From 985b3a6837dee7001e6b618f073ed74f0edf5787 Mon Sep 17 00:00:00 2001 From: "H.J. Lu" Date: Mon, 10 Jun 2019 09:57:15 -0700 Subject: Generate offset adjusted operation for op_by_pieces operations Add an overlap_op_by_pieces_p target hook for op_by_pieces operations between two areas of memory to generate one offset adjusted operation in the smallest integer mode for the remaining bytes on the last piece operation of a memory region to avoid doing more than one smaller operations. Pass the RTL information from the previous iteration to m_constfn in op_by_pieces operation so that builtin_memset_[read|gen]_str can generate the new RTL from the previous RTL. Tested on Linux/x86-64. gcc/ PR middle-end/90773 * builtins.c (builtin_memcpy_read_str): Add a dummy argument. (builtin_strncpy_read_str): Likewise. (builtin_memset_read_str): Add an argument for the previous RTL information and generate the new RTL from the previous RTL info. (builtin_memset_gen_str): Likewise. * builtins.h (builtin_strncpy_read_str): Update the prototype. (builtin_memset_read_str): Likewise. * expr.c (by_pieces_ninsns): If targetm.overlap_op_by_pieces_p() returns true, round up size and alignment to the widest integer mode for maximum size. (pieces_addr::adjust): Add a pointer to by_pieces_prev argument and pass it to m_constfn. (op_by_pieces_d): Add m_push and m_overlap_op_by_pieces. (op_by_pieces_d::op_by_pieces_d): Add a bool argument to initialize m_push. Initialize m_overlap_op_by_pieces with targetm.overlap_op_by_pieces_p (). (op_by_pieces_d::run): Pass the previous RTL information to pieces_addr::adjust and generate overlapping operations if m_overlap_op_by_pieces is true. (PUSHG_P): New. (move_by_pieces_d::move_by_pieces_d): Updated for op_by_pieces_d change. (store_by_pieces_d::store_by_pieces_d): Updated for op_by_pieces_d change. (can_store_by_pieces): Use by_pieces_constfn on constfun. (store_by_pieces): Use by_pieces_constfn on constfun. Updated for op_by_pieces_d change. (clear_by_pieces_1): Add a dummy argument. (clear_by_pieces): Updated for op_by_pieces_d change. (compare_by_pieces_d::compare_by_pieces_d): Likewise. (string_cst_read_str): Add a dummy argument. * expr.h (by_pieces_constfn): Add a dummy argument. (by_pieces_prev): New. * target.def (overlap_op_by_pieces_p): New target hook. * config/i386/i386.c (TARGET_OVERLAP_OP_BY_PIECES_P): New. * doc/tm.texi.in: Add TARGET_OVERLAP_OP_BY_PIECES_P. * doc/tm.texi: Regenerated. gcc/testsuite/ PR middle-end/90773 * g++.dg/pr90773-1.h: New test. * g++.dg/pr90773-1a.C: Likewise. * g++.dg/pr90773-1b.C: Likewise. * g++.dg/pr90773-1c.C: Likewise. * g++.dg/pr90773-1d.C: Likewise. * gcc.target/i386/pr90773-1.c: Likewise. * gcc.target/i386/pr90773-2.c: Likewise. * gcc.target/i386/pr90773-3.c: Likewise. * gcc.target/i386/pr90773-4.c: Likewise. * gcc.target/i386/pr90773-5.c: Likewise. * gcc.target/i386/pr90773-6.c: Likewise. * gcc.target/i386/pr90773-7.c: Likewise. * gcc.target/i386/pr90773-8.c: Likewise. * gcc.target/i386/pr90773-9.c: Likewise. * gcc.target/i386/pr90773-10.c: Likewise. * gcc.target/i386/pr90773-11.c: Likewise. * gcc.target/i386/pr90773-12.c: Likewise. * gcc.target/i386/pr90773-13.c: Likewise. * gcc.target/i386/pr90773-14.c: Likewise. --- gcc/builtins.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'gcc/builtins.h') diff --git a/gcc/builtins.h b/gcc/builtins.h index 307a20f..e71f40c 100644 --- a/gcc/builtins.h +++ b/gcc/builtins.h @@ -110,8 +110,10 @@ extern void expand_builtin_update_setjmp_buf (rtx); extern tree mathfn_built_in (tree, enum built_in_function fn); extern tree mathfn_built_in (tree, combined_fn); extern tree mathfn_built_in_type (combined_fn); -extern rtx builtin_strncpy_read_str (void *, HOST_WIDE_INT, scalar_int_mode); -extern rtx builtin_memset_read_str (void *, HOST_WIDE_INT, scalar_int_mode); +extern rtx builtin_strncpy_read_str (void *, void *, HOST_WIDE_INT, + scalar_int_mode); +extern rtx builtin_memset_read_str (void *, void *, HOST_WIDE_INT, + scalar_int_mode); extern rtx expand_builtin_saveregs (void); extern tree std_build_builtin_va_list (void); extern tree std_fn_abi_va_list (tree); -- cgit v1.1