GPU model | TU116 | GA106 |
---|---|---|
GPU variant | TU116-250-KA-A1 | GA106-150-A1 |
Architecture | Turing | Ampere |
Foundry | TSMC | Samsung |
Manufacturing process | 12 nm | 8 nm |
Number of transistors | 6,600 million | 13,250 million |
Die size | 284 mm² | 276 mm² |
Release date | Nov 22nd, 2019 | 2022 |
---|---|---|
Generation | GeForce 16 | GeForce 30 |
Predecessor | GeForce 10 | GeForce 20 |
Successor | GeForce 20 | — |
Production | Active | Unreleased |
Interface | PCIe 3.0 x16 | PCIe 4.0 x16 |
Reviews | 27 in our database | — |
Launch price | 159 USD | — |
gpu.details.availability | — | 2022 |
Base clock | 1530 MHz | 1552 MHz |
---|---|---|
Boost clock | 1725 MHz | 1777 MHz |
Memory clock | 1500 MHz 12 Gbps effective | 1750 MHz 14 Gbps effective |
Memory size | 4 GB | 8 GB |
---|---|---|
Memory type | GDDR6 | GDDR6 |
Memory bus width | 128 bit | 128 bit |
Bandwidth | 192.0 GB/s | 224.0 GB/s |
Shading units | 1280 | 2560 |
---|---|---|
TMUs | 80 | 80 |
ROPs | 32 | 48 |
SM count | 20 | 20 |
Cache L1 | 64 KB (per SM) | 128 KB (per SM) |
Cache L2 | 1024 KB | 2 MB |
Tensor cores | — | 80 |
RT cores | — | 20 |
Pixel rate | 55.20 GPixel/s | 85.30 GPixel/s |
---|---|---|
Texture rate | 138.0 GTexel/s | 142.2 GTexel/s |
FP16 (half) performance | 8.832 TFLOPS (2:1) | 9.098 TFLOPS (1:1) |
FP32 (float) performance | 4.416 TFLOPS | 9.098 TFLOPS |
FP64 (double) performance | 138.0 GFLOPS (1:32) | 142.2 GFLOPS (1:64) |
Slot width | Dual-slot | Dual-slot |
---|---|---|
Length | 229 mm 9 inches | 242 mm 9.5 inches |
Width | 111 mm 4.4 inches | 112 mm 4.4 inches |
Height | 35 mm 1.4 inches | — |
TDP | 100 W | 90 W |
Suggested PSU | 300 W | 250 W |
Outputs | 1x DVI1x HDMI1x DisplayPort | 1x HDMI3x DisplayPort |
Power connectors | 1x 6-pin | 1x 6-pin |
Board number | PG166 SKU 24 | — |
DirectX | 12 (12_1) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 7.5 | 8.6 |
Shader model | 6.6 | 6.6 |