GPU model | TU102 | GA102 |
---|---|---|
GPU variant | TU102-300A-K1-A1 | — |
Architecture | Turing | Ampere |
Foundry | TSMC | Samsung |
Manufacturing process | 12 nm | 8 nm |
Number of transistors | 18,600 million | 28,300 million |
Die size | 754 mm² | 628 mm² |
Release date | Sep 20th, 2018 | Nov 23rd, 2021 |
---|---|---|
Generation | GeForce 20 | Quadro |
Predecessor | GeForce 10 | — |
Production | Active | Active |
Launch price | 999 USD | — |
Current price | Amazon / Newegg | — |
Interface | PCIe 3.0 x16 | PCIe 4.0 x16 |
Reviews | 88 in our database | — |
Successor | GeForce 30 | — |
Base clock | 1350 MHz | 1050 MHz |
---|---|---|
Boost clock | 1545 MHz | 1650 MHz |
Memory clock | 1750 MHz 14 Gbps effective | 2000 MHz 16 Gbps effective |
Memory size | 11 GB | 20 GB |
---|---|---|
Memory type | GDDR6 | GDDR6 |
Memory bus width | 352 bit | 320 bit |
Bandwidth | 616.0 GB/s | 640.0 GB/s |
Shading units | 4352 | 7168 |
---|---|---|
TMUs | 272 | 224 |
ROPs | 88 | 96 |
SM count | 68 | 56 |
Tensor cores | 544 | 224 |
RT cores | 68 | 56 |
Cache L1 | 64 KB (per SM) | 128 KB (per SM) |
Cache L2 | 5.5 MB | 6 MB |
Pixel rate | 136.0 GPixel/s | 158.4 GPixel/s |
---|---|---|
Texture rate | 420.2 GTexel/s | 369.6 GTexel/s |
FP16 (half) performance | 26.90 TFLOPS (2:1) | 23.65 TFLOPS (1:1) |
FP32 (float) performance | 13.45 TFLOPS | 23.65 TFLOPS |
FP64 (double) performance | 420.2 GFLOPS (1:32) | 739.2 GFLOPS (1:32) |
Slot width | Dual-slot | Dual-slot |
---|---|---|
Length | 267 mm 10.5 inches | 267 mm 10.5 inches |
Width | 116 mm 4.6 inches | 112 mm 4.4 inches |
Height | 35 mm 1.4 inches | — |
TDP | 250 W | 200 W |
Suggested PSU | 600 W | 550 W |
Outputs | 1x HDMI3x DisplayPort1x USB Type-C | 4x DisplayPort |
Power connectors | 2x 8-pin | 1x 8-pin |
Board number | PG150 SKU 32 | — |
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 | 8.6 |
Shader model | 6.6 | 6.6 |