GPU model | Mars | GK208B |
---|---|---|
GPU variant | Mars PRO (216-0842000) | N16V-GM |
Architecture | GCN 1.0 | Kepler 2.0 |
Foundry | TSMC | TSMC |
Manufacturing process | 28 nm | 28 nm |
Number of transistors | 950 million | 1,020 million |
Die size | 77 mm² | 87 mm² |
Release date | Feb 26th, 2013 | Mar 13th, 2015 |
---|---|---|
Generation | Solar System (HD 8700M) | GeForce 900A |
Production | End-of-life | Active |
Interface | PCIe 3.0 x8 | PCIe 3.0 x8 |
Predecessor | London | GeForce 800A |
Successor | Crystal System | — |
Base clock | 620 MHz | — |
---|---|---|
Boost clock | 775 MHz | — |
Memory clock | 1000 MHz 4 Gbps effective | 1001 MHz 2 Gbps effective |
GPU clock | — | 954 MHz |
Memory size | 1024 MB | 2 GB |
---|---|---|
Memory type | GDDR5 | DDR3 |
Memory bus width | 128 bit | 64 bit |
Bandwidth | 64.00 GB/s | 16.02 GB/s |
Shading units | 384 | 384 |
---|---|---|
TMUs | 24 | 32 |
ROPs | 8 | 8 |
Compute units | 6 | — |
Cache L1 | 16 KB (per CU) | 16 KB (per SMX) |
Cache L2 | 256 KB | 512 KB |
SMX count | — | 2 |
Pixel rate | 6.200 GPixel/s | 7.632 GPixel/s |
---|---|---|
Texture rate | 18.60 GTexel/s | 30.53 GTexel/s |
FP32 (float) performance | 595.2 GFLOPS | 732.7 GFLOPS |
FP64 (double) performance | 37.20 GFLOPS (1:16) | 30.53 GFLOPS (1:24) |
TDP | unknown | 33 W |
---|---|---|
Outputs | No outputs | No outputs |
Slot width | — | IGP |
DirectX | 12 (11_1) | 12 (11_0) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 1.2 | 3.0 |
Vulkan | 1.2 | 1.1 |
Shader model | 5.1 | 5.1 |
CUDA | — | 3.5 |