GPU model | NV17 | GV100 |
---|---|---|
GPU variant | NV17GLM A4 | — |
Architecture | Celsius | Volta |
Foundry | TSMC | TSMC |
Manufacturing process | 150 nm | 12 nm |
Number of transistors | 29 million | 21,100 million |
Die size | 65 mm² | 815 mm² |
Release date | Apr 23rd, 2002 | — |
---|---|---|
Generation | Quadro4 Go | — |
Production | End-of-life | — |
Interface | AGP 4x | — |
Reviews | 26 in our database | — |
Predecessor | Quadro2 Go | — |
Successor | Quadro FX Go | — |
GPU clock | 220 MHz | — |
---|---|---|
Memory clock | 220 MHz | 876 MHz 1752 Mbps effective |
Base clock | — | 1297 MHz |
Boost clock | — | 1530 MHz |
Memory size | 64 MB | 32 GB |
---|---|---|
Memory type | SDR | HBM2 |
Memory bus width | 128 bit | 4096 bit |
Bandwidth | 3.520 GB/s | 897.0 GB/s |
Pixel shaders | 2 | — |
---|---|---|
Vertex shaders | 0 | — |
TMUs | 4 | 320 |
ROPs | 2 | 128 |
Shading units | — | 5120 |
SM count | — | 80 |
Tensor cores | — | 640 |
Cache L1 | — | 128 KB (per SM) |
Cache L2 | — | 6 MB |
Pixel rate | 440.0 MPixel/s | 195.8 GPixel/s |
---|---|---|
Texture rate | 880.0 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) |
TDP | unknown | 250 W |
---|---|---|
Outputs | No outputs | No outputs |
Slot width | — | Dual-slot |
Suggested PSU | — | 600 W |
Power connectors | — | None |
DirectX | 7.0 | 12 (12_1) |
---|---|---|
OpenGL | 1.5 | 4.6 |
OpenCL | — | 3.0 |
Vulkan | — | 1.2 |
Pixel shader | 1.1 | — |
Vertex shader | 1.1 | — |
CUDA | — | 7.0 |
Shader model | — | 6.6 |
Release date | — | Mar 27th, 2018 |
---|---|---|
Generation | — | Tesla |
Production | — | End-of-life |
Interface | — | PCIe 3.0 x16 |