@@ -966,13 +966,80 @@ align_variable (tree decl, bool dont_out
align = MAX_OFILE_ALIGNMENT;
}
- /* On some machines, it is good to increase alignment sometimes. */
if (! DECL_USER_ALIGN (decl))
{
+#ifdef DATA_ABI_ALIGNMENT
+ unsigned int data_abi_align
+ = DATA_ABI_ALIGNMENT (TREE_TYPE (decl), align);
+ /* For backwards compatibility, don't assume the ABI alignment for
+ TLS variables. */
+ if (! DECL_THREAD_LOCAL_P (decl) || data_abi_align <= BITS_PER_WORD)
+ align = data_abi_align;
+#endif
+
+ /* On some machines, it is good to increase alignment sometimes.
+ But as DECL_ALIGN is used both for actually emitting the variable
+ and for code accessing the variable as guaranteed alignment, we
+ can only increase the alignment if it is a performance optimization
+ if the references to it must bind to the current definition. */
+ if (decl_binds_to_current_def_p (decl))
+ {
+#ifdef DATA_ALIGNMENT
+ unsigned int data_align = DATA_ALIGNMENT (TREE_TYPE (decl), align);
+ /* Don't increase alignment too much for TLS variables - TLS space
+ is too precious. */
+ if (! DECL_THREAD_LOCAL_P (decl) || data_align <= BITS_PER_WORD)
+ align = data_align;
+#endif
+#ifdef CONSTANT_ALIGNMENT
+ if (DECL_INITIAL (decl) != 0
+ && DECL_INITIAL (decl) != error_mark_node)
+ {
+ unsigned int const_align
+ = CONSTANT_ALIGNMENT (DECL_INITIAL (decl), align);
+ /* Don't increase alignment too much for TLS variables - TLS
+ space is too precious. */
+ if (! DECL_THREAD_LOCAL_P (decl) || const_align <= BITS_PER_WORD)
+ align = const_align;
+ }
+#endif
+ }
+ }
+
+ /* Reset the alignment in case we have made it tighter, so we can benefit
+ from it in get_pointer_alignment. */
+ DECL_ALIGN (decl) = align;
+}
+
+/* Return DECL_ALIGN (decl), possibly increased for optimization purposes
+ beyond what align_variable returned. */
+
+static unsigned int
+get_variable_align (tree decl)
+{
+ unsigned int align = DECL_ALIGN (decl);
+
+ /* For user aligned vars or static vars align_variable already did
+ everything. */
+ if (DECL_USER_ALIGN (decl) || !TREE_PUBLIC (decl))
+ return align;
+
+#ifdef DATA_ABI_ALIGNMENT
+ if (DECL_THREAD_LOCAL_P (decl))
+ align = DATA_ABI_ALIGNMENT (TREE_TYPE (decl), align);
+#endif
+
+ /* For decls that bind to the current definition, align_variable
+ did also everything, except for not assuming ABI required alignment
+ of TLS variables. For other vars, increase the alignment here
+ as an optimization. */
+ if (!decl_binds_to_current_def_p (decl))
+ {
+ /* On some machines, it is good to increase alignment sometimes. */
#ifdef DATA_ALIGNMENT
unsigned int data_align = DATA_ALIGNMENT (TREE_TYPE (decl), align);
/* Don't increase alignment too much for TLS variables - TLS space
- is too precious. */
+ is too precious. */
if (! DECL_THREAD_LOCAL_P (decl) || data_align <= BITS_PER_WORD)
align = data_align;
#endif
@@ -986,12 +1053,10 @@ align_variable (tree decl, bool dont_out
if (! DECL_THREAD_LOCAL_P (decl) || const_align <= BITS_PER_WORD)
align = const_align;
}
-#endif
}
+#endif
- /* Reset the alignment in case we have made it tighter, so we can benefit
- from it in get_pointer_alignment. */
- DECL_ALIGN (decl) = align;
+ return align;
}
/* Return the section into which the given VAR_DECL or CONST_DECL
@@ -1043,7 +1108,8 @@ get_variable_section (tree decl, bool pr
return bss_noswitch_section;
}
- return targetm.asm_out.select_section (decl, reloc, DECL_ALIGN (decl));
+ return targetm.asm_out.select_section (decl, reloc,
+ get_variable_align (decl));
}
/* Return the block into which object_block DECL should be placed. */
@@ -1780,7 +1846,8 @@ emit_bss (tree decl ATTRIBUTE_UNUSED,
unsigned HOST_WIDE_INT rounded ATTRIBUTE_UNUSED)
{
#if defined ASM_OUTPUT_ALIGNED_BSS
- ASM_OUTPUT_ALIGNED_BSS (asm_out_file, decl, name, size, DECL_ALIGN (decl));
+ ASM_OUTPUT_ALIGNED_BSS (asm_out_file, decl, name, size,
+ get_variable_align (decl));
return true;
#endif
}
@@ -1796,10 +1863,11 @@ emit_common (tree decl ATTRIBUTE_UNUSED,
{
#if defined ASM_OUTPUT_ALIGNED_DECL_COMMON
ASM_OUTPUT_ALIGNED_DECL_COMMON (asm_out_file, decl, name,
- size, DECL_ALIGN (decl));
+ size, get_variable_align (decl));
return true;
#elif defined ASM_OUTPUT_ALIGNED_COMMON
- ASM_OUTPUT_ALIGNED_COMMON (asm_out_file, name, size, DECL_ALIGN (decl));
+ ASM_OUTPUT_ALIGNED_COMMON (asm_out_file, name, size,
+ get_variable_align (decl));
return true;
#else
ASM_OUTPUT_COMMON (asm_out_file, name, size, rounded);
@@ -1828,7 +1896,8 @@ emit_tls_common (tree decl ATTRIBUTE_UNU
NAME is the name of DECL's SYMBOL_REF. */
static void
-assemble_noswitch_variable (tree decl, const char *name, section *sect)
+assemble_noswitch_variable (tree decl, const char *name, section *sect,
+ unsigned int align)
{
unsigned HOST_WIDE_INT size, rounded;
@@ -1850,7 +1919,7 @@ assemble_noswitch_variable (tree decl, c
* (BIGGEST_ALIGNMENT / BITS_PER_UNIT));
if (!sect->noswitch.callback (decl, name, size, rounded)
- && (unsigned HOST_WIDE_INT) DECL_ALIGN_UNIT (decl) > rounded)
+ && (unsigned HOST_WIDE_INT) (align / BITS_PER_UNIT) > rounded)
warning (0, "requested alignment for %q+D is greater than "
"implemented alignment of %wu", decl, rounded);
}
@@ -1880,7 +1949,7 @@ assemble_variable_contents (tree decl, c
/* Output the actual data. */
output_constant (DECL_INITIAL (decl),
tree_low_cst (DECL_SIZE_UNIT (decl), 1),
- DECL_ALIGN (decl));
+ get_variable_align (decl));
else
/* Leave space for it. */
assemble_zeros (tree_low_cst (DECL_SIZE_UNIT (decl), 1));
@@ -1904,6 +1973,7 @@ assemble_variable (tree decl, int top_le
const char *name;
rtx decl_rtl, symbol;
section *sect;
+ unsigned int align;
bool asan_protected = false;
/* This function is supposed to handle VARIABLES. Ensure we have one. */
@@ -2003,6 +2073,8 @@ assemble_variable (tree decl, int top_le
set_mem_align (decl_rtl, DECL_ALIGN (decl));
+ align = get_variable_align (decl);
+
if (TREE_PUBLIC (decl))
maybe_assemble_visibility (decl);
@@ -2032,12 +2104,12 @@ assemble_variable (tree decl, int top_le
place_block_symbol (symbol);
}
else if (SECTION_STYLE (sect) == SECTION_NOSWITCH)
- assemble_noswitch_variable (decl, name, sect);
+ assemble_noswitch_variable (decl, name, sect, align);
else
{
switch_to_section (sect);
- if (DECL_ALIGN (decl) > BITS_PER_UNIT)
- ASM_OUTPUT_ALIGN (asm_out_file, floor_log2 (DECL_ALIGN_UNIT (decl)));
+ if (align > BITS_PER_UNIT)
+ ASM_OUTPUT_ALIGN (asm_out_file, floor_log2 (align / BITS_PER_UNIT));
assemble_variable_contents (decl, name, dont_output_data);
if (asan_protected)
{
@@ -6967,7 +7039,7 @@ place_block_symbol (rtx symbol)
else
{
decl = SYMBOL_REF_DECL (symbol);
- alignment = DECL_ALIGN (decl);
+ alignment = get_variable_align (decl);
size = tree_low_cst (DECL_SIZE_UNIT (decl), 1);
if (flag_asan && asan_protect_global (decl))
{
@@ -859,7 +859,18 @@ enum target_cpu_default
cause character arrays to be word-aligned so that `strcpy' calls
that copy constants to character arrays can be done inline. */
-#define DATA_ALIGNMENT(TYPE, ALIGN) ix86_data_alignment ((TYPE), (ALIGN))
+#define DATA_ALIGNMENT(TYPE, ALIGN) \
+ ix86_data_alignment ((TYPE), (ALIGN), true)
+
+/* Similar to DATA_ALIGNMENT, but for the cases where the ABI mandates
+ some alignment increase, instead of optimization only purposes. E.g.
+ AMD x86-64 psABI says that variables with array type larger than 15 bytes
+ must be aligned to 16 byte boundaries.
+
+ If this macro is not defined, then ALIGN is used. */
+
+#define DATA_ABI_ALIGNMENT(TYPE, ALIGN) \
+ ix86_data_alignment ((TYPE), (ALIGN), false)
/* If defined, a C expression to compute the alignment for a local
variable. TYPE is the data type, and ALIGN is the alignment that
@@ -207,7 +207,7 @@ extern void init_cumulative_args (CUMULA
#endif /* RTX_CODE */
#ifdef TREE_CODE
-extern int ix86_data_alignment (tree, int);
+extern int ix86_data_alignment (tree, int, bool);
extern unsigned int ix86_local_alignment (tree, enum machine_mode,
unsigned int);
extern unsigned int ix86_minimum_alignment (tree, enum machine_mode,
@@ -25375,11 +25375,12 @@ ix86_constant_alignment (tree exp, int a
instead of that alignment to align the object. */
int
-ix86_data_alignment (tree type, int align)
+ix86_data_alignment (tree type, int align, bool opt)
{
int max_align = optimize_size ? BITS_PER_WORD : MIN (256, MAX_OFILE_ALIGNMENT);
- if (AGGREGATE_TYPE_P (type)
+ if (opt
+ && AGGREGATE_TYPE_P (type)
&& TYPE_SIZE (type)
&& TREE_CODE (TYPE_SIZE (type)) == INTEGER_CST
&& (TREE_INT_CST_LOW (TYPE_SIZE (type)) >= (unsigned) max_align
@@ -25391,14 +25392,17 @@ ix86_data_alignment (tree type, int alig
to 16byte boundary. */
if (TARGET_64BIT)
{
- if (AGGREGATE_TYPE_P (type)
- && TYPE_SIZE (type)
- && TREE_CODE (TYPE_SIZE (type)) == INTEGER_CST
- && (TREE_INT_CST_LOW (TYPE_SIZE (type)) >= 128
- || TREE_INT_CST_HIGH (TYPE_SIZE (type))) && align < 128)
+ if ((opt ? AGGREGATE_TYPE_P (type) : TREE_CODE (type) == ARRAY_TYPE)
+ && TYPE_SIZE (type)
+ && TREE_CODE (TYPE_SIZE (type)) == INTEGER_CST
+ && (TREE_INT_CST_LOW (TYPE_SIZE (type)) >= 128
+ || TREE_INT_CST_HIGH (TYPE_SIZE (type))) && align < 128)
return 128;
}
+ if (!opt)
+ return align;
+
if (TREE_CODE (type) == ARRAY_TYPE)
{
if (TYPE_MODE (TREE_TYPE (type)) == DFmode && align < 64)
@@ -1062,6 +1062,15 @@ arrays to be word-aligned so that @code{
constants to character arrays can be done inline.
@end defmac
+@defmac DATA_ABI_ALIGNMENT (@var{type}, @var{basic-align})
+Similar to @code{DATA_ALIGNMENT}, but for the cases where the ABI mandates
+some alignment increase, instead of optimization only purposes. E.g.@
+AMD x86-64 psABI says that variables with array type larger than 15 bytes
+must be aligned to 16 byte boundaries.
+
+If this macro is not defined, then @var{basic-align} is used.
+@end defmac
+
@defmac CONSTANT_ALIGNMENT (@var{constant}, @var{basic-align})
If defined, a C expression to compute the alignment given to a constant
that is being placed in memory. @var{constant} is the constant and
@@ -1078,6 +1078,15 @@ arrays to be word-aligned so that @code{
constants to character arrays can be done inline.
@end defmac
+@defmac DATA_ABI_ALIGNMENT (@var{type}, @var{basic-align})
+Similar to @code{DATA_ALIGNMENT}, but for the cases where the ABI mandates
+some alignment increase, instead of optimization only purposes. E.g.@
+AMD x86-64 psABI says that variables with array type larger than 15 bytes
+must be aligned to 16 byte boundaries.
+
+If this macro is not defined, then @var{basic-align} is used.
+@end defmac
+
@defmac CONSTANT_ALIGNMENT (@var{constant}, @var{basic-align})
If defined, a C expression to compute the alignment given to a constant
that is being placed in memory. @var{constant} is the constant and
@@ -0,0 +1,25 @@
+/* PR target/56564 */
+/* { dg-do compile { target { fpic && lp64 } } } */
+/* { dg-options "-O3 -fpic -fdump-tree-optimized" } */
+
+struct S { long a, b; } s = { 5, 6 };
+char t[16] = { 7 };
+
+int
+foo (void)
+{
+ return ((__UINTPTR_TYPE__) &s) & 15;
+}
+
+int
+bar (void)
+{
+ return ((__UINTPTR_TYPE__) &t[0]) & 15;
+}
+
+/* { dg-final { scan-tree-dump-times "&s" 1 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "&t" 0 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "return 0" 1 "optimized" } } */
+/* { dg-final { scan-assembler ".align\[ \t]*16\[^:]*\[\n\r]s:" { target { *-*-linux* } } } } */
+/* { dg-final { scan-assembler ".align\[ \t]*16\[^:]*\[\n\r]t:" { target { *-*-linux* } } } } */
+/* { dg-final { cleanup-tree-dump "optimized" } } */
@@ -0,0 +1,25 @@
+/* PR target/56564 */
+/* { dg-do compile { target { *-*-linux* && lp64 } } } */
+/* { dg-options "-O3 -fno-pic -fdump-tree-optimized" } */
+
+struct S { long a, b; } s = { 5, 6 };
+char t[16] = { 7 };
+
+int
+foo (void)
+{
+ return ((__UINTPTR_TYPE__) &s) & 15;
+}
+
+int
+bar (void)
+{
+ return ((__UINTPTR_TYPE__) &t[0]) & 15;
+}
+
+/* { dg-final { scan-tree-dump-times "&s" 0 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "&t" 0 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "return 0" 2 "optimized" } } */
+/* { dg-final { scan-assembler ".align\[ \t]*16\[^:]*\[\n\r]s:" { target { *-*-linux* } } } } */
+/* { dg-final { scan-assembler ".align\[ \t]*16\[^:]*\[\n\r]t:" { target { *-*-linux* } } } } */
+/* { dg-final { cleanup-tree-dump "optimized" } } */
@@ -0,0 +1,28 @@
+/* PR target/56564 */
+/* { dg-do compile { target { fpic && lp64 } } } */
+/* { dg-options "-O3 -fpic -fdump-tree-optimized" } */
+
+__thread struct S { long a, b; } s = { 5, 6 };
+__thread char t[16] = { 7 };
+
+int
+foo (void)
+{
+ return ((__UINTPTR_TYPE__) &s) & 15;
+}
+
+/* For backwards compatibility we don't assume that t must
+ be aligned to 16 bytes, but align it anyway. */
+
+int
+bar (void)
+{
+ return ((__UINTPTR_TYPE__) &t[0]) & 15;
+}
+
+/* { dg-final { scan-tree-dump-times "&s" 1 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "&t" 1 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "return 0" 0 "optimized" } } */
+/* { dg-final { scan-assembler-not ".align\[ \t]*16\[^:]*\[\n\r]s:" { target { *-*-linux* } } } } */
+/* { dg-final { scan-assembler ".align\[ \t]*16\[^:]*\[\n\r]t:" { target { *-*-linux* } } } } */
+/* { dg-final { cleanup-tree-dump "optimized" } } */
@@ -0,0 +1,22 @@
+/* PR target/56564 */
+/* { dg-do compile { target { *-*-linux* && lp64 } } } */
+/* { dg-options "-O3 -fno-pic -fdump-tree-optimized" } */
+
+__thread struct S { long a, b; } s = { 5, 6 };
+__thread char t[16] = { 7 };
+
+int
+foo (void)
+{
+ return ((__UINTPTR_TYPE__) &s) & 15;
+}
+
+int
+bar (void)
+{
+ return ((__UINTPTR_TYPE__) &t[0]) & 15;
+}
+
+/* { dg-final { scan-assembler-not ".align\[ \t]*16\[^:]*\[\n\r]s:" { target { *-*-linux* } } } } */
+/* { dg-final { scan-assembler ".align\[ \t]*16\[^:]*\[\n\r]t:" { target { *-*-linux* } } } } */
+/* { dg-final { cleanup-tree-dump "optimized" } } */
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O3 -dp -mavx -mno-avx256-split-unaligned-load -mno-avx256-split-unaligned-store" } */
+/* { dg-options "-O3 -dp -mavx -mno-avx256-split-unaligned-load -mno-avx256-split-unaligned-store -fno-common" } */
#define N 1024
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O3 -dp -mavx -mavx256-split-unaligned-store" } */
+/* { dg-options "-O3 -dp -mavx -mavx256-split-unaligned-store -fno-common" } */
#define N 1024
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O3 -dp -mavx -mavx256-split-unaligned-store -mtune=generic" } */
+/* { dg-options "-O3 -dp -mavx -mavx256-split-unaligned-store -mtune=generic -fno-common" } */
#define N 1024
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O3 -dp -mavx -mno-avx256-split-unaligned-load -mno-avx256-split-unaligned-store" } */
+/* { dg-options "-O3 -dp -mavx -mno-avx256-split-unaligned-load -mno-avx256-split-unaligned-store -fno-common" } */
#define N 1024
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O3 -ffast-math -mavx -mtune=generic" } */
+/* { dg-options "-O3 -ffast-math -mavx -mtune=generic -fno-common" } */
double a[1024];
@@ -1,6 +1,6 @@
/* { dg-do compile } */
/* { dg-require-effective-target ia32 } */
-/* { dg-options "-O2 -march=pentiumpro -minline-all-stringops" } */
+/* { dg-options "-O2 -march=pentiumpro -minline-all-stringops -fno-common" } */
/* { dg-final { scan-assembler "rep" } } */
/* { dg-final { scan-assembler "movs" } } */
/* { dg-final { scan-assembler-not "test" } } */
@@ -18,7 +18,7 @@ struct s{
struct t e; /* unaligned (offset 2N+4N+4 B) */
};
-struct s tmp;
+struct s tmp = { 1 };
int main1 ()
{
@@ -18,7 +18,7 @@ struct s{
struct t e; /* unaligned (offset 2N+4N+4 B) */
};
-struct s tmp;
+struct s tmp = { 1 };
int main1 ()
{