用于32位字旋转的ARM内联汇编

Question

我正在尝试制作一些内联汇编来测试ARM上的旋转性能。 该代码是C ++代码库的一部分，因此旋转是模板专业化。 代码在下面，但是它产生的消息对我来说没有多大意义。

根据ARM汇编语言 ，说明大致如下：

# rotate - rotate instruction
# dst - output operand
# lhs - value to be rotated
# rhs - rotate amount (immediate or register)
<rotate> <dst>, <lhs>, <rhs>

它们没有多大意义，因为例如（对我而言），我使用g来约束输出寄存器，而这只是每个Simple Contraints的通用寄存器。 ARM应该有很多，并且特定于机器的约束似乎没有改变约束的行为。

我不确定解决此问题的最佳方法，因此我将提出三个问题：

1. 使用常数或立即数时，如何编码旋转？
2. 使用通过寄存器传递的值时，如何编码旋转？
3. 拇指模式将如何改变内联装配

---

arm-linux-androideabi-g++ -DNDEBUG -g2 -Os -pipe -fPIC -mfloat-abi=softfp
-mfpu=vfpv3-d16 -mthumb --sysroot=/opt/android-ndk-r10e/platforms/android-21/arch-arm
-I/opt/android-ndk-r10e/sources/cxx-stl/stlport/stlport/ -c camellia.cpp
In file included from seckey.h:9:0,
             from camellia.h:9,
             from camellia.cpp:14:
misc.h: In function 'T CryptoPP::rotlFixed(T, unsigned int) [with T = unsigned int]':
misc.h:1121:71: error: matching constraint not valid in output operand
  __asm__ ("rol %2, %0, %1" : "=g2" (z) : "g0" (x), "M1" ((int)(y%32)));
                                                                       ^
misc.h:1121:71: error: matching constraint references invalid operand number
misc.h: In function 'T CryptoPP::rotrFixed(T, unsigned int) [with T = unsigned int]':
misc.h:1129:71: error: matching constraint not valid in output operand
  __asm__ ("ror %2, %0, %1" : "=g2" (z) : "g0" (x), "M1" ((int)(y%32)));
                                                                       ^
misc.h:1129:71: error: matching constraint references invalid operand number
misc.h: In function 'T CryptoPP::rotlVariable(T, unsigned int) [with T = unsigned int]':
misc.h:1137:72: error: matching constraint not valid in output operand
  __asm__ ("rol %2, %0, %1"  : "=g2" (z) : "g0" (x), "g1" ((int)(y%32)));
                                                                        ^
misc.h:1137:72: error: matching constraint references invalid operand number
misc.h: In function 'T CryptoPP::rotrVariable(T, unsigned int) [with T = unsigned int]':
misc.h:1145:72: error: matching constraint not valid in output operand
  __asm__ ("ror %2, %0, %1"  : "=g2" (z) : "g0" (x), "g1" ((int)(y%32)));
                                                                        ^
misc.h:1145:72: error: matching constraint references invalid operand number
misc.h: In function 'T CryptoPP::rotrFixed(T, unsigned int) [with T = unsigned int]':
misc.h:1129:71: error: matching constraint not valid in output operand
  __asm__ ("ror %2, %0, %1" : "=g2" (z) : "g0" (x), "M1" ((int)(y%32)));
                                                                       ^
misc.h:1129:71: error: invalid lvalue in asm output 0
misc.h:1129:71: error: matching constraint references invalid operand number
misc.h: In function 'T CryptoPP::rotlFixed(T, unsigned int) [with T = unsigned int]':
misc.h:1121:71: error: matching constraint not valid in output operand
  __asm__ ("rol %2, %0, %1" : "=g2" (z) : "g0" (x), "M1" ((int)(y%32)));
                                                                       ^
misc.h:1121:71: error: invalid lvalue in asm output 0
misc.h:1121:71: error: matching constraint references invalid operand number

---

// ROL #n Rotate left immediate
template<> inline word32 rotlFixed<word32>(word32 x, unsigned int y)
{
    int z;
    __asm__ ("rol %2, %0, %1" : "=g2" (z) : "g0" (x), "M1" ((int)(y%32)));
    return static_cast<word32>(z);
}

// ROR #n Rotate right immediate
template<> inline word32 rotrFixed<word32>(word32 x, unsigned int y)
{
    int z;
    __asm__ ("ror %2, %0, %1" : "=g2" (z) : "g0" (x), "M1" ((int)(y%32)));
    return static_cast<word32>(z);
}

// ROR rn Rotate left by a register
template<> inline word32 rotlVariable<word32>(word32 x, unsigned int y)
{
    int z;
    __asm__ ("rol %2, %0, %1"  : "=g2" (z) : "g0" (x), "g1" ((int)(y%32)));
    return static_cast<word32>(z);
}

// ROR rn Rotate right by a register
template<> inline word32 rotrVariable<word32>(word32 x, unsigned int y)
{
    int z;
    __asm__ ("ror %2, %0, %1"  : "=g2" (z) : "g0" (x), "g1" ((int)(y%32)));
    return static_cast<word32>(z);
}

template<> inline word32 rotlMod<word32>(word32 x, unsigned int y)
{
    return rotlVariable<word32>(x, y);
}

template<> inline word32 rotrMod<word32>(word32 x, unsigned int y)
{
    return rotrVariable<word32>(x, y);
}

Answer 1

首先，ARM没有向左旋转（ ROL ），您需要通过ROR进行模拟。

其次，由于某种原因， M约束接受0到32，但是ROL在处理立即数时仅接受0到31。

第三， g约束过于笼统，因为它还允许ROR不接受的内存操作数。 最好改用r 。

这是我想出的：

// Rotate right
inline word32 rotr(word32 x, unsigned int y)
{
    int z;
    if (__builtin_constant_p(y))
    {
        y &= 31;
        if (y != 0) // this should be optimized away by the compiler
        {
            __asm__ ("ror %0, %1, %2" : "=r" (z) : "r" (x), "M" (y));
        }
    } else {
        __asm__ ("ror %0, %1, %2" : "=r" (z) : "r" (x), "r" (y));
    }
    return static_cast<word32>(z);
}

// Rotate left
inline word32 rotl(word32 x, unsigned int y)
{
    int z;
    if (__builtin_constant_p(y))
    {
        y &= 31;
        if (y != 0) // this should be optimized away by the compiler
        {
            __asm__ ("ror %0, %1, %2" : "=r" (z) : "r" (x), "M" (32 - y));
        }
    } else {
        __asm__ ("ror %0, %1, %2" : "=r" (z) : "r" (x), "r" (32 - y));
    }
    return static_cast<word32>(z);
}