GPU model | C67 | GV100 |
---|---|---|
Architecture | Curie | Volta |
Manufacturing process | 90 nm | 12 nm |
Number of transistors | 112 million | 21,100 million |
Die size | 81 mm² | 815 mm² |
Foundry | — | TSMC |
Release date | Feb 1st, 2006 | — |
---|---|---|
Generation | GeForce 7 IGP | — |
Production | End-of-life | — |
Interface | PCI | — |
Predecessor | GeForce 6 IGP | — |
Successor | GeForce 8 IGP | — |
GPU clock | 425 MHz | — |
---|---|---|
Memory clock | System Shared | 876 MHz 1752 Mbps effective |
Base clock | — | 1297 MHz |
Boost clock | — | 1530 MHz |
Memory size | System Shared | 32 GB |
---|---|---|
Memory type | System Shared | HBM2 |
Memory bus width | System Shared | 4096 bit |
Bandwidth | System Dependent | 897.0 GB/s |
Pixel shaders | 2 | — |
---|---|---|
Vertex shaders | 1 | — |
TMUs | 1 | 320 |
ROPs | 1 | 128 |
Shading units | — | 5120 |
SM count | — | 80 |
Tensor cores | — | 640 |
Cache L1 | — | 128 KB (per SM) |
Cache L2 | — | 6 MB |
Pixel rate | 425.0 MPixel/s | 195.8 GPixel/s |
---|---|---|
Vertex rate | 106.3 MVertices/s | — |
Texture rate | 425.0 MTexel/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 | IGP | Dual-slot |
---|---|---|
TDP | unknown | 250 W |
Outputs | No outputs | No outputs |
Suggested PSU | — | 600 W |
Power connectors | — | None |
DirectX | 9.0c (9_3) | 12 (12_1) |
---|---|---|
OpenGL | 2.1 | 4.6 |
OpenCL | — | 3.0 |
Vulkan | — | 1.2 |
Shader model | 3.0 | 6.6 |
CUDA | — | 7.0 |
Release date | — | Mar 27th, 2018 |
---|---|---|
Generation | — | Tesla |
Production | — | End-of-life |
Interface | — | PCIe 3.0 x16 |