Question

我找到了一种方法来比较两个__m128d变量之间的上半部分。所以我查找了https://software.intel.com/sites/landingpage/IntrinsicsGuide/相对内在函数。

但我只能找到一些内在函数来比较两个变量之间的下半部分，例如_mm_comieq_sd。

我很奇怪为什么没有关于比较上半部分的内在函数，更重要的是，如何比较两个__m128d变量之间的上半部分？

更新

代码就像

    j0     =  jprev0;
    j1     =  jprev1;

    t_0    =  p_i_x - pj_x_0;
    t_1    =  p_i_x - pj_x_1;
    r2_0   =  t_0 * t_0;
    r2_1   =  t_1 * t_1;

    t_0    =  p_i_y - pj_y_0;
    t_1    =  p_i_y - pj_y_1;
    r2_0  +=  t_0 * t_0;
    r2_1  +=  t_1 * t_1;

    t_0    =  p_i_z - pj_z_0;
    t_1    =  p_i_z - pj_z_1;
    r2_0  +=  t_0 * t_0;
    r2_1  +=  t_1 * t_1;

    #if NAMD_ComputeNonbonded_SortAtoms != 0 && ( 0 PAIR ( + 1 ) )
    sortEntry0 = sortValues + g; 
    sortEntry1 = sortValues + g + 1; 
    jprev0 = sortEntry0->index;
    jprev1 = sortEntry1->index;
    #else
    jprev0     =  glist[g  ];
    jprev1     =  glist[g+1];
    #endif

    pj_x_0     =  p_1[jprev0].position.x;
    pj_x_1     =  p_1[jprev1].position.x;
    pj_y_0     =  p_1[jprev0].position.y; 
    pj_y_1     =  p_1[jprev1].position.y;
    pj_z_0     =  p_1[jprev0].position.z; 
    pj_z_1     =  p_1[jprev1].position.z;

    // want to use sse to compare those
    bool test0 = ( r2_0 < groupplcutoff2 );
    bool test1 = ( r2_1 < groupplcutoff2 );

    //removing ifs benefits on many architectures
    //as the extra stores will only warm the cache up
    goodglist [ hu         ] = j0;
    goodglist [ hu + test0 ] = j1;

    hu += test0 + test1;

我正在尝试用SSE重写它。

Answer 1

你问在比较下半部分之后如何比较上半部分。

SIMD方式做比较是使用压缩比较指令，如__m128d _mm_cmplt_pd (__m128d a, __m128d b)，它产生一个掩码作为输出，而不是设置标志。 AVX有一个改进的vcmppd / vcmpps，它有更多的比较运算符选择，你作为第3个arg传递。 _mm_cmp_pd (__m128d a, __m128d b, const int imm8)。

const __m128d groupplcutoff2_vec = _mm_broadcastsd_pd(groupplcutoff2);
// should emit SSE3 movddup like _mm_movedup_pd() would.

__m128d r2 = ...;

// bool test0 = ( r2_0 < groupplcutoff2 );
// bool test1 = ( r2_1 < groupplcutoff2 );
__m128d ltvec = _mm_cmplt_pd(r2, groupplcutoff2_vec);
int ltmask = _mm_movemask_pd(ltvec);

bool test0 = ltmask & 1;
// bool test1 = ltmask & 2;

// assuming j is double.  I'm not sure from your code, it might be int.
// and you're right, doing both stores unconditionally is prob. fastest, if your code isn't heavy on stores.
// goodglist [ hu         ] = j0;
_mm_store_sd (goodglist [ hu         ], j);
// goodglist [ hu + test0 ] = j1;
_mm_storeh_pd(goodglist [ hu + test0 ], j);
// don't try to use non-AVX _mm_maskmoveu_si128, it's like movnt.  And doesn't do exactly what this needs, anyway, without shuffling j and ltvec.

// hu += test0 + test1;
hu += _popcnt32(ltmask);  // Nehalem or later.  Check the popcnt CPUID flag

popcnt技巧与AVX一样有效（4个双打打包在ymm寄存器中）。打包比较 - ＆gt; movemask和使用位操作是一个很有用的技巧。

如何将上部双精度浮点元素与SSE进行比较

1 个答案: