GPU model | Polaris 20 | TU106 |
---|---|---|
GPU variant | Polaris 20 XTX (215-0910038) | N18E-G1 |
Architecture | GCN 4.0 | Turing |
Foundry | GlobalFoundries | TSMC |
Manufacturing process | 14 nm | 12 nm |
Number of transistors | 5,700 million | 10,800 million |
Die size | 232 mm² | 445 mm² |
Release date | Apr 11th, 2018 | — |
---|---|---|
Generation | Polaris | — |
Production | Active | — |
Interface | PCIe 3.0 x16 | — |
Predecessor | Polaris | — |
Successor | Vega | — |
Base clock | 1257 MHz | 975 MHz |
---|---|---|
Boost clock | 1340 MHz | 1185 MHz |
Memory clock | 2000 MHz 8 Gbps effective | 1375 MHz 11 Gbps effective |
Memory size | 8 GB | 6 GB |
---|---|---|
Memory type | GDDR5 | GDDR6 |
Memory bus width | 256 bit | 192 bit |
Bandwidth | 256.0 GB/s | 264.0 GB/s |
Shading units | 2304 | 1920 |
---|---|---|
TMUs | 144 | 120 |
ROPs | 32 | 48 |
Compute units | 36 | — |
Cache L1 | 16 KB (per CU) | 64 KB (per SM) |
Cache L2 | 2 MB | 3 MB |
SM count | — | 30 |
Tensor cores | — | 240 |
RT cores | — | 30 |
Pixel rate | 42.88 GPixel/s | 56.88 GPixel/s |
---|---|---|
Texture rate | 193.0 GTexel/s | 142.2 GTexel/s |
FP16 (half) performance | 6.175 TFLOPS (1:1) | 9.101 TFLOPS (2:1) |
FP32 (float) performance | 6.175 TFLOPS | 4.550 TFLOPS |
FP64 (double) performance | 385.9 GFLOPS (1:16) | 142.2 GFLOPS (1:32) |
Slot width | Dual-slot | MXM Module |
---|---|---|
Length | 241 mm 9.5 inches | — |
TDP | 185 W | 65 W |
Suggested PSU | 450 W | — |
Outputs | 1x HDMI3x DisplayPort | No outputs |
Power connectors | 1x 8-pin | None |
Board number | D009 | E4914 SKU 31 |
DirectX | 12 (12_0) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader model | 6.4 | 6.6 |
CUDA | — | 7.5 |
Release date | — | Jan 29th, 2020 |
---|---|---|
Generation | — | GeForce 20 Mobile |
Production | — | Active |
Interface | — | PCIe 3.0 x16 |
Predecessor | — | GeForce 10 Mobile |
Successor | — | GeForce 30 Mobile |