procyberian/gcc
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

re PR tree-optimization/59617 ([vectorizer] ICE in vectorizable_mask_load_store with AVX-512F's gathers enabled.)

Browse source 
PR target/59617
	* config/i386/i386.c (ix86_vectorize_builtin_gather): Uncomment
	AVX512F gather builtins.
	* tree-vect-stmts.c (vectorizable_mask_load_store): For now punt
	on gather decls with INTEGER_TYPE masktype.
	(vectorizable_load): For INTEGER_TYPE masktype, put the INTEGER_CST
	directly into the builtin rather than hoisting it before loop.

From-SVN: r206585
This commit is contained in:
Jakub Jelinek 2014-01-13 20:16:30 +01:00 • committed by Jakub Jelinek
parent 19e51b409e
commit 03b9e8e48d
3 changed files with 21 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
gcc/ChangeLog
View file

@ -1,5 +1,13 @@
2014-01-13 Jakub Jelinek <jakub@redhat.com>
PR target/59617
* config/i386/i386.c (ix86_vectorize_builtin_gather): Uncomment
AVX512F gather builtins.
* tree-vect-stmts.c (vectorizable_mask_load_store): For now punt
on gather decls with INTEGER_TYPE masktype.
(vectorizable_load): For INTEGER_TYPE masktype, put the INTEGER_CST
directly into the builtin rather than hoisting it before loop.
PR tree-optimization/59387
* tree-scalar-evolution.c: Include gimple-fold.h and gimplify-me.h.
(scev_const_prop): If folded_casts and type has undefined overflow,

4
gcc/config/i386/i386.c
View file

@ -36565,9 +36565,6 @@ ix86_vectorize_builtin_gather (const_tree mem_vectype,
case V8SImode:
code = si ? IX86_BUILTIN_GATHERSIV8SI : IX86_BUILTIN_GATHERALTDIV8SI;
break;
#if 0
/* FIXME: Commented until vectorizer can work with (mask_type != src_type)
PR59617. */
case V8DFmode:
if (TARGET_AVX512F)
code = si ? IX86_BUILTIN_GATHER3ALTSIV8DF : IX86_BUILTIN_GATHER3DIV8DF;
@ -36592,7 +36589,6 @@ ix86_vectorize_builtin_gather (const_tree mem_vectype,
else
return NULL_TREE;
break;
#endif
default:
return NULL_TREE;
}

14
gcc/tree-vect-stmts.c
View file

@ -1813,6 +1813,17 @@ vectorizable_mask_load_store (gimple stmt, gimple_stmt_iterator *gsi,
"gather index use not simple.");
return false;
}
tree arglist = TYPE_ARG_TYPES (TREE_TYPE (gather_decl));
tree masktype
= TREE_VALUE (TREE_CHAIN (TREE_CHAIN (TREE_CHAIN (arglist))));
if (TREE_CODE (masktype) == INTEGER_TYPE)
{
if (dump_enabled_p ())
dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
"masked gather with integer mask not supported.");
return false;
}
}
else if (tree_int_cst_compare (nested_in_vect_loop
? STMT_VINFO_DR_STEP (stmt_info)
@ -5761,6 +5772,7 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
{
mask = build_int_cst (TREE_TYPE (masktype), -1);
mask = build_vector_from_val (masktype, mask);
mask = vect_init_vector (stmt, mask, masktype, NULL);
}
else if (SCALAR_FLOAT_TYPE_P (TREE_TYPE (masktype)))
{
@ -5771,10 +5783,10 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
real_from_target (&r, tmp, TYPE_MODE (TREE_TYPE (masktype)));
mask = build_real (TREE_TYPE (masktype), r);
mask = build_vector_from_val (masktype, mask);
mask = vect_init_vector (stmt, mask, masktype, NULL);
}
else
gcc_unreachable ();
mask = vect_init_vector (stmt, mask, masktype, NULL);
scale = build_int_cst (scaletype, gather_scale);