GPU model | GK208 | TU102 |
---|---|---|
Architecture | Kepler 2.0 | Turing |
Foundry | TSMC | TSMC |
Manufacturing process | 28 nm | 12 nm |
Number of transistors | 1,020 million | 18,600 million |
Die size | 87 mm² | 754 mm² |
GPU variant | — | TU102-875-A1 |
Release date | Jan 27th, 2014 | — |
---|---|---|
Generation | GeForce 800M | — |
Production | End-of-life | — |
Interface | PCIe 3.0 x8 | — |
Predecessor | GeForce 700M | — |
Successor | GeForce 900M | — |
Base clock | 850 MHz | 1065 MHz |
---|---|---|
Boost clock | 941 MHz | 1395 MHz |
Memory clock | 900 MHz 1800 Mbps effective | 1750 MHz 14 Gbps effective |
Memory size | 1024 MB | 4 GB |
---|---|---|
Memory type | DDR3 | GDDR6 |
Memory bus width | 64 bit | 384 bit |
Bandwidth | 14.40 GB/s | 672.0 GB/s |
Shading units | 384 | 4608 |
---|---|---|
TMUs | 32 | 288 |
ROPs | 8 | 96 |
SMX count | 2 | — |
Cache L1 | 16 KB (per SMX) | 64 KB (per SM) |
Cache L2 | 512 KB | 6 MB |
SM count | — | 72 |
Tensor cores | — | 576 |
RT cores | — | 72 |
Pixel rate | 7.528 GPixel/s | 133.9 GPixel/s |
---|---|---|
Texture rate | 30.11 GTexel/s | 401.8 GTexel/s |
FP32 (float) performance | 722.7 GFLOPS | 12.86 TFLOPS |
FP64 (double) performance | 30.11 GFLOPS (1:24) | 401.8 GFLOPS (1:32) |
FP16 (half) performance | — | 25.71 TFLOPS (2:1) |
Slot width | IGP | Dual-slot |
---|---|---|
TDP | 33 W | 260 W |
Outputs | No outputs | No outputs |
Power connectors | None | 1x 6-pin + 1x 8-pin |
Length | — | 267 mm 10.5 inches |
Suggested PSU | — | 600 W |
Board number | — | PG150 SKU 215 |
DirectX | 12 (11_0) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.1 | 1.2 |
CUDA | 3.5 | 7.5 |
Shader model | 5.1 | 6.6 |
Release date | — | Unknown |
---|---|---|
Generation | — | GRID |
Production | — | Active |
Interface | — | PCIe 3.0 x16 |