void BufferInterface::transferData(bool fromSystemToDevice)throw(BufferException)
{
assert( "CPU buffer must exist for transfer between host and device" && mCPU_Handle);
if(
( hasBufferInContext(OPEN_GL_CONTEXT_TYPE) && PARA_COMP_MANAGER->graphicsAreInControl() )
||
! (hasBufferInContext(OPEN_CL_CONTEXT_TYPE))
)
{
//commented out the guard in case of driver bugs fu**ing up when doing too mush time-shared CL-GL-stuff
//TODO uncomment when stable work is assured
//if(isCLGLShared())
{
PARA_COMP_MANAGER->acquireSharedBuffersForGraphics();
}
GUARD(bindGL());
if(fromSystemToDevice)
{
GUARD(writeGL(mCPU_Handle));
}
else
{
GUARD(readGL(mCPU_Handle));
}
return;
}
if(
( hasBufferInContext(OPEN_CL_CONTEXT_TYPE) && PARA_COMP_MANAGER->computeIsInControl() )
||
! (hasBufferInContext(OPEN_GL_CONTEXT_TYPE))
)
{
//commented out the guard in case of driver bugs fu**ing up when doing too mush time-shared CL-GL-stuff
//TODO uncomment when stable work is assured
//if(isCLGLShared())
{
PARA_COMP_MANAGER->acquireSharedBuffersForCompute();
}
if(fromSystemToDevice)
{
GUARD(writeCL(mCPU_Handle));
}
else
{
GUARD(readCL(mCPU_Handle));
}
return;
}
throw(BufferException("BufferInterface::readBack(): need at least one GL or GL usage context in Buffer"));
}
int main_2dsfs(int argc,char **argv){
if(argc==1){
fprintf(stderr,"./emOptim2 2dsfs pop1 pop2 nChr1 nChr2 [-start FNAME -P nThreds -tole tole -maxIter ] (only works if the two saf files covers the same region)\n");
return 0;
}
argv++;
argc--;
fname1 = *(argv++);
fname2 = *(argv++);
argc -=2;
chr1 = atoi(*(argv++));
chr2 = atoi(*(argv++));
argc -=2;
getArgs(argc,argv);
if(nSites==0){
if(fsize(fname1)+fsize(fname2)>getTotalSystemMemory())
fprintf(stderr,"Looks like you will allocate too much memory, consider starting the program with a lower -nSites argument\n");
//this doesnt make sense if ppl supply a filelist containing safs
nSites=calcNsites(fname1,chr1);
}
fprintf(stderr,"fname1:%sfname2:%s chr1:%d chr2:%d startsfs:%s nThreads=%d tole=%f maxIter=%d nSites:%lu\n",fname1,fname2,chr1,chr2,sfsfname,nThreads,tole,maxIter,nSites);
float bytes_req_megs = nSites*(sizeof(double)*(chr1+1) + sizeof(double)*(chr2+1)+2*sizeof(double*))/1024/1024;
float mem_avail_megs = getTotalSystemMemory()/1024/1024;//in percentile
// fprintf(stderr,"en:%zu to:%f\n",bytes_req_megs,mem_avail_megs);
fprintf(stderr,"The choice of -nSites will require atleast: %f megabyte memory, that is approx: %.2f%% of total memory\n",bytes_req_megs,bytes_req_megs*100/mem_avail_megs);
#if 0
//read in positions, not used, YET...
std::vector<int> p1 = getPosi(fname1);
std::vector<int> p2 = getPosi(fname2);
fprintf(stderr,"nSites in pop1: %zu nSites in pop2: %zu\n",p1.size(),p2.size());
#endif
if(nSites==0){
if(calcNsites(fname1,chr1)!=calcNsites(fname2,chr2)){
fprintf(stderr,"Problem with number of sites in file: %s and %s\n",fname1,fname2);
exit(0);
}
nSites=calcNsites(fname1,chr1);
}
gzFile gz1=getGz(fname1);
gzFile gz2=getGz(fname2);
dim=(chr1+1)*(chr2+1);
Matrix<double> GL1=alloc(nSites,chr1+1);
Matrix<double> GL2=alloc(nSites,chr2+1);
dim=GL1.y*GL2.y;
double *sfs = new double[dim];
while(1){
if(isList ==0){
readGL(gz1,nSites,chr1,GL1);
readGL(gz2,nSites,chr2,GL2);
}else{
readGL2(gz1,nSites,chr1,GL1);
readGL2(gz2,nSites,chr2,GL2);
}
assert(GL1.x==GL2.x);
if(GL1.x==0)
break;
if(sfsfname!=NULL){
readSFS(sfsfname,dim,sfs);
}else{
for(int i=0;i<dim;i++)
sfs[i] = (i+1)/((double)dim);
normalize(sfs,dim);
}
setThreadPars(&GL1,&GL2,sfs,nThreads);
if(calcLike==0){
if(SIG_COND)
em2(sfs,&GL1,&GL2,tole,maxIter);
}
double lik;
if(nThreads>1)
lik = lik1_master();
else
lik = lik1(sfs,&GL1,0,GL1.x);
fprintf(stderr,"likelihood: %f\n",lik);
#if 1
int inc=0;
for(int x=0;x<chr1+1;x++){
for(int y=0;y<chr2+1;y++)
fprintf(stdout,"%f ",log(sfs[inc++]));
fprintf(stdout,"\n");
}
#endif
if(isList==1)
break;
}
dalloc(GL1,nSites);
dalloc(GL2,nSites);
gzclose(gz1);
gzclose(gz2);
return 0;
}
int main_1dsfs(int argc,char **argv){
if(argc<2){
fprintf(stderr,"Must supply afile.saf and number of chromosomes\n");
return 0;
}
fname1 = *(argv++);
chr1 = atoi(*(argv++));
argc-=2;
getArgs(argc,argv);
dim=chr1+1;
//hook for new EJ banded version
if(isNewFormat(fname1))
return main_1dsfs_v2(fname1,chr1,nSites,nThreads,sfsfname,tole,maxIter);
if(nSites==0){//if no -nSites is specified
if(fsize(fname1)>getTotalSystemMemory())
fprintf(stderr,"Looks like you will allocate too much memory, consider starting the program with a lower -nSites argument\n");
//this doesnt make sense if ppl supply a filelist containing safs
nSites=calcNsites(fname1,chr1);
}
fprintf(stderr,"fname1:%s nChr:%d startsfs:%s nThreads:%d tole=%f maxIter=%d nSites=%lu\n",fname1,chr1,sfsfname,nThreads,tole,maxIter,nSites);
float bytes_req_megs = nSites*(sizeof(double)*(chr1+1)+sizeof(double*))/1024/1024;
float mem_avail_megs = getTotalSystemMemory()/1024/1024;//in percentile
// fprintf(stderr,"en:%zu to:%f\n",bytes_req_megs,mem_avail_megs);
fprintf(stderr,"The choice of -nSites will require atleast: %f megabyte memory, that is approx: %.2f%% of total memory\n",bytes_req_megs,bytes_req_megs*100/mem_avail_megs);
Matrix<double> GL1=alloc(nSites,dim);
gzFile gz1=getGz(fname1);
double *sfs=new double[dim];
while(1) {
if(isList==0)
readGL(gz1,nSites,chr1,GL1);
else
readGL2(gz1,nSites,chr1,GL1);
if(GL1.x==0)
break;
fprintf(stderr,"dim(GL1)=%zu,%zu\n",GL1.x,GL1.y);
if(sfsfname!=NULL){
readSFS(sfsfname,dim,sfs);
}else{
for(int i=0;i<dim;i++)
sfs[i] = (i+1)/((double)dim);
if(doBFGS){
double ts=1;
for(int i=0;i<dim-1;i++)
ts += 0.01/(1.0+i);
sfs[0]=1.0/ts;
for(int i=0;i<dim-1;i++)
sfs[i+1] = (0.01/(1.0+i))/ts;
}
normalize(sfs,dim);
}
// em2_smart(sfs2,pops,1e-6,1e3);
setThreadPars(&GL1,NULL,sfs,nThreads);
if(calcLike==0){
if(doBFGS==0)
em1(sfs,&GL1,tole,maxIter);
else
bfgs(sfs,&GL1);
}
double lik;
if(nThreads>1)
lik = lik1_master();
else
lik = lik1(sfs,&GL1,0,GL1.x);
fprintf(stderr,"likelihood: %f\n",lik);
#if 1
for(int x=0;x<dim;x++)
fprintf(stdout,"%f ",log(sfs[x]));
fprintf(stdout,"\n");
fflush(stdout);
#endif
if(isList==1)
break;
}
dalloc(GL1,nSites);
gzclose(gz1);
delete [] sfs;
return 0;
}
