memmap_performance.cpp

void TestReadingMMap()
{
  	double bytesRead = 0;
	double elapsed = 0;
	mapped_file_source file;
	__int64 checksum = 0;

	{
		auto_cpu_timer timer;
		file.open("C:\SomeBigFile.dat", 2147483647);
		stream<mapped_file_source> input(file);

		if(file.is_open()) 
		{
			const int segmentSize = 4096;
			const int size = file.size();
			const int remainder = file.size() % segmentSize;
			const int segmentLoops = file.size() / segmentSize;

			char bytes[segmentSize];
			for (int x=0; x<segmentLoops; x++)
			{
				input.read(bytes, segmentSize);				
                		#pragma unroll 4096
				for (int i=0; i<segmentSize; i++)
				{
					// This block reduces IO rate from 1.6GB/s 
					// to 1GB/s loosing 600MB/s.
				  	checksum += bytes[i];
				}
				bytesRead += segmentSize;
			}

            		// Moving this out here rather than a condition in the loop above 
            		// reduced branch mispredictions.
			if (remainder > 0)
			{
                		input.read(bytes, remainder);
				for (int i=0; i<remainder; i++)
				{
					checksum += bytes[i];
				}
				bytesRead += remainder;
			}

			input.close();
			file.close(); // Unmap the file.

			if (checksum == 43089565243)
			{
				cout << "Checksum passed" << endl;
			}
		}
		else 
		{
			cout << "could not map the file" << std::endl;
		}
		elapsed = timer.elapsed().wall;
	}
	cout << bytesRead / 1048576 << "MB at " << bytesRead / 1048576 / (elapsed/ 1000000000) << " MB/s" << endl;
	cout << "Checksum: " << checksum << endl;
}

I achieved great speedup by using an array of 64bit int and doing 64bit addition instead of 8 times as many 8bit addition
.

    if(file.is_open()) 
    {
        const int segmentSize = 4096;
        const int size = file.size();
        const int remainder = file.size() % segmentSize;
        const int segmentLoops = file.size() / segmentSize;
        __int64 value = 0;

        __int64 bytes[segmentSize/sizeof(__int64)];
        for (int x=0; x<segmentLoops; x++)
        {
            input.read((char*)bytes, segmentSize);
            #pragma unroll 4096
            for (int i=0; i<segmentSize/sizeof(__int64); i++)
            {
                // This block reduces IO rate from 1.6GB/s 
                // to 1GB/s loosing 600MB/s.
                // JRW: original was 220MB/s to 80MB/s on my old system

                checksum += bytes[i];
                // instead of adding lots of 8bit numbers we add 64bit numbers and I keep my 220MB/s
            }
            bytesRead += segmentSize;
        }

        // Moving this out here rather than a condition in the loop above 
        // reduced branch mispredictions.
        if (remainder > 0)
        {
            input.read((char*)bytes, remainder);
            for (int i=0; i<remainder/sizeof(__int64); i++)
            {
                checksum += bytes[i];
            }
            bytesRead += remainder;
        }

        input.close();
        file.close(); // Unmap the file.

        if (checksum == 43089565243)
        {
            cout << "Checksum passed" << endl;
        }