User:Chad Brewbaker/Notebook/Eperimental Algorithmics/2010/11/02

From OpenWetWare
Jump to: navigation, search
Owwnotebook icon.png Project name Report.pngMain project page
Resultset previous.pngPrevious entry      Next entryResultset next.png

Entry title

  • For Bannerman's template I changed the workgroup size to 64 as some ATI cards were having issues at a higher number.
  • Changed the number of particles in Bannerman's template to 4096, which is 16 million dense interactions per iteration.

Timings on commit b5cf7d127453d5940fb5 for Bannerman's (foo.out): real 1m16.780s user 0m0.152s sys 0m0.419s

real 1m16.951s user 0m0.154s sys 0m0.412s

Tried to play with float3 on the MacBook Nvidia 9400M, the libraries seem to be borked.

Reverting in GIT to the last commit is done by $git reset --hard HEAD

HEAD is now at b5cf7d1 Changed the bannerman template to 4096 particles.

...Actually we probably should have just done a git checkout from the last push :p

  • Note for Exp Alg talk, we should have made a branch for the above experiment. Naming convention date_experimentname? 2010_11_02_float3exp ?
  • As per Michał Trybus(Stakoverflow): git checkout -b experiment_name and commit.