GPU model | TU106 | GA104 |
---|---|---|
Architecture | Turing | Ampere |
Foundry | TSMC | Samsung |
Manufacturing process | 12 nm | 8 nm |
Number of transistors | 10,800 million | 17,400 million |
Die size | 445 mm² | 392 mm² |
GPU variant | — | GA104-200-A1 |
Release date | Apr 10th, 2020 | — |
---|---|---|
Generation | GeForce 20 Mobile | — |
Production | Active | — |
Interface | PCIe 3.0 x16 | — |
Reviews | 40 in our database | — |
Base clock | 1305 MHz | 1410 MHz |
---|---|---|
Boost clock | 1485 MHz | 1665 MHz |
Memory clock | 1750 MHz 14000 MHz effective | 1750 MHz 14 Gbps effective |
Memory size | 8 GB | 8 GB |
---|---|---|
Memory type | GDDR6 | GDDR6 |
Memory bus width | 256 bit | 256 bit |
Bandwidth | 448.0 GB/s | 448.0 GB/s |
Shading units | 2176 | 4864 |
---|---|---|
TMUs | 136 | 152 |
ROPs | 64 | 80 |
SM count | 34 | 38 |
Tensor cores | 272 | 152 |
RT cores | 34 | 38 |
Cache L1 | 64 KB (per SM) | 128 KB (per SM) |
Cache L2 | 4 MB | 4 MB |
Pixel rate | 95.04 GPixel/s | 133.2 GPixel/s |
---|---|---|
Texture rate | 202.0 GTexel/s | 253.1 GTexel/s |
FP16 (half) performance | 12.93 TFLOPS (2:1) | 16.20 TFLOPS (1:1) |
FP32 (float) performance | 6.463 TFLOPS | 16.20 TFLOPS |
FP64 (double) performance | 202.0 GFLOPS (1:32) | 253.1 GFLOPS (1:64) |
Slot width | MXM Module | Dual-slot |
---|---|---|
TDP | 100 W | 200 W |
Outputs | No outputs | 1x HDMI3x DisplayPort |
Power connectors | None | 1x 12-pin |
Length | — | 242 mm 9.5 inches |
Width | — | 112 mm 4.4 inches |
Suggested PSU | — | 550 W |
Board number | — | PG142 SKU 20 |
DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 1.2 | 3.0 |
Vulkan | 1.2.140 | 1.2 |
CUDA | 7.5 | 8.6 |
Shader model | 6.5 | 6.6 |
Release date | — | Dec 1st, 2020 |
---|---|---|
gpu.details.availability | — | Dec 2nd, 2020 |
Generation | — | GeForce 30 |
Predecessor | — | GeForce 20 |
Production | — | Active |
Launch price | — | 399 USD |
Interface | — | PCIe 4.0 x16 |
Reviews | — | 64 in our database |