I am a beginner in doing GPU programming with OpenACC. I was trying to do a direct convolution. Convolution consists of 6 nested loops. I only want the first loop to be parallelized. I gave the pragma #pragma acc loop for the first loop and #pragma acc loop seq for the rest. But the output that I am getting is not correct. Is the approach taken by me to parallelize the loop correct ? Specifications for the convolution: Input channels-3, Input Size- 224X224X3, Output channels- 64, Output Size- 111X111X64, filter size- 3X3X3X64.
Code snippet is as follows:
# include <stdio.h>
#include <stdlib.h>
#include <math.h>
#include "squeezenet_params.h"
#include "dog.h"
void conv3x3(
const int input_channels, const int input_size,
const int pad, const int stride, const int start_channel,
const int output_size, const float* restrict input_im, const float* restrict filter_weight,
const float* restrict filter_bias, float* restrict output_im){
#pragma acc data copyin (input_im[0:150527],filter_weight[0:1727],filter_bias[0:63]) copyout(output_im[0:788543])
{
#pragma acc parallel
{
#pragma acc loop
for(int p=0;p<64;++p){
filter_weight += p * input_channels * 9;
float bias = filter_bias[p];
output_im += (start_channel + p) * output_size * output_size;
//loop over output feature map
#pragma acc loop seq
for(int i = 0; i < output_size; i++)
{
#pragma acc loop seq
for(int j = 0; j < output_size; j++)
{
//compute one element in the output feature map
float tmp = bias;
//compute dot product of 2 input_channels x 3 x 3 matrix
#pragma acc loop seq
for(int k = 0; k < input_channels; k++)
{
#pragma acc loop seq
for(int l = 0; l < 3; l++)
{
int h = i * stride + l - pad;
#pragma acc loop seq
for(int m = 0; m < 3; m++)
{
int w = j * stride + m - pad;
if((h >= 0) && (h < input_size) && (w >= 0) && (w < input_size))
{
tmp += input_im[k * input_size * input_size + (i * stride + l - pad) * input_size + j * stride + m - pad] \
* filter_weight[9 * k + 3 * l + m];
}
}
}
}
//add relu activation after conv
output_im[i * output_size + j] = (tmp > 0.0) ? tmp : 0.0;
}
}
}
}
}
}
void main(){
float * result = (float*)malloc(sizeof(float) * (1 * 64 * 111 * 111));
conv3x3(3,224,0,2,0,111,sample,conv1_weight,conv1_bias,result);
for(int i=0;i<64 * 111 * 111;++i){
//if(result[i]>0)
printf("%f:%d\n",result[i],i);
}
}