Optimizing for SIMD: best practices?(i.e. what features are allowed?)

[tsbockman]

On Sunday, 7 March 2021 at 22:54:32 UTC, tsbockman wrote:
> ...
>     result = diffSq[0];
>     static foreach(i; 0 .. 3)
>         result += diffSq[i];
> ...

Oops, that's supposed to say `i; 1 .. 3`. Fixed:

import std.meta : Repeat;
void euclideanDistanceFixedSizeArray(V)(ref Repeat!(3, const(V)) 
a, ref Repeat!(3, const(V)) b, ref V result)
     if(is(V : __vector(float[length]), size_t length))
{
     Repeat!(3, V) diffSq = a;
     static foreach(i; 0 .. 3) {
         diffSq[i] -= b[i];
         diffSq[i] *= diffSq[i];
     }

     result = diffSq[0];
     static foreach(i; 1 .. 3)
         result += diffSq[i];

     version(LDC) { version(X86_64) {
         enum isSupportedPlatform = true;
         import ldc.llvmasm : __asm;
         result = __asm!V(`vsqrtps $1, $0`, `=x, x`, result);
     } }
     static assert(isSupportedPlatform);
}

Fixed asm:

pure nothrow @nogc void 
app.euclideanDistanceFixedSizeArray!(__vector(float[16])).euclideanDistanceFixedSizeArray(ref const(__vector(float[16])), ref const(__vector(float[16])), ref const(__vector(float[16])), ref const(__vector(float[16])), ref const(__vector(float[16])), ref const(__vector(float[16])), ref __vector(float[16])):
         mov     rax, qword ptr [rsp + 8]
         vmovaps zmm0, zmmword ptr [rax]
         vmovaps zmm1, zmmword ptr [r9]
         vmovaps zmm2, zmmword ptr [r8]
         vsubps  zmm0, zmm0, zmmword ptr [rcx]
         vsubps  zmm1, zmm1, zmmword ptr [rdx]
         vmulps  zmm1, zmm1, zmm1
         vsubps  zmm2, zmm2, zmmword ptr [rsi]
         vfmadd231ps     zmm1, zmm0, zmm0
         vfmadd231ps     zmm1, zmm2, zmm2
         vmovaps zmmword ptr [rdi], zmm1
         vsqrtps zmm0, zmm1
         vmovaps zmmword ptr [rdi], zmm0
         vzeroupper
         ret

(I really wish I could just edit my posts here...)