GPU model | Polaris 22 | GP106 |
---|---|---|
GPU variant | VegaM XT (C7398773) | — |
Architecture | GCN 4.0 | Pascal |
Foundry | GlobalFoundries | TSMC |
Manufacturing process | 14 nm | 16 nm |
Number of transistors | 5,000 million | 4,400 million |
Die size | 208 mm² | 200 mm² |
Release date | Feb 1st, 2018 | Feb 1st, 2017 |
---|---|---|
Generation | Vega (Vega M) | GeForce 10 Mobile |
Production | Active | Active |
Interface | IGP | PCIe 3.0 x16 |
Reviews | — | 15 in our database |
Base clock | 1063 MHz | 1354 MHz |
---|---|---|
Boost clock | 1190 MHz | 1493 MHz |
Memory clock | 800 MHz 1600 Mbps effective | 1752 MHz 7008 MHz effective |
Memory size | 4 GB | 2 GB |
---|---|---|
Memory type | HBM2 | GDDR5 |
Memory bus width | 1024 bit | 128 bit |
Bandwidth | 204.8 GB/s | 112.1 GB/s |
Shading units | 1536 | 640 |
---|---|---|
TMUs | 96 | 40 |
ROPs | 64 | 32 |
Compute units | 24 | — |
Cache L1 | 16 KB (per CU) | 48 KB (per SM) |
Cache L2 | 1024 KB | 1024 KB |
SM count | — | 5 |
Pixel rate | 76.16 GPixel/s | 47.78 GPixel/s |
---|---|---|
Texture rate | 114.2 GTexel/s | 59.72 GTexel/s |
FP16 (half) performance | 3.656 TFLOPS (1:1) | 29.86 GFLOPS (1:64) |
FP32 (float) performance | 3.656 TFLOPS | 1.911 TFLOPS |
FP64 (double) performance | 228.5 GFLOPS (1:16) | 59.72 GFLOPS (1:32) |
Slot width | IGP | — |
---|---|---|
TDP | 100 W | 75 W |
Outputs | No outputs | No outputs |
Power connectors | — | None |
DirectX | 12 (12_0) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 1.2 |
Vulkan | 1.2 | 1.2.131 |
Shader model | 6.4 | 6.4 |
CUDA | — | 6.1 |