GPU model | TU106 | TU116 |
---|---|---|
GPU variant | TU106-100-A1 | TU116-250-KA-A1 |
Architecture | Turing | Turing |
Foundry | TSMC | TSMC |
Manufacturing process | 12 nm | 12 nm |
Number of transistors | 10,800 million | 6,600 million |
Die size | 445 mm² | 284 mm² |
Release date | Feb 25th, 2021 | Nov 22nd, 2019 |
---|---|---|
Generation | Mining GPUs | GeForce 16 |
Production | Active | Active |
Launch price | 699 USD | 159 USD |
Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Predecessor | — | GeForce 10 |
Successor | — | GeForce 20 |
Reviews | — | 27 in our database |
Base clock | 1470 MHz | 1530 MHz |
---|---|---|
Boost clock | 1650 MHz | 1725 MHz |
Memory clock | 1750 MHz 14 Gbps effective | 1500 MHz 12 Gbps effective |
Memory size | 8 GB | 4 GB |
---|---|---|
Memory type | GDDR6 | GDDR6 |
Memory bus width | 256 bit | 128 bit |
Bandwidth | 448.0 GB/s | 192.0 GB/s |
Shading units | 2304 | 1280 |
---|---|---|
TMUs | 144 | 80 |
ROPs | 64 | 32 |
SM count | 36 | 20 |
Tensor cores | 288 | — |
RT cores | 36 | — |
Cache L1 | 64 KB (per SM) | 64 KB (per SM) |
Cache L2 | 4 MB | 1024 KB |
Pixel rate | 105.6 GPixel/s | 55.20 GPixel/s |
---|---|---|
Texture rate | 237.6 GTexel/s | 138.0 GTexel/s |
FP16 (half) performance | 15.21 TFLOPS (2:1) | 8.832 TFLOPS (2:1) |
FP32 (float) performance | 7.603 TFLOPS | 4.416 TFLOPS |
FP64 (double) performance | 237.6 GFLOPS (1:32) | 138.0 GFLOPS (1:32) |
Slot width | Dual-slot | Dual-slot |
---|---|---|
Length | 229 mm 9 inches | 229 mm 9 inches |
Width | 111 mm 4.4 inches | 111 mm 4.4 inches |
Height | 35 mm 1.4 inches | 35 mm 1.4 inches |
TDP | 185 W | 100 W |
Suggested PSU | 450 W | 300 W |
Outputs | No outputs | 1x DVI1x HDMI1x DisplayPort |
Power connectors | 1x 8-pin | 1x 6-pin |
Board number | PG161 SKU 100 | PG166 SKU 24 |
DirectX | 12 Ultimate (12_2) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 7.5 | 7.5 |
Shader model | 6.6 | 6.6 |