_mm_max_epu32

Microsoft Specific

Emits the Streaming SIMD Extensions 4 (SSE4) instruction pmaxud. This instruction chooses the larger value of the two parameters.

__m128i _mm_max_epu32( 
   __m128i a,
   __m128i b 
);

Parameters

• [in] a
  A 128-bit parameter that contains four 32-bit unsigned integers.

• [in] b
  A 128-bit parameter that contains four 32-bit unsigned integers.

Return value

A 128-bit parameter that can be defined with the following equations:

r0 := (a0 > b0) ? a0 : b0
r1 := (a1 > b1) ? a1 : b1
r2 := (a2 > b2) ? a2 : b2
r3 := (a3 > b3) ? a3 : b3

Requirements

Header file <smmintrin.h>

Remarks

r0-r3, a0-a3, and b0-b3 are the sequentially ordered 32-bit components of return value r and parameters a and b. r0, a0, and b0 are the least significant 32 bits.

Before you use this intrinsic, software must ensure that the processor supports the instruction.

Example

#include <stdio.h>
#include <smmintrin.h>

int main ()
{
    __m128i a, b;

    a.m128i_u32[0] = 0;
    a.m128i_u32[1] = 65000;
    a.m128i_u32[2] = 128;
    a.m128i_u32[3] = 200000;

    b.m128i_u32[0] = 1;
    b.m128i_u32[1] = 70000;
    b.m128i_u32[2] = 127;
    b.m128i_u32[3] = 100000;

    __m128i res = _mm_max_epu32(a, b);

    printf_s("     a\t     b\t   res\n");
    printf_s("%6d\t%6d\t%6d\n%6d\t%6d\t%6d\n%6d\t%6d\t%6d\n%6d\t%6d\t%6d\n",
                a.m128i_u32[0], b.m128i_u32[0], res.m128i_u32[0],
                a.m128i_u32[1], b.m128i_u32[1], res.m128i_u32[1],
                a.m128i_u32[2], b.m128i_u32[2], res.m128i_u32[2],
                a.m128i_u32[3], b.m128i_u32[3], res.m128i_u32[3]);

    return 0;
}

     a       b     res
     0       1       1
 65000   70000   70000
   128     127     128
200000  100000  200000

See Also

Reference

Compiler Intrinsics