GPU model | GP104 | TU104 |
---|---|---|
GPU variant | N17E-G2-A1 | N18E-G3-A1 |
Architecture | Pascal | Turing |
Foundry | TSMC | TSMC |
Manufacturing process | 16 nm | 12 nm |
Number of transistors | 7,200 million | 13,600 million |
Die size | 314 mm² | 545 mm² |
Release date | Jun 27th, 2017 | Jan 29th, 2019 |
---|---|---|
Generation | GeForce 10 Mobile | GeForce 20 Mobile |
Production | End-of-life | Active |
Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Reviews | 125 in our database | — |
Predecessor | GeForce 900M | GeForce 10 Mobile |
Successor | GeForce 20 Mobile | GeForce 30 Mobile |
Base clock | 1215 MHz | 735 MHz |
---|---|---|
Boost clock | 1379 MHz | 1095 MHz |
Memory clock | 2002 MHz 8 Gbps effective | 1500 MHz 12 Gbps effective |
Memory size | 8 GB | 8 GB |
---|---|---|
Memory type | GDDR5 | GDDR6 |
Memory bus width | 256 bit | 256 bit |
Bandwidth | 256.3 GB/s | 384.0 GB/s |
Shading units | 2048 | 2944 |
---|---|---|
TMUs | 128 | 184 |
ROPs | 64 | 64 |
SM count | 16 | 46 |
Cache L1 | 48 KB (per SM) | 64 KB (per SM) |
Cache L2 | 2 MB | 4 MB |
Tensor cores | — | 368 |
RT cores | — | 46 |
Pixel rate | 88.26 GPixel/s | 70.08 GPixel/s |
---|---|---|
Texture rate | 176.5 GTexel/s | 201.5 GTexel/s |
FP16 (half) performance | 88.26 GFLOPS (1:64) | 12.89 TFLOPS (2:1) |
FP32 (float) performance | 5.648 TFLOPS | 6.447 TFLOPS |
FP64 (double) performance | 176.5 GFLOPS (1:32) | 201.5 GFLOPS (1:32) |
Slot width | MXM Module | Dual-slot |
---|---|---|
TDP | 115 W | 80 W |
Outputs | No outputs | No outputs |
Power connectors | None | None |
Board number | E2914 SKU 10 | E4914 SKU 10 |
DirectX | 12 (12_1) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 6.1 | 7.5 |
Shader model | 6.4 | 6.6 |