GPU model | Baffin | GM107 |
---|---|---|
GPU variant | Baffin PRO | N16P-GT |
Architecture | GCN 4.0 | Maxwell |
Foundry | GlobalFoundries | TSMC |
Manufacturing process | 14 nm | 28 nm |
Number of transistors | 3,000 million | 1,870 million |
Die size | 123 mm² | 148 mm² |
Release date | Mar 1st, 2017 | Mar 13th, 2015 |
---|---|---|
Generation | Radeon Pro Mobile (WX x100) | GeForce 900A |
Production | Active | End-of-life |
Interface | PCIe 3.0 x8 | MXM-B (3.0) |
Predecessor | — | GeForce 800A |
Base clock | 1002 MHz | 993 MHz |
---|---|---|
Boost clock | 1053 MHz | 1124 MHz |
Memory clock | 1500 MHz 6 Gbps effective | 1001 MHz 2 Gbps effective |
Memory size | 4 GB | 2 GB |
---|---|---|
Memory type | GDDR5 | DDR3 |
Memory bus width | 128 bit | 128 bit |
Bandwidth | 96.00 GB/s | 32.03 GB/s |
Shading units | 896 | 640 |
---|---|---|
TMUs | 56 | 40 |
ROPs | 16 | 16 |
Compute units | 14 | — |
Cache L1 | 16 KB (per CU) | 64 KB (per SMM) |
Cache L2 | 1024 KB | 2 MB |
SMM count | — | 5 |
Pixel rate | 16.85 GPixel/s | 17.98 GPixel/s |
---|---|---|
Texture rate | 58.97 GTexel/s | 44.96 GTexel/s |
FP16 (half) performance | 1.887 TFLOPS (1:1) | — |
FP32 (float) performance | 1.887 TFLOPS | 1,439 GFLOPS |
FP64 (double) performance | 117.9 GFLOPS (1:16) | 44.96 GFLOPS (1:32) |
Slot width | MXM Module | MXM Module |
---|---|---|
TDP | 50 W | 75 W |
Outputs | No outputs | No outputs |
Power connectors | None | — |
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 | — | 5.0 |