Hi Kor, For shared-memory systems, uftrace [1] works great. It gives you great visualization with not too much performance impact. Ray Kim [1] https://github.com/namhyung/uftrace -----Original Message----- From: "Jong, K. de (Kor)"<k.dejo...@uu.nl> To: "hpx-users@stellar.cct.lsu.edu"<hpx-users@stellar.cct.lsu.edu>; Cc: Sent: 2019-05-13 (월) 20:19:43 (GMT+09:00) Subject: [hpx-users] Performance evaluation software Dear HPX-ers,
I am currently looking at ways to get insights into where and when time is spent in my HPX processes (on Linux, desktops and MPI clusters). After reading various sources of information I am still a bit uncertain about what a good approach is. Before spending time/money building or buying packages which seem to be useful, but may have overlapping functionality (OTF2, APEX, TAU, Scalasca, Vampir, ...), I would like to ask you what your favorite setup is for profiling and tracing of HPX processes. I am looking for the minimal set of performance evaluation packages that handles the majority of use-cases. Thanks! Kor _______________________________________________ hpx-users mailing list hpx-users@stellar.cct.lsu.edu https://mail.cct.lsu.edu/mailman/listinfo/hpx-users
_______________________________________________ hpx-users mailing list hpx-users@stellar.cct.lsu.edu https://mail.cct.lsu.edu/mailman/listinfo/hpx-users
