runomp on Mac M1 Max is slower than runfast

[tairov]

Recently I did extensive benchmarks of llama2.c ports I found that C version in runfast mode (singlethreaded) is working faster than runomp (multi threaded)

make runomp CC=/opt/homebrew/opt/llvm/bin/clang; OMP_NUM_THREADS=5 ./run ../models/stories15M.bin -t 0.0 -n 256
...
achieved tok/s: 529.976019

VS

make runfast; ./run ../models/stories15M.bin -t 0.0 -n 256
...
achieved tok/s: 657.738095

Does anyone have insights into why this might be happening?

full benchmark report