Why my SSE code is slower than native C++ code? - c++

Question

First of all, I am new to SSE. I decided to accelerate my code, but it seems, that it works slower, then my native code.
This is an example, that calculates the sum of squares. On my Intel i7-6700HQ, it takes 0.43s for native code and 0.52 for SSE. So, where is a bottleneck?
inline float squared_sum(const float x, const float y)
{
return x * x + y * y;
}
#define USE_SIMD
void calculations()
{
high_resolution_clock::time_point t1, t2;
int result_v = 0;
t1 = high_resolution_clock::now();
alignas(16) float data_x[4];
alignas(16) float data_y[4];
alignas(16) float result[4];
__m128 v_x, v_y, v_res;
for (int y = 0; y < 5120; y++)
{
data_y[0] = y;
data_y[1] = y + 1;
data_y[2] = y + 2;
data_y[3] = y + 3;
for (int x = 0; x < 5120; x++)
{
data_x[0] = x;
data_x[1] = x + 1;
data_x[2] = x + 2;
data_x[3] = x + 3;
#ifdef USE_SIMD
v_x = _mm_load_ps(data_x);
v_y = _mm_load_ps(data_y);
v_x = _mm_mul_ps(v_x, v_x);
v_y = _mm_mul_ps(v_y, v_y);
v_res = _mm_add_ps(v_x, v_y);
_mm_store_ps(result, v_res);
#else
result[0] = squared_sum(data_x[0], data_y[0]);
result[1] = squared_sum(data_x[1], data_y[1]);
result[2] = squared_sum(data_x[2], data_y[2]);
result[3] = squared_sum(data_x[3], data_y[3]);
#endif
result_v += (int)(result[0] + result[1] + result[2] + result[3]);
}
}
t2 = high_resolution_clock::now();
duration<double> time_span1 = duration_cast<duration<double>>(t2 - t1);
std::cout << "Exec time:\t" << time_span1.count() << " s\n";
}
UPDATE: fixed code according to comments.
I am using Visual Studio 2017. Compiled for x64.
Optimization: Maximum Optimization (Favor Speed) (/O2);
Inline Function Expansion: Any Suitable (/Ob2);
Favor Size or Speed: Favor fast code (/Ot);
Omit Frame Pointers: Yes (/Oy)
Conclusion
Compilers generate already optimized code, so nowadays it is hard to accelerate it even more. The one thing you can do, to accelerate code more, is parallelization.
Thanks for the answers. They mainly the same, so I accept Søren V. Poulsen answer because it was the first.

Answer 1

Modern compiles are incredible machines and will already use SIMD instructions if possible (and with the correct compilation flags).
One general strategy to determine what the compiler is doing is looking at the disassembly of your code. If you don't want to do it on your own machine you can use an online service like Godbolt: https://gcc.godbolt.org/z/T6GooQ.
One tip is to avoid atomic for storing intermediate results like you are doing here. Atomic values are used to ensure synchronization between threads, and this may come at a very high computational cost, relatively speaking.

Answer 2

Looking through the assembly for the compiler's code based (without your SIMD stuff),
calculations():
pxor xmm2, xmm2
xor edx, edx
movdqa xmm0, XMMWORD PTR .LC0[rip]
movdqa xmm11, XMMWORD PTR .LC1[rip]
movdqa xmm9, XMMWORD PTR .LC2[rip]
movdqa xmm8, XMMWORD PTR .LC3[rip]
movdqa xmm7, XMMWORD PTR .LC4[rip]
.L4:
movdqa xmm5, xmm0
movdqa xmm4, xmm0
cvtdq2ps xmm6, xmm0
movdqa xmm10, xmm0
paddd xmm0, xmm7
cvtdq2ps xmm3, xmm0
paddd xmm5, xmm9
paddd xmm4, xmm8
cvtdq2ps xmm5, xmm5
cvtdq2ps xmm4, xmm4
mulps xmm6, xmm6
mov eax, 5120
paddd xmm10, xmm11
mulps xmm5, xmm5
mulps xmm4, xmm4
mulps xmm3, xmm3
pxor xmm12, xmm12
.L2:
movdqa xmm1, xmm12
cvtdq2ps xmm14, xmm12
mulps xmm14, xmm14
movdqa xmm13, xmm12
paddd xmm12, xmm7
cvtdq2ps xmm12, xmm12
paddd xmm1, xmm9
cvtdq2ps xmm0, xmm1
mulps xmm0, xmm0
paddd xmm13, xmm8
cvtdq2ps xmm13, xmm13
sub eax, 1
mulps xmm13, xmm13
addps xmm14, xmm6
mulps xmm12, xmm12
addps xmm0, xmm5
addps xmm13, xmm4
addps xmm12, xmm3
addps xmm0, xmm14
addps xmm0, xmm13
addps xmm0, xmm12
movdqa xmm12, xmm1
cvttps2dq xmm0, xmm0
paddd xmm2, xmm0
jne .L2
add edx, 1
movdqa xmm0, xmm10
cmp edx, 1280
jne .L4
movdqa xmm0, xmm2
psrldq xmm0, 8
paddd xmm2, xmm0
movdqa xmm0, xmm2
psrldq xmm0, 4
paddd xmm2, xmm0
movd eax, xmm2
ret
main:
xor eax, eax
ret
_GLOBAL__sub_I_calculations():
sub rsp, 8
mov edi, OFFSET FLAT:_ZStL8__ioinit
call std::ios_base::Init::Init() [complete object constructor]
mov edx, OFFSET FLAT:__dso_handle
mov esi, OFFSET FLAT:_ZStL8__ioinit
mov edi, OFFSET FLAT:_ZNSt8ios_base4InitD1Ev
add rsp, 8
jmp __cxa_atexit
.LC0:
.long 0
.long 1
.long 2
.long 3
.LC1:
.long 4
.long 4
.long 4
.long 4
.LC2:
.long 1
.long 1
.long 1
.long 1
.LC3:
.long 2
.long 2
.long 2
.long 2
.LC4:
.long 3
.long 3
.long 3
.long 3
Your SIMD code generates:
calculations():
pxor xmm5, xmm5
xor eax, eax
mov r8d, 1
movabs rdi, -4294967296
cvtsi2ss xmm5, eax
.L4:
mov r9d, r8d
mov esi, 1
movd edx, xmm5
pxor xmm5, xmm5
pxor xmm4, xmm4
mov ecx, edx
mov rdx, QWORD PTR [rsp-24]
cvtsi2ss xmm5, r8d
add r8d, 1
cvtsi2ss xmm4, r8d
and rdx, rdi
or rdx, rcx
pxor xmm2, xmm2
mov edx, edx
movd ecx, xmm5
sal rcx, 32
or rdx, rcx
mov QWORD PTR [rsp-24], rdx
movd edx, xmm4
pxor xmm4, xmm4
mov ecx, edx
mov rdx, QWORD PTR [rsp-16]
and rdx, rdi
or rdx, rcx
lea ecx, [r9+2]
mov edx, edx
cvtsi2ss xmm4, ecx
movd ecx, xmm4
sal rcx, 32
or rdx, rcx
mov QWORD PTR [rsp-16], rdx
movaps xmm4, XMMWORD PTR [rsp-24]
mulps xmm4, xmm4
.L2:
movd edx, xmm2
mov r10d, esi
pxor xmm2, xmm2
pxor xmm7, xmm7
mov ecx, edx
mov rdx, QWORD PTR [rsp-40]
cvtsi2ss xmm2, esi
add esi, 1
and rdx, rdi
cvtsi2ss xmm7, esi
or rdx, rcx
mov ecx, edx
movd r11d, xmm2
movd edx, xmm7
sal r11, 32
or rcx, r11
pxor xmm7, xmm7
mov QWORD PTR [rsp-40], rcx
mov ecx, edx
mov rdx, QWORD PTR [rsp-32]
and rdx, rdi
or rdx, rcx
lea ecx, [r10+2]
mov edx, edx
cvtsi2ss xmm7, ecx
movd ecx, xmm7
sal rcx, 32
or rdx, rcx
mov QWORD PTR [rsp-32], rdx
movaps xmm0, XMMWORD PTR [rsp-40]
mulps xmm0, xmm0
addps xmm0, xmm4
movaps xmm3, xmm0
movaps xmm1, xmm0
shufps xmm3, xmm0, 85
addss xmm1, xmm3
movaps xmm3, xmm0
unpckhps xmm3, xmm0
shufps xmm0, xmm0, 255
addss xmm1, xmm3
addss xmm0, xmm1
cvttss2si edx, xmm0
add eax, edx
cmp r10d, 5120
jne .L2
cmp r9d, 5120
jne .L4
rep ret
main:
xor eax, eax
ret
_GLOBAL__sub_I_calculations():
sub rsp, 8
mov edi, OFFSET FLAT:_ZStL8__ioinit
call std::ios_base::Init::Init() [complete object constructor]
mov edx, OFFSET FLAT:__dso_handle
mov esi, OFFSET FLAT:_ZStL8__ioinit
mov edi, OFFSET FLAT:_ZNSt8ios_base4InitD1Ev
add rsp, 8
jmp __cxa_atexit
Note that the compiler's version is using cvtdq2ps, paddd, cvtdq2ps, mulps, addps, and cvttps2dq. All of these are SIMD instructions. By combining them effectively, the compiler generates fast code.
In constrast, your code generates a lot of add, and, cvtsi2ss, lea, mov, movd, or, pxor, sal, which are not SIMD instructions.
I suspect the compiler does a better job of dealing with data type conversion and data rearrangement than you do, and that this allows it to arrange its math more effectively.