GPU model | Polaris 22 | GP107 |
---|---|---|
GPU variant | VegaM MGL XL | N17P-G1-A1 |
Architecture | GCN 4.0 | Pascal |
Foundry | GlobalFoundries | Samsung |
Manufacturing process | 14 nm | 14 nm |
Number of transistors | 5,000 million | 3,300 million |
Die size | 208 mm² | 132 mm² |
Release date | Apr 24th, 2018 | Jan 3rd, 2018 |
---|---|---|
Generation | Vega (Vega M) | GeForce 10 Mobile |
Production | Active | End-of-life |
Interface | IGP | PCIe 3.0 x16 |
Reviews | — | 58 in our database |
Predecessor | — | GeForce 900M |
Successor | — | GeForce 20 Mobile |
Base clock | 931 MHz | 1152 MHz |
---|---|---|
Boost clock | 1011 MHz | 1291 MHz |
Memory clock | 700 MHz 1400 Mbps effective | 1752 MHz 7 Gbps effective |
Memory size | 4 GB | 4 GB |
---|---|---|
Memory type | HBM2 | GDDR5 |
Memory bus width | 1024 bit | 128 bit |
Bandwidth | 179.2 GB/s | 112.1 GB/s |
Shading units | 1280 | 768 |
---|---|---|
TMUs | 80 | 48 |
ROPs | 32 | 32 |
Compute units | 20 | — |
Cache L1 | 16 KB (per CU) | 48 KB (per SM) |
Cache L2 | 1024 KB | 1024 KB |
SM count | — | 6 |
Pixel rate | 32.35 GPixel/s | 41.31 GPixel/s |
---|---|---|
Texture rate | 80.88 GTexel/s | 61.97 GTexel/s |
FP16 (half) performance | 2.588 TFLOPS (1:1) | 30.98 GFLOPS (1:64) |
FP32 (float) performance | 2.588 TFLOPS | 1.983 TFLOPS |
FP64 (double) performance | 161.8 GFLOPS (1:16) | 61.97 GFLOPS (1:32) |
Slot width | IGP | — |
---|---|---|
TDP | 65 W | 75 W |
Outputs | No outputs | No outputs |
Board number | D136 | E2904 SKU 1 |
Power connectors | — | None |
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 | 6.4 |
CUDA | — | 6.1 |