On Mon, 24 Oct 2011, Jakub Jelinek wrote: > On Mon, Oct 24, 2011 at 04:09:49PM +0200, Richard Guenther wrote: > > This one bootstraps and regtests fine on x86_64-unknown-linux-gnu. > > I didn't find a good pattern to split out, eventually how we call > > the vectorizable_* routines should be re-factored a bit. > > Here is an updated patch on top of what you've checked in. > I kept the explicit listing of what tree codes are allowed in > vectorizable_store, rather than using handled_component_p, because > we don't handle stuff like BIT_FIELD_REF and unlikely ARRAY_RANGE_REF. > And I have kept the useless_type_conversion_p check and changed > build_nonstandard_integer_type in the two helper routines, so that > for char/signed char/unsigned char comparisons there is no cast needed. > > Is this ok if it passes bootstrap/regtest?
Yes. Thanks, RIchard. > 2011-10-24 Jakub Jelinek <ja...@redhat.com> > > PR tree-optimization/50596 > * tree-vect-stmts.c (vect_mark_relevant): Only use > FOR_EACH_IMM_USE_FAST if lhs is SSA_NAME. > (vectorizable_store): If is_pattern_stmt_p look through > VIEW_CONVERT_EXPR on lhs. > * tree-vect-patterns.c (check_bool_pattern, adjust_bool_pattern): > Use unsigned type instead of signed. > (vect_recog_bool_pattern): Optimize also stores into bool memory in > addition to casts from bool to integral types. > (vect_mark_pattern_stmts): If pattern_stmt already has vinfo > created, don't create it again. > > * gcc.dg/vect/vect-cond-10.c: New test. > > --- gcc/tree-vect-stmts.c.jj 2011-10-24 17:48:26.000000000 +0200 > +++ gcc/tree-vect-stmts.c 2011-10-24 17:57:39.000000000 +0200 > @@ -159,19 +159,20 @@ vect_mark_relevant (VEC(gimple,heap) **w > /* This use is out of pattern use, if LHS has other uses that are > pattern uses, we should mark the stmt itself, and not the > pattern > stmt. */ > - FOR_EACH_IMM_USE_FAST (use_p, imm_iter, lhs) > - { > - if (is_gimple_debug (USE_STMT (use_p))) > - continue; > - use_stmt = USE_STMT (use_p); > + if (TREE_CODE (lhs) == SSA_NAME) > + FOR_EACH_IMM_USE_FAST (use_p, imm_iter, lhs) > + { > + if (is_gimple_debug (USE_STMT (use_p))) > + continue; > + use_stmt = USE_STMT (use_p); > > - if (vinfo_for_stmt (use_stmt) > - && STMT_VINFO_IN_PATTERN_P (vinfo_for_stmt (use_stmt))) > - { > - found = true; > - break; > - } > - } > + if (vinfo_for_stmt (use_stmt) > + && STMT_VINFO_IN_PATTERN_P (vinfo_for_stmt (use_stmt))) > + { > + found = true; > + break; > + } > + } > } > > if (!found) > @@ -3722,6 +3723,9 @@ vectorizable_store (gimple stmt, gimple_ > return false; > > scalar_dest = gimple_assign_lhs (stmt); > + if (TREE_CODE (scalar_dest) == VIEW_CONVERT_EXPR > + && is_pattern_stmt_p (stmt_info)) > + scalar_dest = TREE_OPERAND (scalar_dest, 0); > if (TREE_CODE (scalar_dest) != ARRAY_REF > && TREE_CODE (scalar_dest) != INDIRECT_REF > && TREE_CODE (scalar_dest) != COMPONENT_REF > --- gcc/tree-vect-patterns.c.jj 2011-10-24 12:21:14.000000000 +0200 > +++ gcc/tree-vect-patterns.c 2011-10-24 17:57:39.000000000 +0200 > @@ -1617,7 +1617,7 @@ check_bool_pattern (tree var, loop_vec_i > { > enum machine_mode mode = TYPE_MODE (TREE_TYPE (rhs1)); > tree itype > - = build_nonstandard_integer_type (GET_MODE_BITSIZE (mode), 0); > + = build_nonstandard_integer_type (GET_MODE_BITSIZE (mode), 1); > vecitype = get_vectype_for_scalar_type (itype); > if (vecitype == NULL_TREE) > return false; > @@ -1813,11 +1813,11 @@ adjust_bool_pattern (tree var, tree out_ > default: > gcc_assert (TREE_CODE_CLASS (rhs_code) == tcc_comparison); > if (TREE_CODE (TREE_TYPE (rhs1)) != INTEGER_TYPE > - || TYPE_UNSIGNED (TREE_TYPE (rhs1))) > + || !TYPE_UNSIGNED (TREE_TYPE (rhs1))) > { > enum machine_mode mode = TYPE_MODE (TREE_TYPE (rhs1)); > itype > - = build_nonstandard_integer_type (GET_MODE_BITSIZE (mode), 0); > + = build_nonstandard_integer_type (GET_MODE_BITSIZE (mode), 1); > } > else > itype = TREE_TYPE (rhs1); > @@ -1933,6 +1933,44 @@ vect_recog_bool_pattern (VEC (gimple, he > VEC_safe_push (gimple, heap, *stmts, last_stmt); > return pattern_stmt; > } > + else if (rhs_code == SSA_NAME > + && STMT_VINFO_DATA_REF (stmt_vinfo)) > + { > + stmt_vec_info pattern_stmt_info; > + vectype = STMT_VINFO_VECTYPE (stmt_vinfo); > + gcc_assert (vectype != NULL_TREE); > + if (!check_bool_pattern (var, loop_vinfo)) > + return NULL; > + > + rhs = adjust_bool_pattern (var, TREE_TYPE (vectype), NULL_TREE, stmts); > + lhs = build1 (VIEW_CONVERT_EXPR, TREE_TYPE (vectype), lhs); > + if (!useless_type_conversion_p (TREE_TYPE (lhs), TREE_TYPE (rhs))) > + { > + tree rhs2 = vect_recog_temp_ssa_var (TREE_TYPE (lhs), NULL); > + gimple cast_stmt > + = gimple_build_assign_with_ops (NOP_EXPR, rhs2, rhs, NULL_TREE); > + STMT_VINFO_PATTERN_DEF_STMT (stmt_vinfo) = cast_stmt; > + rhs = rhs2; > + } > + pattern_stmt > + = gimple_build_assign_with_ops (SSA_NAME, lhs, rhs, NULL_TREE); > + pattern_stmt_info = new_stmt_vec_info (pattern_stmt, loop_vinfo, NULL); > + set_vinfo_for_stmt (pattern_stmt, pattern_stmt_info); > + STMT_VINFO_DATA_REF (pattern_stmt_info) > + = STMT_VINFO_DATA_REF (stmt_vinfo); > + STMT_VINFO_DR_BASE_ADDRESS (pattern_stmt_info) > + = STMT_VINFO_DR_BASE_ADDRESS (stmt_vinfo); > + STMT_VINFO_DR_INIT (pattern_stmt_info) = STMT_VINFO_DR_INIT > (stmt_vinfo); > + STMT_VINFO_DR_OFFSET (pattern_stmt_info) > + = STMT_VINFO_DR_OFFSET (stmt_vinfo); > + STMT_VINFO_DR_STEP (pattern_stmt_info) = STMT_VINFO_DR_STEP > (stmt_vinfo); > + STMT_VINFO_DR_ALIGNED_TO (pattern_stmt_info) > + = STMT_VINFO_DR_ALIGNED_TO (stmt_vinfo); > + *type_out = vectype; > + *type_in = vectype; > + VEC_safe_push (gimple, heap, *stmts, last_stmt); > + return pattern_stmt; > + } > else > return NULL; > } > @@ -1949,19 +1987,22 @@ vect_mark_pattern_stmts (gimple orig_stm > loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (orig_stmt_info); > gimple def_stmt; > > - set_vinfo_for_stmt (pattern_stmt, > - new_stmt_vec_info (pattern_stmt, loop_vinfo, NULL)); > - gimple_set_bb (pattern_stmt, gimple_bb (orig_stmt)); > pattern_stmt_info = vinfo_for_stmt (pattern_stmt); > + if (pattern_stmt_info == NULL) > + { > + pattern_stmt_info = new_stmt_vec_info (pattern_stmt, loop_vinfo, NULL); > + set_vinfo_for_stmt (pattern_stmt, pattern_stmt_info); > + } > + gimple_set_bb (pattern_stmt, gimple_bb (orig_stmt)); > > STMT_VINFO_RELATED_STMT (pattern_stmt_info) = orig_stmt; > STMT_VINFO_DEF_TYPE (pattern_stmt_info) > - = STMT_VINFO_DEF_TYPE (orig_stmt_info); > + = STMT_VINFO_DEF_TYPE (orig_stmt_info); > STMT_VINFO_VECTYPE (pattern_stmt_info) = pattern_vectype; > STMT_VINFO_IN_PATTERN_P (orig_stmt_info) = true; > STMT_VINFO_RELATED_STMT (orig_stmt_info) = pattern_stmt; > STMT_VINFO_PATTERN_DEF_STMT (pattern_stmt_info) > - = STMT_VINFO_PATTERN_DEF_STMT (orig_stmt_info); > + = STMT_VINFO_PATTERN_DEF_STMT (orig_stmt_info); > if (STMT_VINFO_PATTERN_DEF_STMT (pattern_stmt_info)) > { > def_stmt = STMT_VINFO_PATTERN_DEF_STMT (pattern_stmt_info); > --- gcc/testsuite/gcc.dg/vect/vect-cond-10.c.jj 2011-10-24 > 17:52:16.000000000 +0200 > +++ gcc/testsuite/gcc.dg/vect/vect-cond-10.c 2011-10-24 17:52:16.000000000 > +0200 > @@ -0,0 +1,165 @@ > +/* { dg-require-effective-target vect_cond_mixed } */ > + > +#include "tree-vect.h" > + > +#define N 1024 > +float a[N], b[N], c[N], d[N]; > +_Bool k[N]; > + > +__attribute__((noinline, noclone)) void > +f1 (void) > +{ > + int i; > + for (i = 0; i < N; ++i) > + { > + int x = a[i] < b[i]; > + int y = c[i] < d[i]; > + k[i] = x & y; > + } > +} > + > +__attribute__((noinline, noclone)) void > +f2 (void) > +{ > + int i; > + for (i = 0; i < N; ++i) > + k[i] = (a[i] < b[i]) & (c[i] < d[i]); > +} > + > +__attribute__((noinline, noclone)) void > +f3 (void) > +{ > + int i; > + for (i = 0; i < N; ++i) > + { > + int x = a[i] < b[i]; > + int y = c[i] < d[i]; > + k[i] = x | y; > + } > +} > + > +__attribute__((noinline, noclone)) void > +f4 (void) > +{ > + int i; > + for (i = 0; i < N; ++i) > + k[i] = (a[i] < b[i]) | (c[i] < d[i]); > +} > + > +__attribute__((noinline, noclone)) void > +f5 (_Bool *p) > +{ > + int i; > + for (i = 0; i < N; ++i) > + { > + int x = a[i] < b[i]; > + int y = c[i] < d[i]; > + p[i] = x & y; > + } > +} > + > +__attribute__((noinline, noclone)) void > +f6 (_Bool *p) > +{ > + int i; > + for (i = 0; i < N; ++i) > + p[i] = (a[i] < b[i]) & (c[i] < d[i]); > +} > + > +__attribute__((noinline, noclone)) void > +f7 (_Bool *p) > +{ > + int i; > + for (i = 0; i < N; ++i) > + { > + int x = a[i] < b[i]; > + int y = c[i] < d[i]; > + p[i] = x | y; > + } > +} > + > +__attribute__((noinline, noclone)) void > +f8 (_Bool *p) > +{ > + int i; > + for (i = 0; i < N; ++i) > + p[i] = (a[i] < b[i]) | (c[i] < d[i]); > +} > + > +int > +main () > +{ > + int i; > + > + check_vect (); > + > + for (i = 0; i < N; i++) > + { > + switch (i % 9) > + { > + case 0: asm (""); a[i] = - i - 1; b[i] = i + 1; break; > + case 1: a[i] = 0; b[i] = 0; break; > + case 2: a[i] = i + 1; b[i] = - i - 1; break; > + case 3: a[i] = i; b[i] = i + 7; break; > + case 4: a[i] = i; b[i] = i; break; > + case 5: a[i] = i + 16; b[i] = i + 3; break; > + case 6: a[i] = - i - 5; b[i] = - i; break; > + case 7: a[i] = - i; b[i] = - i; break; > + case 8: a[i] = - i; b[i] = - i - 7; break; > + } > + } > + for (i = 0; i < N; i++) > + { > + switch ((i / 9) % 3) > + { > + case 0: c[i] = a[i / 9]; d[i] = b[i / 9]; break; > + case 1: c[i] = a[i / 9 + 3]; d[i] = b[i / 9 + 3]; break; > + case 2: c[i] = a[i / 9 + 6]; d[i] = b[i / 9 + 6]; break; > + } > + } > + f1 (); > + for (i = 0; i < N; i++) > + if (k[i] != ((i % 3) == 0 && ((i / 9) % 3) == 0)) > + abort (); > + __builtin_memset (k, 0, sizeof (k)); > + f2 (); > + for (i = 0; i < N; i++) > + if (k[i] != ((i % 3) == 0 && ((i / 9) % 3) == 0)) > + abort (); > + __builtin_memset (k, 0, sizeof (k)); > + f3 (); > + for (i = 0; i < N; i++) > + if (k[i] != ((i % 3) == 0 || ((i / 9) % 3) == 0)) > + abort (); > + __builtin_memset (k, 0, sizeof (k)); > + f4 (); > + for (i = 0; i < N; i++) > + if (k[i] != ((i % 3) == 0 || ((i / 9) % 3) == 0)) > + abort (); > + __builtin_memset (k, 0, sizeof (k)); > + f5 (k); > + for (i = 0; i < N; i++) > + if (k[i] != ((i % 3) == 0 && ((i / 9) % 3) == 0)) > + abort (); > + __builtin_memset (k, 0, sizeof (k)); > + f6 (k); > + for (i = 0; i < N; i++) > + if (k[i] != ((i % 3) == 0 && ((i / 9) % 3) == 0)) > + abort (); > + __builtin_memset (k, 0, sizeof (k)); > + f7 (k); > + for (i = 0; i < N; i++) > + if (k[i] != ((i % 3) == 0 || ((i / 9) % 3) == 0)) > + abort (); > + __builtin_memset (k, 0, sizeof (k)); > + f8 (k); > + for (i = 0; i < N; i++) > + if (k[i] != ((i % 3) == 0 || ((i / 9) % 3) == 0)) > + abort (); > + __builtin_memset (k, 0, sizeof (k)); > + > + return 0; > +} > + > +/* { dg-final { scan-tree-dump-times "note: vectorized 1 loops" 8 "vect" } } > */ > +/* { dg-final { cleanup-tree-dump "vect" } } */ > > > Jakub > > -- Richard Guenther <rguent...@suse.de> SUSE / SUSE Labs SUSE LINUX Products GmbH - Nuernberg - AG Nuernberg - HRB 16746 GF: Jeff Hawn, Jennifer Guild, Felix Imendörffer