GPU model | TU116 | C51 |
---|---|---|
GPU variant | TU116-250-KA-A1 | — |
Architecture | Turing | Curie |
Foundry | TSMC | — |
Manufacturing process | 12 nm | 90 nm |
Number of transistors | 6,600 million | unknown |
Die size | 284 mm² | unknown |
Release date | Nov 22nd, 2019 | — |
---|---|---|
Generation | GeForce 16 | — |
Predecessor | GeForce 10 | — |
Successor | GeForce 20 | — |
Production | Active | — |
Interface | PCIe 3.0 x16 | — |
Reviews | 27 in our database | — |
Launch price | 159 USD | — |
Base clock | 1530 MHz | — |
---|---|---|
Boost clock | 1725 MHz | — |
Memory clock | 1500 MHz 12 Gbps effective | System Shared |
GPU clock | — | 425 MHz |
Memory size | 4 GB | System Shared |
---|---|---|
Memory type | GDDR6 | System Shared |
Memory bus width | 128 bit | System Shared |
Bandwidth | 192.0 GB/s | System Dependent |
Shading units | 1280 | — |
---|---|---|
TMUs | 80 | 2 |
ROPs | 32 | 1 |
SM count | 20 | — |
Cache L1 | 64 KB (per SM) | — |
Cache L2 | 1024 KB | — |
Pixel shaders | — | 2 |
Vertex shaders | — | 1 |
Pixel rate | 55.20 GPixel/s | 425.0 MPixel/s |
---|---|---|
Texture rate | 138.0 GTexel/s | 850.0 MTexel/s |
FP16 (half) performance | 8.832 TFLOPS (2:1) | — |
FP32 (float) performance | 4.416 TFLOPS | — |
FP64 (double) performance | 138.0 GFLOPS (1:32) | — |
Vertex rate | — | 106.3 MVertices/s |
Slot width | Dual-slot | IGP |
---|---|---|
Length | 229 mm 9 inches | — |
Width | 111 mm 4.4 inches | — |
Height | 35 mm 1.4 inches | — |
TDP | 100 W | 11 W |
Suggested PSU | 300 W | — |
Outputs | 1x DVI1x HDMI1x DisplayPort | No outputs |
Power connectors | 1x 6-pin | — |
Board number | PG166 SKU 24 | — |
DirectX | 12 (12_1) | 9.0c (9_3) |
---|---|---|
OpenGL | 4.6 | 2.1 |
OpenCL | 3.0 | — |
Vulkan | 1.2 | — |
CUDA | 7.5 | — |
Shader model | 6.6 | 3.0 |
Release date | — | Dec 22nd, 2003 |
---|---|---|
Generation | — | Quadro NVS IGP |
Production | — | End-of-life |
Interface | — | PCI |
Reviews | — | 26 in our database |