GPU model | TU104 | GA104 |
---|---|---|
GPU variant | N19E-Q5-A1 | — |
Architecture | Turing | Ampere |
Foundry | TSMC | Samsung |
Manufacturing process | 12 nm | 8 nm |
Number of transistors | 13,600 million | 17,400 million |
Die size | 545 mm² | 392 mm² |
Release date | May 27th, 2019 | Unknown |
---|---|---|
Generation | Quadro Mobile (Tx000) | Quadro Mobile (Ax000) |
Production | Active | Active |
Interface | PCIe 3.0 x16 | PCIe 4.0 x16 |
Base clock | 1365 MHz | 900 MHz |
---|---|---|
Boost clock | 1770 MHz | 1575 MHz |
Memory clock | 1750 MHz 14 Gbps effective | 1750 MHz 14 Gbps effective |
Memory size | 16 GB | 16 GB |
---|---|---|
Memory type | GDDR6 | GDDR6 |
Memory bus width | 256 bit | 256 bit |
Bandwidth | 448.0 GB/s | 448.0 GB/s |
Shading units | 3072 | 6144 |
---|---|---|
TMUs | 192 | 192 |
ROPs | 64 | 96 |
SM count | 48 | 48 |
Tensor cores | 384 | 192 |
RT cores | 48 | 48 |
Cache L1 | 64 KB (per SM) | 128 KB (per SM) |
Cache L2 | 4 MB | 4 MB |
Pixel rate | 113.3 GPixel/s | 151.2 GPixel/s |
---|---|---|
Texture rate | 339.8 GTexel/s | 302.4 GTexel/s |
FP16 (half) performance | 21.75 TFLOPS (2:1) | 19.35 TFLOPS (1:1) |
FP32 (float) performance | 10.87 TFLOPS | 19.35 TFLOPS |
FP64 (double) performance | 339.8 GFLOPS (1:32) | 604.8 GFLOPS (1:32) |
Slot width | IGP | — |
---|---|---|
TDP | 110 W | 140 W |
Outputs | No outputs | No outputs |
Power connectors | None | None |
DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 7.5 | 8.6 |
Shader model | 6.6 | 6.6 |