GPU model | G92 | TU117 |
---|---|---|
GPU variant | G92-420-A2 | N18S-G5 |
Architecture | Tesla | Turing |
Foundry | TSMC | TSMC |
Manufacturing process | 65 nm | 12 nm |
Number of transistors | 754 million | 4,700 million |
Die size | 324 mm² | 200 mm² |
Release date | Mar 28th, 2008 | — |
---|---|---|
Generation | GeForce 9 | — |
Production | End-of-life | — |
Launch price | 299 USD | — |
Interface | PCIe 2.0 x16 | — |
Reviews | 84 in our database | — |
Predecessor | GeForce 8 | — |
Successor | GeForce 200 | — |
GPU clock | 675 MHz | — |
---|---|---|
Shader clock | 1688 MHz | — |
Memory clock | 1100 MHz 2.2 Gbps effective | 1250 MHz 10 Gbps effective |
Base clock | — | 720 MHz |
Boost clock | — | 930 MHz |
Memory size | 512 MB | 2 GB |
---|---|---|
Memory type | GDDR3 | GDDR6 |
Memory bus width | 256 bit | 64 bit |
Bandwidth | 70.40 GB/s | 80.00 GB/s |
Shading units | 128 | 896 |
---|---|---|
TMUs | 64 | 56 |
ROPs | 16 | 32 |
SM count | 16 | 14 |
Cache L2 | 64 KB | 512 KB |
Cache L1 | — | 64 KB (per SM) |
Pixel rate | 10.80 GPixel/s | 29.76 GPixel/s |
---|---|---|
Texture rate | 43.20 GTexel/s | 52.08 GTexel/s |
FP32 (float) performance | 432.1 GFLOPS | 1.667 TFLOPS |
FP16 (half) performance | — | 3.333 TFLOPS (2:1) |
FP64 (double) performance | — | 52.08 GFLOPS (1:32) |
Slot width | Dual-slot | — |
---|---|---|
Length | 267 mm 10.5 inches | — |
Width | 111 mm 4.4 inches | — |
Height | 38 mm 1.5 inches | — |
TDP | 140 W | 25 W |
Suggested PSU | 300 W | — |
Outputs | 2x DVI1x S-Video | No outputs |
Power connectors | 2x 6-pin | None |
Board number | P392 | — |
DirectX | 11.1 (10_0) | 12 (12_1) |
---|---|---|
OpenGL | 3.3 | 4.6 |
OpenCL | 1.1 | 3.0 |
Vulkan | — | 1.2 |
CUDA | 1.1 | 7.5 |
Shader model | 4.0 | 6.6 |
Release date | — | Aug 15th, 2020 |
---|---|---|
Generation | — | GeForce MX (4xx) |
Production | — | Active |
Interface | — | PCIe 4.0 x4 |