Compute Affine table for GF(2^8) multiplication with 0x11d polynomial

gf-affine-mul8-gen.c

#include <stdio.h>
#include <x86intrin.h>
#include <stdint.h>
#include <stdlib.h>
#include <string.h>

int main(void) {
	__m128i polymask1 = _mm_set1_epi64x(0xff00ffffff000000ULL); // polynomial 0x11d: 0x1d = 0b11101, reverse bits -> 10111000, then replace 1->ff, 0->00
	
	for(int val=0; val<256; val++) {
		__m128i addvals1 = _mm_set_epi8(0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80);
	  __m128i valtest = _mm_set1_epi8(val);
	  __m128i addmask = _mm_cmpgt_epi8(_mm_setzero_si128(), valtest);
	  __m128i depmask1 = _mm_and_si128(addvals1, addmask);
	  for(int i=0; i<7; i++) {
		/* rotate */
		__m128i last = _mm_shuffle_epi8(depmask1, _mm_set1_epi8(0));
		depmask1 = _mm_srli_epi64(depmask1, 8);
		
		/* XOR poly */
		depmask1 = _mm_xor_si128(depmask1, _mm_and_si128(polymask1, last));
		
		valtest = _mm_add_epi8(valtest, valtest);
		addmask = _mm_cmpgt_epi8(_mm_setzero_si128(), valtest);
		
		depmask1 = _mm_xor_si128(depmask1, _mm_and_si128(addvals1, addmask));
	  }
	  
	 // if((val & 0xf) == 0)
	//	  printf("\n");
	  uint64_t ans = _mm_cvtsi128_si64(depmask1);
	  printf("0x%llxULL,", ans);
	}
	printf("\n");
	
	return 0;
}