From 92e29a5e86c8adc88ee17a483d7284d7bb9e090c Mon Sep 17 00:00:00 2001 From: Richard Biener Date: Fri, 28 Jul 2017 11:27:45 +0000 Subject: [PATCH] re PR middle-end/81502 (In some cases the data is moved to memory unnecessarily [partial regression]) 2017-07-28 Richard Biener PR tree-optimization/81502 * match.pd: Add pattern combining BIT_INSERT_EXPR with BIT_FIELD_REF. * tree-cfg.c (verify_expr): Verify types of BIT_FIELD_REF size/pos operands. (verify_gimple_assign_ternary): Likewise for BIT_INSERT_EXPR pos. * gimple-fold.c (maybe_canonicalize_mem_ref_addr): Use bitsizetype for BIT_FIELD_REF args. * fold-const.c (make_bit_field_ref): Likewise. * tree-vect-stmts.c (vectorizable_simd_clone_call): Likewise. * gcc.target/i386/pr81502.c: New testcase. From-SVN: r250659 --- gcc/ChangeLog | 13 ++++++++++ gcc/fold-const.c | 2 +- gcc/gimple-fold.c | 2 +- gcc/match.pd | 22 ++++++++++++++++ gcc/testsuite/ChangeLog | 5 ++++ gcc/testsuite/gcc.target/i386/pr81502.c | 34 +++++++++++++++++++++++++ gcc/tree-cfg.c | 5 +++- gcc/tree-vect-stmts.c | 4 +-- 8 files changed, 82 insertions(+), 5 deletions(-) create mode 100644 gcc/testsuite/gcc.target/i386/pr81502.c diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 61d389e541d..964fa1cdc9c 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,16 @@ +2017-07-28 Richard Biener + + PR tree-optimization/81502 + * match.pd: Add pattern combining BIT_INSERT_EXPR with + BIT_FIELD_REF. + * tree-cfg.c (verify_expr): Verify types of BIT_FIELD_REF + size/pos operands. + (verify_gimple_assign_ternary): Likewise for BIT_INSERT_EXPR pos. + * gimple-fold.c (maybe_canonicalize_mem_ref_addr): Use bitsizetype + for BIT_FIELD_REF args. + * fold-const.c (make_bit_field_ref): Likewise. + * tree-vect-stmts.c (vectorizable_simd_clone_call): Likewise. + 2017-07-28 Jakub Jelinek PR sanitizer/80998 diff --git a/gcc/fold-const.c b/gcc/fold-const.c index d40b9aaaeb4..ae946596528 100644 --- a/gcc/fold-const.c +++ b/gcc/fold-const.c @@ -3936,7 +3936,7 @@ make_bit_field_ref (location_t loc, tree inner, tree orig_inner, tree type, bftype = build_nonstandard_integer_type (bitsize, 0); result = build3_loc (loc, BIT_FIELD_REF, bftype, inner, - size_int (bitsize), bitsize_int (bitpos)); + bitsize_int (bitsize), bitsize_int (bitpos)); REF_REVERSE_STORAGE_ORDER (result) = reversep; if (bftype != type) diff --git a/gcc/gimple-fold.c b/gcc/gimple-fold.c index d94dc9cd563..d82d0606cbe 100644 --- a/gcc/gimple-fold.c +++ b/gcc/gimple-fold.c @@ -4245,7 +4245,7 @@ maybe_canonicalize_mem_ref_addr (tree *t) TREE_TYPE (*t), TREE_OPERAND (TREE_OPERAND (*t, 0), 0), TYPE_SIZE (TREE_TYPE (*t)), - wide_int_to_tree (sizetype, idx)); + wide_int_to_tree (bitsizetype, idx)); res = true; } } diff --git a/gcc/match.pd b/gcc/match.pd index 732b80c04bf..60f262d5926 100644 --- a/gcc/match.pd +++ b/gcc/match.pd @@ -4178,3 +4178,25 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) { CONSTRUCTOR_ELT (ctor, idx / k)->value; }) (BIT_FIELD_REF { CONSTRUCTOR_ELT (ctor, idx / k)->value; } @1 { bitsize_int ((idx % k) * width); }))))))))) + +/* Simplify a bit extraction from a bit insertion for the cases with + the inserted element fully covering the extraction or the insertion + not touching the extraction. */ +(simplify + (BIT_FIELD_REF (bit_insert @0 @1 @ipos) @rsize @rpos) + (with + { + unsigned HOST_WIDE_INT isize; + if (INTEGRAL_TYPE_P (TREE_TYPE (@1))) + isize = TYPE_PRECISION (TREE_TYPE (@1)); + else + isize = tree_to_uhwi (TYPE_SIZE (TREE_TYPE (@1))); + } + (switch + (if (wi::leu_p (@ipos, @rpos) + && wi::leu_p (wi::add (@rpos, @rsize), wi::add (@ipos, isize))) + (BIT_FIELD_REF @1 @rsize { wide_int_to_tree (bitsizetype, + wi::sub (@rpos, @ipos)); })) + (if (wi::geu_p (@ipos, wi::add (@rpos, @rsize)) + || wi::geu_p (@rpos, wi::add (@ipos, isize))) + (BIT_FIELD_REF @0 @rsize @rpos))))) diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog index 5c41f438537..396f0b1fa98 100644 --- a/gcc/testsuite/ChangeLog +++ b/gcc/testsuite/ChangeLog @@ -1,3 +1,8 @@ +2017-07-28 Richard Biener + + PR tree-optimization/81502 + * gcc.target/i386/pr81502.c: New testcase. + 2017-07-28 Martin Liska PR sanitizer/81460 diff --git a/gcc/testsuite/gcc.target/i386/pr81502.c b/gcc/testsuite/gcc.target/i386/pr81502.c new file mode 100644 index 00000000000..d28791aacd7 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr81502.c @@ -0,0 +1,34 @@ +/* { dg-do compile { target lp64 } } */ +/* { dg-options "-O2 -msse2" } */ + +#include + +#define SIZE (sizeof (void *)) + +static int foo(unsigned char (*foo)[SIZE]) +{ + __m128i acc = _mm_set_epi32(0, 0, 0, 0); + size_t i = 0; + for(; i + sizeof(__m128i) <= SIZE; i += sizeof(__m128i)) { + __m128i word; + __builtin_memcpy(&word, foo + i, sizeof(__m128i)); + acc = _mm_add_epi32(word, acc); + } + if (i != SIZE) { + __m128i word = _mm_set_epi32(0, 0, 0, 0); + __builtin_memcpy(&word, foo + i, SIZE - i); // (1) + acc = _mm_add_epi32(word, acc); + } + int res; + __builtin_memcpy(&res, &acc, sizeof(res)); + return res; +} + +int bar(void *ptr) +{ + unsigned char buf[SIZE]; + __builtin_memcpy(buf, &ptr, SIZE); + return foo((unsigned char(*)[SIZE])buf); +} + +/* { dg-final { scan-assembler-times "mov" 1 } } */ diff --git a/gcc/tree-cfg.c b/gcc/tree-cfg.c index f664ffe119a..733c92fcdd0 100644 --- a/gcc/tree-cfg.c +++ b/gcc/tree-cfg.c @@ -3054,7 +3054,9 @@ verify_expr (tree *tp, int *walk_subtrees, void *data ATTRIBUTE_UNUSED) tree t1 = TREE_OPERAND (t, 1); tree t2 = TREE_OPERAND (t, 2); if (!tree_fits_uhwi_p (t1) - || !tree_fits_uhwi_p (t2)) + || !tree_fits_uhwi_p (t2) + || !types_compatible_p (bitsizetype, TREE_TYPE (t1)) + || !types_compatible_p (bitsizetype, TREE_TYPE (t2))) { error ("invalid position or size operand to BIT_FIELD_REF"); return t; @@ -4248,6 +4250,7 @@ verify_gimple_assign_ternary (gassign *stmt) return true; } if (! tree_fits_uhwi_p (rhs3) + || ! types_compatible_p (bitsizetype, TREE_TYPE (rhs3)) || ! tree_fits_uhwi_p (TYPE_SIZE (rhs2_type))) { error ("invalid position or size in BIT_INSERT_EXPR"); diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c index 8a631046cc8..18dd1a4df32 100644 --- a/gcc/tree-vect-stmts.c +++ b/gcc/tree-vect-stmts.c @@ -3531,7 +3531,7 @@ vectorizable_simd_clone_call (gimple *stmt, gimple_stmt_iterator *gsi, arginfo[i].op = vec_oprnd0; vec_oprnd0 = build3 (BIT_FIELD_REF, atype, vec_oprnd0, - size_int (prec), + bitsize_int (prec), bitsize_int ((m & (k - 1)) * prec)); new_stmt = gimple_build_assign (make_ssa_name (atype), @@ -3692,7 +3692,7 @@ vectorizable_simd_clone_call (gimple *stmt, gimple_stmt_iterator *gsi, } else t = build3 (BIT_FIELD_REF, vectype, new_temp, - size_int (prec), bitsize_int (l * prec)); + bitsize_int (prec), bitsize_int (l * prec)); new_stmt = gimple_build_assign (make_ssa_name (vectype), t); vect_finish_stmt_generation (stmt, new_stmt, gsi); -- 2.30.2