= GRAPE-6 Emulation Library =
Performance tests of our GRAPE-6 emulation library. 
We have integrated a Plummer sphere for 0.5 timeunit with a blocked timestep code. 
We have measured the elapsed time for each model and computed the effective performance of the runs. 
In all runs, we used 1 GPU board per system.

== System configuration & Summary ==
|| System      || CPU    || clock || Ncore ||            Pmax || note || CPU threads||
|| Aizu 5870 || Core i7 || 2.66GHz || 4                  ||369|| dn64 || 8 ||
|| Kiev 5870 || AthlonX2 4850e || 2.5GHz || 2     　　　　||253|| dn64 || 2 ||
|| Beijin 4870 || Opteron 2376HE  || 2.3GHz || 4  　　　　||154||     || 4 ||
|| Aizu 4850 || Core2 || 3.16GHz || 2                    ||159||     ||  2 ||

== Results ==
[[Image(bench_DSD.png)]]

[[Image(bench_D.png)]]

[[Image(t_ablock.png)]]

== Supported functions ==
{{{
// standard functions (implemented)
int g6_open(int i);
int g6_close(int i);
int g6_initialize_jp_buffer(int i, int n);
int g6_set_ti(int dev, double t);
int g6_npipes(void);
int g6_set_j_particle(int clusterid, int address, int index, double tj, double dtj, double mass,
                      double a2by18[3], double a1by6[3], double aby2[3], double v[3], double x[3]);
void g6calc_firsthalf(int clusterid, int nj, int ni, int index[], double xi[][3], double vi[][3], 
                      double fold[][3], double jold[][3], double phiold[], double eps2, double h2[]);
int g6calc_lasthalf(int clusterid, int nj, int ni, int index[], double xi[][3], double vi[][3], 
                    double eps2, double h2[], double acc[][3], double jerk[][3], double pot[]);

// standard functions (implemened but stub)
void g6_set_tunit(int newtunit);
void g6_set_xunit(int newxunit);
void g6_set_overflow_flag_test_mode(int aflag, int jflag, int pflag);
}}}