GPU model | TU106 | GM107 |
---|---|---|
GPU variant | TU106-125-A1 | N16P-GT |
Architecture | Turing | Maxwell |
Foundry | TSMC | TSMC |
Manufacturing process | 12 nm | 28 nm |
Number of transistors | 10,800 million | 1,870 million |
Die size | 445 mm² | 148 mm² |
Release date | Jun 18th, 2020 | — |
---|---|---|
Generation | GeForce 16 | — |
Predecessor | GeForce 10 | — |
Successor | GeForce 20 | — |
Production | Active | — |
Interface | PCIe 3.0 x16 | — |
Base clock | 1410 MHz | 993 MHz |
---|---|---|
Boost clock | 1590 MHz | 1124 MHz |
Memory clock | 1500 MHz 12 Gbps effective | 900 MHz 1800 Mbps effective |
Memory size | 4 GB | 4 GB |
---|---|---|
Memory type | GDDR6 | DDR3 |
Memory bus width | 128 bit | 128 bit |
Bandwidth | 192.0 GB/s | 28.80 GB/s |
Shading units | 896 | 640 |
---|---|---|
TMUs | 56 | 40 |
ROPs | 32 | 16 |
SM count | 14 | — |
Tensor cores | 112 | — |
RT cores | 14 | — |
Cache L1 | 64 KB (per SM) | 64 KB (per SMM) |
Cache L2 | 1024 KB | 2 MB |
SMM count | — | 5 |
Pixel rate | 50.88 GPixel/s | 17.98 GPixel/s |
---|---|---|
Texture rate | 89.04 GTexel/s | 44.96 GTexel/s |
FP16 (half) performance | 5.699 TFLOPS (2:1) | — |
FP32 (float) performance | 2.849 TFLOPS | 1,439 GFLOPS |
FP64 (double) performance | 89.04 GFLOPS (1:32) | 44.96 GFLOPS (1:32) |
Slot width | Dual-slot | IGP |
---|---|---|
Length | 229 mm 9 inches | — |
Width | 111 mm 4.4 inches | — |
Height | 35 mm 1.4 inches | — |
TDP | 90 W | 75 W |
Suggested PSU | 250 W | — |
Outputs | 1x DVI1x HDMI1x DisplayPort | No outputs |
Power connectors | 1x 6-pin | — |
DirectX | 12 Ultimate (12_2) | 12 (11_0) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.1 |
CUDA | 7.5 | 5.0 |
Shader model | 6.6 | 5.1 |
Release date | — | Mar 13th, 2015 |
---|---|---|
Generation | — | GeForce 900M |
Production | — | End-of-life |
Interface | — | PCIe 3.0 x8 |
Predecessor | — | GeForce 800M |
Successor | — | GeForce 10 Mobile |