- * Calculate the address of the next transition for
- * all types of nodes. Note that only DFA nodes and range
- * nodes actually transition to another node. Match
- * nodes don't move.
- */
-static inline __attribute__((always_inline)) xmm_t
-calc_addr_sse(xmm_t index_mask, xmm_t next_input, xmm_t shuffle_input,
- xmm_t ones_16, xmm_t indices1, xmm_t indices2)
-{
- xmm_t addr, node_types, range, temp;
- xmm_t dfa_msk, dfa_ofs, quad_ofs;
- xmm_t in, r, t;
-
- const xmm_t range_base = _mm_set_epi32(0xffffff0c, 0xffffff08,
- 0xffffff04, 0xffffff00);
-
- /*
- * Note that no transition is done for a match
- * node and therefore a stream freezes when
- * it reaches a match.
- */
-
- /* Shuffle low 32 into temp and high 32 into indices2 */
- temp = (xmm_t)MM_SHUFFLEPS((__m128)indices1, (__m128)indices2, 0x88);
- range = (xmm_t)MM_SHUFFLEPS((__m128)indices1, (__m128)indices2, 0xdd);
-
- t = MM_XOR(index_mask, index_mask);
-
- /* shuffle input byte to all 4 positions of 32 bit value */
- in = MM_SHUFFLE8(next_input, shuffle_input);
-
- /* Calc node type and node addr */
- node_types = MM_ANDNOT(index_mask, temp);
- addr = MM_AND(index_mask, temp);
-
- /*
- * Calc addr for DFAs - addr = dfa_index + input_byte
- */
-
- /* mask for DFA type (0) nodes */
- dfa_msk = MM_CMPEQ32(node_types, t);
-
- r = _mm_srli_epi32(in, 30);
- r = _mm_add_epi8(r, range_base);
-
- t = _mm_srli_epi32(in, 24);
- r = _mm_shuffle_epi8(range, r);
-
- dfa_ofs = _mm_sub_epi32(t, r);
-
- /*
- * Calculate number of range boundaries that are less than the
- * input value. Range boundaries for each node are in signed 8 bit,
- * ordered from -128 to 127 in the indices2 register.
- * This is effectively a popcnt of bytes that are greater than the
- * input byte.
- */
-
- /* check ranges */
- temp = MM_CMPGT8(in, range);
-
- /* convert -1 to 1 (bytes greater than input byte */
- temp = MM_SIGN8(temp, temp);
-
- /* horizontal add pairs of bytes into words */
- temp = MM_MADD8(temp, temp);
-
- /* horizontal add pairs of words into dwords */
- quad_ofs = MM_MADD16(temp, ones_16);
-
- /* mask to range type nodes */
- temp = _mm_blendv_epi8(quad_ofs, dfa_ofs, dfa_msk);
-
- /* add index into node position */
- return MM_ADD32(addr, temp);
-}
-
-/*
- * Process 4 transitions (in 2 SIMD registers) in parallel