histogram kernel memory issue - opencv

Question

I am trying to implement an algorithm to process images with more than 256 bins.
The main issue to process histogram in such case comes from the impossibility to allocate more than 32 Kb as local tab in the GPU.
All the algorithms I found for 8 bits per pixel images use a fixed size tab locally.
The histogram is the first process in that tab then a barrier is up and at last an addition is made with the output vector.
I am working with IR image which has more than 32K bins of dynamic.
So I cannot allocate a fixed size tab inside the GPU.
My algorithm use an atomic_add in order to create directly the output histogram.
I am interfacing with OpenCV so, in order to manage the possible case of saturation my bins use floating points. Depending on the ability of the GPU to manage single or double precision.
OpenCV doesn't manage unsigned int, long, and unsigned long data type as matrix type.
I have an error... I do think this error is a kind of segmentation fault.
After several days I still have no idea what can be wrong.
Here is my code :
histogram.cl :
#pragma OPENCL EXTENSION cl_khr_fp64: enable
#pragma OPENCL EXTENSION cl_khr_int64_base_atomics: enable
static void Atomic_Add_f64(__global double *val, double delta)
{
union {
double f;
ulong i;
} old;
union {
double f;
ulong i;
} new;
do {
old.f = *val;
new.f = old.f + delta;
}
while (atom_cmpxchg ( (volatile __global ulong *)val, old.i, new.i) != old.i);
}
static void Atomic_Add_f32(__global float *val, double delta)
{
union
{
float f;
uint i;
} old;
union
{
float f;
uint i;
} new;
do
{
old.f = *val;
new.f = old.f + delta;
}
while (atom_cmpxchg ( (volatile __global ulong *)val, old.i, new.i) != old.i);
}
__kernel void khist(
__global const uchar* _src,
const int src_steps,
const int src_offset,
const int rows,
const int cols,
__global uchar* _dst,
const int dst_steps,
const int dst_offset)
{
const int gid = get_global_id(0);
// printf("This message has been printed from the OpenCL kernel %d \n",gid);
if(gid < rows)
{
__global const _Sty* src = (__global const _Sty*)_src;
__global _Dty* dst = (__global _Dty*) _dst;
const int src_step1 = src_steps/sizeof(_Sty);
const int dst_step1 = dst_steps/sizeof(_Dty);
src += mad24(gid,src_step1,src_offset);
dst += mad24(gid,dst_step1,dst_offset);
_Dty one = (_Dty)1;
for(int c=0;c<cols;c++)
{
const _Rty idx = (_Rty)(*(src+c+src_offset));
ATOMIC_FUN(dst+idx+dst_offset,one);
}
}
}
The function Atomic_Add_f64 directly come from here and there
main.cpp
#include <opencv2/core.hpp>
#include <opencv2/core/ocl.hpp>
#include <fstream>
#include <sstream>
#include <chrono>
int main()
{
cv::Mat_<unsigned short> a(480,640);
cv::RNG rng(std::time(nullptr));
std::for_each(a.begin(),a.end(),[&](unsigned short& v){ v = rng.uniform(0,100);});
bool ret = false;
cv::String file_content;
{
std::ifstream file_stream("../test/histogram.cl");
std::ostringstream file_buf;
file_buf<<file_stream.rdbuf();
file_content = file_buf.str();
}
int output_flag = cv::ocl::Device::getDefault().doubleFPConfig() == 0 ? CV_32F : CV_64F;
cv::String atomic_fun = output_flag == CV_32F ? "Atomic_Add_f32" : "Atomic_Add_f64";
cv::ocl::ProgramSource source(file_content);
// std::cout<<source.source()<<std::endl;
cv::ocl::Kernel k;
cv::UMat src;
cv::UMat dst = cv::UMat::zeros(1,65536,output_flag);
a.copyTo(src);
atomic_fun = cv::format("-D _Sty=%s -D _Rty=%s -D _Dty=%s -D ATOMIC_FUN=%s",
cv::ocl::typeToStr(src.depth()),
cv::ocl::typeToStr(src.depth()), // this to manage case like a matrix of usigned short stored as a matrix of float.
cv::ocl::typeToStr(output_flag),
atomic_fun.c_str());
ret = k.create("khist",source,atomic_fun);
std::cout<<"check create : "<<ret<<std::endl;
k.args(cv::ocl::KernelArg::ReadOnly(src),cv::ocl::KernelArg::WriteOnlyNoSize(dst));
std::size_t sz = a.rows;
ret = k.run(1,&sz,nullptr,false);
std::cout<<"check "<<ret<<std::endl;
cv::Mat b;
dst.copyTo(b);
std::copy_n(b.ptr<double>(0),101,std::ostream_iterator<double>(std::cout," "));
std::cout<<std::endl;
return EXIT_SUCCESS;
}

Answer 1

Hello I arrived to fix it.
I don't really know where the issue come from.
But if I suppose the output as a pointer rather than a matrix it work.
The changes I made are these :
histogram.cl :
__kernel void khist(
__global const uchar* _src,
const int src_steps,
const int src_offset,
const int rows,
const int cols,
__global _Dty* _dst)
{
const int gid = get_global_id(0);
if(gid < rows)
{
__global const _Sty* src = (__global const _Sty*)_src;
__global _Dty* dst = _dst;
const int src_step1 = src_steps/sizeof(_Sty);
src += mad24(gid,src_step1,src_offset);
ulong one = 1;
for(int c=0;c<cols;c++)
{
const _Rty idx = (_Rty)(*(src+c+src_offset));
ATOMIC_FUN(dst+idx,one);
}
}
}
main.cpp
k.args(cv::ocl::KernelArg::ReadOnly(src),cv::ocl::KernelArg::PtrWriteOnly(dst));
The rest of the code is the same in the two files.
For me it work fine.
If someone know why it work when the ouput is declared as a pointer rather than a vector (matrix of one row) I am interested.
Nevertheless my issue is fix :).