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

sw-1.c: Force rep;movsb.

Browse source 
* gcc.target/i386/sw-1.c: Force rep;movsb.

        * config/i386/i386.h (processor_costs): Add second dimension to
        stringop_algs array.
        * config/i386/i386.c (cost models): Initialize second dimension of
        stringop_algs arrays.
	(core_cost): New costs based on generic64 costs with updated stringop
	values.
        (promote_duplicated_reg): Add support for vector modes, add
        declaration.
        (promote_duplicated_reg_to_size): Likewise.
	(processor_target): Set core costs for core variants.
        (expand_set_or_movmem_via_loop_with_iter): New function.
        (expand_set_or_movmem_via_loop): Enable reuse of the same iters in
        different loops, produced by this function.
        (emit_strset): New function.
        (expand_movmem_epilogue): Add epilogue generation for bigger sizes,
        use SSE-moves where possible.
        (expand_setmem_epilogue): Likewise.
        (expand_movmem_prologue): Likewise for prologue.
        (expand_setmem_prologue): Likewise.
        (expand_constant_movmem_prologue): Likewise.
        (expand_constant_setmem_prologue): Likewise.
        (decide_alg): Add new argument align_unknown.  Fix algorithm of
        strategy selection if TARGET_INLINE_ALL_STRINGOPS is set; Skip sse_loop
        (decide_alignment): Update desired alignment according to chosen move
        mode.
        (ix86_expand_movmem): Change unrolled_loop strategy to use SSE-moves.
        (ix86_expand_setmem): Likewise.
        (ix86_slow_unaligned_access): Implementation of new hook
        slow_unaligned_access.
        * config/i386/i386.md (strset): Enable half-SSE moves.
        * config/i386/sse.md (vec_dupv4si): Add expand for vec_dupv4si.
        (vec_dupv2di): Add expand for vec_dupv2di.

Co-Authored-By: Jan Hubicka <jh@suse.cz>

From-SVN: r181357
This commit is contained in:
Zolotukhin Michael 2011-11-14 17:28:11 +00:00 • committed by Jan Hubicka
parent f8acdd3c52
commit 38877e9851
12 changed files with 898 additions and 247 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

36
gcc/ChangeLog
View file

@ -1,3 +1,39 @@
2011-11-14 Zolotukhin Michael <michael.v.zolotukhin@gmail.com>
Jan Hubicka <jh@suse.cz>
* config/i386/i386.h (processor_costs): Add second dimension to
stringop_algs array.
* config/i386/i386.c (cost models): Initialize second dimension of
stringop_algs arrays.
(core_cost): New costs based on generic64 costs with updated stringop
values.
(promote_duplicated_reg): Add support for vector modes, add
declaration.
(promote_duplicated_reg_to_size): Likewise.
(processor_target): Set core costs for core variants.
(expand_set_or_movmem_via_loop_with_iter): New function.
(expand_set_or_movmem_via_loop): Enable reuse of the same iters in
different loops, produced by this function.
(emit_strset): New function.
(expand_movmem_epilogue): Add epilogue generation for bigger sizes,
use SSE-moves where possible.
(expand_setmem_epilogue): Likewise.
(expand_movmem_prologue): Likewise for prologue.
(expand_setmem_prologue): Likewise.
(expand_constant_movmem_prologue): Likewise.
(expand_constant_setmem_prologue): Likewise.
(decide_alg): Add new argument align_unknown. Fix algorithm of
strategy selection if TARGET_INLINE_ALL_STRINGOPS is set; Skip sse_loop
(decide_alignment): Update desired alignment according to chosen move
mode.
(ix86_expand_movmem): Change unrolled_loop strategy to use SSE-moves.
(ix86_expand_setmem): Likewise.
(ix86_slow_unaligned_access): Implementation of new hook
slow_unaligned_access.
* config/i386/i386.md (strset): Enable half-SSE moves.
* config/i386/sse.md (vec_dupv4si): Add expand for vec_dupv4si.
(vec_dupv2di): Add expand for vec_dupv2di.
2011-11-14 Dimitrios Apostolou <jimis@gmx.net>
PR bootstrap/51094

2
gcc/cgraph.h
View file

@ -641,6 +641,7 @@ void debug_varpool_node_set (varpool_node_set);
void free_varpool_node_set (varpool_node_set);
void ipa_discover_readonly_nonaddressable_vars (void);
bool cgraph_comdat_can_be_unshared_p (struct cgraph_node *);
bool varpool_externally_visible_p (struct varpool_node *, bool);
/* In predict.c */
bool cgraph_maybe_hot_edge_p (struct cgraph_edge *e);
@ -681,6 +682,7 @@ bool const_value_known_p (tree);
bool varpool_for_node_and_aliases (struct varpool_node *,
bool (*) (struct varpool_node *, void *),
void *, bool);
void varpool_add_new_variable (tree);
/* Walk all reachable static variables. */
#define FOR_EACH_STATIC_VARIABLE(node) \

3
gcc/config/i386/i386-opts.h
View file

@ -37,7 +37,8 @@ enum stringop_alg
rep_prefix_8_byte,
loop_1_byte,
loop,
unrolled_loop
unrolled_loop,
sse_loop
};
/* Available call abi. */

1046
gcc/config/i386/i386.c
View file

File diff suppressed because it is too large Load diff

8
gcc/config/i386/i386.h
View file

@ -159,8 +159,12 @@ struct processor_costs {
const int fchs; /* cost of FCHS instruction. */
const int fsqrt; /* cost of FSQRT instruction. */
/* Specify what algorithm
to use for stringops on unknown size. */
struct stringop_algs memcpy[2], memset[2];
to use for stringops on unknown size.
First index is used to specify whether
alignment is known or not.
Second - to specify whether 32 or 64 bits
are used. */
struct stringop_algs memcpy[2][2], memset[2][2];
const int scalar_stmt_cost; /* Cost of any scalar operation, excluding
load and store. */
const int scalar_load_cost; /* Cost of scalar load. */

3
gcc/config/i386/i386.opt
View file

@ -324,6 +324,9 @@ Enum(stringop_alg) String(loop) Value(loop)
EnumValue
Enum(stringop_alg) String(unrolled_loop) Value(unrolled_loop)
EnumValue
Enum(stringop_alg) String(sse_loop) Value(sse_loop)
mtls-dialect=
Target RejectNegative Joined Var(ix86_tls_dialect) Enum(tls_dialect) Init(TLS_DIALECT_GNU)
Use given thread-local storage dialect

20
gcc/config/i386/sse.md
View file

@ -7501,6 +7501,16 @@
(set_attr "prefix" "maybe_vex,orig,vex,maybe_vex,orig,orig")
(set_attr "mode" "V2SF,TI,TI,TI,V4SF,V2SF")])
(define_expand "vec_dupv4si"
[(set (match_operand:V4SI 0 "register_operand" "")
(vec_duplicate:V4SI
(match_operand:SI 1 "nonimmediate_operand" "")))]
"TARGET_SSE"
{
if (!TARGET_AVX)
operands[1] = force_reg (V4SImode, operands[1]);
})
(define_insn "*vec_dupv4si"
[(set (match_operand:V4SI 0 "register_operand" "=x,x,x")
(vec_duplicate:V4SI
@ -7517,6 +7527,16 @@
(set_attr "prefix" "maybe_vex,vex,orig")
(set_attr "mode" "TI,V4SF,V4SF")])
(define_expand "vec_dupv2di"
[(set (match_operand:V2DI 0 "register_operand" "")
(vec_duplicate:V2DI
(match_operand:DI 1 "nonimmediate_operand" "")))]
"TARGET_SSE"
{
if (!TARGET_AVX)
operands[1] = force_reg (V2DImode, operands[1]);
})
(define_insn "*vec_dupv2di"
[(set (match_operand:V2DI 0 "register_operand" "=x,x,x,x")
(vec_duplicate:V2DI

2
gcc/ipa.c
View file

@ -647,7 +647,7 @@ cgraph_externally_visible_p (struct cgraph_node *node,
/* Return true when variable VNODE should be considered externally visible. */
static bool
bool
varpool_externally_visible_p (struct varpool_node *vnode, bool aliased)
{
if (!DECL_COMDAT (vnode->decl) && !TREE_PUBLIC (vnode->decl))

5
gcc/testsuite/ChangeLog
View file

@ -1,3 +1,8 @@
2011-11-14 Zolotukhin Michael <michael.v.zolotukhin@gmail.com>
Jan Hubicka <jh@suse.cz>
* gcc.target/i386/sw-1.c: Force rep;movsb.
2011-11-14 Iain Sandoe <iains@gcc.gnu.org>
PR testsuite/51059

2
gcc/testsuite/gcc.target/i386/sw-1.c
View file

@ -1,5 +1,5 @@
/* { dg-do compile } */
/* { dg-options "-O2 -fshrink-wrap -fdump-rtl-pro_and_epilogue" } */
/* { dg-options "-O2 -fshrink-wrap -fdump-rtl-pro_and_epilogue -mstringop-strategy=rep_byte" } */
#include <string.h>

4
gcc/tree-emutls.c
View file

@ -262,7 +262,7 @@ get_emutls_init_templ_addr (tree decl)
if (DECL_EXTERNAL (to))
varpool_node (to);
else
varpool_finalize_decl (to);
varpool_add_new_variable (to);
return build_fold_addr_expr (to);
}
@ -334,7 +334,7 @@ new_emutls_decl (tree decl, tree alias_of)
if (DECL_EXTERNAL (to))
varpool_node (to);
else if (!alias_of)
varpool_finalize_decl (to);
varpool_add_new_variable (to);
else
varpool_create_variable_alias (to,
varpool_node_for_asm

14
gcc/varpool.c
View file

@ -414,6 +414,20 @@ varpool_finalize_decl (tree decl)
varpool_assemble_pending_decls ();
}
/* Add the variable DECL to the varpool.
Unlike varpool_finalize_decl function is intended to be used
by middle end and allows insertion of new variable at arbitrary point
of compilation. */
void
varpool_add_new_variable (tree decl)
{
struct varpool_node *node;
varpool_finalize_decl (decl);
node = varpool_node (decl);
if (varpool_externally_visible_p (node, false))
node->externally_visible = true;
}
/* Return variable availability. See cgraph.h for description of individual
return values. */
enum availability