From: Yi Huizhan (yihz_at_paratera.com)
Date: Wed Sep 13 2017 - 22:25:13 CDT
Hi, I have test the namd 2.11 and namd 2.12 on Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz.
The case is stmv, the performance result is as follows:
namd 2.11, 2 cpu with 24cores: 214.28s
namd 2.12, 2 cpu with 24cores: 276.62-314.73s
I am curious why the version 2.12 give poor performace?
My configuration is:
NAMD_ARCH = Linux-x86_64
CHARMARCH = multicore-linux64-iccstatic
FLOATOPTS = -ip -axAVX -xHOST
CXX = icpc -std=c++11
CXXOPTS = -static-intel -O2 $(FLOATOPTS)
CXXNOALIASOPTS = -O2 -fno-alias $(FLOATOPTS)
CXXCOLVAROPTS = -O2 -ip
CC = icc
COPTS = -static-intel -O2 $(FLOATOPTS)
The intel compiler version is composer_xe_2015.1.133.
This archive was generated by hypermail 2.1.6 : Sun Dec 31 2017 - 23:21:40 CST