Hello,
I tried to optimize a small parallel program, which is parallelized with OpenMP.
The program itself does operations on arrays and the optimization I did was to
reduce cache miss.
At first, I compiled the program with GCC under Linux and -O3 was enabled. I ran
the program in a quad-core machine but the running time wasn't very stable. I
thought it was because my program was interrupted by other processes or threads
were scheduled to other cores. So I ran the program with each thread attached to
a CPU and with the highest real-time priority in Linux. But still the running
time varied from 60 to 90 milliseconds. I couldn't find any reason to explain
why the running time could be so different, but I still wasn't really surprised
by the result until I used Intel C compiler.
After I compiled the code with Intel's compiler, the running time is always
about 40ms. The performance improvement isn't surprising to me, but I don't know
why the running time doesn't change any more. At beginning, I thought it might
be caused by cache miss. After I profiled the program with AMD CodeAnalyst, I
didn't see many cache misses in either binary executable.
Since I'm doing optimization, I hope to find out the reason. Can anyone tell me
what is the possible reason that can cause time difference?
I also attach the program in case someone would like to take a look.
Thank you,
Zheng Da
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <math.h>
#include "Aplc.h"
#include "Apl3lib.h"
#define HEAPSIZE 1048576
#define BVBFLE32 512
#define IVBFLE 16384
#define EVBFLE 16384
#define CVBFLE 8192
#define minn -7.237005577332262e75
#define QDCT 1e-13
#define QDRL 16807
#define QDPP 7
int c2[2];
int lf1= 0x80000000;
int bvbf[BVBFLE32];
char cvbf[CVBFLE];
int r0, r1, r2, r8, t, n, i, j, new, time1, time2, th;
int w0, w1, w2, w3, w4, w5, w6, u0, u1, u2, u3, u4, u5, u6;
int q0, q1, q2, q3, q4, q5, q6, v0, v1, v2, v3, c6;
int l0, l1, l2, l3, l4, l5, l6, m0, m1, m2, m3, m4, m5, m6;
int qw, qi, sw, si, s0, s1, s2, s3, s4, s5, s6, freti;
double d, fretf, epsln;
char fretc;
int r15= HEAPSIZE;
int rseed= QDRL, initf;
unsigned int tl,ttl,wa,wb;
unsigned int * twp;
int * v4= bvbf;
char * v7= cvbf;
int * fretip, * v5;
double * fretfp, * v6;
char * fretcp, * lop, * rop, * cad0, * heap;
int lshp[8], rshp[8], cad[50], dl[7], tdl[7], vdl[7];
int * p0, * p1, * lo0, * lo1, * ro0,* ro1,* t0,* t1,* p10,* p11,*p12;
int * lo13, * lo10,* ro13, * ro10, * lo11, * ro11,* lo12,* ro12;
int * id0, * id1, * id2, * id3, * id4, * id5, * id6;
double * p2,* t2,* lo2,* ro2,* p20,* p21,* p22,* lo24,* ro24,* lo25;
double * lo20,* ro20,* lo21,* ro21,* lo22,* ro22,* lo23,* ro23,* ro25;
char *ro30, * p3, *t3, * lo3, * ro3, *pTarg, *pSrc, *pBuff0, *pBuff1;
STOFM2 v49;
STOFM3 v50;
STOFM2 v51;
STOFM3 v52;
STOFM2 v53;
STOFM3 v54;
STOFM3 v28;
main(argc,argv)
int argc; char * argv[];
{
char * lparm, * rparm;
char ltype, rtype;
int g19;
int lleng= 1;
FILE *fpl, *fpr, *fopen();
extern int apl_sec();
init();
initf= 1;
heap=amalloc(HEAPSIZE);
rt_prio();
#pragma omp parallel
{
printf("There are %d threads\n", omp_get_num_threads ());
if (omp_get_num_threads() > 1)
thread_attach_cpu(omp_get_thread_num());
}
v5=amalloc(65536); v6=amalloc(13107200);
{
while (--argc > 0)
if (argc>0) {lparm = *argv; *argv = *argv + 1;}
else rparm = *argv;
}
if( argv[1] == NULL )
fpl= a_fopen("MORGAN.LEF","r");
else
{
sprintf(cvbf, "%s.LEF", argv[1]);
fpl= a_fopen(cvbf, "r");
}
fscanf(fpl,"%c %d",<ype,&lshp[0]);
if( ltype!= 'I') {
printf("The type of the left arguement is mismatched.\n"); exit(99);}
if( lshp[0]!= 0) {
printf("The rank of the left arguement is mismatched.\n"); exit(99);}
for( i = 1; i < 1 + lshp[0]; ++i) {
fscanf(fpl," %d",&lshp[i]); lleng *= lshp[i];}
while (fgetc(fpl) != '\n') {}
fscanf(fpl,"%d",&g19);
lleng = 1;
if( argv[1] == NULL )
fpr= a_fopen("MORGAN.RIG","r");
else
{
sprintf(cvbf, "%s.RIG", argv[1]);
fpr= a_fopen(cvbf, "r");
}
fscanf(fpr,"%c %d",&rtype,&rshp[0]);
if( rtype!= 'E') {
printf("The type of the right arguement is mismatched.\n"); exit(99);}
if( rshp[0]!= 3) {
printf("The rank of the right arguement is mismatched.\n"); exit(99);}
for( i = 1; i < 1 + rshp[0]; ++i) {
fscanf(fpr," %d",&rshp[i]); lleng *= rshp[i];}
while (fgetc(fpr) != '\n') {}
rshp[0]= r0 = lleng;inchp2;
rop= &heap[r15]; p2 = (double *) rop;
// for(i = 0; i < lleng; ++i) {
// fscanf(fpr,"%lf",p2);
// ++p2;
// }
time1 = apl_sec();
MORGAN2 (g19,ro2);
time2 = apl_sec();
fprintf(stderr, "\n execution time in ms %d\n",time2-time1);
/* OUTPUT generates the following code */
// p2 = fretfp;
// w0 = cad[3];
// w1= cad[1]/w0;
// for (u0=0; u0<w1; u0++) {
// if(w0<11) for(v1=0;v1<w0;v1++){a_prtD0(*p2);++p2;}
// else for (v1=0;v1<w0;v1++)
// {a_prtD0(*p2); ++p2; if ((v1%10)==9) printf("\n");}
// putchar('\n');
// }
// putchar('\n');
free(heap); free(v5); free(v6); system("pause"); exit(0);
}
/* CODE SEGMENT FOR FUNCTION MORGAN2 */
MORGAN2 (v19,p20)
int v19;
double* p20;
{
int num = 0;
int cache_start[num_threads];
int max_cache_num;
int start_time;
int cache_idx;
char v8, v11;
int oldr15, v9, v12, v13, v17;
double v10, v14, v15, v16;
STOFM3 v18;
STOFM3 v21;
STOFM3 v22;
STOFM3 v31;
STOFM3 v32;
STOFM3 v34;
STOFM3 v35;
STOFM3 v36;
STOFM3 v37;
STOFM3 v38;
STOFM3 v39;
STOFM3 v40;
STOFM3 v41;
STOFM3 v42;
STOFM3 v43;
STOFM3 v44;
STOFM3 v45;
STOFM3 v46;
STOFM3 v47;
STOFM3 v48;
STOFM3 v20;
v18.maxl = -1;
v49.maxl= -1; v50.maxl= -1; v51.maxl= -1;
v52.maxl= -1; v53.maxl= -1; v54.maxl= -1;
v28.maxl = -1;
v21.maxl = -1;
v22.maxl = -1;
v31.maxl = -1;
v32.maxl = -1;
v34.maxl = -1;
v35.maxl = -1;
v36.maxl = -1;
v37.maxl = -1;
v38.maxl = -1;
v39.maxl = -1;
v40.maxl = -1;
v41.maxl = -1;
v42.maxl = -1;
v43.maxl = -1;
v44.maxl = -1;
v45.maxl = -1;
v46.maxl = -1;
v47.maxl = -1;
v48.maxl = -1;
memset(cache_start, 0, sizeof (cache_start));
r0= rshp[0];
for (v1=0; v1<3; v1++)
v20.dims[v1+0]=rshp[v1+1];
if (initf == 1)
{
v20.valp= rop;
v20.reall= v20.maxl= r0;
initf= 0;
} else {
v20.reall= v20.maxl= r0;
inchp2; v20.valp= &heap[r15];
ro2= (double *) v20.valp;
for (v1=0; v1<r0; v1++)
ro2[v1]= p20[v1];
}
new=0;
/****************** LINE 1 ******************/
/* INDEXV generates the following code */
lo2 = (double *) v20.valp;
dl[2]= t = 1;
for (u0=0; u0<2; u0++)
t= dl[1-u0]= t*v20.dims[2-u0];
cad[2]= v20.dims[1];
cad[3]= v20.dims[2];
n=0;
n += dl[0]*(1-1);
tdl[0] =v20.dims[2];
r0= tdl[0]*v20.dims[1];
cad[1]=r0;
INIT_STARTP(v21);
if (new=r0>v21.maxl) {
v21.maxl=r0;
inchp2;cad0= &heap[r15];
}
else cad0= v21.valp; p2 = (double *) cad0;
if (r0==0) goto l2;
for (u0=0; u0<v20.dims[1]; u0++)
{
w0 = dl[1]*u0;
q0 = tdl[0]*u0;
for (u1=0; u1<v20.dims[2]; u1++)
p2[q0+u1] = lo2[n+w0+dl[2]*u1];
}
l2:
for (v1=0; v1<2; v1++)
v21.dims[v1+0]= cad[v1+2];
v21.valp = cad0;
v21.reall= cad[1];
v21.curr_rows = NULL;
/****************** LINE 2 ******************/
/* INDEXV generates the following code */
lo2 = (double *) v20.valp;
dl[2]= t = 1;
for (u0=0; u0<2; u0++)
t= dl[1-u0]= t*v20.dims[2-u0];
cad[2]= v20.dims[1];
cad[3]= v20.dims[2];
n=0;
n += dl[0]*(2-1);
tdl[0] =v20.dims[2];
r0= tdl[0]*v20.dims[1];
cad[1]=r0;
INIT_STARTP(v22);
if (new=r0>v22.maxl) {
v22.maxl=r0;
inchp2;cad0= &heap[r15];
}
else cad0= v22.valp;
p2 = (double *) cad0;
if (r0==0) goto l3;
for (u0=0; u0<v20.dims[1]; u0++)
{
w0 = dl[1]*u0;
q0 = tdl[0]*u0;
for (u1=0; u1<v20.dims[2]; u1++)
p2[q0+u1] = lo2[n+w0+dl[2]*u1];
}
l3:
for (v1=0; v1<2; v1++)
v22.dims[v1+0]= cad[v1+2];
v22.valp = cad0;
v22.reall= cad[1];
v22.curr_rows = NULL;
max_cache_num = 200; // TODO
int init = 0;
int local_first = 1;
start_time = apl_sec();
#pragma omp parallel for default(shared) private(cache_idx, v1, v2, d) firstprivate(local_first)
for(cache_idx = 0; cache_idx < max_cache_num; cache_idx++)
{
int slice;
STOFM3 v23;
STOFM3 v24;
STOFM3 v25;
STOFM3 v26;
STOFM3 v27;
STOFM3 v33;
v23.maxl = -1;
v24.maxl = -1;
v25.maxl = -1;
v26.maxl = -1;
v27.maxl = -1;
v33.maxl = -1;
if (local_first)
{
//#pragma omp critical
// {
// cache_start[omp_get_thread_num()] = cache_idx;
// }
//#ifdef DEBUG
// fprintf (stderr, "thread %d starts at %d\n", omp_get_thread_num(), cache_idx);
//#endif
}
if (cache_idx && init == 0)
{
while (init == 0)
{
#pragma omp flush(init)
}
}
/****************** LINE 3 ******************/
/****************** LINE 4 ******************/
if (cache_idx == 0)
{
/* GENSCAN generates the following code */
p2 = (double *) v28.valp;
INIT_STARTP(v28);
for (v1=0; v1<2; v1++)
v28.orig_dims[v1+0] = v28.dims[v1+0]= v21.dims[v1+0];
r0 = v21.reall;
cad[1]=r0;
if (new=r0>v28.maxl) {
v28.maxl=r0;
inchp2;v28.valp= &heap[r15];
}
v28.reall=r0; /* 3 instructions genarated by INCHEAPP */
if (r0==0) goto l4;
}
FORAXIS0_CACHE(v28)
{
v2 = 0;
d = 0;
FORAXIS1(v28)
DVAL(v28)=d=d+DVAL(v21);
// SET_ROW(v28, v1);
}
l4:
if (cache_idx == 0)
v9 = -v19; /* code for - */
/***** PFCATENA *****/
if (cache_idx == 0)
{
r0 = cad[1]= 1+1;
cad[1] =r0 =2;
v5[0] = 0;
v5[1]= v9;
/* PFDROP generates the following code */
ro2 = (double *) v28.valp;
dl[1]= t = 1;
for (u0=0; u0<1; u0++)
t= dl[0-u0]= t*v28.dims[1-u0];
r0=t=1;
cad[3] = max(0, v28.dims[1]-abs(v5[1]));
t=tdl[0] = t*cad[3] ;
cad[2] = max(0,v28.dims[0]-abs(v5[0]));
INIT_STARTP(v31);
v31.source = &v28;
if (v5[0] > 0)
v31.startp[0] = v5[0];
else
v31.startp[0] = 0;
if (v5[1] > 0)
v31.startp[1] = v5[1];
else
v31.startp[1] = 0;
v31.dims[0] = cad[2];
v31.dims[1] = cad[3];
memcpy (v31.orig_dims, v28.orig_dims, sizeof (v28.orig_dims));
v31.valp = v28.valp;
v31.reall= v31.dims[0] * v31.dims[1];
}
/***** PFCATENA *****/
if (cache_idx == 0)
v9 = v19-1; /* code for - */
/***** PFCATENA *****/
if (cache_idx == 0)
{
r0 = cad[1]= 1+1;
cad[1] =r0 =2;
v5[0] = 0;
v5[1]= v9;
/* PFDROP generates the following code */
ro2 = (double *) v28.valp;
dl[1]= t = 1;
for (u0=0; u0<1; u0++)
t= dl[0-u0]= t*v28.dims[1-u0];
r0=t=1;
cad[3] = max(0, v28.dims[1]-abs(v5[1]));
t=tdl[0] = t*cad[3];
cad[2] = max(0,v28.dims[0]-abs(v5[0]));
INIT_STARTP(v46);
v46.source = &v28;
if (v5[0] > 0)
v46.startp[0] = v5[0];
else
v46.startp[0] = 0;
if (v5[1] > 0)
v46.startp[1] = v5[1];
else
v46.startp[1] = 0;
v46.dims[0] = cad[2];
v46.dims[1] = cad[3];
memcpy (v46.orig_dims, v28.orig_dims, sizeof (v28.orig_dims));
v46.valp = v28.valp;
v46.reall= v46.dims[0] * v46.dims[1];
}
if (local_first)
{
r0=v46.reall;
INIT_STARTP(v23);
for (v1=0; v1<2; v1++)
v23.dims[v1+0]=v46.dims[v1+0];
memcpy(v23.orig_dims, v23.dims, sizeof(v23.dims));
cad[1]=r0;
if (new=r0>v23.maxl) {
v23.maxl=r0;
inchp2;v23.valp= &heap[r15];
}
v23.reall=r0; /* 3 instructions genarated by INCHEAPP */
}
FORAXIS0_CACHE(v23) /* code for - */
{
// while (!ROW_AVAIL(&v46, v1));
// while (!ROW_AVAIL(&v31, v1));
FORAXIS1(v23)
{
if (v2 == 0)
SLICE_DVAL(v23) = DROPPED_DVAL(v46);
else
SLICE_DVAL(v23) = DROPPED_DVAL(v46) - CD_DVAL(v31, -1);
}
// SET_ROW(v23, v1);
}
/****************** LINE 5 ******************/
/* GENSCAN generates the following code */
if (cache_idx == 0)
{
p2 = (double *) v28.valp;
ro2 = (double *) v22.valp;
INIT_STARTP(v28);
for (v1=0; v1<2; v1++)
v28.orig_dims[v1+0] = v28.dims[v1+0]= v22.dims[v1+0];
r0 = v22.reall;
cad[1]=r0;
if (new=r0>v28.maxl) {
v28.maxl=r0;
inchp2;v28.valp= &heap[r15];
}
v28.reall=r0; /* 3 instructions genarated by INCHEAPP */
p2 = (double *) v28.valp;
if (r0==0) goto l5;
r0=v22.dims[1];
r1=v22.dims[0];
}
FORAXIS0_CACHE(v28)
{
v2 = 0;
d = 0;
FORAXIS1(v28)
DVAL(v28)=d=d+DVAL(v22);
}
l5:
if (cache_idx == 0)
v9 = -v19; /* code for - */
/***** PFCATENA *****/
if (cache_idx == 0)
{
r0 = cad[1]= 1+1;
cad[1] =r0 =2;
v5[0] = 0;
v5[1]= v9;
/* PFDROP generates the following code */
ro2 = (double *) v28.valp;
dl[1]= t = 1;
for (u0=0; u0<1; u0++)
t= dl[0-u0]= t*v28.dims[1-u0];
r0=t=1;
cad[3] = max(0, v28.dims[1]-abs(v5[1]));
t=tdl[0] = t*cad[3];
cad[2] = max(0,v28.dims[0]-abs(v5[0]));
INIT_STARTP(v32);
if (v5[0] > 0)
v32.startp[0] = v5[0];
else
v32.startp[0] = 0;
if (v5[1] > 0)
v32.startp[1] = v5[1];
else
v32.startp[1] = 0;
v32.dims[0] = cad[2];
v32.dims[1] = cad[3];
memcpy (v32.orig_dims, v28.orig_dims, sizeof (v28.orig_dims));
v32.valp = v28.valp;
v32.reall= v32.dims[0] * v32.dims[1];
}
/***** PFCATENA *****/
if (cache_idx == 0)
v9 = v19-1; /* code for - */
/***** PFCATENA *****/
if (cache_idx == 0)
{
r0 = cad[1]= 1+1;
cad[1] =r0 =2;
v5[0] = 0;
v5[1]= v9;
/* PFDROP generates the following code */
ro2 = (double *) v28.valp;
dl[1]= t = 1;
for (u0=0; u0<1; u0++)
t= dl[0-u0]= t*v28.dims[1-u0];
r0=t=1;
cad[3] = max(0, v28.dims[1]-abs(v5[1]));
t=tdl[0] = t*cad[3];
cad[2] = max(0,v28.dims[0]-abs(v5[0]));
INIT_STARTP(v47);
if (v5[0] > 0)
v47.startp[0] = v5[0];
else
v47.startp[0] = 0;
if (v5[1] > 0)
v47.startp[1] = v5[1];
else
v47.startp[1] = 0;
v47.dims[0] = cad[2];
v47.dims[1] = cad[3];
memcpy (v47.orig_dims, v28.orig_dims, sizeof (v28.orig_dims));
v47.valp = v28.valp;
v47.reall= v47.dims[0] * v47.dims[1];
}
if (local_first)
{
r0=v47.reall;
INIT_STARTP(v25);
for (v1=0; v1<2; v1++)
v25.dims[v1+0]=v47.dims[v1+0];
memcpy(v25.orig_dims, v25.dims, sizeof(v25.dims));
cad[1]=r0;
if (new=r0>v25.maxl) {
v25.maxl=r0;
inchp2;v25.valp= &heap[r15];
}
v25.reall=r0; /* 3 instructions genarated by INCHEAPP */
}
FORALL2_CACHE(v25) /* code for - */
{
if (v2 == 0)
SLICE_DVAL(v25) = DROPPED_DVAL(v47);
else
SLICE_DVAL(v25) = DROPPED_DVAL(v47) - CD_DVAL(v32, -1);
}
/****************** LINE 6 ******************/
if (local_first)
{
r0=v21.reall;
for (v1=0; v1<2; v1++)
v33.dims[v1+0]= v21.dims[v1+0];
cad[1]=r0;
if (new=r0>v33.maxl) {
v33.maxl=r0;
inchp2;v33.valp= &heap[r15];
}
v33.reall=r0; /* 3 instructions genarated by INCHEAPP */
p2 = (double *) v33.valp;
lo2 = (double *) v21.valp;
}
FORALL2_CACHE(v33)
DVAL(v33) = DVAL(v21) * DVAL(v21);
/* GENSCAN generates the following code */
if (cache_idx == 0)
{
p2 = (double *) v28.valp;
ro2 = (double *) v33.valp;
INIT_STARTP(v28);
for (v1=0; v1<2; v1++)
v28.orig_dims[v1+0] = v28.dims[v1+0]= v33.dims[v1+0];
r0 = v33.reall;
cad[1]=r0;
if (new=r0>v28.maxl) {
v28.maxl=r0;
inchp2;v28.valp= &heap[r15];
}
v28.reall=r0; /* 3 instructions genarated by INCHEAPP */
p2 = (double *) v28.valp;
if (r0==0) goto l6;
r0=v33.dims[1];
r1=v33.dims[0];
}
FORAXIS0_CACHE(v28)
{
v2 = 0;
d = 0;
FORAXIS1(v28)
DVAL(v28)=d=d+DVAL(v33);
}
l6:
if (cache_idx == 0)
v9 = -v19; /* code for - */
/***** PFCATENA *****/
if (cache_idx == 0)
{
r0 = cad[1]= 1+1;
cad[1] =r0 =2;
v5[0] = 0;
v5[1]= v9;
/* PFDROP generates the following code */
ro2 = (double *) v28.valp;
dl[1]= t = 1;
for (u0=0; u0<1; u0++)
t= dl[0-u0]= t*v28.dims[1-u0];
r0=t=1;
cad[3] = max(0, v28.dims[1]-abs(v5[1]));
t=tdl[0] = t*cad[3];
cad[2] = max(0,v28.dims[0]-abs(v5[0]));
INIT_STARTP(v34);
if (v5[0] > 0)
v34.startp[0] = v5[0];
else
v34.startp[0] = 0;
if (v5[1] > 0)
v34.startp[1] = v5[1];
else
v34.startp[1] = 0;
v34.dims[0] = cad[2];
v34.dims[1] = cad[3];
memcpy (v34.orig_dims, v28.orig_dims, sizeof (v28.orig_dims));
v34.valp = v28.valp;
v34.reall= v34.dims[0] * v34.dims[1];
}
/***** PFCATENA *****/
if (cache_idx == 0)
v9 = v19-1; /* code for - */
/***** PFCATENA *****/
if (cache_idx == 0)
{
r0 = cad[1]= 1+1;
cad[1] =r0 =2;
v5[0] = 0;
v5[1]= v9;
/* PFDROP generates the following code */
ro2 = (double *) v28.valp;
dl[1]= t = 1;
for (u0=0; u0<1; u0++)
t= dl[0-u0]= t*v28.dims[1-u0];
r0=t=1;
cad[3] = max(0, v28.dims[1]-abs(v5[1]));
t=tdl[0] = t*cad[3] ;
cad[2] = max(0,v28.dims[0]-abs(v5[0]));
INIT_STARTP(v48);
if (v5[0] > 0)
v48.startp[0] = v5[0];
else
v48.startp[0] = 0;
if (v5[1] > 0)
v48.startp[1] = v5[1];
else
v48.startp[1] = 0;
v48.dims[0] = cad[2];
v48.dims[1] = cad[3];
memcpy (v48.orig_dims, v28.orig_dims, sizeof (v28.orig_dims));
v48.valp = v28.valp;
v48.reall= v48.dims[0] * v48.dims[1];
}
if (local_first)
{
r0=v48.reall;
INIT_STARTP(v24);
for (v1=0; v1<2; v1++)
v24.dims[v1+0]=v48.dims[v1+0];
memcpy(v24.orig_dims, v24.dims, sizeof(v24.dims));
cad[1]=r0;
if (new=r0>v24.maxl) {
v24.maxl=r0;
inchp2;v24.valp= &heap[r15];
}
v24.reall=r0; /* 3 instructions genarated by INCHEAPP */
}
FORALL2_CACHE(v24) /* code for - */
{
if (v2 == 0)
SLICE_DVAL(v24) = DROPPED_DVAL(v48);
else
SLICE_DVAL(v24) = DROPPED_DVAL(v48) - CD_DVAL(v34, -1);
}
/****************** LINE 7 ******************/
FORALL2_CACHE(v33)
DVAL(v33) = DVAL(v22) * DVAL(v22);
/* GENSCAN generates the following code */
if (cache_idx == 0)
{
p2 = (double *) v28.valp;
ro2 = (double *) v33.valp;
INIT_STARTP(v28);
for (v1=0; v1<2; v1++)
v28.orig_dims[v1+0] = v28.dims[v1+0]= v33.dims[v1+0];
r0 = v33.reall;
cad[1]=r0;
if (new=r0>v28.maxl) {
v28.maxl=r0;
inchp2;v28.valp= &heap[r15];
}
v28.reall=r0; /* 3 instructions genarated by INCHEAPP */
p2 = (double *) v28.valp;
if (r0==0) goto l7;
r0=v33.dims[1];
r1=v33.dims[0];
}
FORAXIS0_CACHE(v28)
{
v2 = 0;
d = 0;
FORAXIS1(v28)
DVAL(v28)=d=d+DVAL(v33);
}
l7:
if (cache_idx == 0)
v9 = -v19; /* code for - */
/***** PFCATENA *****/
if (cache_idx == 0)
{
r0 = cad[1]= 1+1;
cad[1] =r0 =2;
v5[0] = 0;
v5[1]= v9;
/* PFDROP generates the following code */
ro2 = (double *) v28.valp;
dl[1]= t = 1;
for (u0=0; u0<1; u0++)
t= dl[0-u0]= t*v28.dims[1-u0];
r0=t=1;
cad[3] = max(0, v28.dims[1]-abs(v5[1]));
t=tdl[0] = t*cad[3] ;
cad[2] = max(0,v28.dims[0]-abs(v5[0]));
INIT_STARTP(v36);
if (v5[0] > 0)
v36.startp[0] = v5[0];
else
v36.startp[0] = 0;
if (v5[1] > 0)
v36.startp[1] = v5[1];
else
v36.startp[1] = 0;
v36.dims[0] = cad[2];
v36.dims[1] = cad[3];
memcpy (v36.orig_dims, v28.orig_dims, sizeof (v28.orig_dims));
v36.valp = v28.valp;
v36.reall= v36.dims[0] * v36.dims[1];
}
/***** PFCATENA *****/
if (cache_idx == 0)
v9 = v19-1; /* code for - */
/***** PFCATENA *****/
if (cache_idx == 0)
{
r0 = cad[1]= 1+1;
cad[1] =r0 =2;
v5[0] = 0;
v5[1]= v9;
/* PFDROP generates the following code */
ro2 = (double *) v28.valp;
dl[1]= t = 1;
for (u0=0; u0<1; u0++)
t= dl[0-u0]= t*v28.dims[1-u0];
r0=t=1;
cad[3] = max(0, v28.dims[1]-abs(v5[1]));
t=tdl[0] = t*cad[3];
cad[2] = max(0,v28.dims[0]-abs(v5[0]));
INIT_STARTP(v40);
if (v5[0] > 0)
v40.startp[0] = v5[0];
else
v40.startp[0] = 0;
if (v5[1] > 0)
v40.startp[1] = v5[1];
else
v40.startp[1] = 0;
v40.dims[0] = cad[2];
v40.dims[1] = cad[3];
memcpy (v40.orig_dims, v28.orig_dims, sizeof (v28.orig_dims));
v40.valp = v28.valp;
v40.reall= v40.dims[0] * v40.dims[1];
}
if (local_first)
{
r0=v40.reall;
INIT_STARTP(v26);
for (v1=0; v1<2; v1++)
v26.dims[v1+0]= v40.dims[v1+0];
memcpy(v26.orig_dims, v26.dims, sizeof(v26.dims));
cad[1]=r0;
if (new=r0>v26.maxl) {
v26.maxl=r0;
inchp2;v26.valp= &heap[r15];
}
v26.reall=r0; /* 3 instructions genarated by INCHEAPP */
}
FORALL2_CACHE(v26) /* code for - */
{
if (v2 == 0)
SLICE_DVAL(v26) = DROPPED_DVAL(v40);
else
SLICE_DVAL(v26) = DROPPED_DVAL(v40) - CD_DVAL(v36, -1);
}
/****************** LINE 8 ******************/
FORALL2_CACHE(v33)
DVAL(v33) = DVAL(v21) * DVAL(v22);
/* GENSCAN generates the following code */
if (cache_idx == 0)
{
p2 = (double *) v28.valp;
ro2 = (double *) v33.valp;
INIT_STARTP(v28);
for (v1=0; v1<2; v1++)
v28.orig_dims[v1+0] = v28.dims[v1+0]= v33.dims[v1+0];
r0 = v33.reall;
cad[1]=r0;
if (new=r0>v28.maxl) {
v28.maxl=r0;
inchp2;v28.valp= &heap[r15];
}
v28.reall=r0; /* 3 instructions genarated by INCHEAPP */
p2 = (double *) v28.valp;
if (r0==0) goto l8;
r0=v33.dims[1];
r1=v33.dims[0];
}
FORAXIS0_CACHE(v28)
{
v2 = 0;
d = 0;
FORAXIS1(v28)
DVAL(v28)=d=d+DVAL(v33);
}
l8:
if (cache_idx == 0)
v9 = -v19; /* code for - */
/***** PFCATENA *****/
if (cache_idx == 0)
{
r0 = cad[1]= 1+1;
cad[1] =r0 =2;
v5[0] = 0;
v5[1]= v9;
/* PFDROP generates the following code */
ro2 = (double *) v28.valp;
dl[1]= t = 1;
for (u0=0; u0<1; u0++)
t= dl[0-u0]= t*v28.dims[1-u0];
r0=t=1;
cad[3] = max(0, v28.dims[1]-abs(v5[1]));
t=tdl[0] = t*cad[3];
cad[2] = max(0,v28.dims[0]-abs(v5[0]));
INIT_STARTP(v38);
if (v5[0] > 0)
v38.startp[0] = v5[0];
else
v38.startp[0] = 0;
if (v5[1] > 0)
v38.startp[1] = v5[1];
else
v38.startp[1] = 0;
v38.dims[0] = cad[2];
v38.dims[1] = cad[3];
memcpy (v38.orig_dims, v28.orig_dims, sizeof (v28.orig_dims));
v38.valp = v28.valp;
v38.reall= v38.dims[0] * v38.dims[1];
}
/***** PFCATENA *****/
if (cache_idx == 0)
v9 = v19-1; /* code for - */
/***** PFCATENA *****/
if (cache_idx == 0)
{
r0 = cad[1]= 1+1;
cad[1] =r0 =2;
v5[0] = 0;
v5[1]= v9;
/* PFDROP generates the following code */
ro2 = (double *) v28.valp;
dl[1]= t = 1;
for (u0=0; u0<1; u0++)
t= dl[0-u0]= t*v28.dims[1-u0];
r0=t=1;
cad[3] = max(0, v28.dims[1]-abs(v5[1]));
t=tdl[0] = t*cad[3];
cad[2] = max(0,v28.dims[0]-abs(v5[0]));
INIT_STARTP(v39);
if (v5[0] > 0)
v39.startp[0] = v5[0];
else
v39.startp[0] = 0;
if (v5[1] > 0)
v39.startp[1] = v5[1];
else
v39.startp[1] = 0;
v39.dims[0] = cad[2];
v39.dims[1] = cad[3];
memcpy (v39.orig_dims, v28.orig_dims, sizeof (v28.orig_dims));
v39.valp = v28.valp;
v39.reall= v39.dims[0] * v39.dims[1];
}
if (local_first)
{
r0=v39.reall;
INIT_STARTP(v27);
for (v1=0; v1<2; v1++)
v27.dims[v1+0]=v39.dims[v1+0];
memcpy(v27.orig_dims, v27.dims, sizeof(v27.dims));
cad[1]=r0;
if (new=r0>v27.maxl) {
v27.maxl=r0;
inchp2;v27.valp= &heap[r15];
}
v27.reall=r0; /* 3 instructions genarated by INCHEAPP */
}
FORALL2_CACHE(v27) /* code for - */
{
if (v2 == 0)
SLICE_DVAL(v27) = DROPPED_DVAL(v39);
else
SLICE_DVAL(v27) = DROPPED_DVAL(v39) - CD_DVAL(v38, -1);
}
/****************** LINE 9 ******************/
if (cache_idx == 0)
{
r0=v25.reall;
cad[31]=r0;
for (v1=0; v1<2; v1++)
cad[32+v1]= v25.dims[v1+0];
lo2 = (double *) v25.valp;
INIT_STARTP(v18);
for (v1=0; v1<2; v1++)
v18.dims[v1+0]=v25.dims[v1+0];
cad[1]=r0;
if (new=r0>v18.maxl) {
v18.maxl=r0;
inchp2;v18.valp= &heap[r15];
}
v18.reall=r0; /* 3 instructions genarated by INCHEAPP */
memcpy(v18.orig_dims, v18.dims, sizeof(v18.dims));
}
FORALL2_CACHE(v25)
{
double tmp;
double tmp2;
double tmp3;
if (unlikely(SLICE_DVAL(v25)==0 && 0==(double)v19)) tmp = 1;
else
tmp = SLICE_DVAL(v25)/(double)v19;
tmp = tmp*tmp;
if (unlikely(SLICE_DVAL(v26)==0 && 0==(double)v19)) tmp2 = 1;
else
tmp2 = SLICE_DVAL(v26)/(double)v19;
tmp = tmp2-tmp;
tmp = fabs(tmp);
tmp = sqrt(tmp);
if (unlikely(SLICE_DVAL(v23)==0 && 0==(double)v19)) tmp2 = 1;
else
tmp2 = SLICE_DVAL(v23)/(double)v19;
tmp2 = tmp2 * tmp2;
if (unlikely(SLICE_DVAL(v24)==0 && 0==(double)v19)) tmp3 = 1;
else
tmp3 = SLICE_DVAL(v24)/(double)v19;
tmp2 = tmp2 + tmp3;
tmp2 = sqrt(tmp2);
tmp2 = fabs(tmp2);
tmp = tmp * tmp2;
v9 = v19*v19; /* code for * */
tmp2 = SLICE_DVAL(v23) * SLICE_DVAL(v25);
if (unlikely(tmp2==0 && 0==(double)v9)) tmp2 = 1;
else
tmp2 = tmp2/(double)v9;
if (unlikely(SLICE_DVAL(v27)==0 && 0==(double)v19)) tmp3 = 1;
else
tmp3 = SLICE_DVAL(v27)/(double)v19;
tmp2 = tmp3 - tmp2;
if (unlikely(tmp2==0 && 0==tmp)) DVAL(v18) = 1;
else
DVAL(v18) = tmp2/tmp;
num++;
}
init = 1;
local_first = 0;
}
fprintf(stderr, "the big loop takes %dms, there are %d iterations\n",
apl_sec() - start_time, num);
for (v1=0; v1<2; v1++)
cad[2+v1]= v18.dims[v1+0];
cad[1]= v18.reall;
fprintf (stderr, "size: %d\n", v18.reall);
fretfp= (double *) v18.valp;
}
