GPU model | GF106 | GF100 |
---|---|---|
GPU variant | GF106-250-KA-A1 | GF100-876-A1 |
Architecture | Fermi | Fermi |
Foundry | TSMC | TSMC |
Manufacturing process | 40 nm | 40 nm |
Number of transistors | 1,170 million | 3,100 million |
Die size | 238 mm² | 529 mm² |
Release date | Sep 13th, 2010 | Jul 25th, 2011 |
---|---|---|
Generation | GeForce 400 | Tesla |
Production | End-of-life | End-of-life |
Launch price | 129 USD | 5,489 USD |
Interface | PCIe 2.0 x16 | PCIe 2.0 x16 |
Reviews | 80 in our database | — |
Predecessor | GeForce 200 | — |
Successor | GeForce 500 | — |
GPU clock | 783 MHz | 574 MHz |
---|---|---|
Shader clock | 1566 MHz | 1147 MHz |
Memory clock | 902 MHz 3.6 Gbps effective | 783 MHz 3.1 Gbps effective |
Memory size | 1024 MB | 6 GB |
---|---|---|
Memory type | GDDR5 | GDDR5 |
Memory bus width | 128 bit | 384 bit |
Bandwidth | 57.73 GB/s | 150.3 GB/s |
Shading units | 192 | 448 |
---|---|---|
TMUs | 32 | 56 |
ROPs | 16 | 48 |
SM count | 4 | 14 |
Cache L1 | 64 KB (per SM) | 64 KB (per SM) |
Cache L2 | 256 KB | 768 KB |
Pixel rate | 6.264 GPixel/s | 16.07 GPixel/s |
---|---|---|
Texture rate | 25.06 GTexel/s | 32.14 GTexel/s |
FP32 (float) performance | 601.3 GFLOPS | 1,028 GFLOPS |
FP64 (double) performance | 50.11 GFLOPS (1:12) | 513.9 GFLOPS (1:2) |
Slot width | Dual-slot | Dual-slot |
---|---|---|
Length | 210 mm 8.3 inches | 248 mm 9.8 inches |
Width | 111 mm 4.4 inches | — |
TDP | 106 W | 225 W |
Suggested PSU | 300 W | 550 W |
Outputs | 2x DVI1x mini-HDMI | No outputs |
Power connectors | 1x 6-pin | 1x 6-pin + 1x 8-pin |
Board number | P1060 | — |
DirectX | 12 (11_0) | 12 (11_0) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 1.1 | 1.1 |
Vulkan | — | — |
CUDA | 2.1 | 2.0 |
Shader model | 5.1 | 5.1 |