Sequence Query Performance

With a 1.4GB test file (influenza.fna) and FX8150 (3.6GHz, no turbo):

init: 20591756442 nanoseconds    
sequence query (sequential-access latency benchmark, single thread): 20556579905 nanoseconds     
(bandwidth = 63.28 MB/s)      (throughput = 25142.99 nanoseconds per iteration) 

sequence query (sequential-access latency benchmark, multi thread): 3905752569 nanoseconds     
(bandwidth = 333.04 MB/s)      (throughput = 4777.17 nanoseconds per iteration) 

sequence query (random-access latency benchmark, single thread): 32844866933 nanoseconds     
(bandwidth = 39.60 MB/s)      (throughput = 40172.93 nanoseconds per iteration) 

equence query (random-access latency benchmark, multi thread): 5199542168 nanoseconds     
(bandwidth = 250.17 MB/s)      (throughput = 6359.62 nanoseconds per iteration) 

#include "FastaGeneIndexer.h"
#include "CpuBenchmarker.h"
#include <random>
int main(int argC, char** argV)
{
    try
    {
        bool debug = true;
        FastaGeneIndexer cache("./data/influenza.fna", debug);

        size_t n = cache.n();
        size_t byteCount = 0;
        {
        	CpuBenchmarker bench(0,"init");
        	for(int i=0;i<n;i++)
        	{
        		std::string str = cache.getSequence(i);
        		byteCount += str.length();

        	}
        }

        {
        	CpuBenchmarker bench(byteCount,"sequence query (sequential-access latency benchmark, single thread)",n);
        	for(int i=0;i<n;i++)
        	{
        		std::string str = cache.getSequence(i);
        	}
        }

        {
        	CpuBenchmarker bench(byteCount,"sequence query (sequential-access latency benchmark, multi thread)",n);

			#pragma omp parallel for
        	for(int i=0;i<n;i++)
        	{
        		std::string str = cache.getSequence(i);
        	}
        }

        {
        	CpuBenchmarker bench(byteCount,"sequence query (random-access latency benchmark, single thread)",n);
        	for(int i=0;i<n;i++)
        	{
            	auto f = [](const int & min, const int & max) {
            	    static thread_local std::mt19937 generator;
            	    std::uniform_int_distribution<int> distribution(min,max);
            	    return distribution(generator);
            	};

        		std::string str = cache.getSequence(f(0,n-1));
        	}
        }


        {
        	CpuBenchmarker bench(byteCount,"equence query (random-access latency benchmark, multi thread)",n);

			#pragma omp parallel for
        	for(int i=0;i<n;i++)
        	{
            	auto f = [](const int & min, const int & max) {
            	    static thread_local std::mt19937 generator;
            	    std::uniform_int_distribution<int> distribution(min,max);
            	    return distribution(generator);
            	};

        		std::string str = cache.getSequence(f(0,n-1));
        	}
        }
    }
    catch(std::exception & e)
    {
        std::cout<< e.what() <<std::endl;
    }
    return 0;
}