GPU model | Broadwell GT2 | TU116 |
---|---|---|
Architecture | Generation 8.0 | Turing |
Foundry | Intel | TSMC |
Manufacturing process | 14 nm | 12 nm |
Number of transistors | unknown | 6,600 million |
Die size | unknown | 284 mm² |
GPU variant | — | TU116-300-A1 |
Release date | Sep 5th, 2014 | — |
---|---|---|
Generation | HD Graphics-M (Broadwell) | — |
Production | End-of-life | — |
Interface | Ring Bus | — |
Reviews | 1 in our database | — |
Base clock | 300 MHz | 1530 MHz |
---|---|---|
Boost clock | 850 MHz | 1785 MHz |
Memory clock | System Shared | 1750 MHz 14 Gbps effective |
Memory size | System Shared | 6 GB |
---|---|---|
Memory type | System Shared | GDDR6 |
Memory bus width | System Shared | 192 bit |
Bandwidth | System Dependent | 336.0 GB/s |
Shading units | 192 | 1408 |
---|---|---|
TMUs | 24 | 88 |
ROPs | 3 | 48 |
Execution units | 24 | — |
SM count | — | 22 |
Cache L1 | — | 64 KB (per SM) |
Cache L2 | — | 1536 KB |
Pixel rate | 2.550 GPixel/s | 85.68 GPixel/s |
---|---|---|
Texture rate | 20.40 GTexel/s | 157.1 GTexel/s |
FP32 (float) performance | 326.4 GFLOPS | 5.027 TFLOPS |
FP64 (double) performance | 81.60 GFLOPS (1:4) | 157.1 GFLOPS (1:32) |
FP16 (half) performance | — | 10.05 TFLOPS (2:1) |
Slot width | IGP | Dual-slot |
---|---|---|
TDP | 15 W | 125 W |
Outputs | No outputs | 1x DVI1x HDMI1x DisplayPort |
Length | — | 229 mm 9 inches |
Width | — | 111 mm 4.4 inches |
Height | — | 35 mm 1.4 inches |
Suggested PSU | — | 300 W |
Power connectors | — | 1x 8-pin |
Board number | — | PG161 SKU 26 |
DirectX | 12 (11_1) | 12 (12_1) |
---|---|---|
OpenGL | 4.4 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.0 | 1.2 |
Shader model | 5.1 | 6.6 |
CUDA | — | 7.5 |
Release date | — | Oct 29th, 2019 |
---|---|---|
Generation | — | GeForce 16 |
Predecessor | — | GeForce 10 |
Successor | — | GeForce 20 |
Production | — | Active |
Launch price | — | 229 USD |
Interface | — | PCIe 3.0 x16 |
Reviews | — | 42 in our database |