inline float Dot(const CVector4 &vVector)
		{
			__m128 vec1;
			__m128 vec2;


			vec1 = _mm_mul_ps(this->v, vVector.v);
			vec2 = _mm_movehl_ps(vec1, vec1);
			vec2 = _mm_add_ss(vec2,vec1);
			vec1 = _mm_shuffle_ps(vec1,vec1, _MM_SHUFFLE(1,0,0,0));
			vec1 = _mm_add_ss(vec1,vec2);
			return vec1.m128_f32[0];			
		}

	mov	eax, DWORD PTR _vVector$[ebp]
	movaps	xmm1, XMMWORD PTR [ecx]
	movaps	xmm0, XMMWORD PTR [eax]
	mulps	xmm0, xmm1
	movaps	xmm1, xmm0 <--- ???
	movhlps	xmm1, xmm0 
	movaps	xmm2, xmm0 <--- ???
	addss	xmm1, xmm0
	shufps	xmm2, xmm0, 1 
	addss	xmm2, xmm1
	movaps	XMMWORD PTR _vec1$[esp+16], xmm2
	movss	xmm0, DWORD PTR _vec1$[esp+16]

__declspec(naked)inline float Dot(const CVector4 &vVector){   __asm   {   ...   }}

Quote:Original post by Spoonbender
Are you compiling in debug or release mode?
Also, don't store your results back into vars you're using already.

For example, try changing this:
vec2 = _mm_add_ss(vec2,vec1);
to
__m128 vec3 = _mm_add_ss(vec2,vec1);

Aliasing is evil, especially in cases where the compiler might be a bit shaky to begin with (such as SIMD code). So even simple stuff like the above might help.

I'd definitely avoid inline asm and stick with assembly. (For now, at least. If you profile it and find it to be too slow still, and you then write an inline ASM version, profile that and find it to be a lot faster, you might go with that)