aboutsummaryrefslogtreecommitdiff
path: root/gcc/tree-vect-loop-manip.cc
diff options
context:
space:
mode:
authorliuhongt <hongtao.liu@intel.com>2023-02-01 13:30:12 +0800
committerliuhongt <hongtao.liu@intel.com>2023-02-02 17:02:01 +0800
commit209f02b0a9e9adc0bf0247cb5eef04e0f175d64e (patch)
tree536170ab9e00d799297b6d85f3258b604107ba77 /gcc/tree-vect-loop-manip.cc
parent0f349928e16fdc7dba52561e8d40347909f9f0ff (diff)
downloadgcc-209f02b0a9e9adc0bf0247cb5eef04e0f175d64e.zip
gcc-209f02b0a9e9adc0bf0247cb5eef04e0f175d64e.tar.gz
gcc-209f02b0a9e9adc0bf0247cb5eef04e0f175d64e.tar.bz2
Don't peel nonlinear iv(mult or shift) for epilog when vf is not constant.
Normally when vf is not constant, it will be prevented by vectorizable_nonlinear_inductions, but for this case, it failed going into if (STMT_VINFO_RELEVANT_P (stmt_info)) { need_to_vectorize = true; if (STMT_VINFO_DEF_TYPE (stmt_info) == vect_induction_def && ! PURE_SLP_STMT (stmt_info)) ok = vectorizable_induction (loop_vinfo, stmt_info, NULL, NULL, &cost_vec); since the iv is never used outside of the loop, and will be dce later, so vectorizer doesn't bother checking if it's vectorizable. it's true but hit gcc_assert in vect_can_peel_nonlinear_iv_p when vf is not constant. One solution is ignoring the nonlinear iv peeling if it's !STMT_VINFO_RELEVANT_P (stmt_info) just like the upper code, the other solution is returning false earlier in the vect_can_peel_nonlinear_iv_p when vf is not constant, the patch chooses the second incase there's other cases using vect_can_advance_ivs_p which calls vect_can_peel_nonlinear_iv_p. Also remove vect_peel_nonlinear_iv_p from vectorizable_nonlinear_inductions. gcc/ChangeLog: PR tree-optimization/108601 * tree-vectorizer.h (vect_can_peel_nonlinear_iv_p): Removed. * tree-vect-loop.cc (vectorizable_nonlinear_induction): Remove vect_can_peel_nonlinear_iv_p. (vect_can_peel_nonlinear_iv_p): Don't peel nonlinear iv(mult or shift) for epilog when vf is not constant and moved the defination to .. * tree-vect-loop-manip.cc (vect_can_peel_nonlinear_iv_p): .. Here. gcc/testsuite/ChangeLog: * gcc.target/aarch64/pr108601.c: New test.
Diffstat (limited to 'gcc/tree-vect-loop-manip.cc')
-rw-r--r--gcc/tree-vect-loop-manip.cc44
1 files changed, 44 insertions, 0 deletions
diff --git a/gcc/tree-vect-loop-manip.cc b/gcc/tree-vect-loop-manip.cc
index b5c5f85..c04fcf4 100644
--- a/gcc/tree-vect-loop-manip.cc
+++ b/gcc/tree-vect-loop-manip.cc
@@ -1390,6 +1390,50 @@ iv_phi_p (stmt_vec_info stmt_info)
return true;
}
+/* Return true if vectorizer can peel for nonlinear iv. */
+static bool
+vect_can_peel_nonlinear_iv_p (loop_vec_info loop_vinfo,
+ enum vect_induction_op_type induction_type)
+{
+ tree niters_skip;
+ /* Init_expr will be update by vect_update_ivs_after_vectorizer,
+ if niters or vf is unkown:
+ For shift, when shift mount >= precision, there would be UD.
+ For mult, don't known how to generate
+ init_expr * pow (step, niters) for variable niters.
+ For neg, it should be ok, since niters of vectorized main loop
+ will always be multiple of 2. */
+ if ((!LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo)
+ || !LOOP_VINFO_VECT_FACTOR (loop_vinfo).is_constant ())
+ && induction_type != vect_step_op_neg)
+ {
+ if (dump_enabled_p ())
+ dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
+ "Peeling for epilogue is not supported"
+ " for nonlinear induction except neg"
+ " when iteration count is unknown.\n");
+ return false;
+ }
+
+ /* Also doens't support peel for neg when niter is variable.
+ ??? generate something like niter_expr & 1 ? init_expr : -init_expr? */
+ niters_skip = LOOP_VINFO_MASK_SKIP_NITERS (loop_vinfo);
+ if ((niters_skip != NULL_TREE
+ && TREE_CODE (niters_skip) != INTEGER_CST)
+ || (!vect_use_loop_mask_for_alignment_p (loop_vinfo)
+ && LOOP_VINFO_PEELING_FOR_ALIGNMENT (loop_vinfo) < 0))
+ {
+ if (dump_enabled_p ())
+ dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
+ "Peeling for alignement is not supported"
+ " for nonlinear induction when niters_skip"
+ " is not constant.\n");
+ return false;
+ }
+
+ return true;
+}
+
/* Function vect_can_advance_ivs_p
In case the number of iterations that LOOP iterates is unknown at compile