This fixes PR48172 by properly doing the runtime alias check for vectorization.
Bootstrapped and tested on x86_64-unknown-linux-gnu, applied to trunk sofar. Richard. 2011-05-12 Richard Guenther <rguent...@suse.de> PR tree-optimization/48172 * tree-vect-loop-manip.c (vect_vfa_segment_size): Do not exclude the number of iterations from the segment size calculation. (vect_create_cond_for_alias_checks): Adjust. * gcc.dg/vect/pr48172.c: New testcase. Index: gcc/tree-vect-loop-manip.c =================================================================== *** gcc/tree-vect-loop-manip.c (revision 173693) --- gcc/tree-vect-loop-manip.c (working copy) *************** vect_create_cond_for_align_checks (loop_ *** 2354,2379 **** Input: DR: The data reference. VECT_FACTOR: vectorization factor. Return an expression whose value is the size of segment which will be accessed by DR. */ static tree ! vect_vfa_segment_size (struct data_reference *dr, tree vect_factor) { ! tree segment_length = fold_build2 (MULT_EXPR, integer_type_node, ! DR_STEP (dr), vect_factor); ! if (vect_supportable_dr_alignment (dr, false) == dr_explicit_realign_optimized) { tree vector_size = TYPE_SIZE_UNIT (STMT_VINFO_VECTYPE (vinfo_for_stmt (DR_STMT (dr)))); ! segment_length = fold_build2 (PLUS_EXPR, integer_type_node, ! segment_length, vector_size); } ! return fold_convert (sizetype, segment_length); } --- 2354,2384 ---- Input: DR: The data reference. VECT_FACTOR: vectorization factor. + SCALAR_LOOP_NITERS: number of iterations. Return an expression whose value is the size of segment which will be accessed by DR. */ static tree ! vect_vfa_segment_size (struct data_reference *dr, int vect_factor, ! tree scalar_loop_niters) { ! tree segment_length; ! segment_length = size_binop (MULT_EXPR, ! fold_convert (sizetype, DR_STEP (dr)), ! size_int (vect_factor)); ! segment_length = size_binop (MULT_EXPR, ! segment_length, ! fold_convert (sizetype, scalar_loop_niters)); if (vect_supportable_dr_alignment (dr, false) == dr_explicit_realign_optimized) { tree vector_size = TYPE_SIZE_UNIT (STMT_VINFO_VECTYPE (vinfo_for_stmt (DR_STMT (dr)))); ! segment_length = size_binop (PLUS_EXPR, segment_length, vector_size); } ! return segment_length; } *************** vect_create_cond_for_alias_checks (loop_ *** 2407,2414 **** struct loop *loop = LOOP_VINFO_LOOP (loop_vinfo); VEC (ddr_p, heap) * may_alias_ddrs = LOOP_VINFO_MAY_ALIAS_DDRS (loop_vinfo); ! tree vect_factor = ! build_int_cst (integer_type_node, LOOP_VINFO_VECT_FACTOR (loop_vinfo)); ddr_p ddr; unsigned int i; --- 2412,2419 ---- struct loop *loop = LOOP_VINFO_LOOP (loop_vinfo); VEC (ddr_p, heap) * may_alias_ddrs = LOOP_VINFO_MAY_ALIAS_DDRS (loop_vinfo); ! int vect_factor = LOOP_VINFO_VECT_FACTOR (loop_vinfo); ! tree scalar_loop_iters = LOOP_VINFO_NITERS (loop_vinfo); ddr_p ddr; unsigned int i; *************** vect_create_cond_for_alias_checks (loop_ *** 2460,2467 **** vect_create_addr_base_for_vector_ref (stmt_b, cond_expr_stmt_list, NULL_TREE, loop); ! segment_length_a = vect_vfa_segment_size (dr_a, vect_factor); ! segment_length_b = vect_vfa_segment_size (dr_b, vect_factor); if (vect_print_dump_info (REPORT_DR_DETAILS)) { --- 2465,2474 ---- vect_create_addr_base_for_vector_ref (stmt_b, cond_expr_stmt_list, NULL_TREE, loop); ! segment_length_a = vect_vfa_segment_size (dr_a, vect_factor, ! scalar_loop_iters); ! segment_length_b = vect_vfa_segment_size (dr_b, vect_factor, ! scalar_loop_iters); if (vect_print_dump_info (REPORT_DR_DETAILS)) { Index: gcc/testsuite/gcc.dg/vect/pr48172.c =================================================================== *** gcc/testsuite/gcc.dg/vect/pr48172.c (revision 0) --- gcc/testsuite/gcc.dg/vect/pr48172.c (revision 0) *************** *** 0 **** --- 1,33 ---- + /* { dg-do run } */ + + extern void *memset(void *s, int c, __SIZE_TYPE__ n); + extern void abort (void); + + #define ASIZE 1028 + #define HALF (ASIZE/2) + + int main() { + unsigned int array[ASIZE]; + int i; + + memset(array, 0, sizeof(array)); + + /* initialize first half of the array */ + for (i = 0; i < HALF; i++) + array[i] = i; + + /* fill second half of array in by summing earlier elements of the array + gcc 4.5.1 and 4.5.2 incorrectly vectorize this loop! aray[1025] is left + at 0 for ASIZE=1028 */ + for (i = 0; i < HALF-1; i++) + array[HALF+i] = array[2*i] + array[2*i + 1]; + + /* see if we have any failures */ + for (i = 0; i < HALF - 1; i++) + if (array[HALF+i] != array[2*i] + array[2*i + 1]) + abort (); + + return 0; + } + + /* { dg-final { cleanup-tree-dump "vect" } } */