GPU model | NV31 | GV100 |
---|---|---|
GPU variant | 5600 | — |
Architecture | Rankine | Volta |
Foundry | TSMC | TSMC |
Manufacturing process | 130 nm | 12 nm |
Number of transistors | 80 million | 21,100 million |
Die size | 121 mm² | 815 mm² |
Release date | Mar 6th, 2003 | Mar 27th, 2018 |
---|---|---|
Generation | GeForce FX | Tesla |
Production | End-of-life | End-of-life |
Interface | AGP 8x | PCIe 3.0 x16 |
Reviews | 2 in our database | — |
Predecessor | GeForce 4 Ti | — |
Successor | GeForce 6 AGP | — |
GPU clock | 325 MHz | — |
---|---|---|
Memory clock | 250 MHz 500 Mbps effective | 876 MHz 1752 Mbps effective |
Base clock | — | 1290 MHz |
Boost clock | — | 1530 MHz |
Memory size | 128 MB | 32 GB |
---|---|---|
Memory type | DDR | HBM2 |
Memory bus width | 128 bit | 4096 bit |
Bandwidth | 8.000 GB/s | 897.0 GB/s |
Pixel shaders | 4 | — |
---|---|---|
Vertex shaders | 2 | — |
TMUs | 4 | 320 |
ROPs | 4 | 128 |
Shading units | — | 5120 |
SM count | — | 80 |
Tensor cores | — | 640 |
Cache L1 | — | 128 KB (per SM) |
Cache L2 | — | 6 MB |
Pixel rate | 1.300 GPixel/s | 195.8 GPixel/s |
---|---|---|
Vertex rate | 162.5 MVertices/s | — |
Texture rate | 1.300 GTexel/s | 489.6 GTexel/s |
FP16 (half) performance | — | 31.33 TFLOPS (2:1) |
FP32 (float) performance | — | 15.67 TFLOPS |
FP64 (double) performance | — | 7.834 TFLOPS (1:2) |
Slot width | Single-slot | Dual-slot |
---|---|---|
TDP | 37 W | 250 W |
Suggested PSU | 200 W | 600 W |
Outputs | 1x DVI1x VGA1x S-Video | No outputs |
Power connectors | None | None |
DirectX | 9.0a | 12 (12_1) |
---|---|---|
OpenGL | 2.0 | 4.6 |
OpenCL | — | 3.0 |
Vulkan | — | 1.2 |
Pixel shader | 2.0a | — |
Vertex shader | 2.0a | — |
CUDA | — | 7.0 |
Shader model | — | 6.6 |