#GNU Assembler(x86_64 Mac OS X), 97 bytes This is a proper function that can be called from C:

.text
.globl _f
_f:
movq %rdi,%xmm0;movq %rsi,%xmm1;pclmulqdq $0,%xmm1,%xmm0;movq %xmm0,%rax;ret

& can be tested with this C program:

#include <stdio.h>
int f(int a, int b);
#define p(a,b) printf("%d %d %d\n", a, b, f(a, b))
int main(void)
{
    p(0,1);
    p(1,2);
    p(9,0);
    p(6,1);
    p(3,3);
    p(2,5);
    p(7,9);
    p(13,11);
    p(5,17);
    p(14,13);
    p(19,1);
    p(63,63);
}

Note that on Mac OS X, you have to use clang -x c to compile it as C & not C++.

For linux(if I remember right), the code would be 95 bytes:

.text
.globl f
f:
movq %rdi,%xmm0;movq %rsi,%xmm1;pclmulqdq $0,%xmm1,%xmm0;movq %xmm0,%rax;ret

Strangely enough, this version is actually longer than defining the function in inline assembly, but that one was longer than the pure C solution we already have, so I decided to try assembly.

###edit If it's counted by the assembled size(excluding any labels &c.), then it's #x86_64 Assembler, 22 bytes: 0: 66 48 0f 6e c7 movq %rdi, %xmm0 5: 66 48 0f 6e ce movq %rsi, %xmm1 a: 66 0f 3a 44 c1 00 pclmullqlqdq $0, %xmm1,%xmm0 10: 66 48 0f 7e c0 movq %xmm0, %rax 15: c3 ret

GNU Assembler(x86_64 Mac OS X), 97 bytes

This is a proper function that can be called from C:

.text
.globl _f
_f:
movq %rdi,%xmm0;movq %rsi,%xmm1;pclmulqdq $0,%xmm1,%xmm0;movq %xmm0,%rax;ret

& can be tested with this C program:

#include <stdio.h>
int f(int a, int b);
#define p(a,b) printf("%d %d %d\n", a, b, f(a, b))
int main(void)
{
    p(0,1);
    p(1,2);
    p(9,0);
    p(6,1);
    p(3,3);
    p(2,5);
    p(7,9);
    p(13,11);
    p(5,17);
    p(14,13);
    p(19,1);
    p(63,63);
}

Note that on Mac OS X, you have to use clang -x c to compile it as C & not C++.

For linux(if I remember right), the code would be 95 bytes:

.text
.globl f
f:
movq %rdi,%xmm0;movq %rsi,%xmm1;pclmulqdq $0,%xmm1,%xmm0;movq %xmm0,%rax;ret

Strangely enough, this version is actually longer than defining the function in inline assembly, but that one was longer than the pure C solution we already have, so I decided to try assembly.

edit

If it's counted by the assembled size(excluding any labels &c.), then it's

x86_64 Assembler, 22 bytes:

0:  66 48 0f 6e c7          movq         %rdi,  %xmm0
5:  66 48 0f 6e ce          movq         %rsi,  %xmm1
a:  66 0f 3a 44 c1 00       pclmullqlqdq $0,    %xmm1,%xmm0
10: 66 48 0f 7e c0          movq         %xmm0, %rax
15: c3                      ret

#GNU Assembler(x86_64 Mac OS X), 97 bytes This is a proper function that can be called from C:

.text
.globl _f
_f:
movq %rdi,%xmm0;movq %rsi,%xmm1;pclmulqdq $0,%xmm1,%xmm0;movq %xmm0,%rax;ret

& can be tested with this C program:

#include <stdio.h>
int f(int a, int b);
#define p(a,b) printf("%d %d %d\n", a, b, f(a, b))
int main(void)
{
    p(0,1);
    p(1,2);
    p(9,0);
    p(6,1);
    p(3,3);
    p(2,5);
    p(7,9);
    p(13,11);
    p(5,17);
    p(14,13);
    p(19,1);
    p(63,63);
}

Note that on Mac OS X, you have to use clang -x c to compile it as C & not C++.

For linux(if I remember right), the code would be 95 bytes:

.text
.globl f
f:
movq %rdi,%xmm0;movq %rsi,%xmm1;pclmulqdq $0,%xmm1,%xmm0;movq %xmm0,%rax;ret

Strangely enough, this version is actually longer than defining the function in inline assembly, but that one was longer than the pure C solution we already have, so I decided to try assembly.

#GNU Assembler(x86_64 Mac OS X), 97 bytes This is a proper function that can be called from C:

.text
.globl _f
_f:
movq %rdi,%xmm0;movq %rsi,%xmm1;pclmulqdq $0,%xmm1,%xmm0;movq %xmm0,%rax;ret

& can be tested with this C program:

#include <stdio.h>
int f(int a, int b);
#define p(a,b) printf("%d %d %d\n", a, b, f(a, b))
int main(void)
{
    p(0,1);
    p(1,2);
    p(9,0);
    p(6,1);
    p(3,3);
    p(2,5);
    p(7,9);
    p(13,11);
    p(5,17);
    p(14,13);
    p(19,1);
    p(63,63);
}

Note that on Mac OS X, you have to use clang -x c to compile it as C & not C++.

For linux(if I remember right), the code would be 95 bytes:

.text
.globl f
f:
movq %rdi,%xmm0;movq %rsi,%xmm1;pclmulqdq $0,%xmm1,%xmm0;movq %xmm0,%rax;ret

Strangely enough, this version is actually longer than defining the function in inline assembly, but that one was longer than the pure C solution we already have, so I decided to try assembly.

###edit If it's counted by the assembled size(excluding any labels &c.), then it's #x86_64 Assembler, 22 bytes: 0: 66 48 0f 6e c7 movq %rdi, %xmm0 5: 66 48 0f 6e ce movq %rsi, %xmm1 a: 66 0f 3a 44 c1 00 pclmullqlqdq $0, %xmm1,%xmm0 10: 66 48 0f 7e c0 movq %xmm0, %rax 15: c3 ret