GPU model | Polaris 20 | GK104 |
---|---|---|
GPU variant | Polaris 20 XL (215-0910052) | N14E-Q3-A2 |
Architecture | GCN 4.0 | Kepler |
Foundry | GlobalFoundries | TSMC |
Manufacturing process | 14 nm | 28 nm |
Number of transistors | 5,700 million | 3,540 million |
Die size | 232 mm² | 294 mm² |
Release date | Apr 11th, 2018 | — |
---|---|---|
Generation | Polaris | — |
Production | Active | — |
Interface | PCIe 3.0 x16 | — |
Predecessor | Polaris | — |
Successor | Vega | — |
Base clock | 1168 MHz | — |
---|---|---|
Boost clock | 1244 MHz | — |
Memory clock | 1750 MHz 7 Gbps effective | 700 MHz 2.8 Gbps effective |
GPU clock | — | 601 MHz |
Memory size | 8 GB | 4 GB |
---|---|---|
Memory type | GDDR5 | GDDR5 |
Memory bus width | 256 bit | 256 bit |
Bandwidth | 224.0 GB/s | 89.60 GB/s |
Shading units | 2048 | 960 |
---|---|---|
TMUs | 128 | 80 |
ROPs | 32 | 32 |
Compute units | 32 | — |
Cache L1 | 16 KB (per CU) | 16 KB (per SMX) |
Cache L2 | 2 MB | 512 KB |
SMX count | — | 5 |
Pixel rate | 39.81 GPixel/s | 12.02 GPixel/s |
---|---|---|
Texture rate | 159.2 GTexel/s | 48.08 GTexel/s |
FP16 (half) performance | 5.095 TFLOPS (1:1) | — |
FP32 (float) performance | 5.095 TFLOPS | 1,154 GFLOPS |
FP64 (double) performance | 318.5 GFLOPS (1:16) | 48.08 GFLOPS (1:24) |
Slot width | Dual-slot | MXM Module |
---|---|---|
Length | 241 mm 9.5 inches | — |
TDP | 150 W | 100 W |
Suggested PSU | 450 W | — |
Outputs | 1x DVI1x HDMI3x DisplayPort | No outputs |
Power connectors | 1x 6-pin | — |
Board number | D000 | — |
DirectX | 12 (12_0) | 12 (11_0) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.1 |
Shader model | 6.4 | 5.1 |
CUDA | — | 3.0 |
Release date | — | Jun 1st, 2012 |
---|---|---|
Generation | — | Quadro Mobile (Kx000M) |
Production | — | End-of-life |
Interface | — | MXM-B (3.0) |
Reviews | — | 26 in our database |