Xbyak - x86, x64 JIT assembler -

NASM              Xbyak
mov eax, ebx  --> mov(eax, ebx);
inc ecx       --> inc(ecx);
ret           --> ret();

NASM                   Xbyak
mov eax, [ebx+ecx] --> mov (eax, ptr[ebx+ecx]);
test byte [esp], 4 --> test (byte [esp], 4);

L("L1");
    jmp ("L1");

	jmp ("L2");
	...
	少しの命令の場合．
	...
L("L2");

	jmp ("L3", T_NEAR);
	...
	沢山の命令がある場合
	...
L("L3");

#include <stdio.h>
#include "xbyak/xbyak.h"

struct AddFunc : public Xbyak::CodeGenerator {
    AddFunc(int y)
    {
        mov(eax, ptr[esp+4]);
        add(eax, y);
        ret();
    }
};

int main()
{
    AddFunc a(3);
    int (*add3)(int) = (int (*)(int))a.getCode();
    printf("3 + 2 = %d\n", add3(2));
}

    mov    eax, dword ptr [esp+4]
    add    eax, 3
    ret

/*!
    1からnまでの和を求める
*/
class Sample : public Xbyak::CodeGenerator {
public:
    Sample(int n)
    {
        mov(ecx, n); // -- (A)
        xor(eax, eax); // sum
        test(ecx, ecx);
        jbe("exit");
        xor(edx, edx); // i
    L("lp");
        add(eax, edx);
        inc(edx);
        cmp(edx, ecx);
        jbe("lp");
    L("exit");
        ret();
    }
};
int main(int argc, char *argv[])
{
    int n = argc < 2 ? 100 : atoi(argv[1]);
    try {
        Sample s(n);
        printf("1 + ... + %d = %d\n", n, ((int (*)())s.getCode())());
    } catch (Xbyak::Error err) {
        printf("ERR:%s(%d)\n", Xbyak::ConvertErrorToString(err), err);
    } catch (...) {
        printf("unkwon error\n");
    }
    return 0;
}

func(int n)
{
    __asm {
        mov eax, n
    }
}

    push    ebp
    mov     ebp, esp
    mov     eax, [ebp+8]

void quantize(uint32 dest[64],
              const uint32 src[64], const uint32 qTbl[64])
{
    for (int i = 0; i < N; i++) {
        dest[i] = src[i] / qTbl[i];
    }
}

// C
uint32 func(uint32 n)
{
    return n / 10;
}

// asm
    mov    eax, cccccccdH
    mul    DWORD PTR _n$[esp-4]
    mov    eax, edx
    shr    eax, 3
    ret

; q = 1のときに実行時生成されたコード
    push        esi
    push        edi
    mov         edi,dword ptr [esp+0Ch]
    mov         esi,dword ptr [esp+10h]
    mov         eax,dword ptr [esi]
    shr         eax,4
    mov         dword ptr [edi],eax      ; 16で割る
    mov         eax,dword ptr [esi+4]
    mov         edx,0BA2E8BA3h
    mul         eax,edx
    shr         edx,3                    ; 11で割る
    ...

; q = 100のときに実行時生成されたコード
     push        esi
     push        edi
     mov         edi,dword ptr [esp+0Ch]
     mov         esi,dword ptr [esp+10h]
     mov         eax,dword ptr [esi]
     mov         dword ptr [edi],eax
     mov         eax,dword ptr [esi+4]    ; 1で割る
     mov         dword ptr [edi+4],eax
     mov         eax,dword ptr [esi+8]
     mov         dword ptr [edi+8],eax    ; 1で割る
     mov         eax,dword ptr [esi+0Ch]
     mov         dword ptr [edi+0Ch],eax
     ...

    void genPush(double n)
    {
        if (constTblPos_ == MAX_CONST_NUM) throw;
        constTbl_[constTblPos_] = static_cast<float>(n);
        if (regIdx_ == 7) throw;
        movss(Xbyak::Xmm(++regIdx_), ptr[edx+constTblPos_*sizeof(float)]);
        constTblPos_++;
    }
    void genSub(const char*, const char*)
    {
        subss(Xbyak::Xmm(regIdx_ - 1), Xbyak::Xmm(regIdx_)); regIdx_--;
    }

struct Grammar : public boost::spirit::grammar<Grammar> {
    FuncGen& f_;
    Grammar(FuncGen& f) : f_(f) { }
    template<typename ScannerT>
    struct definition {
        boost::spirit::rule<ScannerT> exp0, exp1, exp2, val;

        definition(const Grammar& self)
        {
            using namespace boost;
            using namespace boost::spirit;

            exp0 = exp1 >> *(('+' >> exp1)[bind(&FuncGen::genAdd, ref(self.f_), _1, _2)]
                           | ('-' >> exp1)[bind(&FuncGen::genSub, ref(self.f_), _1, _2)]);
            exp1 = exp2 >> *(('*' >> exp2)[bind(&FuncGen::genMul, ref(self.f_), _1, _2)]
                           | ('/' >> exp2)[bind(&FuncGen::genDiv, ref(self.f_), _1, _2)]);
            val = ch_p('x')[bind(&FuncGen::genX, ref(self.f_))];
            exp2 = real_p[bind(&FuncGen::genPush, ref(self.f_), _1)]
                 | val
                 | '(' >> exp0 >> ')';
        }
        const boost::spirit::rule<ScannerT>& start() const { return exp0; }
    };
};

    void (*func)(float *ret, const float *x) = (void (*)(float *, const float*))funcGen.getCode();
    for (float x = 0; x < 10; x += 0.7f) {
        float y;
        func(&y, &x);
        printf("f(%f)=%f\n", x, y);
    }

    ; @param y [out] f(x)
    ; @param x [in] x
    ; void func(float *y, const float *x);

    mov         eax,dword ptr [esp+8]
    mov         edx,12FEA8h 
    movss       xmm0,dword ptr [eax] 
    movss       xmm1,dword ptr [edx] 
    movss       xmm2,dword ptr [eax] 
    movss       xmm3,dword ptr [eax] 
    mulss       xmm2,xmm3 
    movss       xmm3,dword ptr [edx+4]
    movss       xmm4,dword ptr [eax] 
    divss       xmm3,xmm4 
    addss       xmm2,xmm3 
    mulss       xmm1,xmm2 
    addss       xmm0,xmm1 
    mov         eax,dword ptr [esp+4]
    movss       dword ptr [eax],xmm0 
    ret              

実行結果
>calc "x*x+3*x+5"
f(0.000000)=5.000000
f(0.700000)=7.590000
f(1.400000)=11.160000
f(2.100000)=15.709999
f(2.800000)=21.240000
f(3.500000)=27.750000
f(4.200000)=35.239998
f(4.900000)=43.709995
f(5.599999)=53.159992
f(6.299999)=63.589989
f(6.999999)=74.999985
f(7.699999)=87.389977
f(8.399999)=100.759972
f(9.099998)=115.109970
f(9.799998)=130.439957