Geek Answers Handbook

De / Interleave fast in C #

I am looking for the fastest way to delete / strip a buffer. To be more specific, I deal with audio data, so I am trying to optimize the time I spend splitting / combining channels and FFT buffers.

I am currently using a for loop with 2 index variables for each array, so only plus operations, but all checks of the managed array will not be compared with the C pointer method.

I like the Buffer.BlockCopy and Array.Copy methods, which reduce a lot of time when processing pipes, but there is no way for the array to have a custom indexer.

I tried to find a way to create an array mask where it would be a fake array with a custom index, but this turned out to be twice as slow when using it in my FFT operation. I think that there are many optimization tricks that the compiler can extract with direct access to the array, but access to it through the index index cannot be optimized.

I do not want an unsafe solution, although, in appearance, this is the only way to optimize this type of operation.

Thanks.

Here is what I am doing right now:

private float[][] DeInterleave(float[] buffer, int channels)
{
    float[][] tempbuf = new float[channels][];
    int length = buffer.Length / channels;
    for (int c = 0; c < channels; c++)
    {
        tempbuf[c] = new float[length];
        for (int i = 0, offset = c; i < tempbuf[c].Length; i++, offset += channels)
            tempbuf[c][i] = buffer[offset];
    }
    return tempbuf;
}
+5
source share
5 answers

I did some tests, and here is the code I tested:

delegate(float[] inout)
{ // My Original Code
    float[][] tempbuf = new float[2][];
    int length = inout.Length / 2;
    for (int c = 0; c < 2; c++)
    {
        tempbuf[c] = new float[length];
        for (int i = 0, offset = c; i < tempbuf[c].Length; i++, offset += 2)
            tempbuf[c][i] = inout[offset];
    }
}
delegate(float[] inout)
{ // jerryjvl recommendation: loop unrolling
    float[][] tempbuf = new float[2][];
    int length = inout.Length / 2;
    for (int c = 0; c < 2; c++)
        tempbuf[c] = new float[length];
    for (int ix = 0, i = 0; ix < length; ix++)
    {
        tempbuf[0][ix] = inout[i++];
        tempbuf[1][ix] = inout[i++];
    }

}
delegate(float[] inout)
{ // Unsafe Code
    unsafe
    {
        float[][] tempbuf = new float[2][];
        int length = inout.Length / 2;
        fixed (float* buffer = inout)
            for (int c = 0; c < 2; c++)
            {
                tempbuf[c] = new float[length];
                float* offset = buffer + c;
                fixed (float* buffer2 = tempbuf[c])
                {
                    float* p = buffer2;
                    for (int i = 0; i < length; i++, offset += 2)
                        *p++ = *offset;
                }
            }
    }
}
delegate(float[] inout)
{ // Modifying my original code to see if the compiler is not as smart as i think it is.
    float[][] tempbuf = new float[2][];
    int length = inout.Length / 2;
    for (int c = 0; c < 2; c++)
    {
        float[] buf = tempbuf[c] = new float[length];
        for (int i = 0, offset = c; i < buf.Length; i++, offset += 2)
            buf[i] = inout[offset];
    }
}

and results: (buffer size = 2 ^ 17, number of iterations, dedicated to the test = 200)

Average for test #1:      0.001286 seconds +/- 0.000026
Average for test #2:      0.001193 seconds +/- 0.000025
Average for test #3:      0.000686 seconds +/- 0.000009
Average for test #4:      0.000847 seconds +/- 0.000008

Average for test #1:      0.001210 seconds +/- 0.000012
Average for test #2:      0.001048 seconds +/- 0.000012
Average for test #3:      0.000690 seconds +/- 0.000009
Average for test #4:      0.000883 seconds +/- 0.000011

Average for test #1:      0.001209 seconds +/- 0.000015
Average for test #2:      0.001060 seconds +/- 0.000013
Average for test #3:      0.000695 seconds +/- 0.000010
Average for test #4:      0.000861 seconds +/- 0.000009

. , , , , CLS , jagged . , - .

: , . :

delegate(float[] inout)
{
    float[][] tempbuf = new float[2][];
    int length = inout.Length / 2;
    float[] tempbuf0 = tempbuf[0] = new float[length];
    float[] tempbuf1 = tempbuf[1] = new float[length];

    for (int ix = 0, i = 0; ix < length; ix++)
    {
        tempbuf0[ix] = inout[i++];
        tempbuf1[ix] = inout[i++];
    }
}

№ 4 1%. №4 - , .

jerryjvl, , CLS , (& offset < inout.Length) ...

2: IDE, :

2^17 items, repeated 200 times
******************************************
Average for test #1:      0.000533 seconds +/- 0.000017
Average for test #2:      0.000527 seconds +/- 0.000016
Average for test #3:      0.000407 seconds +/- 0.000008
Average for test #4:      0.000374 seconds +/- 0.000008
Average for test #5:      0.000424 seconds +/- 0.000009

2^17 items, repeated 200 times
******************************************
Average for test #1:      0.000547 seconds +/- 0.000016
Average for test #2:      0.000732 seconds +/- 0.000020
Average for test #3:      0.000423 seconds +/- 0.000009
Average for test #4:      0.000360 seconds +/- 0.000008
Average for test #5:      0.000406 seconds +/- 0.000008


2^18 items, repeated 200 times
******************************************
Average for test #1:      0.001295 seconds +/- 0.000036
Average for test #2:      0.001283 seconds +/- 0.000020
Average for test #3:      0.001085 seconds +/- 0.000027
Average for test #4:      0.001035 seconds +/- 0.000025
Average for test #5:      0.001130 seconds +/- 0.000025

2^18 items, repeated 200 times
******************************************
Average for test #1:      0.001234 seconds +/- 0.000026
Average for test #2:      0.001319 seconds +/- 0.000023
Average for test #3:      0.001309 seconds +/- 0.000025
Average for test #4:      0.001191 seconds +/- 0.000026
Average for test #5:      0.001196 seconds +/- 0.000022

Test#1 = My Original Code
Test#2 = Optimized safe loop unrolling
Test#3 = Unsafe code - loop unrolling
Test#4 = Unsafe code
Test#5 = My Optimized Code

, . - 10% . , (i < buf.Length) , (offset < inout.Length), (inout [offset]), .

+5

, - , . , , , JIT .

, , - unsafe, . ( ), unsafe # ( , , C) , .

+1

( 20% ), . :

static private float[][] Alternative(float[] buffer, int channels)
{
    float[][] result = new float[channels][];
    int length = buffer.Length / channels;
    for (int c = 0; c < channels; c++)
        result[c] = new float[length];

    int i = 0;
    if (channels == 8)
    {
        for (int ix = 0; ix < length; ix++)
        {
            result[0][ix] = buffer[i++];
            result[1][ix] = buffer[i++];
            result[2][ix] = buffer[i++];
            result[3][ix] = buffer[i++];
            result[4][ix] = buffer[i++];
            result[5][ix] = buffer[i++];
            result[6][ix] = buffer[i++];
            result[7][ix] = buffer[i++];
        }
    }
    else
        for (int ix = 0; ix < length; ix++)
            for (int ch = 0; ch < channels; ch++)
                result[ch][ix] = buffer[i++];


    return result;
}

, , , .

+1

, :

delegate(float[] inout)
{
    unsafe
    {
        float[][] tempbuf = new float[2][];
        int length = inout.Length / 2;

        fixed (float* buffer = inout)
        {
            float* pbuffer = buffer;

            tempbuf[0] = new float[length];
            tempbuf[1] = new float[length];

            fixed (float* buffer0 = tempbuf[0])
            fixed (float* buffer1 = tempbuf[1])
            {
                float* pbuffer0 = buffer0;
                float* pbuffer1 = buffer1;

                for (int i = 0; i < length; i++)
                {
                    *pbuffer0++ = *pbuffer++;
                    *pbuffer1++ = *pbuffer++;
                }
            }
        }
    }
}

.

+1

I think many readers will ask why you don’t want an unsafe solution for something like sound processing. This is the type of thing that requires hot and optimistic optimization, and I would be unreasonable knowing that it is being forced through vm.

0
source

More articles:


All Articles