Memory throughput would generally be measured in GB/sec, not GB. In general, the best achievable bandwidth of GPU memory is typically in the range of 75% to 85% of the theoretical value, dependent on a variety of factors (e.g. ECC on/off, the type of DRAM used, GPU core frequency).
Related Topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Quadro 4000 Bandwidth The device to device bandwidth obtained with | 8 | 3511 | March 7, 2011 | |
| Using bandwidthTest tool, D2D performance More than the official given bandwidth | 6 | 779 | October 28, 2022 | |
| Is my bandwidth calculation right? bandwidth | 3 | 1445 | November 13, 2009 | |
| Bandwith Problem | 7 | 2633 | March 16, 2009 | |
| Device to device bandwidth, bandwidth test vs theoretical maximum | 7 | 3149 | May 27, 2014 | |
| Using bandwidthTest, D2D performance exceeds theoretical bandwidth | 1 | 380 | October 27, 2022 | |
| Is the GDDR5X transfer size 256B on the GTX 1080 Ti? | 6 | 1183 | September 28, 2017 | |
| Effective Bandwidth Problem | 13 | 7706 | March 23, 2011 | |
| Bandwidth measurement Theortical bandwidth vs BandwidthTest(SDK) results | 4 | 1541 | May 30, 2011 | |
| How to Implement Performance Metrics in CUDA C/C++ | 20 | 838 | March 11, 2020 |