GPU model | TU106 | GV100 |
---|---|---|
GPU variant | TU106-300-KA-A1 | — |
Architecture | Turing | Volta |
Foundry | TSMC | TSMC |
Manufacturing process | 12 nm | 12 nm |
Number of transistors | 10,800 million | 21,100 million |
Die size | 445 mm² | 815 mm² |
Release date | Dec 7th, 2021 | Jun 21st, 2017 |
---|---|---|
Generation | GeForce 20 | Tesla |
Predecessor | GeForce 10 | — |
Successor | GeForce 30 | — |
Production | Active | End-of-life |
Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Reviews | 86 in our database | — |
Base clock | 1470 MHz | 1245 MHz |
---|---|---|
Boost clock | 1650 MHz | 1380 MHz |
Memory clock | 1750 MHz 14 Gbps effective | 876 MHz 1752 Mbps effective |
Memory size | 12 GB | 16 GB |
---|---|---|
Memory type | GDDR6 | HBM2 |
Memory bus width | 192 bit | 4096 bit |
Bandwidth | 336.0 GB/s | 897.0 GB/s |
Shading units | 2176 | 5120 |
---|---|---|
TMUs | 136 | 320 |
ROPs | 48 | 128 |
SM count | 34 | 80 |
Tensor cores | 272 | 640 |
RT cores | 34 | — |
Cache L1 | 64 KB (per SM) | 128 KB (per SM) |
Cache L2 | 3 MB | 6 MB |
Pixel rate | 79.20 GPixel/s | 176.6 GPixel/s |
---|---|---|
Texture rate | 224.4 GTexel/s | 441.6 GTexel/s |
FP16 (half) performance | 14.36 TFLOPS (2:1) | 28.26 TFLOPS (2:1) |
FP32 (float) performance | 7.181 TFLOPS | 14.13 TFLOPS |
FP64 (double) performance | 224.4 GFLOPS (1:32) | 7.066 TFLOPS (1:2) |
Slot width | Dual-slot | Dual-slot |
---|---|---|
Length | 229 mm 9 inches | — |
Width | 113 mm 4.4 inches | — |
Height | 35 mm 1.4 inches | — |
TDP | 184 W | 300 W |
Suggested PSU | 450 W | 700 W |
Outputs | 1x DVI1x HDMI2x DisplayPort1x USB Type-C | No outputs |
Power connectors | 1x 8-pin | 2x 8-pin |
Board number | — | PG500 SKU 200 |
DirectX | 12 Ultimate (12_2) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 7.5 | 7.0 |
Shader model | 6.6 | 6.6 |