From dbde384bd56f07bfbcae86f81fc74aa92e3786ad Mon Sep 17 00:00:00 2001 From: liuhongt Date: Wed, 18 Oct 2023 10:08:24 +0800 Subject: Avoid compile time hog on vect_peel_nonlinear_iv_init for nonlinear induction vec_step_op_mul when iteration count is too big. There's loop in vect_peel_nonlinear_iv_init to get init_expr * pow (step_expr, skip_niters). When skipn_iters is too big, compile time hogs. To avoid that, optimize init_expr * pow (step_expr, skip_niters) to init_expr << (exact_log2 (step_expr) * skip_niters) when step_expr is pow of 2, otherwise give up vectorization when skip_niters >= TYPE_PRECISION (TREE_TYPE (init_expr)). Also give up vectorization when niters_skip is negative which will be used for fully masked loop. gcc/ChangeLog: PR tree-optimization/111820 PR tree-optimization/111833 * tree-vect-loop-manip.cc (vect_can_peel_nonlinear_iv_p): Give up vectorization for nonlinear iv vect_step_op_mul when step_expr is not exact_log2 and niters is greater than TYPE_PRECISION (TREE_TYPE (step_expr)). Also don't vectorize for nagative niters_skip which will be used by fully masked loop. (vect_can_advance_ivs_p): Pass whole phi_info to vect_can_peel_nonlinear_iv_p. * tree-vect-loop.cc (vect_peel_nonlinear_iv_init): Optimize init_expr * pow (step_expr, skipn) to init_expr << (log2 (step_expr) * skipn) when step_expr is exact_log2. gcc/testsuite/ChangeLog: * gcc.target/i386/pr111820-1.c: New test. * gcc.target/i386/pr111820-2.c: New test. * gcc.target/i386/pr111820-3.c: New test. * gcc.target/i386/pr103144-mul-1.c: Adjust testcase. * gcc.target/i386/pr103144-mul-2.c: Adjust testcase. --- gcc/tree-vect-loop.cc | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'gcc/tree-vect-loop.cc') diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc index 4a8b0a1..40f167d 100644 --- a/gcc/tree-vect-loop.cc +++ b/gcc/tree-vect-loop.cc @@ -9222,12 +9222,17 @@ vect_peel_nonlinear_iv_init (gimple_seq* stmts, tree init_expr, { tree utype = unsigned_type_for (type); init_expr = gimple_convert (stmts, utype, init_expr); - unsigned skipn = TREE_INT_CST_LOW (skip_niters); + wide_int skipn = wi::to_wide (skip_niters); wide_int begin = wi::to_wide (step_expr); - for (unsigned i = 0; i != skipn - 1; i++) - begin = wi::mul (begin, wi::to_wide (step_expr)); + auto_mpz base, exp, mod, res; + wi::to_mpz (begin, base, TYPE_SIGN (type)); + wi::to_mpz (skipn, exp, UNSIGNED); + mpz_ui_pow_ui (mod, 2, TYPE_PRECISION (type)); + mpz_powm (res, base, exp, mod); + begin = wi::from_mpz (type, res, TYPE_SIGN (type)); tree mult_expr = wide_int_to_tree (utype, begin); - init_expr = gimple_build (stmts, MULT_EXPR, utype, init_expr, mult_expr); + init_expr = gimple_build (stmts, MULT_EXPR, utype, + init_expr, mult_expr); init_expr = gimple_convert (stmts, type, init_expr); } break; -- cgit v1.1