Hi All, In GCC 14 VEC_PERM_EXPR was relaxed to be able to permute to a 2x larger vector than the size of the input vectors. However various passes and transformations were not updated to account for this.
I have patches in these area that I will be upstreaming with individual patches that expose them. This one is that vectlower tries to lower based on the size of the input vectors rather than the size of the output. As a consequence it creates an invalid vector of half the size. Luckily we ICE because the resulting nunits doesn't match the vector size. Tests in the AArch64 patch test for this behaviour. Bootstrapped Regtested on aarch64-none-linux-gnu, arm-none-linux-gnueabihf, x86_64-pc-linux-gnu -m32, -m64 and no issues. Ok for master? Thanks, Tamar gcc/ChangeLog: * tree-vect-generic.cc (lower_vec_perm): Use output vector size instead of input vector when determining output nunits. --- diff --git a/gcc/tree-vect-generic.cc b/gcc/tree-vect-generic.cc index 3041fb8fcf235ba86f37ef73aa089330a2fd0b77..f86f7eabb255fde50b30fa3b85db367df930f321 100644 --- a/gcc/tree-vect-generic.cc +++ b/gcc/tree-vect-generic.cc @@ -1500,6 +1500,7 @@ lower_vec_perm (gimple_stmt_iterator *gsi) tree mask = gimple_assign_rhs3 (stmt); tree vec0 = gimple_assign_rhs1 (stmt); tree vec1 = gimple_assign_rhs2 (stmt); + tree res_vect_type = TREE_TYPE (gimple_assign_lhs (stmt)); tree vect_type = TREE_TYPE (vec0); tree mask_type = TREE_TYPE (mask); tree vect_elt_type = TREE_TYPE (vect_type); @@ -1512,7 +1513,7 @@ lower_vec_perm (gimple_stmt_iterator *gsi) location_t loc = gimple_location (gsi_stmt (*gsi)); unsigned i; - if (!TYPE_VECTOR_SUBPARTS (vect_type).is_constant (&elements)) + if (!TYPE_VECTOR_SUBPARTS (res_vect_type).is_constant (&elements)) return; if (TREE_CODE (mask) == SSA_NAME) @@ -1672,9 +1673,9 @@ lower_vec_perm (gimple_stmt_iterator *gsi) } if (constant_p) - constr = build_vector_from_ctor (vect_type, v); + constr = build_vector_from_ctor (res_vect_type, v); else - constr = build_constructor (vect_type, v); + constr = build_constructor (res_vect_type, v); gimple_assign_set_rhs_from_tree (gsi, constr); update_stmt (gsi_stmt (*gsi)); } --
diff --git a/gcc/tree-vect-generic.cc b/gcc/tree-vect-generic.cc index 3041fb8fcf235ba86f37ef73aa089330a2fd0b77..f86f7eabb255fde50b30fa3b85db367df930f321 100644 --- a/gcc/tree-vect-generic.cc +++ b/gcc/tree-vect-generic.cc @@ -1500,6 +1500,7 @@ lower_vec_perm (gimple_stmt_iterator *gsi) tree mask = gimple_assign_rhs3 (stmt); tree vec0 = gimple_assign_rhs1 (stmt); tree vec1 = gimple_assign_rhs2 (stmt); + tree res_vect_type = TREE_TYPE (gimple_assign_lhs (stmt)); tree vect_type = TREE_TYPE (vec0); tree mask_type = TREE_TYPE (mask); tree vect_elt_type = TREE_TYPE (vect_type); @@ -1512,7 +1513,7 @@ lower_vec_perm (gimple_stmt_iterator *gsi) location_t loc = gimple_location (gsi_stmt (*gsi)); unsigned i; - if (!TYPE_VECTOR_SUBPARTS (vect_type).is_constant (&elements)) + if (!TYPE_VECTOR_SUBPARTS (res_vect_type).is_constant (&elements)) return; if (TREE_CODE (mask) == SSA_NAME) @@ -1672,9 +1673,9 @@ lower_vec_perm (gimple_stmt_iterator *gsi) } if (constant_p) - constr = build_vector_from_ctor (vect_type, v); + constr = build_vector_from_ctor (res_vect_type, v); else - constr = build_constructor (vect_type, v); + constr = build_constructor (res_vect_type, v); gimple_assign_set_rhs_from_tree (gsi, constr); update_stmt (gsi_stmt (*gsi)); }