GPU model | TU106B | TU106 |
---|---|---|
Architecture | Turing | Turing |
Foundry | TSMC | TSMC |
Manufacturing process | 12 nm | 12 nm |
Number of transistors | 10,800 million | 10,800 million |
Die size | 445 mm² | 445 mm² |
GPU variant | — | N18E-G2-A1 |
Release date | Jan 29th, 2019 | Jan 29th, 2019 |
---|---|---|
Generation | GeForce 20 Mobile | GeForce 20 Mobile |
Production | Active | Active |
Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Predecessor | GeForce 10 Mobile | GeForce 10 Mobile |
Successor | GeForce 30 Mobile | GeForce 30 Mobile |
Base clock | 960 MHz | 885 MHz |
---|---|---|
Boost clock | 1200 MHz | 1185 MHz |
Memory clock | 1353 MHz 10.8 Gbps effective | 1500 MHz 12 Gbps effective |
Memory size | 6 GB | 8 GB |
---|---|---|
Memory type | GDDR6 | GDDR6 |
Memory bus width | 192 bit | 256 bit |
Bandwidth | 259.8 GB/s | 384.0 GB/s |
Shading units | 1920 | 2304 |
---|---|---|
TMUs | 120 | 144 |
ROPs | 48 | 64 |
SM count | 30 | 36 |
Tensor cores | 240 | 288 |
RT cores | 30 | 36 |
Cache L1 | 64 KB (per SM) | 64 KB (per SM) |
Cache L2 | 3 MB | 4 MB |
Pixel rate | 57.60 GPixel/s | 75.84 GPixel/s |
---|---|---|
Texture rate | 144.0 GTexel/s | 170.6 GTexel/s |
FP16 (half) performance | 9.216 TFLOPS (2:1) | 10.92 TFLOPS (2:1) |
FP32 (float) performance | 4.608 TFLOPS | 5.460 TFLOPS |
FP64 (double) performance | 144.0 GFLOPS (1:32) | 170.6 GFLOPS (1:32) |
Slot width | MXM Module | MXM Module |
---|---|---|
TDP | 115 W | 90 W |
Outputs | No outputs | No outputs |
Power connectors | None | None |
Board number | E4914 SKU 31 | E4914 SKU 30 |
DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 7.5 | 7.5 |
Shader model | 6.6 | 6.6 |