| | | | | | | requested parallelism | walltime sum (s) | nb instances | any sync average per thread time (s) | any wait average per thread time (s) | parallelism overhead (%) | local speedup if perfectly balanced | global speedup if perfectly balanced |
|---|
| start addr | function name | source location | level | ancestor thread num | invoker | parallel or teams | orig_0 | orig_0 | orig_0 | orig_0 | orig_0 | orig_0 | orig_0 | orig_0 |
|---|
| libggml-cpu.so:0x142b0 | ggml_graph_compute | ggml-cpu.c:682 | 0 | 0 | runtime | parallel | 192 | 19.289 | 513 | 14.329 | 14.269 | 74.3 | 3.889 | 3.437 |
| libggml-cpu.so:0x44936 | ggml_backend_amx_convert_weight(ggml_tensor*, void const*, u... | mmq.cpp:2337 | 0 | 0 | runtime | parallel | 192 | 0.162 | 225 | 68.4 E-3 | 68.4 E-3 | 42.1 | 1.728 | 1.003 |
