mshr-h commented on PR #19580: URL: https://github.com/apache/tvm/pull/19580#issuecomment-4469824240
Benchmark on NVIDIA DGX Spark: | Model | Partitions | Baseline mean ms | XNNPACK mean ms | Speedup | |---|---:|---:|---:|---:| | `xnnpack_tiny_cnn` | 4 | 0.002500 | 0.003049 | 0.820x | | `xnnpack_static_qs8_tiny_cnn` | 2 | 0.002587 | 0.001711 | 1.512x | | `xnnpack_large_cnn_fp32` | 5 | 0.412256 | 0.044388 | 9.288x | | `xnnpack_large_mlp_fp32` | 4 | 0.148401 | 0.018079 | 8.209x | | `xnnpack_large_qs8_cnn` | 2 | 0.003716 | 0.002309 | 1.609x | -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
