0

我正在重写一些旧代码以使用新类型的参数表示。旧版本使用矩阵来表示参数，而新版本使用 aList和 an arma::fcube。我得到的性能损失只有在从另一个函数中多次调用该函数时才能观察到：

旧函数ConditionalProbs比名为 的新函数慢了近 2 倍conditional_probabilities。另一方面， （多次multiple_times_old调用）比 快 4 倍左右，即使此函数之间的唯一区别是多次调用的函数。ConditionalProbsmultiple_times_new

我为长代码道歉：这是我的旧代码（请注意，我正在使用但我确实通过在新代码上NumericMatrix更改它来提高速度）IntegerMatrix

// [[Rcpp::depends(RcppArmadillo)]]
// [[Rcpp::export]]
NumericVector ConditionalProbs(NumericMatrix X, IntegerVector position,  int C, NumericMatrix cMat, NumericMatrix vMat, NumericVector V) {

  int n = X.nrow(); int m = X.ncol();
  int n_neighbors = cMat.nrow();
  int x = position[0] -1; int y = position[1] -1;
  int neix, neiy;
  NumericVector p(C + 1);
  IntegerVector vals = seq_len(C+1) - 1;
  double U;
  int dif;

  for(int value = 0; value <= C; value++){
    U = V[value];
    for(int ne=0; ne < n_neighbors; ne++){
      neix = x + cMat(ne,0); neiy = y + cMat(ne,1);
      if(neix < n && neix >=0 && neiy < m && neiy>=0){
        dif = X(neix,neiy) - vals[value] ;
        U = U + vMat(ne,dif+C);
      }
    }
    p[value] = exp(U);
  }
  p = p/sum(p);
  return(p);
}


// [[Rcpp::depends(RcppArmadillo)]]
// [[Rcpp::export]]
NumericMatrix multiple_times_old(NumericMatrix X, NumericMatrix cMat, NumericMatrix vMat, NumericVector V, int C, int n_times){
  NumericVector probability;
  int N = X.nrow(); int M = X.ncol();
  int x,y;
  IntegerVector position(2);
  for(int i = 0; i < n_times; i++){
    x = 2;
    y = 2;
    position[0] = x; position[1] = y;
    probability = ConditionalProbs(X, position, C, cMat, vMat, V);
  }
  return(X);
}

现在新版本是：

// [[Rcpp::depends(RcppArmadillo)]]
// [[Rcpp::export]]
NumericVector conditional_probabilities(IntegerMatrix X, IntegerVector position, List R, arma::fcube theta){
  int n_neighbors = theta.n_rows;
  int C = theta.n_cols - 1;
  int x = position[0] - 1; int y = position[1] - 1;
  int N = X.nrow(); int M = X.ncol();

  IntegerVector this_pos;
  NumericVector probs(C+1);
  float this_prob;
  int dx, dy;

  for(int value = 0; value <= C; value++){
    this_prob = 0;
    for(int i = 0; i < n_neighbors; i++){
      this_pos = as<IntegerVector>(R[i]);
      dx = this_pos[0]; dy = this_pos[1];
      if(0 <= x+dx && x+dx < N && 0 <= y+dy && y+dy < M){
        this_prob = this_prob + theta(i, value, X(x+dx, y+dy));}
      //if(0 <= x-dx && x-dx < N && 0 <= y-dy && y-dy < M){
      // this_prob = this_prob + theta(i, X(x-dx, y-dy), value);}
    }
    probs[value] = exp(this_prob);
  }
  return(probs/sum(probs));
}

// [[Rcpp::depends(RcppArmadillo)]]
// [[Rcpp::export]]
IntegerMatrix multiple_times_new(IntegerMatrix X, List R, arma::fcube theta, int n_times){
  NumericVector probability;
  int N = X.nrow(); int M = X.ncol();
  int x,y;
  IntegerVector position(2);
  for(int i = 0; i < n_times; i++){
    x = 2;
    y = 2;
    position[0] = x; position[1] = y;
    probability = conditional_probabilities(X, position, R, theta);
  }
  return(X);
}

我编写了基准测试来测试这些功能：

library(Rcpp)
sourceCpp("bench.cpp") #All the c++ functions are on this file

# parameters for old functions
cMat <- matrix(c(1,0,0,1), nrow = 2, byrow = TRUE)
vMat <- matrix(c(-1,-1,-1,-1,1,-1,-1,-1,-1,
                 -1,-1,-1,-1,1,-1,-1,-1,-1), nrow = 2, byrow = TRUE)
vMat <- rbind(vMat, vMat) + 0.0
cMat <- rbind(cMat, -cMat)
V <- rep(0.0,5)

# parameters for new functions
R <- list(c(1L,0L), c(0L,1L), c(-1L,0L), c(0L, -1L))
theta <- array(0, c(4,5,5))
theta[1,,] <- theta[2,,] <- theta[3,,] <- theta[4,,] <- diag(rep(2,5)) - 1.0

X <- matrix(sample(0:4,64*64, replace = TRUE), nrow = 64)

library(rbenchmark)

benchmark(ConditionalProbs = ConditionalProbs(X, c(30,30), 4, cMat, vMat, V),
          conditional_probabilities = conditional_probabilities(X, c(30,30), R, theta), 
          replications = 50000)[ ,c("test", "relative","elapsed", "replications")]

                       test relative elapsed replications
2 conditional_probabilities    1.000   0.314        50000
1          ConditionalProbs    1.538   0.483        50000

benchmark(multiple_times_old = multiple_times_old(X, cMat2, vMat2, V, 4, 50000),
          multiple_times_new = multiple_times_new(X, R, theta, 50000),
          replications = 10)[ ,c("test", "relative", "elapsed", "replications")]

                test relative elapsed replications
2 multiple_times_new    4.359   0.959           10
1 multiple_times_old    1.000   0.220           10

为什么multiple_times_new比multiple_times_old第一个调用的函数比第二个调用的函数快？

4

0 回答 0