Hello.
During compilation of Chromium project, I noticed (perf top) that
ix86_valid_target_attribute is utilized by about 0.8-1.9%.
Following patch introduces simple optimization that reduces the utilization to
~0.05%.
Tests have been running on x86_64-linux-pc.
Ready for trunk?
Martin
>From d20232455993882e4b7f769725a0c1589747b8a3 Mon Sep 17 00:00:00 2001
From: marxin <marxin.li...@gmail.com>
Date: Sun, 8 Mar 2015 19:39:55 -0500
Subject: [PATCH] def_builtin_const: speed-up.
gcc/ChangeLog:
2015-03-09 Martin Liska <marxin.li...@gmail.com>
* config/i386/i386.c (def_builtin): Collect union of all
possible masks.
(ix86_add_new_builtins): Do not iterate over all builtins
in cases that isa value has no intersection with possible masks
and(or) last passed value is equal to the provided.
---
gcc/config/i386/i386.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index ab8f03a..5f180b6 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -30592,6 +30592,8 @@ struct builtin_isa {
static struct builtin_isa ix86_builtins_isa[(int) IX86_BUILTIN_MAX];
+/* Union of all masks that are part of builtin_isa structures. */
+static HOST_WIDE_INT defined_isa_values = 0;
/* Add an ix86 target builtin function with CODE, NAME and TYPE. Save the MASK
of which isa_flags to use in the ix86_builtins_isa array. Stores the
@@ -30619,6 +30621,7 @@ def_builtin (HOST_WIDE_INT mask, const char *name,
if (!(mask & OPTION_MASK_ISA_64BIT) || TARGET_64BIT)
{
ix86_builtins_isa[(int) code].isa = mask;
+ defined_isa_values |= mask;
mask &= ~OPTION_MASK_ISA_64BIT;
if (mask == 0
@@ -30670,6 +30673,14 @@ def_builtin_const (HOST_WIDE_INT mask, const char *name,
static void
ix86_add_new_builtins (HOST_WIDE_INT isa)
{
+ /* Last cached isa value. */
+ static HOST_WIDE_INT last_tested_isa_value = 0;
+
+ if ((isa & defined_isa_values) == 0 || isa == last_tested_isa_value)
+ return;
+
+ last_tested_isa_value = isa;
+
int i;
tree saved_current_target_pragma = current_target_pragma;
current_target_pragma = NULL_TREE;
--
2.1.2
