GPU model | M92 | GF108 |
---|---|---|
Architecture | TeraScale | Fermi |
Foundry | TSMC | TSMC |
Manufacturing process | 55 nm | 40 nm |
Number of transistors | 242 million | 585 million |
Die size | 73 mm² | 116 mm² |
GPU variant | — | GF108-300-A1 |
Release date | Jan 9th, 2009 | Sep 17th, 2012 |
---|---|---|
Generation | M9x (Mobility HD 4300) | NVS Mobile (x200M) |
Production | End-of-life | End-of-life |
Interface | PCIe 2.0 x16 | MXM |
Reviews | 2 in our database | 26 in our database |
Predecessor | M8x | — |
Successor | Manhattan | — |
GPU clock | 450 MHz | 672 MHz |
---|---|---|
Memory clock | 600 MHz 1200 Mbps effective | 785 MHz 3.1 Gbps effective |
Shader clock | — | 1344 MHz |
Memory size | 512 MB | 1024 MB |
---|---|---|
Memory type | GDDR3 | GDDR5 |
Memory bus width | 64 bit | 64 bit |
Bandwidth | 9.600 GB/s | 25.12 GB/s |
Shading units | 80 | 96 |
---|---|---|
TMUs | 8 | 16 |
ROPs | 4 | 4 |
Compute units | 1 | — |
Cache L1 | 16 KB (per CU) | 64 KB (per SM) |
Cache L2 | 64 KB | 128 KB |
SM count | — | 2 |
Pixel rate | 1.800 GPixel/s | 2.688 GPixel/s |
---|---|---|
Texture rate | 3.600 GTexel/s | 10.75 GTexel/s |
FP32 (float) performance | 72.00 GFLOPS | 258.0 GFLOPS |
FP64 (double) performance | — | 21.50 GFLOPS (1:12) |
Slot width | MXM Module | MXM Module |
---|---|---|
TDP | unknown | 25 W |
Outputs | No outputs | No outputs |
DirectX | 10.1 (10_1) | 12 (11_0) |
---|---|---|
OpenGL | 3.3 | 4.6 |
OpenCL | 1.1 | 1.1 |
Vulkan | — | — |
Shader model | 4.1 | 5.1 |
CUDA | — | 2.1 |