/[escript]/trunk/escript/src/DataLazy.cpp
ViewVC logotype

Diff of /trunk/escript/src/DataLazy.cpp

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 1898 by jfenwick, Mon Oct 20 01:20:18 2008 UTC revision 1935 by jfenwick, Mon Oct 27 06:06:39 2008 UTC
# Line 27  Line 27 
27  #include "Data.h"  #include "Data.h"
28  #include "UnaryFuncs.h"     // for escript::fsign  #include "UnaryFuncs.h"     // for escript::fsign
29    
30    /*
31    How does DataLazy work?
32    ~~~~~~~~~~~~~~~~~~~~~~~
33    
34    Each instance represents a single operation on one or two other DataLazy instances. These arguments are normally
35    denoted left and right.
36    
37    A special operation, IDENTITY, stores an instance of DataReady in the m_id member.
38    This means that all "internal" nodes in the structure are instances of DataLazy.
39    
40    Each operation has a string representation as well as an opgroup - eg G_IDENTITY, G_BINARY, ...
41    Note that IDENITY is not considered a unary operation.
42    
43    I am avoiding calling the structure formed a tree because it is not guaranteed to be one (eg c=a+a).
44    It must however form a DAG (directed acyclic graph).
45    I will refer to individual DataLazy objects with the structure as nodes.
46    
47    Each node also stores:
48    - m_readytype \in {'E','T','C','?'} ~ indicates what sort of DataReady would be produced if the expression was
49        evaluated.
50    - m_length ~ how many values would be stored in the answer if the expression was evaluated.
51    - m_buffsrequired ~ the larged number of samples which would need to be kept simultaneously in order to
52        evaluate the expression.
53    - m_samplesize ~ the number of doubles stored in a sample.
54    
55    When a new node is created, the above values are computed based on the values in the child nodes.
56    Eg: if left requires 4 samples and right requires 6 then left+right requires 7 samples.
57    
58    The resolve method, which produces a DataReady from a DataLazy, does the following:
59    1) Create a DataReady to hold the new result.
60    2) Allocate a vector (v) big enough to hold m_buffsrequired samples.
61    3) For each sample, call resolveSample with v, to get its values and copy them into the result object.
62    
63    (In the case of OMP, multiple samples are resolved in parallel so the vector needs to be larger.)
64    
65    resolveSample returns a Vector* and an offset within that vector where the result is stored.
66    Normally, this would be v, but for identity nodes their internal vector is returned instead.
67    
68    The convention that I use, is that the resolve methods should store their results starting at the offset they are passed.
69    
70    For expressions which evaluate to Constant or Tagged, there is a different evaluation method.
71    The collapse method invokes the (non-lazy) operations on the Data class to evaluate the expression.
72    */
73    
74    
75  using namespace std;  using namespace std;
76  using namespace boost;  using namespace boost;
77    
# Line 39  opToString(ES_optype op); Line 84  opToString(ES_optype op);
84  namespace  namespace
85  {  {
86    
   
   
87  enum ES_opgroup  enum ES_opgroup
88  {  {
89     G_UNKNOWN,     G_UNKNOWN,
90     G_IDENTITY,     G_IDENTITY,
91     G_BINARY,     G_BINARY,        // pointwise operations with two arguments
92     G_UNARY     G_UNARY      // pointwise operations with one argument
93  };  };
94    
95    
96    
97    
98  string ES_opstrings[]={"UNKNOWN","IDENTITY","+","-","*","/","sin","cos","tan",  string ES_opstrings[]={"UNKNOWN","IDENTITY","+","-","*","/","^",
99                "sin","cos","tan",
100              "asin","acos","atan","sinh","cosh","tanh","erf",              "asin","acos","atan","sinh","cosh","tanh","erf",
101              "asinh","acosh","atanh",              "asinh","acosh","atanh",
102              "log10","log","sign","abs","neg","pos","exp","sqrt",              "log10","log","sign","abs","neg","pos","exp","sqrt",
103              "1/","where>0","where<0","where>=0","where<=0"};              "1/","where>0","where<0","where>=0","where<=0"};
104  int ES_opcount=32;  int ES_opcount=33;
105  ES_opgroup opgroups[]={G_UNKNOWN,G_IDENTITY,G_BINARY,G_BINARY,G_BINARY,G_BINARY,G_UNARY,G_UNARY,G_UNARY, //9  ES_opgroup opgroups[]={G_UNKNOWN,G_IDENTITY,G_BINARY,G_BINARY,G_BINARY,G_BINARY, G_BINARY,
106              G_UNARY,G_UNARY,G_UNARY,G_UNARY,G_UNARY,G_UNARY,G_UNARY,    // 16              G_UNARY,G_UNARY,G_UNARY, //10
107              G_UNARY,G_UNARY,G_UNARY,                    // 19              G_UNARY,G_UNARY,G_UNARY,G_UNARY,G_UNARY,G_UNARY,G_UNARY,    // 17
108              G_UNARY,G_UNARY,G_UNARY,G_UNARY,G_UNARY,G_UNARY,G_UNARY,G_UNARY,        // 27              G_UNARY,G_UNARY,G_UNARY,                    // 20
109                G_UNARY,G_UNARY,G_UNARY,G_UNARY,G_UNARY,G_UNARY,G_UNARY,G_UNARY,        // 28
110              G_UNARY,G_UNARY,G_UNARY,G_UNARY,G_UNARY};              G_UNARY,G_UNARY,G_UNARY,G_UNARY,G_UNARY};
111  inline  inline
112  ES_opgroup  ES_opgroup
# Line 93  resultShape(DataAbstract_ptr left, DataA Line 138  resultShape(DataAbstract_ptr left, DataA
138  {  {
139      if (left->getShape()!=right->getShape())      if (left->getShape()!=right->getShape())
140      {      {
141          throw DataException("Shapes not the same - shapes must match for lazy data.");        if (getOpgroup(op)!=G_BINARY)
142          {
143            throw DataException("Shapes not the name - shapes must match for (point)binary operations.");
144          }
145          if (left->getRank()==0)   // we need to allow scalar * anything
146          {
147            return right->getShape();
148          }
149          if (right->getRank()==0)
150          {
151            return left->getShape();
152          }
153          throw DataException("Shapes not the same - arguments must have matching shapes (or be scalars) for (point)binary operations on lazy data.");
154      }      }
155      return left->getShape();      return left->getShape();
156  }  }
157    
158    // determine the number of points in the result of "left op right"
159  size_t  size_t
160  resultLength(DataAbstract_ptr left, DataAbstract_ptr right, ES_optype op)  resultLength(DataAbstract_ptr left, DataAbstract_ptr right, ES_optype op)
161  {  {
# Line 110  resultLength(DataAbstract_ptr left, Data Line 168  resultLength(DataAbstract_ptr left, Data
168     }     }
169  }  }
170    
171    // determine the number of samples requires to evaluate an expression combining left and right
172  int  int
173  calcBuffs(const DataLazy_ptr& left, const DataLazy_ptr& right, ES_optype op)  calcBuffs(const DataLazy_ptr& left, const DataLazy_ptr& right, ES_optype op)
174  {  {
# Line 123  calcBuffs(const DataLazy_ptr& left, cons Line 182  calcBuffs(const DataLazy_ptr& left, cons
182     }     }
183  }  }
184    
185    
186  }   // end anonymous namespace  }   // end anonymous namespace
187    
188    
189    
190    // Return a string representing the operation
191  const std::string&  const std::string&
192  opToString(ES_optype op)  opToString(ES_optype op)
193  {  {
# Line 143  DataLazy::DataLazy(DataAbstract_ptr p) Line 205  DataLazy::DataLazy(DataAbstract_ptr p)
205  {  {
206     if (p->isLazy())     if (p->isLazy())
207     {     {
     // TODO: fix this.   We could make the new node a copy of p?  
208      // I don't want identity of Lazy.      // I don't want identity of Lazy.
209      // Question: Why would that be so bad?      // Question: Why would that be so bad?
210      // Answer: We assume that the child of ID is something we can call getVector on      // Answer: We assume that the child of ID is something we can call getVector on
# Line 163  DataLazy::DataLazy(DataAbstract_ptr p) Line 224  DataLazy::DataLazy(DataAbstract_ptr p)
224  cout << "(1)Lazy created with " << m_samplesize << endl;  cout << "(1)Lazy created with " << m_samplesize << endl;
225  }  }
226    
227    
228    
229    
230  DataLazy::DataLazy(DataAbstract_ptr left, ES_optype op)  DataLazy::DataLazy(DataAbstract_ptr left, ES_optype op)
231      : parent(left->getFunctionSpace(),left->getShape()),      : parent(left->getFunctionSpace(),left->getShape()),
232      m_op(op)      m_op(op)
# Line 188  DataLazy::DataLazy(DataAbstract_ptr left Line 252  DataLazy::DataLazy(DataAbstract_ptr left
252  }  }
253    
254    
 // DataLazy::DataLazy(DataLazy_ptr left, DataLazy_ptr right, ES_optype op)  
 //  : parent(resultFS(left,right,op), resultShape(left,right,op)),  
 //  m_left(left),  
 //  m_right(right),  
 //  m_op(op)  
 // {  
 //    if (getOpgroup(op)!=G_BINARY)  
 //    {  
 //  throw DataException("Programmer error - constructor DataLazy(left, right, op) will only process BINARY operations.");  
 //    }  
 //    m_length=resultLength(m_left,m_right,m_op);  
 //    m_samplesize=getNumDPPSample()*getNoValues();  
 //    m_buffsRequired=calcBuffs(m_left, m_right, m_op);  
 // cout << "(2)Lazy created with " << m_samplesize << endl;  
 // }  
   
255  DataLazy::DataLazy(DataAbstract_ptr left, DataAbstract_ptr right, ES_optype op)  DataLazy::DataLazy(DataAbstract_ptr left, DataAbstract_ptr right, ES_optype op)
256      : parent(resultFS(left,right,op), resultShape(left,right,op)),      : parent(resultFS(left,right,op), resultShape(left,right,op)),
257      m_op(op)      m_op(op)
# Line 212  DataLazy::DataLazy(DataAbstract_ptr left Line 260  DataLazy::DataLazy(DataAbstract_ptr left
260     {     {
261      throw DataException("Programmer error - constructor DataLazy(left, right, op) will only process BINARY operations.");      throw DataException("Programmer error - constructor DataLazy(left, right, op) will only process BINARY operations.");
262     }     }
263     if (left->isLazy())     if (left->isLazy())          // the children need to be DataLazy. Wrap them in IDENTITY if required
264     {     {
265      m_left=dynamic_pointer_cast<DataLazy>(left);      m_left=dynamic_pointer_cast<DataLazy>(left);
266     }     }
# Line 243  DataLazy::DataLazy(DataAbstract_ptr left Line 291  DataLazy::DataLazy(DataAbstract_ptr left
291      m_readytype='C';      m_readytype='C';
292     }     }
293     m_length=resultLength(m_left,m_right,m_op);     m_length=resultLength(m_left,m_right,m_op);
294     m_samplesize=getNumDPPSample()*getNoValues();     m_samplesize=getNumDPPSample()*getNoValues();    
295     m_buffsRequired=calcBuffs(m_left, m_right,m_op);     m_buffsRequired=calcBuffs(m_left, m_right,m_op);
296  cout << "(3)Lazy created with " << m_samplesize << endl;  cout << "(3)Lazy created with " << m_samplesize << endl;
297  }  }
# Line 261  DataLazy::getBuffsRequired() const Line 309  DataLazy::getBuffsRequired() const
309  }  }
310    
311    
312    /*
313      \brief Evaluates the expression using methods on Data.
314      This does the work for the collapse method.
315      For reasons of efficiency do not call this method on DataExpanded nodes.
316    */
317  DataReady_ptr  DataReady_ptr
318  DataLazy::collapseToReady()  DataLazy::collapseToReady()
319  {  {
# Line 380  DataLazy::collapseToReady() Line 433  DataLazy::collapseToReady()
433    return result.borrowReadyPtr();    return result.borrowReadyPtr();
434  }  }
435    
436    /*
437       \brief Converts the DataLazy into an IDENTITY storing the value of the expression.
438       This method uses the original methods on the Data class to evaluate the expressions.
439       For this reason, it should not be used on DataExpanded instances. (To do so would defeat
440       the purpose of using DataLazy in the first place).
441    */
442  void  void
443  DataLazy::collapse()  DataLazy::collapse()
444  {  {
# Line 395  DataLazy::collapse() Line 454  DataLazy::collapse()
454    m_op=IDENTITY;    m_op=IDENTITY;
455  }  }
456    
457    /*
458      \brief Compute the value of the expression (binary operation) for the given sample.
459      \return Vector which stores the value of the subexpression for the given sample.
460      \param v A vector to store intermediate results.
461      \param offset Index in v to begin storing results.
462      \param sampleNo Sample number to evaluate.
463      \param roffset (output parameter) the offset in the return vector where the result begins.
464    
465      The return value will be an existing vector so do not deallocate it.
466      If the result is stored in v it should be stored at the offset given.
467      Everything from offset to the end of v should be considered available for this method to use.
468    */
469  DataTypes::ValueType*  DataTypes::ValueType*
470  DataLazy::resolveUnary(ValueType& v, size_t offset, int sampleNo, size_t& roffset) const  DataLazy::resolveUnary(ValueType& v, size_t offset, int sampleNo, size_t& roffset) const
471  {  {
# Line 516  DataLazy::resolveUnary(ValueType& v, siz Line 587  DataLazy::resolveUnary(ValueType& v, siz
587    
588    
589    
590  // const double*  
 // DataLazy::resolveUnary(ValueType& v,int sampleNo,  size_t offset) const  
 // {  
 //  // we assume that any collapsing has been done before we get here  
 //  // since we only have one argument we don't need to think about only  
 //  // processing single points.  
 //   if (m_readytype!='E')  
 //   {  
 //     throw DataException("Programmer error - resolveUnary should only be called on expanded Data.");  
 //   }  
 //   const double* left=m_left->resolveSample(v,sampleNo,offset);  
 //   double* result=&(v[offset]);  
 //   switch (m_op)  
 //   {  
 //     case SIN:      
 //  tensor_unary_operation(m_samplesize, left, result, ::sin);  
 //  break;  
 //     case COS:  
 //  tensor_unary_operation(m_samplesize, left, result, ::cos);  
 //  break;  
 //     case TAN:  
 //  tensor_unary_operation(m_samplesize, left, result, ::tan);  
 //  break;  
 //     case ASIN:  
 //  tensor_unary_operation(m_samplesize, left, result, ::asin);  
 //  break;  
 //     case ACOS:  
 //  tensor_unary_operation(m_samplesize, left, result, ::acos);  
 //  break;  
 //     case ATAN:  
 //  tensor_unary_operation(m_samplesize, left, result, ::atan);  
 //  break;  
 //     case SINH:  
 //  tensor_unary_operation(m_samplesize, left, result, ::sinh);  
 //  break;  
 //     case COSH:  
 //  tensor_unary_operation(m_samplesize, left, result, ::cosh);  
 //  break;  
 //     case TANH:  
 //  tensor_unary_operation(m_samplesize, left, result, ::tanh);  
 //  break;  
 //     case ERF:  
 // #ifdef _WIN32  
 //  throw DataException("Error - Data:: erf function is not supported on _WIN32 platforms.");  
 // #else  
 //  tensor_unary_operation(m_samplesize, left, result, ::erf);  
 //  break;  
 // #endif  
 //    case ASINH:  
 // #ifdef _WIN32  
 //  tensor_unary_operation(m_samplesize, left, result, escript::asinh_substitute);  
 // #else  
 //  tensor_unary_operation(m_samplesize, left, result, ::asinh);  
 // #endif    
 //  break;  
 //    case ACOSH:  
 // #ifdef _WIN32  
 //  tensor_unary_operation(m_samplesize, left, result, escript::acosh_substitute);  
 // #else  
 //  tensor_unary_operation(m_samplesize, left, result, ::acosh);  
 // #endif    
 //  break;  
 //    case ATANH:  
 // #ifdef _WIN32  
 //  tensor_unary_operation(m_samplesize, left, result, escript::atanh_substitute);  
 // #else  
 //  tensor_unary_operation(m_samplesize, left, result, ::atanh);  
 // #endif    
 //  break;  
 //     case LOG10:  
 //  tensor_unary_operation(m_samplesize, left, result, ::log10);  
 //  break;  
 //     case LOG:  
 //  tensor_unary_operation(m_samplesize, left, result, ::log);  
 //  break;  
 //     case SIGN:  
 //  tensor_unary_operation(m_samplesize, left, result, escript::fsign);  
 //  break;  
 //     case ABS:  
 //  tensor_unary_operation(m_samplesize, left, result, ::fabs);  
 //  break;  
 //     case NEG:  
 //  tensor_unary_operation(m_samplesize, left, result, negate<double>());  
 //  break;  
 //     case POS:  
 //  // it doesn't mean anything for delayed.  
 //  // it will just trigger a deep copy of the lazy object  
 //  throw DataException("Programmer error - POS not supported for lazy data.");  
 //  break;  
 //     case EXP:  
 //  tensor_unary_operation(m_samplesize, left, result, ::exp);  
 //  break;  
 //     case SQRT:  
 //  tensor_unary_operation(m_samplesize, left, result, ::sqrt);  
 //  break;  
 //     case RECIP:  
 //  tensor_unary_operation(m_samplesize, left, result, bind1st(divides<double>(),1.));  
 //  break;  
 //     case GZ:  
 //  tensor_unary_operation(m_samplesize, left, result, bind2nd(greater<double>(),0.0));  
 //  break;  
 //     case LZ:  
 //  tensor_unary_operation(m_samplesize, left, result, bind2nd(less<double>(),0.0));  
 //  break;  
 //     case GEZ:  
 //  tensor_unary_operation(m_samplesize, left, result, bind2nd(greater_equal<double>(),0.0));  
 //  break;  
 //     case LEZ:  
 //  tensor_unary_operation(m_samplesize, left, result, bind2nd(less_equal<double>(),0.0));  
 //  break;  
 //  
 //     default:  
 //  throw DataException("Programmer error - resolveUnary can not resolve operator "+opToString(m_op)+".");  
 //   }  
 //   return result;  
 // }  
591    
592  #define PROC_OP(X) \  #define PROC_OP(X) \
593      for (int i=0;i<steps;++i,resultp+=getNoValues()) \      for (int i=0;i<steps;++i,resultp+=resultStep) \
594      { \      { \
595  cout << "Step#" << i << " chunk=" << chunksize << endl; \         tensor_binary_operation(chunksize, &((*left)[lroffset]), &((*right)[rroffset]), resultp, X); \
596  cout << left[0] << left[1] << left[2] << endl; \         lroffset+=leftStep; \
597  cout << right[0] << right[1] << right[2] << endl; \         rroffset+=rightStep; \
        tensor_binary_operation(chunksize, left, right, resultp, X); \  
        left+=leftStep; \  
        right+=rightStep; \  
 cout << "Result=" << result << " " << result[0] << result[1] << result[2] << endl; \  
598      }      }
599    
600    /*
601      \brief Compute the value of the expression (binary operation) for the given sample.
602      \return Vector which stores the value of the subexpression for the given sample.
603      \param v A vector to store intermediate results.
604      \param offset Index in v to begin storing results.
605      \param sampleNo Sample number to evaluate.
606      \param roffset (output parameter) the offset in the return vector where the result begins.
607    
608      The return value will be an existing vector so do not deallocate it.
609      If the result is stored in v it should be stored at the offset given.
610      Everything from offset to the end of v should be considered available for this method to use.
611    */
612    // This method assumes that any subexpressions which evaluate to Constant or Tagged Data
613    // have already been collapsed to IDENTITY. So we must have at least one expanded child.
614    // If both children are expanded, then we can process them in a single operation (we treat
615    // the whole sample as one big datapoint.
616    // If one of the children is not expanded, then we need to treat each point in the sample
617    // individually.
618    // There is an additional complication when scalar operations are considered.
619    // For example, 2+Vector.
620    // In this case each double within the point is treated individually
621  DataTypes::ValueType*  DataTypes::ValueType*
622  DataLazy::resolveBinary(ValueType& v,  size_t offset ,int sampleNo, size_t& roffset) const  DataLazy::resolveBinary(ValueType& v,  size_t offset, int sampleNo, size_t& roffset) const
623  {  {
     // again we assume that all collapsing has already been done  
     // so we have at least one expanded child.  
     // however, we could still have one of the children being not expanded.  
   
624  cout << "Resolve binary: " << toString() << endl;  cout << "Resolve binary: " << toString() << endl;
625    
626    size_t lroffset=0, rroffset=0;    size_t lroffset=0, rroffset=0;    // offsets in the left and right result vectors
627        // first work out which of the children are expanded
628    bool leftExp=(m_left->m_readytype=='E');    bool leftExp=(m_left->m_readytype=='E');
629    bool rightExp=(m_right->m_readytype=='E');    bool rightExp=(m_right->m_readytype=='E');
630    bool bigloops=((leftExp && rightExp) || (!leftExp && !rightExp)); // is processing in single step    bool bigloops=((leftExp && rightExp) || (!leftExp && !rightExp)); // is processing in single step?
631    int steps=(bigloops?1:getNumDPPSample());    int steps=(bigloops?1:getNumDPPSample());
632    size_t chunksize=(bigloops? m_samplesize : getNoValues());    size_t chunksize=(bigloops? m_samplesize : getNoValues());    // if bigloops, pretend the whole sample is a datapoint
633    int leftStep=((leftExp && !rightExp)? getNoValues() : 0);    if (m_left->getRank()!=m_right->getRank())    // need to deal with scalar * ? ops
634    int rightStep=((rightExp && !leftExp)? getNoValues() : 0);    {
635        EsysAssert((m_left->getRank()==0) || (m_right->getRank()==0), "Error - Ranks must match unless one is 0.");
636        steps=getNumDPPSample()*max(m_left->getNoValues(),m_right->getNoValues());
637        chunksize=1;    // for scalar
638      }    
639      int leftStep=((leftExp && !rightExp)? m_right->getNoValues() : 0);
640      int rightStep=((rightExp && !leftExp)? m_left->getNoValues() : 0);
641      int resultStep=max(leftStep,rightStep);   // only one (at most) should be !=0
642        // Get the values of sub-expressions
643    const ValueType* left=m_left->resolveSample(v,offset,sampleNo,lroffset);    const ValueType* left=m_left->resolveSample(v,offset,sampleNo,lroffset);
644    const ValueType* right=m_right->resolveSample(v,offset,sampleNo,rroffset);        const ValueType* right=m_right->resolveSample(v,offset+m_samplesize,sampleNo,rroffset); // Note
645      // now we need to know which args are expanded      // the right child starts further along.
646  cout << "left=" << left << " right=" << right << endl;    double* resultp=&(v[offset]);     // results are stored at the vector offset we recieved
 cout << "(Length) l=" << left->size() << " r=" << right->size() << " res=" << v.size() << endl;  
   double* resultp=&(v[offset]);  
647    switch(m_op)    switch(m_op)
648    {    {
649      case ADD:      case ADD:
650      for (int i=0;i<steps;++i,resultp+=getNoValues())      PROC_OP(plus<double>());
651      {      break;
652  cerr << "Step#" << i << " chunk=" << chunksize << endl;      case SUB:
653  cerr << left << "[" << lroffset << "] " << right << "[" << rroffset << "]" << endl;      PROC_OP(minus<double>());
654         tensor_binary_operation(chunksize, &((*left)[lroffset]), &((*right)[rroffset]), resultp, plus<double>());      break;
655         lroffset+=leftStep;      case MUL:
656         rroffset+=rightStep;      PROC_OP(multiplies<double>());
657  cerr << "left=" << lroffset << " right=" << rroffset << endl;      break;
658      }      case DIV:
659        PROC_OP(divides<double>());
660        break;
661        case POW:
662        PROC_OP(::pow);
663      break;      break;
 // need to fill in the rest  
664      default:      default:
665      throw DataException("Programmer error - resolveBinary can not resolve operator "+opToString(m_op)+".");      throw DataException("Programmer error - resolveBinary can not resolve operator "+opToString(m_op)+".");
666    }    }
667    roffset=offset;    roffset=offset;  
668    return &v;    return &v;
669  }  }
670    
671    
672    
673  // #define PROC_OP(X) \  /*
674  //  for (int i=0;i<steps;++i,resultp+=getNoValues()) \    \brief Compute the value of the expression for the given sample.
675  //  { \    \return Vector which stores the value of the subexpression for the given sample.
676  // cout << "Step#" << i << " chunk=" << chunksize << endl; \    \param v A vector to store intermediate results.
677  // cout << left[0] << left[1] << left[2] << endl; \    \param offset Index in v to begin storing results.
678  // cout << right[0] << right[1] << right[2] << endl; \    \param sampleNo Sample number to evaluate.
679  //     tensor_binary_operation(chunksize, left, right, resultp, X); \    \param roffset (output parameter) the offset in the return vector where the result begins.
 //     left+=leftStep; \  
 //     right+=rightStep; \  
 // cout << "Result=" << result << " " << result[0] << result[1] << result[2] << endl; \  
 //  }  
 //  
 // const double*  
 // DataLazy::resolveBinary(ValueType& v,int sampleNo,  size_t offset) const  
 // {  
 //  // again we assume that all collapsing has already been done  
 //  // so we have at least one expanded child.  
 //  // however, we could still have one of the children being not expanded.  
 //  
 // cout << "Resolve binary: " << toString() << endl;  
 //  
 //   const double* left=m_left->resolveSample(v,sampleNo,offset);  
 // // cout << "Done Left " << /*left[0] << left[1] << left[2] << */endl;  
 //   const double* right=m_right->resolveSample(v,sampleNo,offset);  
 // // cout << "Done Right"  << /*right[0] << right[1] << right[2] <<*/ endl;  
 //      // now we need to know which args are expanded  
 //   bool leftExp=(m_left->m_readytype=='E');  
 //   bool rightExp=(m_right->m_readytype=='E');  
 //   bool bigloops=((leftExp && rightExp) || (!leftExp && !rightExp));  // is processing in single step  
 //   int steps=(bigloops?1:getNumSamples());  
 //   size_t chunksize=(bigloops? m_samplesize : getNoValues());  
 //   int leftStep=((leftExp && !rightExp)? getNoValues() : 0);  
 //   int rightStep=((rightExp && !leftExp)? getNoValues() : 0);  
 // cout << "left=" << left << " right=" << right << endl;  
 //   double* result=&(v[offset]);  
 //   double* resultp=result;  
 //   switch(m_op)  
 //   {  
 //     case ADD:  
 //  for (int i=0;i<steps;++i,resultp+=getNoValues())  
 //  {  
 // cout << "Step#" << i << " chunk=" << chunksize << endl; \  
 // // cout << left[0] << left[1] << left[2] << endl;  
 // // cout << right[0] << right[1] << right[2] << endl;  
 //     tensor_binary_operation(chunksize, left, right, resultp, plus<double>());  
 // cout << "left=" << left << " right=" << right << " resp=" << resultp << endl;  
 //     left+=leftStep;  
 //     right+=rightStep;  
 // cout << "left=" << left << " right=" << right << endl;  
 // // cout << "Result=" << result << " " << result[0] << result[1] << result[2] << endl;  
 //  }  
 //  break;  
 // // need to fill in the rest  
 //     default:  
 //  throw DataException("Programmer error - resolveBinay can not resolve operator "+opToString(m_op)+".");  
 //   }  
 // // cout << "About to return "  << result[0] << result[1] << result[2] << endl;;  
 //   return result;  
 // }  
   
 // // the vector and the offset are a place where the method could write its data if it wishes  
 // // it is not obligated to do so. For example, if it has its own storage already, it can use that.  
 // // Hence the return value to indicate where the data is actually stored.  
 // // Regardless, the storage should be assumed to be used, even if it isn't.  
 // const double*  
 // DataLazy::resolveSample(ValueType& v,int sampleNo,  size_t offset )  
 // {  
 // cout << "Resolve sample " << toString() << endl;  
 //  // collapse so we have a 'E' node or an IDENTITY for some other type  
 //   if (m_readytype!='E' && m_op!=IDENTITY)  
 //   {  
 //  collapse();  
 //   }  
 //   if (m_op==IDENTITY)      
 //   {  
 //     const ValueType& vec=m_id->getVector();  
 //     if (m_readytype=='C')  
 //     {  
 //  return &(vec[0]);  
 //     }  
 //     return &(vec[m_id->getPointOffset(sampleNo, 0)]);  
 //   }  
 //   if (m_readytype!='E')  
 //   {  
 //     throw DataException("Programmer Error - Collapse did not produce an expanded node.");  
 //   }  
 //   switch (getOpgroup(m_op))  
 //   {  
 //   case G_UNARY: return resolveUnary(v,sampleNo,offset);  
 //   case G_BINARY: return resolveBinary(v,sampleNo,offset);  
 //   default:  
 //     throw DataException("Programmer Error - resolveSample does not know how to process "+opToString(m_op)+".");  
 //   }  
 // }  
   
   
680    
681      The return value will be an existing vector so do not deallocate it.
682    */
683  // the vector and the offset are a place where the method could write its data if it wishes  // the vector and the offset are a place where the method could write its data if it wishes
684  // it is not obligated to do so. For example, if it has its own storage already, it can use that.  // it is not obligated to do so. For example, if it has its own storage already, it can use that.
685  // Hence the return value to indicate where the data is actually stored.  // Hence the return value to indicate where the data is actually stored.
# Line 830  cout << "Resolve sample " << toString() Line 720  cout << "Resolve sample " << toString()
720  }  }
721    
722    
723    // To simplify the memory management, all threads operate on one large vector, rather than one each.
724    // Each sample is evaluated independently and copied into the result DataExpanded.
 // This version uses double* trying again with vectors  
 // DataReady_ptr  
 // DataLazy::resolve()  
 // {  
 //  
 // cout << "Sample size=" << m_samplesize << endl;  
 // cout << "Buffers=" << m_buffsRequired << endl;  
 //  
 //   if (m_readytype!='E')  
 //   {  
 //     collapse();  
 //   }  
 //   if (m_op==IDENTITY)  
 //   {  
 //     return m_id;  
 //   }  
 //      // from this point on we must have m_op!=IDENTITY and m_readytype=='E'  
 //   size_t threadbuffersize=m_samplesize*(max(1,m_buffsRequired)+1);  
 //   int numthreads=1;  
 // #ifdef _OPENMP  
 //   numthreads=getNumberOfThreads();  
 //   int threadnum=0;  
 // #endif  
 //   ValueType v(numthreads*threadbuffersize);    
 // cout << "Buffer created with size=" << v.size() << endl;  
 //   DataExpanded* result=new DataExpanded(getFunctionSpace(),getShape(),  ValueType(getNoValues()));  
 //   ValueType& resvec=result->getVector();  
 //   DataReady_ptr resptr=DataReady_ptr(result);  
 //   int sample;  
 //   int resoffset;  
 //   int totalsamples=getNumSamples();  
 //   const double* res=0;  
 //   #pragma omp parallel for private(sample,resoffset,threadnum,res) schedule(static)  
 //   for (sample=0;sample<totalsamples;++sample)  
 //   {  
 // cout << "################################# " << sample << endl;  
 // #ifdef _OPENMP  
 //     res=resolveSample(v,sample,threadbuffersize*omp_get_thread_num());  
 // #else  
 //     res=resolveSample(v,sample,0);   // this would normally be v, but not if its a single IDENTITY op.  
 // #endif  
 // cerr << "-------------------------------- " << endl;  
 //     resoffset=result->getPointOffset(sample,0);  
 // cerr << "offset=" << resoffset << endl;  
 //     for (unsigned int i=0;i<m_samplesize;++i,++resoffset)    // copy values into the output vector  
 //     {  
 //  resvec[resoffset]=res[i];  
 //     }  
 // cerr << "*********************************" << endl;  
 //   }  
 //   return resptr;  
 // }  
   
   
725  DataReady_ptr  DataReady_ptr
726  DataLazy::resolve()  DataLazy::resolve()
727  {  {
# Line 893  DataLazy::resolve() Line 729  DataLazy::resolve()
729  cout << "Sample size=" << m_samplesize << endl;  cout << "Sample size=" << m_samplesize << endl;
730  cout << "Buffers=" << m_buffsRequired << endl;  cout << "Buffers=" << m_buffsRequired << endl;
731    
732    if (m_readytype!='E')    if (m_readytype!='E')     // if the whole sub-expression is Constant or Tagged, then evaluate it normally
733    {    {
734      collapse();      collapse();
735    }    }
736    if (m_op==IDENTITY)    if (m_op==IDENTITY)       // So a lazy expression of Constant or Tagged data will be returned here.
737    {    {
738      return m_id;      return m_id;
739    }    }
740      // from this point on we must have m_op!=IDENTITY and m_readytype=='E'      // from this point on we must have m_op!=IDENTITY and m_readytype=='E'
741    size_t threadbuffersize=m_samplesize*(max(1,m_buffsRequired)+1);    size_t threadbuffersize=m_samplesize*(max(1,m_buffsRequired));    // Each thread needs to have enough
742        // storage to evaluate its expression
743    int numthreads=1;    int numthreads=1;
744  #ifdef _OPENMP  #ifdef _OPENMP
745    numthreads=getNumberOfThreads();    numthreads=getNumberOfThreads();
# Line 916  cout << "Buffer created with size=" << v Line 753  cout << "Buffer created with size=" << v
753    int sample;    int sample;
754    size_t outoffset;     // offset in the output data    size_t outoffset;     // offset in the output data
755    int totalsamples=getNumSamples();    int totalsamples=getNumSamples();
756    const ValueType* res=0;    const ValueType* res=0;   // Vector storing the answer
757    size_t resoffset=0;    size_t resoffset=0;       // where in the vector to find the answer
758    #pragma omp parallel for private(sample,resoffset,outoffset,threadnum,res) schedule(static)    #pragma omp parallel for private(sample,resoffset,outoffset,threadnum,res) schedule(static)
759    for (sample=0;sample<totalsamples;++sample)    for (sample=0;sample<totalsamples;++sample)
760    {    {
# Line 925  cout << "############################### Line 762  cout << "###############################
762  #ifdef _OPENMP  #ifdef _OPENMP
763      res=resolveSample(v,threadbuffersize*omp_get_thread_num(),sample,resoffset);      res=resolveSample(v,threadbuffersize*omp_get_thread_num(),sample,resoffset);
764  #else  #else
765      res=resolveSample(v,0,sample,resoffset);   // this would normally be v, but not if its a single IDENTITY op.      res=resolveSample(v,0,sample,resoffset);   // res would normally be v, but not if its a single IDENTITY op.
766  #endif  #endif
767  cerr << "-------------------------------- " << endl;  cerr << "-------------------------------- " << endl;
768      outoffset=result->getPointOffset(sample,0);      outoffset=result->getPointOffset(sample,0);
# Line 948  DataLazy::toString() const Line 785  DataLazy::toString() const
785    return oss.str();    return oss.str();
786  }  }
787    
788    
789  void  void
790  DataLazy::intoString(ostringstream& oss) const  DataLazy::intoString(ostringstream& oss) const
791  {  {
# Line 989  DataLazy::intoString(ostringstream& oss) Line 827  DataLazy::intoString(ostringstream& oss)
827    }    }
828  }  }
829    
 // Note that in this case, deepCopy does not make copies of the leaves.  
 // Hopefully copy on write (or whatever we end up using) will take care of this.  
830  DataAbstract*  DataAbstract*
831  DataLazy::deepCopy()  DataLazy::deepCopy()
832  {  {
833    if (m_op==IDENTITY)    switch (getOpgroup(m_op))
834    {    {
835      return new DataLazy(m_left);    // we don't need to copy the child here    case G_IDENTITY:  return new DataLazy(m_id->deepCopy()->getPtr());
836      case G_UNARY: return new DataLazy(m_left->deepCopy()->getPtr(),m_op);
837      case G_BINARY:    return new DataLazy(m_left->deepCopy()->getPtr(),m_right->deepCopy()->getPtr(),m_op);
838      default:
839        throw DataException("Programmer error - do not know how to deepcopy operator "+opToString(m_op)+".");
840    }    }
   return new DataLazy(m_left->deepCopy()->getPtr(),m_right->deepCopy()->getPtr(),m_op);  
841  }  }
842    
843    
# Line 1015  DataLazy::getSlice(const DataTypes::Regi Line 854  DataLazy::getSlice(const DataTypes::Regi
854    throw DataException("getSlice - not implemented for Lazy objects.");    throw DataException("getSlice - not implemented for Lazy objects.");
855  }  }
856    
857    
858    // To do this we need to rely on our child nodes
859    DataTypes::ValueType::size_type
860    DataLazy::getPointOffset(int sampleNo,
861                     int dataPointNo)
862    {
863      if (m_op==IDENTITY)
864      {
865        return m_id->getPointOffset(sampleNo,dataPointNo);
866      }
867      if (m_readytype!='E')
868      {
869        collapse();
870        return m_id->getPointOffset(sampleNo,dataPointNo);
871      }
872      // at this point we do not have an identity node and the expression will be Expanded
873      // so we only need to know which child to ask
874      if (m_left->m_readytype=='E')
875      {
876        return m_left->getPointOffset(sampleNo,dataPointNo);
877      }
878      else
879      {
880        return m_right->getPointOffset(sampleNo,dataPointNo);
881      }
882    }
883    
884    // To do this we need to rely on our child nodes
885  DataTypes::ValueType::size_type  DataTypes::ValueType::size_type
886  DataLazy::getPointOffset(int sampleNo,  DataLazy::getPointOffset(int sampleNo,
887                   int dataPointNo) const                   int dataPointNo) const
888  {  {
889    throw DataException("getPointOffset - not implemented for Lazy objects - yet.");    if (m_op==IDENTITY)
890      {
891        return m_id->getPointOffset(sampleNo,dataPointNo);
892      }
893      if (m_readytype=='E')
894      {
895        // at this point we do not have an identity node and the expression will be Expanded
896        // so we only need to know which child to ask
897        if (m_left->m_readytype=='E')
898        {
899        return m_left->getPointOffset(sampleNo,dataPointNo);
900        }
901        else
902        {
903        return m_right->getPointOffset(sampleNo,dataPointNo);
904        }
905      }
906      if (m_readytype=='C')
907      {
908        return m_left->getPointOffset(sampleNo,dataPointNo); // which child doesn't matter
909      }
910      throw DataException("Programmer error - getPointOffset on lazy data may require collapsing (but this object is marked const).");
911    }
912    
913    // It would seem that DataTagged will need to be treated differently since even after setting all tags
914    // to zero, all the tags from all the DataTags would be in the result.
915    // However since they all have the same value (0) whether they are there or not should not matter.
916    // So I have decided that for all types this method will create a constant 0.
917    // It can be promoted up as required.
918    // A possible efficiency concern might be expanded->constant->expanded which has an extra memory management
919    // but we can deal with that if it arrises.
920    void
921    DataLazy::setToZero()
922    {
923      DataTypes::ValueType v(getNoValues(),0);
924      m_id=DataReady_ptr(new DataConstant(getFunctionSpace(),getShape(),v));
925      m_op=IDENTITY;
926      m_right.reset();  
927      m_left.reset();
928      m_readytype='C';
929      m_buffsRequired=1;
930  }  }
931    
932  }   // end namespace  }   // end namespace

Legend:
Removed from v.1898  
changed lines
  Added in v.1935

  ViewVC Help
Powered by ViewVC 1.1.26