GPU model | TU116 | GP104 |
---|---|---|
GPU variant | TU116-300-A1 | GP104-875-A1 |
Architecture | Turing | Pascal |
Foundry | TSMC | TSMC |
Manufacturing process | 12 nm | 16 nm |
Number of transistors | 6,600 million | 7,200 million |
Die size | 284 mm² | 314 mm² |
Release date | Oct 29th, 2019 | Oct 1st, 2016 |
---|---|---|
Generation | GeForce 16 | Quadro |
Predecessor | GeForce 10 | — |
Successor | GeForce 20 | — |
Production | Active | End-of-life |
Launch price | 229 USD | 2,499 USD |
Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Reviews | 42 in our database | — |
Base clock | 1530 MHz | 1607 MHz |
---|---|---|
Boost clock | 1785 MHz | 1733 MHz |
Memory clock | 1750 MHz 14 Gbps effective | 1127 MHz 9 Gbps effective |
Memory size | 6 GB | 16 GB |
---|---|---|
Memory type | GDDR6 | GDDR5X |
Memory bus width | 192 bit | 256 bit |
Bandwidth | 336.0 GB/s | 288.5 GB/s |
Shading units | 1408 | 2560 |
---|---|---|
TMUs | 88 | 160 |
ROPs | 48 | 64 |
SM count | 22 | 20 |
Cache L1 | 64 KB (per SM) | 48 KB (per SM) |
Cache L2 | 1536 KB | 2 MB |
Pixel rate | 85.68 GPixel/s | 110.9 GPixel/s |
---|---|---|
Texture rate | 157.1 GTexel/s | 277.3 GTexel/s |
FP16 (half) performance | 10.05 TFLOPS (2:1) | 138.6 GFLOPS (1:64) |
FP32 (float) performance | 5.027 TFLOPS | 8.873 TFLOPS |
FP64 (double) performance | 157.1 GFLOPS (1:32) | 277.3 GFLOPS (1:32) |
Slot width | Dual-slot | Dual-slot |
---|---|---|
Length | 229 mm 9 inches | 267 mm 10.5 inches |
Width | 111 mm 4.4 inches | 111 mm 4.4 inches |
Height | 35 mm 1.4 inches | — |
TDP | 125 W | 180 W |
Suggested PSU | 300 W | 450 W |
Outputs | 1x DVI1x HDMI1x DisplayPort | 1x DVI4x DisplayPort |
Power connectors | 1x 8-pin | 1x 8-pin |
Board number | PG161 SKU 26 | PG413 SKU 500 |
DirectX | 12 (12_1) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 7.5 | 6.1 |
Shader model | 6.6 | 6.4 |