From 441d0aa048a51d2e9c4f4227916d2a1a2f06b4e5 Mon Sep 17 00:00:00 2001 From: Jan Hubicka Date: Wed, 24 Jan 2024 18:13:17 +0100 Subject: [PATCH] Add -fmin-function-alignmnet To: gcc-patches@gcc.gnu.org -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. * lto-streamer.h (LTO_minor_version): Bump. --- gcc/common.opt | 10 +++++++--- gcc/doc/invoke.texi | 18 +++++++++++++++++- gcc/lto-streamer.h | 2 +- gcc/varasm.cc | 5 +++++ 4 files changed, 30 insertions(+), 5 deletions(-) diff --git a/gcc/common.opt b/gcc/common.opt index 862c474d3c8..5d35391b99f 100644 --- a/gcc/common.opt +++ b/gcc/common.opt @@ -1027,9 +1027,6 @@ 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. @@ -2165,6 +2162,10 @@ fmessage-length= Common RejectNegative Joined UInteger -fmessage-length= Limit diagnostics to 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. @@ -2489,6 +2490,9 @@ 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 b777fc92755..d39cb26326c 100644 --- a/gcc/doc/invoke.texi +++ b/gcc/doc/invoke.texi @@ -531,6 +531,7 @@ 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 @@ -13650,6 +13651,9 @@ 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}. @@ -13713,6 +13717,8 @@ 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. @@ -13735,6 +13741,8 @@ 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. @@ -13748,6 +13756,14 @@ 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. @@ -13844,7 +13860,7 @@ 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/lto-streamer.h b/gcc/lto-streamer.h index 75cebcd02d3..2827897cc7a 100644 --- a/gcc/lto-streamer.h +++ b/gcc/lto-streamer.h @@ -122,7 +122,7 @@ along with GCC; see the file COPYING3. If not see form followed by the data for the string. */ #define LTO_major_version GCC_major_version -#define LTO_minor_version 1 +#define LTO_minor_version 2 typedef unsigned char lto_decl_flags_t; diff --git a/gcc/varasm.cc b/gcc/varasm.cc index cd0cd88321c..5de821b63e6 100644 --- a/gcc/varasm.cc +++ b/gcc/varasm.cc @@ -1914,6 +1914,11 @@ 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); -- 2.35.3