GPU model | TU102 | TU102 |
---|---|---|
Architecture | Turing | Turing |
Foundry | TSMC | TSMC |
Manufacturing process | 12 nm | 12 nm |
Number of transistors | 18,600 million | 18,600 million |
Die size | 754 mm² | 754 mm² |
GPU variant | — | TU102-875-A1 |
Release date | 2020 | — |
---|---|---|
Generation | Quadro Mobile (Tx000) | — |
Production | Active | — |
Interface | PCIe 3.0 x16 | — |
Base clock | 1275 MHz | 1230 MHz |
---|---|---|
Boost clock | 1455 MHz | 1620 MHz |
Memory clock | 1750 MHz 14 Gbps effective | 1750 MHz 14 Gbps effective |
Memory size | 24 GB | 48 GB |
---|---|---|
Memory type | GDDR6 | GDDR6 |
Memory bus width | 384 bit | 384 bit |
Bandwidth | 672.0 GB/s | 672.0 GB/s |
Shading units | 4608 | 4608 |
---|---|---|
TMUs | 288 | 288 |
ROPs | 96 | 96 |
SM count | 72 | 72 |
Tensor cores | 576 | 576 |
RT cores | 72 | 72 |
Cache L1 | 64 KB (per SM) | 64 KB (per SM) |
Cache L2 | 6 MB | 6 MB |
Pixel rate | 139.7 GPixel/s | 155.5 GPixel/s |
---|---|---|
Texture rate | 419.0 GTexel/s | 466.6 GTexel/s |
FP16 (half) performance | 26.82 TFLOPS (2:1) | 29.86 TFLOPS (2:1) |
FP32 (float) performance | 13.41 TFLOPS | 14.93 TFLOPS |
FP64 (double) performance | 419.0 GFLOPS (1:32) | 466.6 GFLOPS (1:32) |
TDP | unknown | 260 W |
---|---|---|
Outputs | No outputs | No outputs |
Power connectors | None | 1x 6-pin + 1x 8-pin |
Slot width | — | Dual-slot |
Length | — | 267 mm 10.5 inches |
Width | — | 111 mm 4.4 inches |
Suggested PSU | — | 600 W |
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 |
Release date | — | Aug 13th, 2018 |
---|---|---|
Generation | — | Quadro |
Production | — | Active |
Launch price | — | 9,999 USD |
Interface | — | PCIe 3.0 x16 |