TypeError：recv（）获得了意外的关键字参数“ dest”

Question

I am trying to use MPI in python to do some parallel computing for midpoint integration. I am not really familiar with MPI and I have looked around at some examples to produce what I have thus far. I am having trouble with a couple of errors where MPI.COMM does not recognize a couple of input arguments. Again I am not that familiar with MPI.

Below I have attached my code:

from mpi4py import MPI
import numpy as np
from numpy import *
import time

#initialize variables
n = 10e5 #number of increments within each process
a = 0.0; #lower bound
b = 5.0; #upper bound
dest = 0; #define the process that computes the final result

#Functions
def integral(my_a, num, h):
    s = 0;
    h2 = h/2;
    for i in range(0,num):
        temp = my_a + i*h;
        s = s + fct(temp+h2)*h;
    return (s)

def fct(x):
    return x**2;

#Start the MPI process
comm = MPI.COMM_WORLD
p = comm.Get_size(); #gather number of processes
print "Number of processes (p): ", p;
myid = comm.Get_rank() #gather rank of the comm (number of cores)
print "Rank of (p): ", myid;

h = (b-a)/n; #length of increment
num = int(n/p); #number of intervals calculated by each process
print "Number of intervals calculated by a process: ", num;
my_range = (b-a)/p; #range per process
my_a = a + myid*my_range; #next lower limit
ti = time.clock();
my_result = integral(my_a,num,h) #get the result

print "Process " + str(myid) + " has the partial result of " + str(my_result) + ".";

if myid == 0:
    result = my_result;
    for i in range(1,p):
        source = 1;
        comm.recv(my_result, dest=1, tag=123);
        result = result + my_result;
    print "The result = " + str(result) + ".";

else :
    comm.send(my_result, source=0, tag=123);
    MPI_Finalize();


tf = time.clock();
print "Time(s): ", tf-ti;

Here is the error that I get when I try to run this code:

--------------------------------------------------------------------------
*******************************-VirtualBox ~/Documents/ME701/HW/HW5 $ mpirun -np 2 python HW5_prb3.py
Number of processes (p):  2
Rank of (p):  1
Number of intervals calculated by a process:  500000
Number of processes (p):  2
Rank of (p):  0
Number of intervals calculated by a process:  500000
Process 1 has the partial result of 36.4583333333.
Traceback (most recent call last):
  File "HW5_prb3.py", line 50, in <module>
    comm.send(my_result, source=0, tag=123);
  File "Comm.pyx", line 1127, in mpi4py.MPI.Comm.send (src/mpi4py.MPI.c:90067)
**TypeError: send() got an unexpected keyword argument 'source'**
Process 0 has the partial result of 5.20833333333.
Traceback (most recent call last):
  File "HW5_prb3.py", line 45, in <module>
    comm.recv(my_result, dest=1, tag=123);
  File "Comm.pyx", line 1142, in mpi4py.MPI.Comm.recv (src/mpi4py.MPI.c:90513)
**TypeError: recv() got an unexpected keyword argument 'dest'**
-------------------------------------------------------
Primary job  terminated normally, but 1 process returned
a non-zero exit code.. Per user-direction, the job has been aborted.
-------------------------------------------------------
--------------------------------------------------------------------------
mpirun detected that one or more processes exited with non-zero status, thus causing
the job to be terminated. The first process to do so was:

  Process name: [[45152,1],1]
  Exit code:    1
--------------------------------------------------------------------------
*******************************-VirtualBox ~/Documents/ME701/HW/HW5 $ 

The answer to the midpoint integration should be 41.66667. My teacher just wants us to perform a simple time study on parallel computing so we can see the power of it.

Thank you for your time.

Answer 1

I guess you just mixed up send and recv arguments - source is the process rank you receive data from, and dest (short for destination ) is the rank of the process you send data to (you can see the docs , if you want).

So, just interchanging source and dest keywords in send and receive should be fine.