Nom du GPU | GP104 | GA107 |
---|---|---|
GPU variant | GP104-150-KA-A1 | — |
Architecture | Pascal | Ampere |
Fonderie | TSMC | Samsung |
Taille du processus | 16 nm | 8 nm |
Transistors | 7,200 million | unknown |
Taille des matrices | 314 mm² | unknown |
Date de publication | Mar 8th, 2018 | — |
---|---|---|
Génération | GeForce 10 | — |
Prédécesseur | GeForce 900 | — |
Successeur | GeForce 20 | — |
Production | End-of-life | — |
Bus interface | PCIe 3.0 x16 | — |
Critiques | 117 in our database | — |
Base clock | 1506 MHz | 712 MHz |
---|---|---|
Boost clock | 1708 MHz | 1057 MHz |
Mémoire clock | 2002 MHz 8 Gbps effective | 1500 MHz 12 Gbps effective |
Taille de la mémoire | 6 GB | 4 GB |
---|---|---|
Type de mémoire | GDDR5 | GDDR6 |
Bus mémoire | 192 bit | 128 bit |
Bande passante | 192.2 GB/s | 192.0 GB/s |
Shading units | 1280 | 2048 |
---|---|---|
TMUs | 80 | 64 |
ROPs | 48 | 40 |
Comptage SM | 10 | 16 |
Cache L1 | 48 KB (per SM) | 128 KB (per SM) |
Cache L2 | 1536 KB | 2 MB |
Tensor cores | — | 64 |
RT cores | — | 16 |
Taux de pixel | 81.98 GPixel/s | 42.28 GPixel/s |
---|---|---|
Taux de texture | 136.6 GTexel/s | 67.65 GTexel/s |
FP16 (half) performance | 68.32 GFLOPS (1:64) | 4.329 TFLOPS (1:1) |
FP32 (float) performance | 4.372 TFLOPS | 4.329 TFLOPS |
FP64 (double) performance | 136.6 GFLOPS (1:32) | 67.65 GFLOPS (1:64) |
Taille Slot | Dual-slot | IGP |
---|---|---|
Longueur | 250 mm 9.8 inches | — |
TDP | 120 W | 75 W |
Suggestions pour le PSU | 300 W | — |
Sorties | 1x DVI1x HDMI3x DisplayPort | No outputs |
Connecteurs de puissance | 1x 6-pin | None |
Board number | PG410 SKU 10 | — |
DirectX | 12 (12_1) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 6.1 | 8.6 |
Shader model | 6.4 | 6.6 |
Date de publication | — | May 11th, 2021 |
---|---|---|
gpu.details.availability | — | 2021 |
Génération | — | GeForce 30 Mobile |
Prédécesseur | — | GeForce 20 Mobile |
Production | — | Active |
Bus interface | — | PCIe 4.0 x16 |