Add -fmin-function-alignmnet

-falign-functions is ignored in cold code, since it is an optimization intended to
improve instruction prefetch.  In some case it is necessary to force alignment for
all functions, so this patch adds -fmin-function-alignment for this purpose.

gcc/ChangeLog:

	PR middle-end/88345
	* common.opt: (flimit-function-alignment): Reorder alphabeticaly
	(fmin-function-alignment): New parameter.
	* doc/invoke.texi: (-fmin-function-alignment): Document.
	(-falign-functions,-falign-loops,-falign-labels): Mention that
	aglinments are ignored in cold code.
	* varasm.cc (assemble_start_function): Handle min-function-alignment.

diff --git a/gcc/common.opt b/gcc/common.opt
index 7dc380cc153d45d905b113a21198e0dd6a1539e3..51c4a17da83bf2adb57b92414bb26f36ca5dc27c 100644 (file)
--- a/gcc/common.opt
+++ b/gcc/common.opt
@@ -1040,9 +1040,6 @@ Align the start of functions.
 falign-functions=
 Common RejectNegative Joined Var(str_align_functions) Optimization
 
-flimit-function-alignment
-Common Var(flag_limit_function_alignment) Optimization Init(0)
-
 falign-jumps
 Common Var(flag_align_jumps) Optimization
 Align labels which are only reached by jumping.
@@ -2277,6 +2274,10 @@ fmessage-length=
 Common RejectNegative Joined UInteger
 -fmessage-length=<number>      Limit diagnostics to <number> characters per line.  0 suppresses line-wrapping.
 
+fmin-function-alignment=
+Common Joined RejectNegative UInteger Var(flag_min_function_alignment) Optimization
+Align the start of every function.
+
 fmodulo-sched
 Common Var(flag_modulo_sched) Optimization
 Perform SMS based modulo scheduling before the first scheduling pass.
@@ -2601,6 +2602,9 @@ starts and when the destructor finishes.
 flifetime-dse=
 Common Joined RejectNegative UInteger Var(flag_lifetime_dse) Optimization IntegerRange(0, 2)
 
+flimit-function-alignment
+Common Var(flag_limit_function_alignment) Optimization Init(0)
+
 flive-patching
 Common RejectNegative Alias(flive-patching=,inline-clone) Optimization
 

diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 5f904cf1ef2e4ded6a7ac7b77111feebc4d24dcc..6ec56493e59c88886c1af4cf03f115e7e8ff4615 100644 (file)
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -547,6 +547,7 @@ Objective-C and Objective-C++ Dialects}.
 -falign-jumps[=@var{n}[:@var{m}:[@var{n2}[:@var{m2}]]]]
 -falign-labels[=@var{n}[:@var{m}:[@var{n2}[:@var{m2}]]]]
 -falign-loops[=@var{n}[:@var{m}:[@var{n2}[:@var{m2}]]]]
+-fmin-function-alignment=[@var{n}]
 -fno-allocation-dce -fallow-store-data-races
 -fassociative-math  -fauto-profile  -fauto-profile[=@var{path}]
 -fauto-inc-dec  -fbranch-probabilities
@@ -14234,6 +14235,9 @@ Align the start of functions to the next power-of-two greater than or
 equal to @var{n}, skipping up to @var{m}-1 bytes.  This ensures that at
 least the first @var{m} bytes of the function can be fetched by the CPU
 without crossing an @var{n}-byte alignment boundary.
+This is an optimization of code performance and alignment is ignored for
+functions considered cold.  If alignment is required for all functions,
+use @option{-fmin-function-alignment}.
 
 If @var{m} is not specified, it defaults to @var{n}.
 
@@ -14297,6 +14301,8 @@ Enabled at levels @option{-O2}, @option{-O3}.
 Align loops to a power-of-two boundary.  If the loops are executed
 many times, this makes up for any execution of the dummy padding
 instructions.
+This is an optimization of code performance and alignment is ignored for
+loops considered cold.
 
 If @option{-falign-labels} is greater than this value, then its value
 is used instead.
@@ -14319,6 +14325,8 @@ Enabled at levels @option{-O2}, @option{-O3}.
 Align branch targets to a power-of-two boundary, for branch targets
 where the targets can only be reached by jumping.  In this case,
 no dummy operations need be executed.
+This is an optimization of code performance and alignment is ignored for
+jumps considered cold.
 
 If @option{-falign-labels} is greater than this value, then its value
 is used instead.
@@ -14332,6 +14340,14 @@ The maximum allowed @var{n} option value is 65536.
 
 Enabled at levels @option{-O2}, @option{-O3}.
 
+@opindex fmin-function-alignment=@var{n}
+@item -fmin-function-alignment
+Specify minimal alignment of functions to the next power-of-two greater than or
+equal to @var{n}. Unlike @option{-falign-functions} this alignment is applied
+also to all functions (even those considered cold).  The alignment is also not
+affected by @option{-flimit-function-alignment}
+
+
 @opindex fno-allocation-dce
 @item -fno-allocation-dce
 Do not remove unused C++ allocations in dead code elimination.
@@ -14428,7 +14444,7 @@ To use the link-time optimizer, @option{-flto} and optimization
 options should be specified at compile time and during the final link.
 It is recommended that you compile all the files participating in the
 same link with the same options and also specify those options at
-link time.  
+link time.
 For example:
 
 @smallexample

diff --git a/gcc/varasm.cc b/gcc/varasm.cc
index d2c879b7da44df7c8d09ef1532902c20c73dd841..fa17eff551e87e8dbc97687601ddef22c3e1a5d3 100644 (file)
--- a/gcc/varasm.cc
+++ b/gcc/varasm.cc
@@ -1939,6 +1939,11 @@ assemble_start_function (tree decl, const char *fnname)
 
   /* Tell assembler to move to target machine's alignment for functions.  */
   align = floor_log2 (align / BITS_PER_UNIT);
+  /* Handle forced alignment.  This really ought to apply to all functions,
+     since it is used by patchable entries.  */
+  if (flag_min_function_alignment)
+    align = MAX (align, floor_log2 (flag_min_function_alignment));
+
   if (align > 0)
     {
       ASM_OUTPUT_ALIGN (asm_out_file, align);