问将int64_t移动到AVX2 __m256i向量的高四字

EN

#include <immintrin.h>
#include <stdint.h>

// integer version.  An FP version would still use _mm256_set1_epi64x, then a cast
template<unsigned elem>
static inline
__m256i merge_epi64(__m256i v, int64_t newval)
{
    static_assert(elem <= 3, "a __m256i only has 4 qword elements");

    __m256i splat = _mm256_set1_epi64x(newval);

    constexpr unsigned dword_blendmask = 0b11 << (elem*2);  // vpblendd uses 2 bits per qword
    return  _mm256_blend_epi32(v, splat, dword_blendmask);
}

__m256i merge3(__m256i v, int64_t newval) {
    return merge_epi64<3> (v, newval);
}
// and so on for 2..0

# clang7.0 -O3 -march=haswell
merge3(long long __vector(4), long):
    vmovq   xmm1, rdi
    vpbroadcastq    ymm1, xmm1
    vpblendd        ymm0, ymm0, ymm1, 192 # ymm0 = ymm0[0,1,2,3,4,5],ymm1[6,7]
                      # 192 = 0xC0 = 0b11000000
    ret

merge2(long long __vector(4), long):
    vmovq   xmm1, rdi
    vinserti128     ymm1, ymm0, xmm1, 1          # Runs on more ports than vbroadcast on AMD Ryzen
        #  But it introduced a dependency on  v (ymm0) before the blend for no reason, for the low half of ymm1.  Could have used xmm1, xmm1.
    vpblendd        ymm0, ymm0, ymm1, 48 # ymm0 = ymm0[0,1,2,3],ymm1[4,5],ymm0[6,7]
    ret

merge1(long long __vector(4), long):
    vmovq   xmm1, rdi
    vpbroadcastq    xmm1, xmm1           # only an *XMM* broadcast, 1c latency instead of 3.
    vpblendd        ymm0, ymm0, ymm1, 12 # ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5,6,7]
    ret

merge0(long long __vector(4), long):
    vmovq   xmm1, rdi
           # broadcast optimized away, newval is already in the low element
    vpblendd        ymm0, ymm0, ymm1, 3 # ymm0 = ymm1[0,1],ymm0[2,3,4,5,6,7]
    ret

# gcc8.2 -O3 -march=haswell
merge0(long long __vector(4), long):
    push    rbp
    mov     rbp, rsp
    and     rsp, -32          # align the stack even though no YMM is spilled/loaded
    mov     QWORD PTR [rsp-8], rdi
    vpbroadcastq    ymm1, QWORD PTR [rsp-8]   # 1 uop on Intel
    vpblendd        ymm0, ymm0, ymm1, 3
    leave
    ret

; GCC trunk: g++ (GCC-Explorer-Build) 9.0.0 20190103 (experimental)
; MSVC and ICC do this, too.  (For MSVC, make sure to compile with -arch:AVX2)
merge0(long long __vector(4), long):
    vmovq   xmm2, rdi
    vpbroadcastq    ymm1, xmm2
    vpblendd        ymm0, ymm0, ymm1, 3
    ret