Ad:

C++ Discussion Thread
Unsolved
Views: 896

Nov 11th, 2009

float and double behavior

Expand Post »

I am trying to optimize code for Monte Carlo simulation. Even minute performance differences piles up after 100 million iterations and thus I need to squeeze every nanosecond from math operations!
One area where I thought I could save a lot stems from the fact that I only require precision of 4 significant digits. It therefore seems natural to use float rather than double.
However, some testing suggests that double still performs better! This is unexpected.
Why is it that despite the fact that float is 32 bits and double 64 bits, mathh functions are quicker to perform exp(double) and pow(double, double) than exp(float) and pow(float, float) (or even expf and powf)? Here is some code...

C++ Syntax (Toggle Plain Text)
 
#include <math.h>
#include <iostream>
#include "Timer.h"
 
int main()
{
	double a = 23.14;
	float c = 23.14;
	Timer t;
	t.tic();
	for (int i = 0; i < 10000000; i++)
		expf(c);
	cout<<"expf(float) returns " << expf(c)<<" and took "<<t.toc()<< " seconds." << endl;
	t.tic();
	for (int i = 0; i < 10000000; i++)
		exp(c);
	cout<<"exp(float) returns " << exp(c)<<" and took "<<t.toc()<< " seconds." << endl;
	t.tic();
	for (int i = 0; i < 10000000; i++)
		exp(a);
	cout<<"exp(double) returns " << exp(a)<<" and took "<<t.toc()<< " seconds." << endl;
}
 
#include <math.h>
#include <iostream>
#include "Timer.h"

int main()
{
	double a = 23.14;
	float c = 23.14;
	Timer t;
	t.tic();
	for (int i = 0; i < 10000000; i++)
		expf(c);
	cout<<"expf(float) returns " << expf(c)<<" and took "<<t.toc()<< " seconds." << endl;
	t.tic();
	for (int i = 0; i < 10000000; i++)
		exp(c);
	cout<<"exp(float) returns " << exp(c)<<" and took "<<t.toc()<< " seconds." << endl;
	t.tic();
	for (int i = 0; i < 10000000; i++)
		exp(a);
	cout<<"exp(double) returns " << exp(a)<<" and took "<<t.toc()<< " seconds." << endl;
}

Similar Threads

Difference between float and double in C++
error: invalid operands to binary ^ (have ‘float’ and ‘double’) in C
problem with Float and Double in C
Conversion of Float/Double to binary in Java
using float, double numbers in mips assembly language in Assembly

abie

Reputation Points: 10

Solved Threads: 0

Newbie Poster

Offline

1 posts
since Nov 2009

Permalink

Nov 11th, 2009

-7

Re: float and double behavior

>>However, some testing suggests that double still performs better! This is unexpected.

Yup. floats are always converted to doubles when used as function parameters. Other factors may influence it too, such as the math coprocessor on your computer.

Ancient Dragon

Sponsor

Team Colleague

Featured Poster

Reputation Points: 5608

Solved Threads: 2282

Retired and Enjoying Life

Online

21,959 posts
since Aug 2005

Permalink

Nov 11th, 2009

Re: float and double behavior

Click to Expand / Collapse Quote originally posted by Ancient Dragon ...

Yup. floats are always converted to doubles when used as function parameters.

http://groups.google.com/group/comp....p.lang.c&pli=1

Quote ...

No, that's only true if
(1) you call the function without a prototype in scope, or
(2) it's a variable argument to a variadic function like 'printf'.

Last edited by Dave Sinkula; Nov 11th, 2009 at 12:59 pm.

Dave Sinkula

Team Colleague

Reputation Points: 2780

Solved Threads: 312

long time no c

Offline

4,790 posts
since Apr 2004

Permalink

Nov 11th, 2009

-7

Re: float and double behavior

Dave: Yes, I see you are correct. I wrote a short test program and had the compiler produce assembler instructions, which showed the same behavior as what you posted.

Ancient Dragon

Sponsor

Team Colleague

Featured Poster

Reputation Points: 5608

Solved Threads: 2282

Retired and Enjoying Life

Online

21,959 posts
since Aug 2005

Permalink

Nov 11th, 2009

Re: float and double behavior

floats are made for spaced optimization, it does not necessarily have to
be faster than double, especially in a 64bit CPU.

firstPerson

Reputation Points: 840

Solved Threads: 594

Senior Poster

Offline

3,864 posts
since Dec 2008

Permalink

Nov 11th, 2009

Re: float and double behavior

How about you show some code, so we can try to help you,
although monte carlo problem should be slow to execute as it is quite
easy to implement.

Last edited by firstPerson; Nov 11th, 2009 at 7:58 pm.

firstPerson

Reputation Points: 840

Solved Threads: 594

Senior Poster

Offline

3,864 posts
since Dec 2008

This thread is more than three months old

No one has posted to this discussion for at least three months. Please let old threads die and do not reply to them unless you feel you have something new and valuable to contribute that absolutely must be added to make the discussion complete. Otherwise, please start a new thread in this forum instead.

Previous Thread in C++ Forum Timeline: very basic c++ question on vectors

Next Thread in C++ Forum Timeline: waveOutWrite is creating complex wave instead of simple sine wave

DaniWeb Message

Cancel Changes

User Name
Password