Load vector from large vector with mask based simd

Hope someone can help here.

I have a large vector of bytes from which I create a small byte vector (based on a mask) which I then process with simd.

The mask is currently a baseOffset + subpattern array (bytes [256]), optimized to store as is> 10 ^ 8. I create a maxsize subsector, then loop through the mask array multiplies baseOffssetby 256 and for each bit offset in the load mass from of a large vector and sequentially places the values ​​into the smaller vector. The smaller vector is then processed by multiple VPMADDUBSWs and accumulated. I can change this structure. for example walk a bit once to use an 8KB array buffer and then create a small vector.

Is there a faster way to create a subarray?

I pulled the code from the application into the test program, but the original is in a flow state (going to AVX2 and pulling more from C #)

#include "stdafx.h"
#include<stdio.h>
#include <mmintrin.h>
#include <emmintrin.h>
#include <tmmintrin.h>
#include <smmintrin.h>
#include <immintrin.h>


//from 
char N[4096] = { 9, 5, 5, 5, 9, 5, 5, 5, 5, 5 };
//W
char W[4096] = { 1, 2, -3, 5, 5, 5, 5, 5, 5, 5 };

char buffer[4096] ; 





__declspec(align(2))
struct packed_destination{
    char blockOffset;
    __int8   bitMask[32];

};

__m128i sum = _mm_setzero_si128();
packed_destination packed_destinations[10];



void  process128(__m128i u, __m128i s)
{
    __m128i calc = _mm_maddubs_epi16(u, s); // pmaddubsw 
    __m128i loints = _mm_cvtepi16_epi32(calc);
    __m128i hiints = _mm_cvtepi16_epi32(_mm_shuffle_epi32(calc, 0x4e));
    sum = _mm_add_epi32(_mm_add_epi32(loints, hiints), sum);
}

void process_array(char n[], char w[], int length)
{
    sum = _mm_setzero_si128();
    int length128th  = length >> 7;
    for (int i = 0; i < length128th; i++)
    {
        __m128i u = _mm_load_si128((__m128i*)&n[i * 128]);
        __m128i s = _mm_load_si128((__m128i*)&w[i * 128]);
        process128(u, s);
    }
}


void populate_buffer_from_vector(packed_destination packed_destinations[], char n[]  , int  dest_length)
{
    int buffer_dest_index = 0; 
    for (int i = 0; i < dest_length; i++)
    {
        int blockOffset = packed_destinations[i].blockOffset <<8 ;
        // go through mask and copy to buffer
        for (int j = 0; j < 32; j++)
        {
           int joffset = blockOffset  + j << 3; 
            int mask = packed_destinations[i].bitMask[j];
            if (mask & 1 << 0)
                buffer[buffer_dest_index++] = n[joffset +  1<<0 ];
            if (mask & 1 << 1)
                buffer[buffer_dest_index++] = n[joffset +  1<<1];
            if (mask & 1 << 2)
                buffer[buffer_dest_index++] = n[joffset +  1<<2];
            if (mask & 1 << 3)
                buffer[buffer_dest_index++] = n[joffset +   1<<3];
            if (mask & 1 << 4)
                buffer[buffer_dest_index++] = n[joffset +  1<<4];
            if (mask & 1 << 5)
                buffer[buffer_dest_index++] = n[joffset +  1<<5];
            if (mask & 1 << 6)
                buffer[buffer_dest_index++] = n[joffset + 1<<6];
            if (mask & 1 << 7)
                buffer[buffer_dest_index++] = n[joffset +  1<<7];
        };

    }


}

int _tmain(int argc, _TCHAR* argv[])
{
    for (int i = 0; i < 32; ++i)
    {
        packed_destinations[0].bitMask[i] = 0x0f;
        packed_destinations[1].bitMask[i] = 0x04;
    }
    packed_destinations[1].blockOffset = 1;

    populate_buffer_from_vector(packed_destinations, N, 1);
    process_array(buffer, W, 256);

    int val = sum.m128i_i32[0] +
        sum.m128i_i32[1] +
        sum.m128i_i32[2] +
        sum.m128i_i32[3];
    printf("sum is %d"  , val);
    printf("Press Any Key to Continue\n");
    getchar();
    return 0;
}

      

        
        
        
      

    

Typically mask usage will be 5-15% for some workloads, this will be 25-100%.

MASKMOVDQU is close, but then we'll need to repackage / swl according to the mask before saving.