GPU model | Polaris 20 | TU116 |
---|---|---|
GPU variant | Polaris 20 XTX (215-0910038) | TU116-150-KA-A1 |
Architecture | GCN 4.0 | Turing |
Foundry | GlobalFoundries | TSMC |
Manufacturing process | 14 nm | 12 nm |
Number of transistors | 5,700 million | 6,600 million |
Die size | 232 mm² | 284 mm² |
Release date | Apr 11th, 2018 | Jul 7th, 2020 |
---|---|---|
Generation | Polaris | GeForce 16 |
Production | Active | Active |
Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Predecessor | Polaris | GeForce 10 |
Successor | Vega | GeForce 20 |
Base clock | 1257 MHz | 1410 MHz |
---|---|---|
Boost clock | 1340 MHz | 1590 MHz |
Memory clock | 2000 MHz 8 Gbps effective | 1500 MHz 12 Gbps effective |
Memory size | 8 GB | 4 GB |
---|---|---|
Memory type | GDDR5 | GDDR6 |
Memory bus width | 256 bit | 128 bit |
Bandwidth | 256.0 GB/s | 192.0 GB/s |
Shading units | 2304 | 896 |
---|---|---|
TMUs | 144 | 56 |
ROPs | 32 | 32 |
Compute units | 36 | — |
Cache L1 | 16 KB (per CU) | 64 KB (per SM) |
Cache L2 | 2 MB | 1024 KB |
SM count | — | 14 |
Pixel rate | 42.88 GPixel/s | 50.88 GPixel/s |
---|---|---|
Texture rate | 193.0 GTexel/s | 89.04 GTexel/s |
FP16 (half) performance | 6.175 TFLOPS (1:1) | 5.699 TFLOPS (2:1) |
FP32 (float) performance | 6.175 TFLOPS | 2.849 TFLOPS |
FP64 (double) performance | 385.9 GFLOPS (1:16) | 89.04 GFLOPS (1:32) |
Slot width | Dual-slot | Dual-slot |
---|---|---|
Length | 241 mm 9.5 inches | 229 mm 9 inches |
TDP | 185 W | 80 W |
Suggested PSU | 450 W | 250 W |
Outputs | 1x HDMI3x DisplayPort | 1x DVI1x HDMI1x DisplayPort |
Power connectors | 1x 8-pin | None |
Board number | D009 | — |
Width | — | 111 mm 4.4 inches |
Height | — | 35 mm 1.4 inches |
DirectX | 12 (12_0) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader model | 6.4 | 6.6 |
CUDA | — | 7.5 |