GPU model | TU116 | GV100 |
---|---|---|
GPU variant | TU116-150-KA-A1 | — |
Architecture | Turing | Volta |
Foundry | TSMC | TSMC |
Manufacturing process | 12 nm | 12 nm |
Number of transistors | 6,600 million | 21,100 million |
Die size | 284 mm² | 815 mm² |
Release date | Jul 7th, 2020 | Nov 26th, 2019 |
---|---|---|
Generation | GeForce 16 | Tesla |
Predecessor | GeForce 10 | — |
Successor | GeForce 20 | — |
Production | Active | End-of-life |
Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Base clock | 1410 MHz | 1245 MHz |
---|---|---|
Boost clock | 1590 MHz | 1597 MHz |
Memory clock | 1500 MHz 12 Gbps effective | 1106 MHz 2.2 Gbps effective |
Memory size | 4 GB | 32 GB |
---|---|---|
Memory type | GDDR6 | HBM2 |
Memory bus width | 128 bit | 4096 bit |
Bandwidth | 192.0 GB/s | 1,133 GB/s |
Shading units | 896 | 5120 |
---|---|---|
TMUs | 56 | 320 |
ROPs | 32 | 128 |
SM count | 14 | 80 |
Cache L1 | 64 KB (per SM) | 128 KB (per SM) |
Cache L2 | 1024 KB | 6 MB |
Tensor cores | — | 640 |
Pixel rate | 50.88 GPixel/s | 204.4 GPixel/s |
---|---|---|
Texture rate | 89.04 GTexel/s | 511.0 GTexel/s |
FP16 (half) performance | 5.699 TFLOPS (2:1) | 32.71 TFLOPS (2:1) |
FP32 (float) performance | 2.849 TFLOPS | 16.35 TFLOPS |
FP64 (double) performance | 89.04 GFLOPS (1:32) | 8.177 TFLOPS (1:2) |
Slot width | Dual-slot | Dual-slot |
---|---|---|
Length | 229 mm 9 inches | — |
Width | 111 mm 4.4 inches | — |
Height | 35 mm 1.4 inches | — |
TDP | 80 W | 250 W |
Suggested PSU | 250 W | 600 W |
Outputs | 1x DVI1x HDMI1x DisplayPort | No outputs |
Power connectors | None | 2x 8-pin |
Board number | — | PG500 |
DirectX | 12 (12_1) | 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 |