GPU model | GF106 | TU102 |
---|---|---|
Architecture | Fermi | Turing |
Foundry | TSMC | TSMC |
Manufacturing process | 40 nm | 12 nm |
Number of transistors | 1,170 million | 18,600 million |
Die size | 238 mm² | 754 mm² |
GPU variant | — | TU102-875-A1 |
Release date | Oct 11th, 2010 | Unknown |
---|---|---|
Generation | GeForce 400 | GRID |
Production | End-of-life | Active |
Interface | PCIe 2.0 x16 | PCIe 3.0 x16 |
Reviews | 5 in our database | — |
Predecessor | GeForce 200 | — |
Successor | GeForce 500 | — |
GPU clock | 810 MHz | — |
---|---|---|
Shader clock | 1620 MHz | — |
Memory clock | 900 MHz 1800 Mbps effective | 1750 MHz 14 Gbps effective |
Base clock | — | 1065 MHz |
Boost clock | — | 1395 MHz |
Memory size | 1536 MB | 4 GB |
---|---|---|
Memory type | DDR3 | GDDR6 |
Memory bus width | 192 bit | 384 bit |
Bandwidth | 43.20 GB/s | 672.0 GB/s |
Shading units | 144 | 4608 |
---|---|---|
TMUs | 24 | 288 |
ROPs | 24 | 96 |
SM count | 3 | 72 |
Cache L1 | 64 KB (per SM) | 64 KB (per SM) |
Cache L2 | 384 KB | 6 MB |
Tensor cores | — | 576 |
RT cores | — | 72 |
Pixel rate | 4.860 GPixel/s | 133.9 GPixel/s |
---|---|---|
Texture rate | 19.44 GTexel/s | 401.8 GTexel/s |
FP32 (float) performance | 466.6 GFLOPS | 12.86 TFLOPS |
FP64 (double) performance | 38.88 GFLOPS (1:12) | 401.8 GFLOPS (1:32) |
FP16 (half) performance | — | 25.71 TFLOPS (2:1) |
Slot width | Single-slot | Dual-slot |
---|---|---|
Length | 145 mm 5.7 inches | 267 mm 10.5 inches |
TDP | 65 W | 260 W |
Suggested PSU | 250 W | 600 W |
Outputs | 1x DVI1x HDMI1x VGA | No outputs |
Power connectors | None | 1x 6-pin + 1x 8-pin |
Board number | P1062 | PG150 SKU 215 |
DirectX | 12 (11_0) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 1.1 | 3.0 |
Vulkan | — | 1.2 |
CUDA | 2.1 | 7.5 |
Shader model | 5.1 | 6.6 |