falign-functions=N is too simplistic.
Ingo Molnar ran some tests and it looks on latest x86 CPUs, 64-byte alignment
runs fastest (he tried many other possibilites).
However, developers are less than thrilled by the idea of a slam-dunk 64-byte
aligning everything. Too much waste:
On 05/20/2015 02:47 AM, Linus Torvalds wrote:
> At the same time, I have to admit that I abhor a 64-byte function
> alignment, when we have a fair number of functions that are (much)
> smaller than that.
>
> Is there some way to get gcc to take the size of the function into
> account? Because aligning a 16-byte or 32-byte function on a 64-byte
> alignment is just criminally nasty and wasteful.
This change makes it possible to align function to 64-byte boundaries *IF*
this does not introduce huge amount of padding.
Patch drops forced alignment to 8 if requested alignment is higher than 8:
before the patch, -falign-functions=9 was generating
.p2align 4,,8
.p2align 3
which means: "align to 16 if the skip is 8 bytes or less; else align to 8".
After this change, ".p2align 3" is not emitted.
It is dropped because I ultimately want to do something
like -falign-functions=64,8 - IOW, I want to align functions to 64 bytes,
but only if that generates padding of less than 8 bytes - otherwise I want
*no alignment at all*. The forced ".p2align 3" interferes with that intention.
Testing:
tested that with -falign-functions=N (tried 8, 15, 16, 17...) the alignment
directives are the same before and after the patch.
Tested that -falign-functions=N,N (two equal paramenters) works exactly
like -falign-functions=N.
Index: gcc/common.opt
===================================================================
--- gcc/common.opt (revision 239390)
+++ gcc/common.opt (working copy)
@@ -900,7 +900,7 @@ Common Report Var(align_functions,0) Optimization
Align the start of functions.
falign-functions=
-Common RejectNegative Joined UInteger Var(align_functions)
+Common RejectNegative Joined Var(flag_align_functions)
falign-jumps
Common Report Var(align_jumps,0) Optimization UInteger
@@ -907,7 +907,7 @@ Common Report Var(align_jumps,0) Optimization UInt
Align labels which are only reached by jumping.
falign-jumps=
-Common RejectNegative Joined UInteger Var(align_jumps)
+Common RejectNegative Joined Var(flag_align_jumps)
falign-labels
Common Report Var(align_labels,0) Optimization UInteger
@@ -914,7 +914,7 @@ Common Report Var(align_labels,0) Optimization UIn
Align all labels.
falign-labels=
-Common RejectNegative Joined UInteger Var(align_labels)
+Common RejectNegative Joined Var(flag_align_labels)
falign-loops
Common Report Var(align_loops,0) Optimization UInteger
@@ -921,7 +921,7 @@ Common Report Var(align_loops,0) Optimization UInt
Align the start of loops.
falign-loops=
-Common RejectNegative Joined UInteger Var(align_loops)
+Common RejectNegative Joined Var(flag_align_loops)
fargument-alias
Common Ignore
Index: gcc/config/i386/freebsd.h
===================================================================
--- gcc/config/i386/freebsd.h (revision 239390)
+++ gcc/config/i386/freebsd.h (working copy)
@@ -92,25 +92,17 @@ along with GCC; see the file COPYING3. If not see
/* A C statement to output to the stdio stream FILE an assembler
command to advance the location counter to a multiple of 1<<LOG
- bytes if it is within MAX_SKIP bytes.
+ bytes if it is within MAX_SKIP bytes. */
- This is used to align code labels according to Intel recommendations. */
-
#ifdef HAVE_GAS_MAX_SKIP_P2ALIGN
#undef ASM_OUTPUT_MAX_SKIP_ALIGN
#define ASM_OUTPUT_MAX_SKIP_ALIGN(FILE,LOG,MAX_SKIP) \
do { \
if ((LOG) != 0) { \
- if ((MAX_SKIP) == 0) fprintf ((FILE), "\t.p2align %d\n", (LOG)); \
- else { \
+ if ((MAX_SKIP) == 0 || (MAX_SKIP) >= (1<<(LOG))) \
+ fprintf ((FILE), "\t.p2align %d\n", (LOG)); \
+ else \
fprintf ((FILE), "\t.p2align %d,,%d\n", (LOG), (MAX_SKIP)); \
- /* Make sure that we have at least 8 byte alignment if > 8 byte \
- alignment is preferred. */ \
- if ((LOG) > 3 \
- && (1 << (LOG)) > ((MAX_SKIP) + 1) \
- && (MAX_SKIP) >= 7) \
- fputs ("\t.p2align 3\n", (FILE)); \
- }
\
} \
} while (0)
#endif
Index: gcc/config/i386/gnu-user.h
===================================================================
--- gcc/config/i386/gnu-user.h (revision 239390)
+++ gcc/config/i386/gnu-user.h (working copy)
@@ -94,24 +94,16 @@ along with GCC; see the file COPYING3. If not see
/* A C statement to output to the stdio stream FILE an assembler
command to advance the location counter to a multiple of 1<<LOG
- bytes if it is within MAX_SKIP bytes.
+ bytes if it is within MAX_SKIP bytes. */
- This is used to align code labels according to Intel recommendations. */
-
#ifdef HAVE_GAS_MAX_SKIP_P2ALIGN
#define ASM_OUTPUT_MAX_SKIP_ALIGN(FILE,LOG,MAX_SKIP) \
do { \
if ((LOG) != 0) { \
- if ((MAX_SKIP) == 0) fprintf ((FILE), "\t.p2align %d\n", (LOG)); \
- else { \
+ if ((MAX_SKIP) == 0 || (MAX_SKIP) >= (1<<(LOG))) \
+ fprintf ((FILE), "\t.p2align %d\n", (LOG)); \
+ else \
fprintf ((FILE), "\t.p2align %d,,%d\n", (LOG), (MAX_SKIP)); \
- /* Make sure that we have at least 8 byte alignment if > 8 byte \
- alignment is preferred. */ \
- if ((LOG) > 3 \
- && (1 << (LOG)) > ((MAX_SKIP) + 1) \
- && (MAX_SKIP) >= 7) \
- fputs ("\t.p2align 3\n", (FILE)); \
- }
\
} \
} while (0)
#endif
Index: gcc/config/i386/iamcu.h
===================================================================
--- gcc/config/i386/iamcu.h (revision 239390)
+++ gcc/config/i386/iamcu.h (working copy)
@@ -62,23 +62,15 @@ see the files COPYING3 and COPYING.RUNTIME respect
/* A C statement to output to the stdio stream FILE an assembler
command to advance the location counter to a multiple of 1<<LOG
- bytes if it is within MAX_SKIP bytes.
+ bytes if it is within MAX_SKIP bytes. */
- This is used to align code labels according to Intel recommendations. */
-
#define ASM_OUTPUT_MAX_SKIP_ALIGN(FILE,LOG,MAX_SKIP) \
do { \
if ((LOG) != 0) { \
- if ((MAX_SKIP) == 0) fprintf ((FILE), "\t.p2align %d\n", (LOG)); \
- else { \
+ if ((MAX_SKIP) == 0 || (MAX_SKIP) >= (1<<(LOG))) \
+ fprintf ((FILE), "\t.p2align %d\n", (LOG)); \
+ else \
fprintf ((FILE), "\t.p2align %d,,%d\n", (LOG), (MAX_SKIP)); \
- /* Make sure that we have at least 8 byte alignment if > 8 byte \
- alignment is preferred. */ \
- if ((LOG) > 3 \
- && (1 << (LOG)) > ((MAX_SKIP) + 1) \
- && (MAX_SKIP) >= 7) \
- fputs ("\t.p2align 3\n", (FILE)); \
- }
\
} \
} while (0)
Index: gcc/config/i386/openbsdelf.h
===================================================================
--- gcc/config/i386/openbsdelf.h (revision 239390)
+++ gcc/config/i386/openbsdelf.h (working copy)
@@ -63,24 +63,16 @@ along with GCC; see the file COPYING3. If not see
/* A C statement to output to the stdio stream FILE an assembler
command to advance the location counter to a multiple of 1<<LOG
- bytes if it is within MAX_SKIP bytes.
+ bytes if it is within MAX_SKIP bytes. */
- This is used to align code labels according to Intel recommendations. */
-
#ifdef HAVE_GAS_MAX_SKIP_P2ALIGN
#define ASM_OUTPUT_MAX_SKIP_ALIGN(FILE,LOG,MAX_SKIP) \
do { \
if ((LOG) != 0) { \
- if ((MAX_SKIP) == 0) fprintf ((FILE), "\t.p2align %d\n", (LOG)); \
- else { \
+ if ((MAX_SKIP) == 0 || (MAX_SKIP) >= (1<<(LOG))) \
+ fprintf ((FILE), "\t.p2align %d\n", (LOG)); \
+ else \
fprintf ((FILE), "\t.p2align %d,,%d\n", (LOG), (MAX_SKIP)); \
- /* Make sure that we have at least 8 byte alignment if > 8 byte \
- alignment is preferred. */ \
- if ((LOG) > 3 \
- && (1 << (LOG)) > ((MAX_SKIP) + 1) \
- && (MAX_SKIP) >= 7) \
- fputs ("\t.p2align 3\n", (FILE)); \
- }
\
} \
} while (0)
#endif
Index: gcc/config/i386/x86-64.h
===================================================================
--- gcc/config/i386/x86-64.h (revision 239390)
+++ gcc/config/i386/x86-64.h (working copy)
@@ -65,16 +65,10 @@ see the files COPYING3 and COPYING.RUNTIME respect
#define ASM_OUTPUT_MAX_SKIP_ALIGN(FILE,LOG,MAX_SKIP) \
do { \
if ((LOG) != 0) { \
- if ((MAX_SKIP) == 0) fprintf ((FILE), "\t.p2align %d\n", (LOG)); \
- else { \
+ if ((MAX_SKIP) == 0 || (MAX_SKIP) >= (1<<(LOG))) \
+ fprintf ((FILE), "\t.p2align %d\n", (LOG)); \
+ else \
fprintf ((FILE), "\t.p2align %d,,%d\n", (LOG), (MAX_SKIP)); \
- /* Make sure that we have at least 8 byte alignment if > 8 byte \
- alignment is preferred. */ \
- if ((LOG) > 3 \
- && (1 << (LOG)) > ((MAX_SKIP) + 1) \
- && (MAX_SKIP) >= 7) \
- fputs ("\t.p2align 3\n", (FILE)); \
- }
\
} \
} while (0)
#undef ASM_OUTPUT_MAX_SKIP_PAD
Index: gcc/flags.h
===================================================================
--- gcc/flags.h (revision 239390)
+++ gcc/flags.h (working copy)
@@ -55,6 +55,7 @@ struct target_flag_state {
int x_align_labels_log;
int x_align_labels_max_skip;
int x_align_functions_log;
+ int x_align_functions_max_skip;
/* The excess precision currently in effect. */
enum excess_precision x_flag_excess_precision;
@@ -81,6 +82,8 @@ extern struct target_flag_state *this_target_flag_
(this_target_flag_state->x_align_labels_max_skip)
#define align_functions_log \
(this_target_flag_state->x_align_functions_log)
+#define align_functions_max_skip \
+ (this_target_flag_state->x_align_functions_max_skip)
#define flag_excess_precision \
(this_target_flag_state->x_flag_excess_precision)
Index: gcc/toplev.c
===================================================================
--- gcc/toplev.c (revision 239390)
+++ gcc/toplev.c (working copy)
@@ -1177,29 +1177,58 @@ target_supports_section_anchors_p (void)
return true;
}
+static int
+parse_N_M (int *align, int *maxskip, const char *flag, const char *name)
+{
+ int _align = *align;
+ int _maxskip = *maxskip;
+
+ if (flag)
+ {
+ unsigned int n, m;
+ if (strchr (flag, ','))
+ {
+ if (sscanf (flag, "%u,%u", &n, &m) != 2) goto bad;
+ _maxskip = m;
+ }
+ else
+ {
+ if (sscanf (flag, "%u", &n) != 1) goto bad;
+ _maxskip = n;
+ }
+ _align = n;
+ if (_maxskip > 0)
+ _maxskip--; /* -falign-xyz=N,M means M-1 max bytes of padding, not M */
+ }
+
+normalize:
+ if (_align <= 0)
+ _align = 1;
+ if ((unsigned)_maxskip > (unsigned)_align)
+ _maxskip = _align - 1;
+
+ *align = _align;
+ *maxskip = _maxskip;
+ return floor_log2 (_align * 2 - 1);
+
+bad:
+ error_at (UNKNOWN_LOCATION, "-falign-%s parameter '%s' is bad", name, flag);
+ goto normalize;
+}
+
/* Default the align_* variables to 1 if they're still unset, and
set up the align_*_log variables. */
static void
init_alignments (void)
{
- if (align_loops <= 0)
- align_loops = 1;
- if (align_loops_max_skip > align_loops)
- align_loops_max_skip = align_loops - 1;
- align_loops_log = floor_log2 (align_loops * 2 - 1);
- if (align_jumps <= 0)
- align_jumps = 1;
- if (align_jumps_max_skip > align_jumps)
- align_jumps_max_skip = align_jumps - 1;
- align_jumps_log = floor_log2 (align_jumps * 2 - 1);
- if (align_labels <= 0)
- align_labels = 1;
- align_labels_log = floor_log2 (align_labels * 2 - 1);
- if (align_labels_max_skip > align_labels)
- align_labels_max_skip = align_labels - 1;
- if (align_functions <= 0)
- align_functions = 1;
- align_functions_log = floor_log2 (align_functions * 2 - 1);
+ align_loops_log = parse_N_M (&align_loops, &align_loops_max_skip,
+ flag_align_loops, "loops");
+ align_jumps_log = parse_N_M (&align_jumps, &align_jumps_max_skip,
+ flag_align_jumps, "jumps");
+ align_labels_log = parse_N_M (&align_labels, &align_labels_max_skip,
+ flag_align_labels, "labels");
+ align_functions_log = parse_N_M (&align_functions, &align_functions_max_skip,
+ flag_align_functions, "functions");
}
/* Process the options that have been parsed. */
Index: gcc/varasm.c
===================================================================
--- gcc/varasm.c (revision 239390)
+++ gcc/varasm.c (working copy)
@@ -1790,7 +1790,7 @@ assemble_start_function (tree decl, const char *fn
{
#ifdef ASM_OUTPUT_MAX_SKIP_ALIGN
ASM_OUTPUT_MAX_SKIP_ALIGN (asm_out_file,
- align_functions_log, align_functions - 1);
+ align_functions_log, align_functions_max_skip);
#else
ASM_OUTPUT_ALIGN (asm_out_file, align_functions_log);
#endif
