moebiusband/MD-Bench
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
26 Commits 8 Branches 0 Tags 3.4 MiB
C 88.8%
Cuda 8.4%
Makefile 2.8%
cb0ae2b0bb
Go to file
Rafael Ravedutti cb0ae2b0bb Replace inline calls by macros 
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-03-22 21:51:47 +01:00
src Replace inline calls by macros 2021-03-22 21:51:47 +01:00
util Switch License to LGPL3 2020-08-19 10:47:40 +02:00
.gitignore Initial commit 2020-07-23 16:41:14 +02:00
include_CLANG.mk Include Likwid Markers. Allow to switch between SP and DP floats. 2020-11-05 12:41:44 +01:00
include_GCC.mk Initial checkin of simplified miniMD port. Does not work yet. 2020-08-11 16:34:22 +02:00
include_ICC.mk Include Likwid Markers. Allow to switch between SP and DP floats. 2020-11-05 12:41:44 +01:00
LICENSE Switch License to LGPL3 2020-08-19 10:47:40 +02:00
Makefile Add support for AoS data layout 2021-03-20 18:32:50 +01:00
README.md Update README.md 2020-09-07 07:42:45 +02:00

README.md

MD-Bench

A simple, sequential C implementation of the Mantevo miniMD benchmark in less than 1000 LOC.

Build

  1. Open the Makefile and edit the TAG value according to the tool chain used. Currently supported is GCC, CLANG (LLVM), and ICC (Intel).
  2. Open and adapt the compiler flags in <include_<TOOLCHAIN>.mk, e.g. in include_ICC.mk for the Intel tool chain.
  3. Build the binary calling make.

You can clean intermediate build results with make clean, and all build results with make distclean. You have to call make clean before make if you changed the build settings.

Configuration

Currently all settings apart from the options described below are hard-coded in main.c.

Run the benchmark

Without any options 200 steps with system size 32x32x32 is used.

The default can be changed using the following options:

-n / --nsteps <int>:  set number of timesteps for simulation
-nx/-ny/-nz <int>:    set linear dimension of systembox in x/y/z direction