首先,我是新来的SSE。我决定加快我的代码,但现在看来,它的工作原理比较慢,然后我的本地代码。
这是一个例子,计算平方和。在我的英特尔i7-6700HQ,它需要对SSE 0.43s本地代码和0.52。所以,哪里是一个瓶颈?
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";
}
我使用的编译用于基于x64的Visual Studio 2017。
编译器生成的已经优化的代码,所以现在很难更加快了。有一两件事可以做,以加快代码更是并行。
感谢您的答案。他们主要是一样的,所以我接受瑟伦V.波尔森的答案,因为这是第一次。
现代编译是令人难以置信的机器,将已经使用SIMD指令(如果可能,并用正确编译标志)。
一个总体战略,以确定哪些编译器做的是看你的代码的反汇编。如果你不想做你自己的机器上,你可以像使用Godbolt在线服务:https://gcc.godbolt.org/z/T6GooQ。
一个技巧是避免atomic
存储中间结果就像你在这里干嘛。原子值是用来确保线程之间的同步,这可能会在一个很高的计算成本,相对来说。
通过装配了基于编译器的代码展望(没有你的SIMD东西),
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
你的SIMD代码生成:
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
需要注意的是编译器的版本使用cvtdq2ps
,paddd
,cvtdq2ps
,mulps
,addps
和cvttps2dq
。所有这些都是SIMD指令。通过他们有效地结合,编译器生成的代码快。
在constrast,你的代码产生大量qazxsw POI,qazxsw POI,qazxsw POI,add
,and
,cvtsi2ss
,lea
,mov
,movd
,这是不SIMD指令的。
我怀疑编译器处理的数据类型转换,比你做的数据重排的一个更好的工作,并认为这使得它更有效地安排其数学。