GPU model | GP106 | GA106 |
---|---|---|
Architecture | Pascal | Ampere |
Foundry | TSMC | Samsung |
Manufacturing process | 16 nm | 8 nm |
Number of transistors | 4,400 million | 13,250 million |
Die size | 200 mm² | 276 mm² |
GPU variant | — | GA106-150-A1 |
Release date | Feb 1st, 2017 | — |
---|---|---|
Generation | GeForce 10 Mobile | — |
Production | Active | — |
Interface | PCIe 3.0 x16 | — |
Reviews | 15 in our database | — |
Base clock | 1354 MHz | 1552 MHz |
---|---|---|
Boost clock | 1493 MHz | 1777 MHz |
Memory clock | 1752 MHz 7008 MHz effective | 1750 MHz 14 Gbps effective |
Memory size | 2 GB | 8 GB |
---|---|---|
Memory type | GDDR5 | GDDR6 |
Memory bus width | 128 bit | 128 bit |
Bandwidth | 112.1 GB/s | 224.0 GB/s |
Shading units | 640 | 2560 |
---|---|---|
TMUs | 40 | 80 |
ROPs | 32 | 48 |
SM count | 5 | 20 |
Cache L1 | 48 KB (per SM) | 128 KB (per SM) |
Cache L2 | 1024 KB | 2 MB |
Tensor cores | — | 80 |
RT cores | — | 20 |
Pixel rate | 47.78 GPixel/s | 85.30 GPixel/s |
---|---|---|
Texture rate | 59.72 GTexel/s | 142.2 GTexel/s |
FP16 (half) performance | 29.86 GFLOPS (1:64) | 9.098 TFLOPS (1:1) |
FP32 (float) performance | 1.911 TFLOPS | 9.098 TFLOPS |
FP64 (double) performance | 59.72 GFLOPS (1:32) | 142.2 GFLOPS (1:64) |
TDP | 75 W | 90 W |
---|---|---|
Outputs | No outputs | 1x HDMI3x DisplayPort |
Power connectors | None | 1x 6-pin |
Slot width | — | Dual-slot |
Length | — | 242 mm 9.5 inches |
Width | — | 112 mm 4.4 inches |
Suggested PSU | — | 250 W |
DirectX | 12 (12_1) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 1.2 | 3.0 |
Vulkan | 1.2.131 | 1.2 |
CUDA | 6.1 | 8.6 |
Shader model | 6.4 | 6.6 |
Release date | — | 2022 |
---|---|---|
gpu.details.availability | — | 2022 |
Generation | — | GeForce 30 |
Predecessor | — | GeForce 20 |
Production | — | Unreleased |
Interface | — | PCIe 4.0 x16 |