GPU model | GP108 | GA107S |
---|---|---|
GPU variant | N17S-G2-A1 | — |
Architecture | Pascal | Ampere |
Foundry | Samsung | Samsung |
Manufacturing process | 14 nm | 8 nm |
Number of transistors | 1,800 million | unknown |
Die size | 74 mm² | unknown |
Release date | Feb 21st, 2019 | 2022 |
---|---|---|
Generation | GeForce MX (2xx) | GeForce 20 Mobile |
Production | End-of-life | Unreleased |
Interface | PCIe 3.0 x4 | PCIe 3.0 x16 |
Predecessor | — | GeForce 10 Mobile |
Successor | — | GeForce 30 Mobile |
Base clock | 1519 MHz | 1155 MHz |
---|---|---|
Boost clock | 1582 MHz | 1477 MHz |
Memory clock | 1502 MHz 6 Gbps effective | 1750 MHz 14 Gbps effective |
Memory size | 2 GB | 4 GB |
---|---|---|
Memory type | GDDR5 | GDDR6 |
Memory bus width | 64 bit | 64 bit |
Bandwidth | 48.06 GB/s | 112.0 GB/s |
Shading units | 384 | 2048 |
---|---|---|
TMUs | 24 | 128 |
ROPs | 16 | 48 |
SM count | 3 | 32 |
Cache L1 | 48 KB (per SM) | 64 KB (per SM) |
Cache L2 | 512 KB | 2 MB |
Tensor cores | — | 256 |
RT cores | — | 32 |
Pixel rate | 25.31 GPixel/s | 70.90 GPixel/s |
---|---|---|
Texture rate | 37.97 GTexel/s | 189.1 GTexel/s |
FP16 (half) performance | 18.98 GFLOPS (1:64) | 12.10 TFLOPS (2:1) |
FP32 (float) performance | 1,215 GFLOPS | 6.050 TFLOPS |
FP64 (double) performance | 37.97 GFLOPS (1:32) | 189.1 GFLOPS (1:32) |
Slot width | IGP | Dual-slot |
---|---|---|
TDP | 25 W | 45 W |
Outputs | No outputs | 1x DVI1x HDMI2x DisplayPort |
Power connectors | None | 1x 6-pin |
Length | — | 229 mm 9 inches |
Width | — | 113 mm 4.4 inches |
Height | — | 35 mm 1.4 inches |
DirectX | 12 (12_1) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 6.1 | 8.6 |
Shader model | 6.4 | 6.6 |