GPU model | M96 | GF108 |
---|---|---|
Architecture | TeraScale | Fermi |
Foundry | TSMC | TSMC |
Manufacturing process | 55 nm | 40 nm |
Number of transistors | 514 million | 585 million |
Die size | 146 mm² | 116 mm² |
GPU variant | — | N11P-GE-A1 |
Release date | Jan 9th, 2009 | Sep 3rd, 2010 |
---|---|---|
Generation | M9x (Mobility HD 4600) | GeForce 400M |
Production | End-of-life | End-of-life |
Interface | PCIe 2.0 x16 | PCIe 2.0 x16 |
Reviews | 2 in our database | — |
Predecessor | M8x | GeForce 300M |
Successor | Manhattan | GeForce 500M |
GPU clock | 500 MHz | 500 MHz |
---|---|---|
Memory clock | 600 MHz 1200 Mbps effective | 800 MHz 1600 Mbps effective |
Shader clock | — | 1000 MHz |
Memory size | 512 MB | 512 MB |
---|---|---|
Memory type | DDR2 | DDR3 |
Memory bus width | 128 bit | 128 bit |
Bandwidth | 19.20 GB/s | 25.60 GB/s |
Shading units | 320 | 96 |
---|---|---|
TMUs | 32 | 16 |
ROPs | 8 | 4 |
Compute units | 4 | — |
Cache L1 | 16 KB (per CU) | 64 KB (per SM) |
Cache L2 | 128 KB | 256 KB |
SM count | — | 2 |
Pixel rate | 4.000 GPixel/s | 2.000 GPixel/s |
---|---|---|
Texture rate | 16.00 GTexel/s | 8.000 GTexel/s |
FP32 (float) performance | 320.0 GFLOPS | 192.0 GFLOPS |
FP64 (double) performance | — | 16.00 GFLOPS (1:12) |
TDP | 35 W | 23 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 |