This post covers the steps to profile a C code using GNU’s profiler – gprof.
Profiling your serial code is one of the most important step in writing parallel codes. We use profilers to find out the most time consuming parts of the code.
Let us consider following sample C code.
#include<stdio.h>
#include<stdlib.h>
#define ARRSIZE 99999999
void print_data(int *C)
{
int i;
//print the data
printf("\tC Array values : ");
for(i=0;i<ARRSIZE;i++)
{
printf("\t%d\n", C[i]);
}
}
void initialize(int *A, int *B, int *C)
{
int i;
//Initialize data to some value
for(i=0;i<ARRSIZE;i++)
{
A[i] = 2*(i+1);
B[i] = i+1;
}
//print_data(C);
}
void add_arrays(int *A, int *B, int *C)
{
int i;
for(i=0;i<ARRSIZE;i++)
{
C[i] = A[i] + B[i];
}
//print_data(C);
}
void sub_arrays(int *A, int *B, int *C)
{
int i;
for(i=0;i<ARRSIZE;i++)
{
C[i] = A[i] - B[i];
}
//print_data(C);
}
void mul_arrays(int *A, int *B, int *C)
{
int i;
for(i=0;i<ARRSIZE;i++)
{
C[i] = A[i] * B[i];
}
//print_data(C);
}
void div_arrays(int *A, int *B, int *C)
{
int i;
for(i=0;i<ARRSIZE;i++)
{
C[i] = A[i] / B[i];
}
//print_data(C);
}
int main(int argc, char **argv)
{
int myid, size;
int i;
int *A, *B, *C;
//Allocate and initialize the arrays
A = (int *)malloc(ARRSIZE*sizeof(int));
B = (int *)malloc(ARRSIZE*sizeof(int));
C = (int *)malloc(ARRSIZE*sizeof(int));
initialize(A,B,C);
//print the data
//printf("\nInitial data: \n");
//for(i=0;i<ARRSIZE;i++)
//{
// printf("\t%d \t %d\n", A[i], B[i]);
//}
add_arrays(A,B,C);
sub_arrays(A,B,C);
mul_arrays(A,B,C);
div_arrays(A,B,C);
printf("\nProgram exit!\n");
//Free arrays
free(A);
free(B);
free(C);
}Fore this code, we would like to identify the amount of time spent in different parts of the code. For this, we can use GNU’s gprof utility.
First step is to compile the code using gcc compiler with specific flags.
gcc -pg mycode.cThis compilation command creates the a.out as a executable as usual. Additionally, we have used two flags.
-g flag for adding debugging information
-p flag for adding extra code to generate profiling information when the code is executed.
When we execute this code using ./a.out command, it generates a file named gmon.out which contains the profiling output for the recent execution of this executable.
To view the profiling output, we can use following command (gprof <executable_name>)
gprof ./a.outFor the above code, I get following output on my system –
Flat profile:
Each sample counts as 0.01 seconds.
% cumulative self self total
time seconds seconds calls ms/call ms/call name
27.80 0.62 0.62 1 620.00 620.00 initialize
25.11 1.18 0.56 1 560.00 560.00 add_arrays
17.49 1.57 0.39 1 390.00 390.00 sub_arrays
15.25 1.91 0.34 1 340.00 340.00 div_arrays
14.35 2.23 0.32 1 320.00 320.00 mul_arrays
% the percentage of the total running time of the
time program used by this function.
cumulative a running sum of the number of seconds accounted
seconds for by this function and those listed above it.
self the number of seconds accounted for by this
seconds function alone. This is the major sort for this
listing.
calls the number of times this function was invoked, if
this function is profiled, else blank.
self the average number of milliseconds spent in this
ms/call function per call, if this function is profiled,
else blank.
total the average number of milliseconds spent in this
ms/call function and its descendents per call, if this
function is profiled, else blank.
name the name of the function. This is the minor sort
for this listing. The index shows the location of
the function in the gprof listing. If the index is
in parenthesis it shows where it would appear in
the gprof listing if it were to be printed.
Copyright (C) 2012-2022 Free Software Foundation, Inc.
Copying and distribution of this file, with or without modification,
are permitted in any medium without royalty provided the copyright
notice and this notice are preserved.
Call graph (explanation follows)
granularity: each sample hit covers 4 byte(s) for 0.45% of 2.23 seconds
index % time self children called name
<spontaneous>
[1] 100.0 0.00 2.23 main [1]
0.62 0.00 1/1 initialize [2]
0.56 0.00 1/1 add_arrays [3]
0.39 0.00 1/1 sub_arrays [4]
0.34 0.00 1/1 div_arrays [5]
0.32 0.00 1/1 mul_arrays [6]
-----------------------------------------------
0.62 0.00 1/1 main [1]
[2] 27.8 0.62 0.00 1 initialize [2]
-----------------------------------------------
0.56 0.00 1/1 main [1]
[3] 25.1 0.56 0.00 1 add_arrays [3]
-----------------------------------------------
0.39 0.00 1/1 main [1]
[4] 17.5 0.39 0.00 1 sub_arrays [4]
-----------------------------------------------
0.34 0.00 1/1 main [1]
[5] 15.2 0.34 0.00 1 div_arrays [5]
-----------------------------------------------
0.32 0.00 1/1 main [1]
[6] 14.3 0.32 0.00 1 mul_arrays [6]
-----------------------------------------------
This table describes the call tree of the program, and was sorted by
the total amount of time spent in each function and its children.
Each entry in this table consists of several lines. The line with the
index number at the left hand margin lists the current function.
The lines above it list the functions that called this function,
and the lines below it list the functions this one called.
This line lists:
index A unique number given to each element of the table.
Index numbers are sorted numerically.
The index number is printed next to every function name so
it is easier to look up where the function is in the table.
% time This is the percentage of the `total' time that was spent
in this function and its children. Note that due to
different viewpoints, functions excluded by options, etc,
these numbers will NOT add up to 100%.
self This is the total amount of time spent in this function.
children This is the total amount of time propagated into this
function by its children.
called This is the number of times the function was called.
If the function called itself recursively, the number
only includes non-recursive calls, and is followed by
a `+' and the number of recursive calls.
name The name of the current function. The index number is
printed after it. If the function is a member of a
cycle, the cycle number is printed between the
function's name and the index number.
For the function's parents, the fields have the following meanings:
self This is the amount of time that was propagated directly
from the function into this parent.
children This is the amount of time that was propagated from
the function's children into this parent.
called This is the number of times this parent called the
function `/' the total number of times the function
was called. Recursive calls to the function are not
included in the number after the `/'.
name This is the name of the parent. The parent's index
number is printed after it. If the parent is a
member of a cycle, the cycle number is printed between
the name and the index number.
If the parents of the function cannot be determined, the word
`<spontaneous>' is printed in the `name' field, and all the other
fields are blank.
For the function's children, the fields have the following meanings:
self This is the amount of time that was propagated directly
from the child into the function.
children This is the amount of time that was propagated from the
child's children to the function.
called This is the number of times the function called
this child `/' the total number of times the child
was called. Recursive calls by the child are not
listed in the number after the `/'.
name This is the name of the child. The child's index
number is printed after it. If the child is a
member of a cycle, the cycle number is printed
between the name and the index number.
If there are any cycles (circles) in the call graph, there is an
entry for the cycle-as-a-whole. This entry shows who called the
cycle (as parents) and the members of the cycle (as children.)
The `+' recursive calls entry shows the number of function calls that
were internal to the cycle, and the calls entry for each member shows,
for that member, how many times it was called from other members of
the cycle.
Copyright (C) 2012-2022 Free Software Foundation, Inc.
Copying and distribution of this file, with or without modification,
are permitted in any medium without royalty provided the copyright
notice and this notice are preserved.
Index by function name
[3] add_arrays [2] initialize [4] sub_arrays
[5] div_arrays [6] mul_arraysFirst table offers the list of functions sorted in descending order based on their execution time. This table provides details about how much time these function took, how many times these functions were called etc.
Second table provides call graph – in simple words, who calls whom and in which order. It provides similar information as that of the first table.
For parallelization of the code, we will start from the most time consuming function and parallelize the function one-by-one in descending order(until we achieve reasonable parallel performance).