From 5486a99614790b4b310fedb774f086222490b2c0 Mon Sep 17 00:00:00 2001 From: Jun Ma Date: Thu, 16 May 2019 08:21:17 +0000 Subject: [PATCH] re PR tree-optimization/90106 (builtin sqrt() ignoring libm's sqrt call result) PR tree-optimization/90106 * tree-call-cdce.c (shrink_wrap_one_built_in_call_with_conds): Add new parameter as new internal function call, also move it to new basic block. (use_internal_fn): Pass internal function call to shrink_wrap_one_built_in_call_with_conds. gcc/testsuite * gcc.dg/cdce1.c: Check tailcall code generation after cdce pass. * gcc.dg/cdce2.c: Likewise. From-SVN: r271281 --- gcc/ChangeLog | 25 ++++------ gcc/testsuite/ChangeLog | 6 +++ gcc/testsuite/gcc.dg/cdce1.c | 3 +- gcc/testsuite/gcc.dg/cdce2.c | 3 +- gcc/tree-call-cdce.c | 90 +++++++++++++++++++++++++++--------- 5 files changed, 85 insertions(+), 42 deletions(-) diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 5fd00d9ecc3..4a891c90048 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,20 +1,11 @@ -2019-05-16 Sebastian Huber - - * config/arm/t-rtems: Replace ARMv7-M multilibs with Cortex-M - multilibs. - -2019-05-16 Richard Biener - - PR tree-optimization/90424 - * tree-ssa.c (non_rewritable_lvalue_p): Handle inserts from - aligned subvectors. - (execute_update_addresses_taken): Likewise. - * tree-cfg.c (verify_gimple_assign_ternary): Likewise. - -2019-05-16 Richard Biener - - * gimple-pretty-print.c (dump_ternary_rhs): Dump BIT_INSERT_EXPR - as __BIT_INSERT with -gimple. +2019-05-16 Jun Ma + + PR tree-optimization/90106 + * tree-call-cdce.c (shrink_wrap_one_built_in_call_with_conds): Add + new parameter as new internal function call, also move it to new + basic block. + (use_internal_fn): Pass internal function call to + shrink_wrap_one_built_in_call_with_conds. 2019-05-15 Jakub Jelinek diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog index 5f01fdf15a8..dc4edeffabc 100644 --- a/gcc/testsuite/ChangeLog +++ b/gcc/testsuite/ChangeLog @@ -1,3 +1,9 @@ +2019-05-16 Jun Ma + + PR tree-optimization/90106 + * gcc.dg/cdce1.c: Check tailcall code generation after cdce pass. + * gcc.dg/cdce2.c: Likewise. + 2019-05-16 Richard Biener PR tree-optimization/90424 diff --git a/gcc/testsuite/gcc.dg/cdce1.c b/gcc/testsuite/gcc.dg/cdce1.c index b23ad637112..424d80fcdec 100644 --- a/gcc/testsuite/gcc.dg/cdce1.c +++ b/gcc/testsuite/gcc.dg/cdce1.c @@ -1,7 +1,8 @@ /* { dg-do run } */ /* { dg-options "-O2 -fmath-errno -fdump-tree-cdce-details -lm" } */ /* { dg-require-effective-target int32plus } */ -/* { dg-final { scan-tree-dump "cdce1.c:16: .* function call is shrink-wrapped into error conditions\." "cdce" } } */ +/* { dg-final { scan-tree-dump "cdce1.c:17: .* function call is shrink-wrapped into error conditions\." "cdce" } } */ +/* { dg-final { scan-assembler "jmp pow" } } */ /* { dg-require-effective-target large_double } */ #include diff --git a/gcc/testsuite/gcc.dg/cdce2.c b/gcc/testsuite/gcc.dg/cdce2.c index 30e7cb1fa0a..2af2893549d 100644 --- a/gcc/testsuite/gcc.dg/cdce2.c +++ b/gcc/testsuite/gcc.dg/cdce2.c @@ -1,7 +1,8 @@ /* { dg-do run } */ /* { dg-skip-if "doubles are floats" { "avr-*-*" } } */ /* { dg-options "-O2 -fmath-errno -fdump-tree-cdce-details -lm" } */ -/* { dg-final { scan-tree-dump "cdce2.c:15: .* function call is shrink-wrapped into error conditions\." "cdce" } } */ +/* { dg-final { scan-tree-dump "cdce2.c:16: .* function call is shrink-wrapped into error conditions\." "cdce" } } */ +/* { dg-final { scan-assembler "jmp log" } } */ #include #include diff --git a/gcc/tree-call-cdce.c b/gcc/tree-call-cdce.c index 2e482b37ea2..9e3372fe56c 100644 --- a/gcc/tree-call-cdce.c +++ b/gcc/tree-call-cdce.c @@ -93,10 +93,10 @@ along with GCC; see the file COPYING3. If not see y = sqrt (x); ==> - y = IFN_SQRT (x); if (__builtin_isless (x, 0)) - sqrt (x); - + y = sqrt (x); + else + y = IFN_SQRT (x); In the vast majority of cases we should then never need to call sqrt. Note that library functions are not supposed to clear errno to zero without @@ -793,14 +793,16 @@ gen_shrink_wrap_conditions (gcall *bi_call, vec conds, } /* Shrink-wrap BI_CALL so that it is only called when one of the NCONDS - conditions in CONDS is false. */ + conditions in CONDS is false. Also move BI_NEWCALL to a new basic block + when it is non-null, it is called while all of the CONDS are true. */ static void shrink_wrap_one_built_in_call_with_conds (gcall *bi_call, vec conds, - unsigned int nconds) + unsigned int nconds, + gcall *bi_newcall = NULL) { gimple_stmt_iterator bi_call_bsi; - basic_block bi_call_bb, join_tgt_bb, guard_bb; + basic_block bi_call_bb, bi_newcall_bb, join_tgt_bb, guard_bb; edge join_tgt_in_edge_from_call, join_tgt_in_edge_fall_thru; edge bi_call_in_edge0, guard_bb_in_edge; unsigned tn_cond_stmts; @@ -809,27 +811,26 @@ shrink_wrap_one_built_in_call_with_conds (gcall *bi_call, vec conds, gimple *cond_expr_start; /* The cfg we want to create looks like this: - - [guard n-1] <- guard_bb (old block) - | \ - | [guard n-2] } - | / \ } - | / ... } new blocks - | / [guard 0] } - | / / | } - [ call ] | <- bi_call_bb } - | \ | - | \ | - | [ join ] <- join_tgt_bb (old iff call must end bb) - | + [guard n-1] <- guard_bb (old block) + | \ + | [guard n-2] } + | / \ } + | / ... } new blocks + | / [guard 0] } + | / / | } + [call] | <- bi_call_bb } + \ [newcall] <-bi_newcall_bb} + \ | + [join] <- join_tgt_bb (old iff call must end bb) possible EH edges (only if [join] is old) When [join] is new, the immediate dominators for these blocks are: 1. [guard n-1]: unchanged 2. [call]: [guard n-1] - 3. [guard m]: [guard m+1] for 0 <= m <= n-2 - 4. [join]: [guard n-1] + 3. [newcall]: [guard 0] + 4. [guard m]: [guard m+1] for 0 <= m <= n-2 + 5. [join]: [guard n-1] We punt for the more complex case case of [join] being old and simply free the dominance info. We also punt on postdominators, @@ -927,6 +928,47 @@ shrink_wrap_one_built_in_call_with_conds (gcall *bi_call, vec conds, edges.quick_push (edge_pair (bi_call_in_edge, guard_bb_in_edge)); } + /* Move BI_NEWCALL to new basic block when it is non-null. */ + if (bi_newcall) + { + /* Get bi_newcall_bb by split join_tgt_in_edge_fall_thru edge, + and move BI_NEWCALL to bi_newcall_bb. */ + bi_newcall_bb = split_edge (join_tgt_in_edge_fall_thru); + gimple_stmt_iterator to_gsi = gsi_start_bb (bi_newcall_bb); + gimple_stmt_iterator from_gsi = gsi_for_stmt (bi_newcall); + gsi_move_before (&from_gsi, &to_gsi); + join_tgt_in_edge_fall_thru = EDGE_SUCC (bi_newcall_bb, 0); + join_tgt_bb = join_tgt_in_edge_fall_thru->dest; + + tree bi_newcall_lhs = gimple_call_lhs (bi_newcall); + tree bi_call_lhs = gimple_call_lhs (bi_call); + if (!bi_call_lhs) + { + bi_call_lhs = copy_ssa_name (bi_newcall_lhs); + gimple_call_set_lhs (bi_call, bi_call_lhs); + SSA_NAME_DEF_STMT (bi_call_lhs) = bi_call; + } + + /* Create phi node for lhs of BI_CALL and BI_NEWCALL. */ + gphi *new_phi = create_phi_node (copy_ssa_name (bi_newcall_lhs), + join_tgt_bb); + SSA_NAME_OCCURS_IN_ABNORMAL_PHI (PHI_RESULT (new_phi)) + = SSA_NAME_OCCURS_IN_ABNORMAL_PHI (bi_newcall_lhs); + add_phi_arg (new_phi, bi_call_lhs, join_tgt_in_edge_from_call, + gimple_location (bi_call)); + add_phi_arg (new_phi, bi_newcall_lhs, join_tgt_in_edge_fall_thru, + gimple_location (bi_newcall)); + + /* Replace all use of original return value with result of phi node. */ + use_operand_p use_p; + gimple *use_stmt; + imm_use_iterator iterator; + FOR_EACH_IMM_USE_STMT (use_stmt, iterator, bi_newcall_lhs) + if (use_stmt != new_phi) + FOR_EACH_IMM_USE_ON_STMT (use_p, iterator) + SET_USE (use_p, PHI_RESULT (new_phi)); + } + /* Now update the probability and profile information, processing the guards in order of execution. @@ -1030,9 +1072,11 @@ use_internal_fn (gcall *call) unsigned nconds = 0; auto_vec conds; + bool is_arg_conds = false; if (can_test_argument_range (call)) { gen_shrink_wrap_conditions (call, conds, &nconds); + is_arg_conds = true; gcc_assert (nconds != 0); } else @@ -1082,8 +1126,8 @@ use_internal_fn (gcall *call) call = new_call; } } - - shrink_wrap_one_built_in_call_with_conds (call, conds, nconds); + shrink_wrap_one_built_in_call_with_conds (call, conds, nconds, + is_arg_conds ? new_call : NULL); } /* The top level function for conditional dead code shrink -- 2.30.2