCIe 4.0 x4 | — |
Critiques | 1 in our database | — |
Base clock | 300 MHz | — |
---|---|---|
Boost clock | 1650 MHz | — |
Mémoire clock | 2133 MHz 4.3 Gbps effective | 900 MHz 3.6 Gbps effective |
GPU clock | — | 675 MHz |
Shader clock | — | 1350 MHz |
Taille de la mémoire | 4 GB | 768 MB |
---|---|---|
Type de mémoire | LPDDR4X | GDDR5 |
Bus mémoire | 128 bit | 192 bit |
Bande passante | 68.26 GB/s | 86.40 GB/s |
Shading units | 768 | 336 |
---|---|---|
TMUs | 48 | 56 |
ROPs | 24 | 24 |
Unités d'exécution | 96 | — |
Cache L2 | 1024 KB | 384 KB |
gpu.details.l3-cache | 16 MB | — |
Comptage SM | — | 7 |
Cache L1 | — | 64 KB (per SM) |
Taux de pixel | 39.60 GPixel/s | 9.450 GPixel/s |
---|---|---|
Taux de texture | 79.20 GTexel/s | 37.80 GTexel/s |
FP16 (half) performance | 5.069 TFLOPS (2:1) | — |
FP32 (float) performance | 2.534 TFLOPS | 907.2 GFLOPS |
FP64 (double) performance | 633.6 GFLOPS (1:4) | 75.60 GFLOPS (1:12) |
Taille Slot | IGP | Dual-slot |
---|---|---|
TDP | 25 W | 160 W |
Sorties | No outputs | 2x DVI1x mini-HDMI |
Longueur | — | 210 mm 8.3 inches |
Suggestions pour le PSU | — | 450 W |
DirectX | 12 (12_1) | 12 (11_0) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 1.1 |
Vulkan | 1.2 | — |
Shader model | 6.4 | 5.1 |
CUDA | — | 2.1 |
Date de publication | — | Jul 12th, 2010 |
---|---|---|
Génération | — | GeForce 400 |
Production | — | End-of-life |
Prix de lancement | — | 199 USD |
Bus interface | — | PCIe 2.0 x16 |
Critiques | — | 154 in our database |
Prédécesseur | — | GeForce 200 |
Successeur | — | GeForce 500 |