GPU model | GA104 | GP104 |
---|---|---|
GPU variant | GA104-770-A1 | — |
Architecture | Ampere | Pascal |
Foundry | Samsung | TSMC |
Manufacturing process | 8 nm | 16 nm |
Number of transistors | 17,400 million | 7,200 million |
Die size | 392 mm² | 314 mm² |
Release date | Jan 12th, 2021 | Feb 21st, 2018 |
---|---|---|
gpu.details.availability | Feb 2nd, 2021 | — |
Generation | GeForce 30 Mobile | Quadro Mobile (Px200) |
Predecessor | GeForce 20 Mobile | — |
Production | Active | End-of-life |
Interface | PCIe 4.0 x16 | MXM-B (3.0) |
Reviews | 1 in our database | — |
Base clock | 1110 MHz | 1557 MHz |
---|---|---|
Boost clock | 1560 MHz | 1747 MHz |
Memory clock | 1750 MHz 14 Gbps effective | 1804 MHz 7.2 Gbps effective |
Memory size | 8 GB | 16 GB |
---|---|---|
Memory type | GDDR6 | GDDR5 |
Memory bus width | 256 bit | 256 bit |
Bandwidth | 448.0 GB/s | 230.9 GB/s |
Shading units | 5120 | 2560 |
---|---|---|
TMUs | 160 | 160 |
ROPs | 80 | 64 |
SM count | 40 | 20 |
Tensor cores | 160 | — |
RT cores | 40 | — |
Cache L1 | 128 KB (per SM) | 48 KB (per SM) |
Cache L2 | 4 MB | 2 MB |
Pixel rate | 124.8 GPixel/s | 111.8 GPixel/s |
---|---|---|
Texture rate | 249.6 GTexel/s | 279.5 GTexel/s |
FP16 (half) performance | 15.97 TFLOPS (1:1) | 139.8 GFLOPS (1:64) |
FP32 (float) performance | 15.97 TFLOPS | 8.945 TFLOPS |
FP64 (double) performance | 249.6 GFLOPS (1:64) | 279.5 GFLOPS (1:32) |
TDP | 115 W | 100 W |
---|---|---|
Outputs | No outputs | No outputs |
Power connectors | None | None |
Slot width | — | MXM Module |
DirectX | 12 Ultimate (12_2) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 8.6 | 6.1 |
Shader model | 6.6 | 6.4 |