GPU model | TU104 | GV100 |
---|---|---|
GPU variant | N18E-G3-A1 | — |
Architecture | Turing | Volta |
Foundry | TSMC | TSMC |
Manufacturing process | 12 nm | 12 nm |
Number of transistors | 13,600 million | 21,100 million |
Die size | 545 mm² | 815 mm² |
Release date | Jan 29th, 2019 | — |
---|---|---|
Generation | GeForce 20 Mobile | — |
Production | Active | — |
Interface | PCIe 3.0 x16 | — |
Predecessor | GeForce 10 Mobile | — |
Successor | GeForce 30 Mobile | — |
Base clock | 735 MHz | 1200 MHz |
---|---|---|
Boost clock | 1095 MHz | 1455 MHz |
Memory clock | 1500 MHz 12 Gbps effective | 848 MHz 1696 Mbps effective |
Memory size | 8 GB | 32 GB |
---|---|---|
Memory type | GDDR6 | HBM2 |
Memory bus width | 256 bit | 4096 bit |
Bandwidth | 384.0 GB/s | 868.4 GB/s |
Shading units | 2944 | 5120 |
---|---|---|
TMUs | 184 | 320 |
ROPs | 64 | 128 |
SM count | 46 | 80 |
Tensor cores | 368 | 640 |
RT cores | 46 | — |
Cache L1 | 64 KB (per SM) | 128 KB (per SM) |
Cache L2 | 4 MB | 6 MB |
Pixel rate | 70.08 GPixel/s | 186.2 GPixel/s |
---|---|---|
Texture rate | 201.5 GTexel/s | 465.6 GTexel/s |
FP16 (half) performance | 12.89 TFLOPS (2:1) | 29.80 TFLOPS (2:1) |
FP32 (float) performance | 6.447 TFLOPS | 14.90 TFLOPS |
FP64 (double) performance | 201.5 GFLOPS (1:32) | 7.450 TFLOPS (1:2) |
Slot width | Dual-slot | Dual-slot |
---|---|---|
TDP | 80 W | 250 W |
Outputs | No outputs | 1x HDMI3x DisplayPort |
Power connectors | None | 1x 6-pin + 1x 8-pin |
Board number | E4914 SKU 10 | PG500 SKU 0 |
Length | — | 267 mm 10.5 inches |
Width | — | 112 mm 4.4 inches |
Height | — | 40 mm 1.6 inches |
Suggested PSU | — | 600 W |
DirectX | 12 Ultimate (12_2) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 7.5 | 7.0 |
Shader model | 6.6 | 6.6 |
Release date | — | Jun 21st, 2018 |
---|---|---|
Generation | — | GeForce 10 |
Predecessor | — | GeForce 900 |
Successor | — | GeForce 20 |
Production | — | End-of-life |
Interface | — | PCIe 3.0 x16 |