diff --git a/gcc/tree-vect-data-refs.c b/gcc/tree-vect-data-refs.c index 274cdbd..042b97c 100644 --- a/gcc/tree-vect-data-refs.c +++ b/gcc/tree-vect-data-refs.c @@ -4365,13 +4365,14 @@ vect_grouped_store_supported (tree vectype, unsigned HOST_WIDE_INT count) { enum machine_mode mode = TYPE_MODE (vectype); - /* vect_permute_store_chain requires the group size to be a power of two. */ - if (exact_log2 (count) == -1) + /* vect_permute_store_chain requires the group size to be equal to 3 or + be a power of two. */ + if (count != 3 && exact_log2 (count) == -1) { if (dump_enabled_p ()) dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location, - "the size of the group of accesses" - " is not a power of 2\n"); + "the size of the group of accesses" + " is not a power of 2 or not eqaul to 3\n"); return false; } @@ -4380,23 +4381,73 @@ vect_grouped_store_supported (tree vectype, unsigned HOST_WIDE_INT count) { unsigned int i, nelt = GET_MODE_NUNITS (mode); unsigned char *sel = XALLOCAVEC (unsigned char, nelt); - for (i = 0; i < nelt / 2; i++) + + if (exact_log2 (count) != -1) { - sel[i * 2] = i; - sel[i * 2 + 1] = i + nelt; + for (i = 0; i < nelt / 2; i++) + { + sel[i * 2] = i; + sel[i * 2 + 1] = i + nelt; + } + if (can_vec_perm_p (mode, false, sel)) + { + for (i = 0; i < nelt; i++) + sel[i] += nelt / 2; + if (can_vec_perm_p (mode, false, sel)) + return true; + } } - if (can_vec_perm_p (mode, false, sel)) + else if (count == 3) { - for (i = 0; i < nelt; i++) - sel[i] += nelt / 2; - if (can_vec_perm_p (mode, false, sel)) - return true; - } + unsigned int j0 = 0, j1 = 0, j2 = 0; + unsigned int i, j; + + for (j = 0; j < 3; j++) + { + int nelt0 = ((3 - j) * nelt) % 3; + int nelt1 = ((3 - j) * nelt + 1) % 3; + int nelt2 = ((3 - j) * nelt + 2) % 3; + for (i = 0; i < nelt; i++) + { + if (3 * i + nelt0 < nelt) + sel[3 * i + nelt0] = j0++; + if (3 * i + nelt1 < nelt) + sel[3 * i + nelt1] = nelt + j1++; + if (3 * i + nelt2 < nelt) + sel[3 * i + nelt2] = 0; + } + if (!can_vec_perm_p (mode, false, sel)) + { + if (dump_enabled_p ()) + dump_printf (MSG_MISSED_OPTIMIZATION, + "permutaion op not supported by target.\n"); + return false; + } + + for (i = 0; i < nelt; i++) + { + if (3 * i + nelt0 < nelt) + sel[3 * i + nelt0] = 3 * i + nelt0; + if (3 * i + nelt1 < nelt) + sel[3 * i + nelt1] = 3 * i + nelt1; + if (3 * i + nelt2 < nelt) + sel[3 * i + nelt2] = nelt + j2++; + } + if (!can_vec_perm_p (mode, false, sel)) + { + if (dump_enabled_p ()) + dump_printf (MSG_MISSED_OPTIMIZATION, + "permutaion op not supported by target.\n"); + return false; + } + } + return true; + } } if (dump_enabled_p ()) dump_printf (MSG_MISSED_OPTIMIZATION, - "interleave op not supported by target.\n"); + "permutaion op not supported by target.\n"); return false; } @@ -4416,9 +4467,9 @@ vect_store_lanes_supported (tree vectype, unsigned HOST_WIDE_INT count) /* Function vect_permute_store_chain. Given a chain of interleaved stores in DR_CHAIN of LENGTH that must be - a power of 2, generate interleave_high/low stmts to reorder the data - correctly for the stores. Return the final references for stores in - RESULT_CHAIN. + a power of 2 or equal to 3, generate interleave_high/low stmts to reorder + the data correctly for the stores. Return the final references for stores + in RESULT_CHAIN. E.g., LENGTH is 4 and the scalar type is short, i.e., VF is 8. The input is 4 vectors each containing 8 elements. We assign a number to @@ -4485,7 +4536,9 @@ vect_permute_store_chain (vec dr_chain, gimple perm_stmt; tree vectype = STMT_VINFO_VECTYPE (vinfo_for_stmt (stmt)); tree perm_mask_low, perm_mask_high; - unsigned int i, n; + tree data_ref; + tree perm3_mask_low, perm3_mask_high; + unsigned int i, n, log_length = exact_log2 (length); unsigned int j, nelt = TYPE_VECTOR_SUBPARTS (vectype); unsigned char *sel = XALLOCAVEC (unsigned char, nelt); @@ -4493,47 +4546,117 @@ vect_permute_store_chain (vec dr_chain, memcpy (result_chain->address (), dr_chain.address (), length * sizeof (tree)); - for (i = 0, n = nelt / 2; i < n; i++) + if (log_length != (unsigned int)-1) { - sel[i * 2] = i; - sel[i * 2 + 1] = i + nelt; - } - perm_mask_high = vect_gen_perm_mask (vectype, sel); - gcc_assert (perm_mask_high != NULL); + for (i = 0, n = nelt / 2; i < n; i++) + { + sel[i * 2] = i; + sel[i * 2 + 1] = i + nelt; + } + perm_mask_high = vect_gen_perm_mask (vectype, sel); + gcc_assert (perm_mask_high != NULL); - for (i = 0; i < nelt; i++) - sel[i] += nelt / 2; - perm_mask_low = vect_gen_perm_mask (vectype, sel); - gcc_assert (perm_mask_low != NULL); + for (i = 0; i < nelt; i++) + sel[i] += nelt / 2; + perm_mask_low = vect_gen_perm_mask (vectype, sel); + gcc_assert (perm_mask_low != NULL); - for (i = 0, n = exact_log2 (length); i < n; i++) + for (i = 0, n = log_length; i < n; i++) + { + for (j = 0; j < length/2; j++) + { + vect1 = dr_chain[j]; + vect2 = dr_chain[j+length/2]; + + /* Create interleaving stmt: + high = VEC_PERM_EXPR */ + high = make_temp_ssa_name (vectype, NULL, "vect_inter_high"); + perm_stmt + = gimple_build_assign_with_ops (VEC_PERM_EXPR, high, + vect1, vect2, perm_mask_high); + vect_finish_stmt_generation (stmt, perm_stmt, gsi); + (*result_chain)[2*j] = high; + + /* Create interleaving stmt: + low = VEC_PERM_EXPR */ + low = make_temp_ssa_name (vectype, NULL, "vect_inter_low"); + perm_stmt + = gimple_build_assign_with_ops (VEC_PERM_EXPR, low, + vect1, vect2, perm_mask_low); + vect_finish_stmt_generation (stmt, perm_stmt, gsi); + (*result_chain)[2*j+1] = low; + } + memcpy (dr_chain.address (), result_chain->address (), + length * sizeof (tree)); + } + } + /* length is not a power of 2. */ + else { - for (j = 0; j < length/2; j++) - { - vect1 = dr_chain[j]; - vect2 = dr_chain[j+length/2]; + unsigned int j0 = 0, j1 = 0, j2 = 0; + + /* currently only length 3 is supported as most frequent case. */ + gcc_assert (length == 3); + + for (j = 0; j < 3; j++) + { + int nelt0 = ((3 - j) * nelt) % 3; + int nelt1 = ((3 - j) * nelt + 1) % 3; + int nelt2 = ((3 - j) * nelt + 2) % 3; + + for (i = 0; i < nelt; i++) + { + if (3 * i + nelt0 < nelt) + sel[3 * i + nelt0] = j0++; + if (3 * i + nelt1 < nelt) + sel[3 * i + nelt1] = nelt + j1++; + if (3 * i + nelt2 < nelt) + sel[3 * i + nelt2] = 0; + } + perm3_mask_low = vect_gen_perm_mask (vectype, sel); + gcc_assert (perm3_mask_low != NULL); + + for (i = 0; i < nelt; i++) + { + if (3 * i + nelt0 < nelt) + sel[3 * i + nelt0] = 3 * i + nelt0; + if (3 * i + nelt1 < nelt) + sel[3 * i + nelt1] = 3 * i + nelt1; + if (3 * i + nelt2 < nelt) + sel[3 * i + nelt2] = nelt + j2++; + } + perm3_mask_high = vect_gen_perm_mask (vectype, sel); + gcc_assert (perm3_mask_high != NULL); + + vect1 = dr_chain[0]; + vect2 = dr_chain[1]; /* Create interleaving stmt: - high = VEC_PERM_EXPR */ - high = make_temp_ssa_name (vectype, NULL, "vect_inter_high"); - perm_stmt - = gimple_build_assign_with_ops (VEC_PERM_EXPR, high, - vect1, vect2, perm_mask_high); + low = VEC_PERM_EXPR */ + data_ref = make_temp_ssa_name (vectype, NULL, "vect_shuffle3_low"); + perm_stmt = gimple_build_assign_with_ops (VEC_PERM_EXPR, data_ref, + vect1, vect2, + perm3_mask_low); vect_finish_stmt_generation (stmt, perm_stmt, gsi); - (*result_chain)[2*j] = high; + vect1 = data_ref; + vect2 = dr_chain[2]; /* Create interleaving stmt: - low = VEC_PERM_EXPR */ - low = make_temp_ssa_name (vectype, NULL, "vect_inter_low"); - perm_stmt - = gimple_build_assign_with_ops (VEC_PERM_EXPR, low, - vect1, vect2, perm_mask_low); + low = VEC_PERM_EXPR */ + data_ref = make_temp_ssa_name (vectype, NULL, "vect_shuffle3_high"); + perm_stmt = gimple_build_assign_with_ops (VEC_PERM_EXPR, data_ref, + vect1, vect2, + perm3_mask_high); vect_finish_stmt_generation (stmt, perm_stmt, gsi); - (*result_chain)[2*j+1] = low; + (*result_chain)[j] = data_ref; } - memcpy (dr_chain.address (), result_chain->address (), - length * sizeof (tree)); } } @@ -4812,36 +4935,74 @@ vect_grouped_load_supported (tree vectype, unsigned HOST_WIDE_INT count) { enum machine_mode mode = TYPE_MODE (vectype); - /* vect_permute_load_chain requires the group size to be a power of two. */ - if (exact_log2 (count) == -1) + /* vect_permute_load_chain requires the group size to be equal to 3 or + be a power of two. */ + if (count != 3 && exact_log2 (count) == -1) { if (dump_enabled_p ()) dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location, - "the size of the group of accesses" - " is not a power of 2\n"); + "the size of the group of accesses" + " is not a power of 2 or not eqaul to 3\n"); return false; } /* Check that the permutation is supported. */ if (VECTOR_MODE_P (mode)) { - unsigned int i, nelt = GET_MODE_NUNITS (mode); + unsigned int i, j, nelt = GET_MODE_NUNITS (mode); unsigned char *sel = XALLOCAVEC (unsigned char, nelt); - for (i = 0; i < nelt; i++) - sel[i] = i * 2; - if (can_vec_perm_p (mode, false, sel)) + if (exact_log2 (count) != -1) { for (i = 0; i < nelt; i++) - sel[i] = i * 2 + 1; + sel[i] = i * 2; if (can_vec_perm_p (mode, false, sel)) - return true; + { + for (i = 0; i < nelt; i++) + sel[i] = i * 2 + 1; + if (can_vec_perm_p (mode, false, sel)) + return true; + } + } + else if (count == 3) + { + unsigned int k; + for (k = 0; k < 3; k++) + { + for (i = 0; i < nelt; i++) + if (3 * i + k < 2 * nelt) + sel[i] = 3 * i + k; + else + sel[i] = 0; + if (!can_vec_perm_p (mode, false, sel)) + { + if (dump_enabled_p ()) + dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location, + "shuffle of 3 loads is not supported by \ + target\n"); + return false; + } + for (i = 0, j = 0; i < nelt; i++) + if (3 * i + k < 2 * nelt) + sel[i] = i; + else + sel[i] = nelt + ((nelt + k) % 3) + 3 * (j++); + if (!can_vec_perm_p (mode, false, sel)) + { + if (dump_enabled_p ()) + dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location, + "shuffle of 3 loads is not supported by \ + target\n"); + return false; + } + } + return true; } } if (dump_enabled_p ()) dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location, - "extract even/odd not supported by target\n"); + "extract even/odd not supported by target\n"); return false; } @@ -4859,8 +5020,9 @@ vect_load_lanes_supported (tree vectype, unsigned HOST_WIDE_INT count) /* Function vect_permute_load_chain. Given a chain of interleaved loads in DR_CHAIN of LENGTH that must be - a power of 2, generate extract_even/odd stmts to reorder the input data - correctly. Return the final references for loads in RESULT_CHAIN. + a power of 2 or equal to 3, generate extract_even/odd stmts to reorder + the input data correctly. Return the final references for loads in + RESULT_CHAIN. E.g., LENGTH is 4 and the scalar type is short, i.e., VF is 8. The input is 4 vectors each containing 8 elements. We assign a number to each @@ -4941,6 +5103,7 @@ vect_permute_load_chain (vec dr_chain, { tree data_ref, first_vect, second_vect; tree perm_mask_even, perm_mask_odd; + tree perm3_mask_low, perm3_mask_high; gimple perm_stmt; tree vectype = STMT_VINFO_VECTYPE (vinfo_for_stmt (stmt)); unsigned int i, j, log_length = exact_log2 (length); @@ -4951,45 +5114,99 @@ vect_permute_load_chain (vec dr_chain, memcpy (result_chain->address (), dr_chain.address (), length * sizeof (tree)); - for (i = 0; i < nelt; ++i) - sel[i] = i * 2; - perm_mask_even = vect_gen_perm_mask (vectype, sel); - gcc_assert (perm_mask_even != NULL); + if (log_length != (unsigned int)-1) + { + for (i = 0; i < nelt; ++i) + sel[i] = i * 2; + perm_mask_even = vect_gen_perm_mask (vectype, sel); + gcc_assert (perm_mask_even != NULL); - for (i = 0; i < nelt; ++i) - sel[i] = i * 2 + 1; - perm_mask_odd = vect_gen_perm_mask (vectype, sel); - gcc_assert (perm_mask_odd != NULL); + for (i = 0; i < nelt; ++i) + sel[i] = i * 2 + 1; + perm_mask_odd = vect_gen_perm_mask (vectype, sel); + gcc_assert (perm_mask_odd != NULL); - for (i = 0; i < log_length; i++) - { - for (j = 0; j < length; j += 2) + for (i = 0; i < log_length; i++) { - first_vect = dr_chain[j]; - second_vect = dr_chain[j+1]; + for (j = 0; j < length; j += 2) + { + first_vect = dr_chain[j]; + second_vect = dr_chain[j+1]; + + /* data_ref = permute_even (first_data_ref, second_data_ref); */ + data_ref = make_temp_ssa_name (vectype, NULL, "vect_perm_even"); + perm_stmt = gimple_build_assign_with_ops (VEC_PERM_EXPR, data_ref, + first_vect, second_vect, + perm_mask_even); + vect_finish_stmt_generation (stmt, perm_stmt, gsi); + (*result_chain)[j/2] = data_ref; + + /* data_ref = permute_odd (first_data_ref, second_data_ref); */ + data_ref = make_temp_ssa_name (vectype, NULL, "vect_perm_odd"); + perm_stmt = gimple_build_assign_with_ops (VEC_PERM_EXPR, data_ref, + first_vect, second_vect, + perm_mask_odd); + vect_finish_stmt_generation (stmt, perm_stmt, gsi); + (*result_chain)[j/2+length/2] = data_ref; + } + memcpy (dr_chain.address (), result_chain->address (), + length * sizeof (tree)); + } + } + /* length is not a power of 2. */ + else + { + unsigned int k; + + /* currently only length 3 is supported as most frequent case. */ + gcc_assert (length == 3); - /* data_ref = permute_even (first_data_ref, second_data_ref); */ - data_ref = make_temp_ssa_name (vectype, NULL, "vect_perm_even"); + for (k = 0; k < 3; k++) + { + for (i = 0; i < nelt; i++) + if (3 * i + k < 2 * nelt) + sel[i] = 3 * i + k; + else + sel[i] = 0; + perm3_mask_low = vect_gen_perm_mask (vectype, sel); + gcc_assert (perm3_mask_low != NULL); + + for (i = 0, j = 0; i < nelt; i++) + if (3 * i + k < 2 * nelt) + sel[i] = i; + else + sel[i] = nelt + ((nelt + k) % 3) + 3 * (j++); + + perm3_mask_high = vect_gen_perm_mask (vectype, sel); + gcc_assert (perm3_mask_high != NULL); + + first_vect = dr_chain[0]; + second_vect = dr_chain[1]; + + /* Create interleaving stmt (low part of): + low = VEC_PERM_EXPR */ + data_ref = make_temp_ssa_name (vectype, NULL, "vect_suffle3_low"); perm_stmt = gimple_build_assign_with_ops (VEC_PERM_EXPR, data_ref, first_vect, second_vect, - perm_mask_even); + perm3_mask_low); vect_finish_stmt_generation (stmt, perm_stmt, gsi); - (*result_chain)[j/2] = data_ref; - /* data_ref = permute_odd (first_data_ref, second_data_ref); */ - data_ref = make_temp_ssa_name (vectype, NULL, "vect_perm_odd"); + /* Create interleaving stmt (high part of): + high = VEC_PERM_EXPR */ + first_vect = data_ref; + second_vect = dr_chain[2]; + data_ref = make_temp_ssa_name (vectype, NULL, "vect_suffle3_high"); perm_stmt = gimple_build_assign_with_ops (VEC_PERM_EXPR, data_ref, first_vect, second_vect, - perm_mask_odd); + perm3_mask_high); vect_finish_stmt_generation (stmt, perm_stmt, gsi); - (*result_chain)[j/2+length/2] = data_ref; + (*result_chain)[k] = data_ref; } - memcpy (dr_chain.address (), result_chain->address (), - length * sizeof (tree)); } } - /* Function vect_transform_grouped_load. Given a chain of input interleaved data-refs (in DR_CHAIN), build statements diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c index 1a51d6d..24d0b94 100644 --- a/gcc/tree-vect-stmts.c +++ b/gcc/tree-vect-stmts.c @@ -974,9 +974,9 @@ vect_model_store_cost (stmt_vec_info stmt_info, int ncopies, include the cost of the permutes. */ if (!store_lanes_p && group_size > 1) { - /* Uses a high and low interleave operation for each needed permute. */ - - int nstmts = ncopies * exact_log2 (group_size) * group_size; + /* Uses a high and low interleave or shuffle operations for each + needed permute. */ + int nstmts = ncopies * ceil_log2 (group_size) * group_size; inside_cost = record_stmt_cost (body_cost_vec, nstmts, vec_perm, stmt_info, 0, vect_body); @@ -1091,10 +1091,11 @@ vect_model_load_cost (stmt_vec_info stmt_info, int ncopies, include the cost of the permutes. */ if (!load_lanes_p && group_size > 1) { - /* Uses an even and odd extract operations for each needed permute. */ - int nstmts = ncopies * exact_log2 (group_size) * group_size; - inside_cost += record_stmt_cost (body_cost_vec, nstmts, vec_perm, - stmt_info, 0, vect_body); + /* Uses an even and odd extract operations or shuffle operations + for each needed permute. */ + int nstmts = ncopies * ceil_log2 (group_size) * group_size; + inside_cost = record_stmt_cost (body_cost_vec, nstmts, vec_perm, + stmt_info, 0, vect_body); if (dump_enabled_p ()) dump_printf_loc (MSG_NOTE, vect_location,