Question

我试图了解有关gcc中自动矢量化的更多信息。在我的项目中，我必须使用gcc 4.8.5，我看到一些循环没有被向量化。因此，我创建了一个小例子来玩，看看为什么没有。

我感兴趣的是gcc不能向量化循环，并且无法找到如何向量化的事实。不幸的是，我对GCC的输出消息不是很熟悉。

a）我希望这个循环会被向量化为普通情况

b）我缺少什么琐碎的东西？

非常感谢大家...

一个小例子是：

#include <iostream>
#include <vector>

using namespace std;

class test
{

public:
    test();
    ~test();
    void calc_test();
};

test::test()
{
}

test::~test()
{
}

void
test::calc_test(void)
{
vector<int> ffs_psd(10000,5.0);
vector<int> G_qh_sp(10000,1.0);
vector<int> G_qv_sp(10000,3.0);
vector<int> B_erm_qh(10000,50.0);
vector<int> B_erm_qv(10000,2.0);


for ( uint ang=0; ang < 6808; ang++)
{
   ffs_psd[0] += (G_qh_sp[ang] * B_erm_qh[ang])  +  (G_qv_sp[ang] * B_erm_qv[ang]);      
}

}

int main(int argc, char * argv[])
{
  test m_test;
  m_test.calc_test();
}

我用gcc 4.8.5编译它：

c++ -O3 -ftree-vectorize -fopt-info-vec-missed -ftree-vectorizer-verbose=5 -std=c++11 test.cpp

我从编译器得到的输出是：

test.cpp:34: note: ===vect_slp_analyze_bb===

test.cpp:34: note: === vect_analyze_data_refs ===

test.cpp:34: note: get vectype with 4 units of type value_type
test.cpp:34: note: vectype: vector(4) int
test.cpp:34: note: get vectype with 4 units of type value_type
test.cpp:34: note: vectype: vector(4) int
test.cpp:34: note: get vectype with 4 units of type value_type
test.cpp:34: note: vectype: vector(4) int
test.cpp:34: note: get vectype with 4 units of type value_type
test.cpp:34: note: vectype: vector(4) int
test.cpp:34: note: get vectype with 4 units of type value_type
test.cpp:34: note: vectype: vector(4) int
test.cpp:34: note: === vect_pattern_recog ===
test.cpp:34: note: vect_is_simple_use: operand _27
test.cpp:34: note: def_stmt: _27 = (long unsigned int) ang_212;

test.cpp:34: note: type of def: 3.
test.cpp:34: note: vect_is_simple_use: operand ang_212
test.cpp:34: note: def_stmt: ang_212 = PHI <ang_43(78), 0(76)>

test.cpp:34: note: type of def: 2.
test.cpp:34: note: vect_is_simple_use: operand 4
test.cpp:34: note: vect_recog_widen_mult_pattern: detected: 
test.cpp:34: note: get vectype with 4 units of type uint
test.cpp:34: note: vectype: vector(4) unsigned int
test.cpp:34: note: get vectype with 2 units of type long unsigned int
test.cpp:34: note: vectype: vector(2) long unsigned int
test.cpp:34: note: patt_2 = ang_212 w* 4;

test.cpp:34: note: pattern recognized: patt_2 = ang_212 w* 4;

test.cpp:34: note: vect_is_simple_use: operand _29
test.cpp:34: note: def_stmt: _29 = *_67;

test.cpp:34: note: type of def: 3.
test.cpp:34: note: vect_is_simple_use: operand _34
test.cpp:34: note: def_stmt: _34 = *_69;

test.cpp:34: note: type of def: 3.
test.cpp:34: note: === vect_analyze_dependences ===
test.cpp:34: note: can't determine dependence between *_67 and MEM[(value_type &)__first_111]
test.cpp:34: note: can't determine dependence between *_68 and MEM[(value_type &)__first_111]
test.cpp:34: note: can't determine dependence between *_69 and MEM[(value_type &)__first_111]
test.cpp:34: note: can't determine dependence between *_70 and MEM[(value_type &)__first_111]
test.cpp:34: note: === vect_analyze_data_refs_alignment ===
test.cpp:34: note: vect_compute_data_ref_alignment:
test.cpp:34: note: SLP: step doesn't divide the vector-size.
test.cpp:34: note: Unknown alignment for access: *__first_125
test.cpp:34: note: vect_compute_data_ref_alignment:
test.cpp:34: note: SLP: step doesn't divide the vector-size.
test.cpp:34: note: Unknown alignment for access: *__first_153
test.cpp:34: note: vect_compute_data_ref_alignment:
test.cpp:34: note: SLP: step doesn't divide the vector-size.
test.cpp:34: note: Unknown alignment for access: *__first_139
test.cpp:34: note: vect_compute_data_ref_alignment:
test.cpp:34: note: SLP: step doesn't divide the vector-size.
test.cpp:34: note: Unknown alignment for access: *__first_167
test.cpp:34: note: vect_compute_data_ref_alignment:
test.cpp:34: note: can't force alignment of ref: MEM[(value_type &)__first_111]
test.cpp:34: note: === vect_analyze_data_ref_accesses ===
test.cpp:34: note: not consecutive access MEM[(value_type &)__first_111] = _41;

test.cpp:34: note: === vect_analyze_slp ===
test.cpp:34: note: Failed to SLP the basic block.
test.cpp:34: note: not vectorized: failed to find SLP opportunities in basic block.

编辑： 在Matts回答之后：

@马特：

非常感谢您的回答。我不知道矢量未对齐。该信息非常有用，因为很多人都认为即使将向量用作容器，循环也将被向量化。

不幸的是，即使您进行了更改，gcc的报告仍然没有进行矢量化处理（这次有不同的消息）：

test.cpp:47: note: misalign = 0 bytes of ref MEM[(value_type &)&ffs_psd]
test.cpp:47: note: not consecutive access _25 = MEM[(value_type &)&ffs_psd];

test.cpp:47: note: Failed to SLP the basic block.
test.cpp:47: note: not vectorized: failed to find SLP opportunities in basic block.

test.cpp:47: note: misalign = 0 bytes of ref MEM[(value_type &)&ffs_psd]
test.cpp:47: note: not consecutive access _25 = MEM[(value_type &)&ffs_psd];

test.cpp:47: note: Failed to SLP the basic block.
test.cpp:47: note: not vectorized: failed to find SLP opportunities in basic block.

程序集输出为（希望我复制粘贴正确的部分，导致我的程序集知识不是很好）：

.L16
vmovdqa 40000(%rsp,%rax), %ymm1
vmovdqa 80000(%rsp,%rax), %ymm0
vpmulld 120000(%rsp,%rax), %ymm1, %ymm1
vpmulld 160000(%rsp,%rax), %ymm0, %ymm0
vpaddd  %ymm0, %ymm1, %ymm0
vpaddd  (%rsp,%rax), %ymm0, %ymm0
vmovdqa %ymm0, (%rsp,%rax)
addq    $32, %rax
cmpq    $27232, %rax
jne .L16

Answer 1

为了使用向量化指令，操作数需要沿适当的边界对齐。例如__attribute__((aligned(32)))或__attribute__((aligned(16)))等。std::vector的标准分配器不保证对齐，即使类已对齐也是如此。例如，std::vector<__m64> A创建了一个SSE数据类型的向量，但是它们可能未对齐，因为std::allocator并未对齐所有内容。我认为最简单的更改是将std::array和__attribute__((aligned(32)))一起使用

#include <iostream>
#include <array>

using namespace std;

int main()
{
    array<int, 10000> ffs_psd __attribute__((aligned(32)));
    ffs_psd.fill(5);
    array<int, 10000> G_qh_sp __attribute__((aligned(32)));
    G_qh_sp.fill(1);
    array<int, 10000> G_qv_sp __attribute__((aligned(32)));
    G_qv_sp.fill(3);
    array<int, 10000> B_erm_qh __attribute__((aligned(32)));
    B_erm_qh.fill(50);
    array<int, 10000> B_erm_qv __attribute__((aligned(32)));
    B_erm_qv.fill(2);


    for ( uint ang=0; ang < 6808; ang++)
    {
        ffs_psd[0] += (G_qh_sp[ang] * B_erm_qh[ang])  +  (G_qv_sp[ang] * B_erm_qv[ang]);      
    }
    cout << ffs_psd[0] << endl;
}

循环会产生以下结果：

vmovdqa ymm2, YMMWORD PTR [rsp+40000+rax]
vmovdqa ymm1, YMMWORD PTR [rsp+80000+rax]
vpmulld ymm2, ymm2, YMMWORD PTR [rsp+120000+rax]
vpmulld ymm1, ymm1, YMMWORD PTR [rsp+160000+rax]
add     rax, 32
vpaddd  ymm1, ymm2, ymm1
cmp     rax, 27232
vpaddd  ymm0, ymm0, ymm1
jne     .L13
vmovdqa xmm1, xmm0

在GCC 4.8.3 -std=c++11 -Wall -Wextra -pedantic-errors -O2 -ftree-vectorize -march=native上的Godbolt上

另一种选择是对向量使用boost::alignment::aligned_allocator。

最后，您可以编写自己的allocator，vector可用于正确对齐内容。这是一篇介绍allocator的要求的文章。同样，这是关于同一基本内容的question。

琐碎的循环无法使用gcc 4.8.5

1 个答案: