OpenMP slower than single threaded even though embarrassingly parallelizable [duplicate] - c

Question

I have optimized as much as I could my function for sequential running.
When I use openMP I see no gain in performance.
I tried my program on a machine with 1 cores and on a machine with 8 cores, and the performance is the same.
With year set to 20, I have
1 core: 1 sec.
8 core: 1 sec.
With year set to 25 I have
1 core: 40 sec.
8 core: 40 sec.
1 core machine: my laptop's intel core 2 duo 1.8 GHz, ubuntu linux
8 core machine: 3.25 GHz, ubuntu linux
My program enumerate all the possible path of a binomial tree and do some work on each path. So my loop size increase exponentially and I would expect the footprint of openMP thread to be zero. In my loop, I only do a reduction of one variable. All other variable are read-only. I only use function I wrote, and I think they are thread safe.
I also run Valgrind cachegrind on my program. I don't fully understand the output but there seems to be no cache miss or false sharing.
I compile with
gcc -O3 -g3 -Wall -c -fmessage-length=0 -lm -fopenmp -ffast-math
My complete program is as below. Sorry for posting a lot of code. I'm not familiar with openMP nor C, and I couldn't resume my code more without loosing the main task.
How can I improve performance when I use openMP?
Are they some compiler flags or C tricks that will make the program run faster?
test.c
#include <stdio.h>
#include <stdlib.h>
#include <math.h>
#include <omp.h>
#include "test.h"
int main(){
printf("starting\n");
int year=20;
int tradingdate0=1;
globalinit(year,tradingdate0);
int i;
float v=0;
long n=pow(tradingdate0+1,year);
#pragma omp parallel for reduction(+:v)
for(i=0;i<n;i++)
v+=pathvalue(i);
globaldel();
printf("finished\n");
return 0;
}
//***function on which openMP is applied
float pathvalue(long pathindex) {
float value = -ctx.firstpremium;
float personalaccount = ctx.personalaccountat0;
float account = ctx.firstpremium;
int i;
for (i = 0; i < ctx.year-1; i++) {
value *= ctx.accumulationfactor;
double index = getindex(i,pathindex);
account = account * index;
double death = fmaxf(account,ctx.guarantee[i]);
value += qx(i) * death;
if (haswithdraw(i)){
double withdraw = personalaccount*ctx.allowed;
value += px(i) * withdraw;
personalaccount = fmaxf(personalaccount-withdraw,0);
account = fmaxf(account-withdraw,0);
}
}
//last year
double index = getindex(ctx.year-1,pathindex);
account = account * index;
value+=fmaxf(account,ctx.guarantee[ctx.year-1]);
return value * ctx.discountfactor;
}
int haswithdraw(int period){
return 1;
}
float getindex(int period, long pathindex){
int ndx = (pathindex/ctx.chunksize[period])%ctx.tradingdate;
return ctx.stock[ndx];
}
float qx(int period){
return 0;
}
float px(int period){
return 1;
}
//****global
struct context ctx;
void globalinit(int year, int tradingdate0){
ctx.year = year;
ctx.tradingdate0 = tradingdate0;
ctx.firstpremium = 1;
ctx.riskfreerate = 0.06;
ctx.volatility=0.25;
ctx.personalaccountat0 = 1;
ctx.allowed = 0.07;
ctx.guaranteerate = 0.03;
ctx.alpha=1;
ctx.beta = 1;
ctx.tradingdate=tradingdate0+1;
ctx.discountfactor = exp(-ctx.riskfreerate * ctx.year);
ctx.accumulationfactor = exp(ctx.riskfreerate);
ctx.guaranteefactor = 1+ctx.guaranteerate;
ctx.upmove=exp(ctx.volatility/sqrt(ctx.tradingdate0));
ctx.downmove=1/ctx.upmove;
ctx.stock=(float*)malloc(sizeof(float)*ctx.tradingdate);
int i;
for(i=0;i<ctx.tradingdate;i++)
ctx.stock[i]=pow(ctx.upmove,ctx.tradingdate0-i)*pow(ctx.downmove,i);
ctx.chunksize=(long*)malloc(sizeof(long)*ctx.year);
for(i=0;i<year;i++)
ctx.chunksize[i]=pow(ctx.tradingdate,ctx.year-i-1);
ctx.guarantee=(float*)malloc(sizeof(float)*ctx.year);
for(i=0;i<ctx.year;i++)
ctx.guarantee[i]=ctx.beta*pow(ctx.guaranteefactor,i+1);
}
void globaldel(){
free(ctx.stock);
free(ctx.chunksize);
free(ctx.guarantee);
}
test.h
float pathvalue(long pathindex);
int haswithdraw(int period);
float getindex(int period, long pathindex);
float qx(int period);
float px(int period);
//***global
struct context{
int year;
int tradingdate0;
float firstpremium;
float riskfreerate;
float volatility;
float personalaccountat0;
float allowed;
float guaranteerate;
float alpha;
float beta;
int tradingdate;
float discountfactor;
float accumulationfactor;
float guaranteefactor;
float upmove;
float downmove;
float* stock;
long* chunksize;
float* guarantee;
};
struct context ctx;
void globalinit();
void globaldel();
EDIT I simplify all global variables as constant. For 20 year, the program run two time faster (great!). I tried to set the number of thread with OMP_NUM_THREADS=4 ./test for example. But it didn't give me any performance gain.
Can my gcc have some problem?
test.c
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#include <math.h>
#include <omp.h>
#include "test.h"
int main(){
starttimer();
printf("starting\n");
int i;
float v=0;
#pragma omp parallel for reduction(+:v)
for(i=0;i<numberofpath;i++)
v+=pathvalue(i);
printf("v:%f\nfinished\n",v);
endtimer();
return 0;
}
//function on which openMP is applied
float pathvalue(long pathindex) {
float value = -firstpremium;
float personalaccount = personalaccountat0;
float account = firstpremium;
int i;
for (i = 0; i < year-1; i++) {
value *= accumulationfactor;
double index = getindex(i,pathindex);
account = account * index;
double death = fmaxf(account,guarantee[i]);
value += death;
double withdraw = personalaccount*allowed;
value += withdraw;
personalaccount = fmaxf(personalaccount-withdraw,0);
account = fmaxf(account-withdraw,0);
}
//last year
double index = getindex(year-1,pathindex);
account = account * index;
value+=fmaxf(account,guarantee[year-1]);
return value * discountfactor;
}
float getindex(int period, long pathindex){
int ndx = (pathindex/chunksize[period])%tradingdate;
return stock[ndx];
}
//timing
clock_t begin;
void starttimer(){
begin = clock();
}
void endtimer(){
clock_t end = clock();
double elapsed = (double)(end - begin) / CLOCKS_PER_SEC;
printf("\nelapsed: %f\n",elapsed);
}
test.h
float pathvalue(long pathindex);
int haswithdraw(int period);
float getindex(int period, long pathindex);
float qx(int period);
float px(int period);
//timing
void starttimer();
void endtimer();
//***constant
const int year= 20 ;
const int tradingdate0= 1 ;
const float firstpremium= 1 ;
const float riskfreerate= 0.06 ;
const float volatility= 0.25 ;
const float personalaccountat0= 1 ;
const float allowed= 0.07 ;
const float guaranteerate= 0.03 ;
const float alpha= 1 ;
const float beta= 1 ;
const int tradingdate= 2 ;
const int numberofpath= 1048576 ;
const float discountfactor= 0.301194211912 ;
const float accumulationfactor= 1.06183654655 ;
const float guaranteefactor= 1.03 ;
const float upmove= 1.28402541669 ;
const float downmove= 0.778800783071 ;
const float stock[2]={1.2840254166877414, 0.7788007830714049};
const long chunksize[20]={524288, 262144, 131072, 65536, 32768, 16384, 8192, 4096, 2048, 1024, 512, 256, 128, 64, 32, 16, 8, 4, 2, 1};
const float guarantee[20]={1.03, 1.0609, 1.092727, 1.1255088100000001, 1.1592740743, 1.1940522965290001, 1.2298738654248702, 1.2667700813876164, 1.304773183829245, 1.3439163793441222, 1.384233870724446, 1.4257608868461793, 1.4685337134515648, 1.512589724855112, 1.557967416600765, 1.6047064390987882, 1.6528476322717518, 1.7024330612399046, 1.7535060530771016, 1.8061112346694148};

Answer 1

Even if your program benefits from using OpenMP, you won't see it because you are measuring the wrong time.
clock() returns the total CPU time spent in all threads. If you run with four threads and each runs for 1/4 of the time, clock() will still return the same value since 4*(1/4) = 1. You should be measuring the wall-clock time instead.
Replace calls to clock() with omp_get_wtime() or gettimeofday(). They both provide high precision wall-clock timing.
P.S. Why are there so many people around SO using clock() for timing?

Answer 2

It seems as if it should work. Probably you need to specify the number of threads to use. You can do so by setting the OMP_NUM_THREADS variable. For instance, for using 4 threads:
OMP_NUM_THREADS=4 ./test
EDIT: I just compiled the code and I observe significant speedups when changing the number of threads.

Answer 3

I don't see any section in which you're specifying the number of cores OpenMP will use. It's supposed to, by default, use the number of CPUs it sees, but for my purposes, I've always forced it to use as many as I specified.
Add this line before your parallel for construct:
#pragma omp parallel num_threads(num_threads)
{
// Your parallel for follows here
}
...where num_threads is an integer between 1 and the number of cores on your machine.
EDIT: Here's the makefile used to build the code. Place this in a text file named Makefile in the same directory.
test: test.c test.h
cc -o $# $< -O3 -g3 -fmessage-length=0 -lm -fopenmp -ffast-math