From 214eb2cce5caa99f476ae8abd406077e2c293a3c Mon Sep 17 00:00:00 2001 From: Kevin Modzelewski Date: Thu, 18 Aug 2022 17:33:54 -0400 Subject: gh-90536: Add support for the BOLT post-link binary optimizer (gh-95908) * Add support for the BOLT post-link binary optimizer Using [bolt](https://github.com/llvm/llvm-project/tree/main/bolt) provides a fairly large speedup without any code or functionality changes. It provides roughly a 1% speedup on pyperformance, and a 4% improvement on the Pyston web macrobenchmarks. It is gated behind an `--enable-bolt` configure arg because not all toolchains and environments are supported. It has been tested on a Linux x86_64 toolchain, using llvm-bolt built from the LLVM 14.0.6 sources (their binary distribution of this version did not include bolt). Compared to [a previous attempt](https://github.com/faster-cpython/ideas/issues/224), this commit uses bolt's preferred "instrumentation" approach, as well as adds some non-PIE flags which enable much better optimizations from bolt. The effects of this change are a bit more dependent on CPU microarchitecture than other changes, since it optimizes i-cache behavior which seems to be a bit more variable between architectures. The 1%/4% numbers were collected on an Intel Skylake CPU, and on an AMD Zen 3 CPU I got a slightly larger speedup (2%/4%), and on a c6i.xlarge EC2 instance I got a slightly lower speedup (1%/3%). The low speedup on pyperformance is not entirely unexpected, because BOLT improves i-cache behavior, and the benchmarks in the pyperformance suite are small and tend to fit in i-cache. This change uses the existing pgo profiling task (`python -m test --pgo`), though I was able to measure about a 1% macrobenchmark improvement by using the macrobenchmarks as the training task. I personally think that both the PGO and BOLT tasks should be updated to use macrobenchmarks, but for the sake of splitting up the work this PR uses the existing pgo task. * Simplify the build flags * Add a NEWS entry * Update Makefile.pre.in Co-authored-by: Dong-hee Na * Update configure.ac Co-authored-by: Dong-hee Na * Add myself to ACKS * Add docs * Other review comments * fix tab/space issue * Make it more clear that --enable-bolt is experimental * Add link to bolt's github page Co-authored-by: Dong-hee Na --- Doc/using/configure.rst | 21 +- Doc/whatsnew/3.12.rst | 4 + Makefile.pre.in | 10 + Misc/ACKS | 1 + .../2022-08-12-13-06-03.gh-issue-90536.qMpF6p.rst | 2 + configure | 261 +++++++++++++++++++++ configure.ac | 53 +++++ 7 files changed, 351 insertions(+), 1 deletion(-) create mode 100644 Misc/NEWS.d/next/Build/2022-08-12-13-06-03.gh-issue-90536.qMpF6p.rst diff --git a/Doc/using/configure.rst b/Doc/using/configure.rst index 4e50e73..ef770d7 100644 --- a/Doc/using/configure.rst +++ b/Doc/using/configure.rst @@ -191,7 +191,8 @@ Performance options ------------------- Configuring Python using ``--enable-optimizations --with-lto`` (PGO + LTO) is -recommended for best performance. +recommended for best performance. The experimental ``--enable-bolt`` flag can +also be used to improve performance. .. cmdoption:: --enable-optimizations @@ -231,6 +232,24 @@ recommended for best performance. .. versionadded:: 3.11 To use ThinLTO feature, use ``--with-lto=thin`` on Clang. +.. cmdoption:: --enable-bolt + + Enable usage of the `BOLT post-link binary optimizer + ` (disabled by + default). + + BOLT is part of the LLVM project but is not always included in their binary + distributions. This flag requires that ``llvm-bolt`` and ``merge-fdata`` + are available. + + BOLT is still a fairly new project so this flag should be considered + experimental for now. Because this tool operates on machine code its success + is dependent on a combination of the build environment + the other + optimization configure args + the CPU architecture, and not all combinations + are supported. + + .. versionadded:: 3.12 + .. cmdoption:: --with-computed-gotos Enable computed gotos in evaluation loop (enabled by default on supported diff --git a/Doc/whatsnew/3.12.rst b/Doc/whatsnew/3.12.rst index 9689d9d..f9fa8ac 100644 --- a/Doc/whatsnew/3.12.rst +++ b/Doc/whatsnew/3.12.rst @@ -133,6 +133,10 @@ Optimizations It reduces object size by 8 or 16 bytes on 64bit platform. (:pep:`623`) (Contributed by Inada Naoki in :gh:`92536`.) +* Added experimental support for using the BOLT binary optimizer in the build + process, which improves performance by 1-5%. + (Contributed by Kevin Modzelewski in :gh:`90536`.) + CPython bytecode changes ======================== diff --git a/Makefile.pre.in b/Makefile.pre.in index c647853..ae7735c 100644 --- a/Makefile.pre.in +++ b/Makefile.pre.in @@ -640,6 +640,16 @@ profile-opt: profile-run-stamp -rm -f profile-clean-stamp $(MAKE) @DEF_MAKE_RULE@ CFLAGS_NODIST="$(CFLAGS_NODIST) $(PGO_PROF_USE_FLAG)" LDFLAGS_NODIST="$(LDFLAGS_NODIST)" +bolt-opt: @PREBOLT_RULE@ + rm -f *.fdata + @LLVM_BOLT@ ./$(BUILDPYTHON) -instrument -instrumentation-file-append-pid -instrumentation-file=$(abspath $(BUILDPYTHON).bolt) -o $(BUILDPYTHON).bolt_inst + ./$(BUILDPYTHON).bolt_inst $(PROFILE_TASK) || true + @MERGE_FDATA@ $(BUILDPYTHON).*.fdata > $(BUILDPYTHON).fdata + @LLVM_BOLT@ ./$(BUILDPYTHON) -o $(BUILDPYTHON).bolt -data=$(BUILDPYTHON).fdata -update-debug-sections -reorder-blocks=ext-tsp -reorder-functions=hfsort+ -split-functions=3 -icf=1 -inline-all -split-eh -reorder-functions-use-hot-size -peepholes=all -jump-tables=aggressive -inline-ap -indirect-call-promotion=all -dyno-stats -use-gnu-stack -frame-opt=hot + rm -f *.fdata + rm -f $(BUILDPYTHON).bolt_inst + mv $(BUILDPYTHON).bolt $(BUILDPYTHON) + # Compile and run with gcov .PHONY=coverage coverage-lcov coverage-report coverage: diff --git a/Misc/ACKS b/Misc/ACKS index c1f570a..16a482e 100644 --- a/Misc/ACKS +++ b/Misc/ACKS @@ -1212,6 +1212,7 @@ Gideon Mitchell Tim Mitchell Zubin Mithra Florian Mladitsch +Kevin Modzelewski Doug Moen Jakub Molinski Juliette Monsel diff --git a/Misc/NEWS.d/next/Build/2022-08-12-13-06-03.gh-issue-90536.qMpF6p.rst b/Misc/NEWS.d/next/Build/2022-08-12-13-06-03.gh-issue-90536.qMpF6p.rst new file mode 100644 index 0000000..4605e03 --- /dev/null +++ b/Misc/NEWS.d/next/Build/2022-08-12-13-06-03.gh-issue-90536.qMpF6p.rst @@ -0,0 +1,2 @@ +Use the BOLT post-link optimizer to improve performance, particularly on +medium-to-large applications. diff --git a/configure b/configure index 82b55a3..fb3a3c3 100755 --- a/configure +++ b/configure @@ -887,6 +887,9 @@ LLVM_PROF_FILE LLVM_PROF_MERGER PGO_PROF_USE_FLAG PGO_PROF_GEN_FLAG +MERGE_FDATA +LLVM_BOLT +PREBOLT_RULE LLVM_AR_FOUND LLVM_AR PROFILE_TASK @@ -1049,6 +1052,7 @@ enable_pystats with_assertions enable_optimizations with_lto +enable_bolt with_address_sanitizer with_memory_sanitizer with_undefined_behavior_sanitizer @@ -1774,6 +1778,8 @@ Optional Features: --enable-pystats enable internal statistics gathering (default is no) --enable-optimizations enable expensive, stable optimizations (PGO, etc.) (default is no) + --enable-bolt enable usage of the llvm-bolt post-link optimizer + (default is no) --enable-loadable-sqlite-extensions support loadable extensions in the sqlite3 module, see Doc/library/sqlite3.rst (default is no) @@ -7878,6 +7884,261 @@ $as_echo "$as_me: llvm-ar found via xcrun: ${LLVM_AR}" >&6;} LDFLAGS_NODIST="$LDFLAGS_NODIST $LTOFLAGS" fi +# Enable bolt flags +Py_BOLT='false' +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for --enable-bolt" >&5 +$as_echo_n "checking for --enable-bolt... " >&6; } +# Check whether --enable-bolt was given. +if test "${enable_bolt+set}" = set; then : + enableval=$enable_bolt; +if test "$enableval" != no +then + Py_BOLT='true' + { $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5 +$as_echo "yes" >&6; }; +else + Py_BOLT='false' + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; }; +fi +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + + +if test "$Py_BOLT" = 'true' ; then + PREBOLT_RULE="${DEF_MAKE_ALL_RULE}" + DEF_MAKE_ALL_RULE="bolt-opt" + DEF_MAKE_RULE="build_all" + + # These flags are required for bolt to work: + CFLAGS_NODIST="$CFLAGS_NODIST -fno-reorder-blocks-and-partition" + LDFLAGS_NODIST="$LDFLAGS_NODIST -Wl,--emit-relocs" + + # These flags are required to get good performance from bolt: + CFLAGS_NODIST="$CFLAGS_NODIST -fno-pie" + # We want to add these no-pie flags to linking executables but not shared libraries: + LINKCC="$LINKCC -fno-pie -no-pie" + # Designate the DWARF version into 4 since the LLVM-BOLT does not support DWARF5 yet. + CFLAGS="$CFLAGS -gdwarf-4" + LDFLAGS="$LDFLAGS -gdwarf-4" + + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}llvm-bolt", so it can be a program name with args. +set dummy ${ac_tool_prefix}llvm-bolt; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_path_LLVM_BOLT+:} false; then : + $as_echo_n "(cached) " >&6 +else + case $LLVM_BOLT in + [\\/]* | ?:[\\/]*) + ac_cv_path_LLVM_BOLT="$LLVM_BOLT" # Let the user override the test with a path. + ;; + *) + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in ${llvm_path} +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_path_LLVM_BOLT="$as_dir/$ac_word$ac_exec_ext" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + + ;; +esac +fi +LLVM_BOLT=$ac_cv_path_LLVM_BOLT +if test -n "$LLVM_BOLT"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $LLVM_BOLT" >&5 +$as_echo "$LLVM_BOLT" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$ac_cv_path_LLVM_BOLT"; then + ac_pt_LLVM_BOLT=$LLVM_BOLT + # Extract the first word of "llvm-bolt", so it can be a program name with args. +set dummy llvm-bolt; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_path_ac_pt_LLVM_BOLT+:} false; then : + $as_echo_n "(cached) " >&6 +else + case $ac_pt_LLVM_BOLT in + [\\/]* | ?:[\\/]*) + ac_cv_path_ac_pt_LLVM_BOLT="$ac_pt_LLVM_BOLT" # Let the user override the test with a path. + ;; + *) + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in ${llvm_path} +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_path_ac_pt_LLVM_BOLT="$as_dir/$ac_word$ac_exec_ext" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + + ;; +esac +fi +ac_pt_LLVM_BOLT=$ac_cv_path_ac_pt_LLVM_BOLT +if test -n "$ac_pt_LLVM_BOLT"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_pt_LLVM_BOLT" >&5 +$as_echo "$ac_pt_LLVM_BOLT" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + if test "x$ac_pt_LLVM_BOLT" = x; then + LLVM_BOLT="''" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + LLVM_BOLT=$ac_pt_LLVM_BOLT + fi +else + LLVM_BOLT="$ac_cv_path_LLVM_BOLT" +fi + + if test -n "${LLVM_BOLT}" -a -x "${LLVM_BOLT}" + then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: \"Found llvm-bolt\"" >&5 +$as_echo "\"Found llvm-bolt\"" >&6; } + else + as_fn_error $? "llvm-bolt is required for a --enable-bolt build but could not be found." "$LINENO" 5 + fi + + + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}merge-fdata", so it can be a program name with args. +set dummy ${ac_tool_prefix}merge-fdata; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_path_MERGE_FDATA+:} false; then : + $as_echo_n "(cached) " >&6 +else + case $MERGE_FDATA in + [\\/]* | ?:[\\/]*) + ac_cv_path_MERGE_FDATA="$MERGE_FDATA" # Let the user override the test with a path. + ;; + *) + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in ${llvm_path} +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_path_MERGE_FDATA="$as_dir/$ac_word$ac_exec_ext" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + + ;; +esac +fi +MERGE_FDATA=$ac_cv_path_MERGE_FDATA +if test -n "$MERGE_FDATA"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $MERGE_FDATA" >&5 +$as_echo "$MERGE_FDATA" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + +fi +if test -z "$ac_cv_path_MERGE_FDATA"; then + ac_pt_MERGE_FDATA=$MERGE_FDATA + # Extract the first word of "merge-fdata", so it can be a program name with args. +set dummy merge-fdata; ac_word=$2 +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 +$as_echo_n "checking for $ac_word... " >&6; } +if ${ac_cv_path_ac_pt_MERGE_FDATA+:} false; then : + $as_echo_n "(cached) " >&6 +else + case $ac_pt_MERGE_FDATA in + [\\/]* | ?:[\\/]*) + ac_cv_path_ac_pt_MERGE_FDATA="$ac_pt_MERGE_FDATA" # Let the user override the test with a path. + ;; + *) + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in ${llvm_path} +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_path_ac_pt_MERGE_FDATA="$as_dir/$ac_word$ac_exec_ext" + $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done + done +IFS=$as_save_IFS + + ;; +esac +fi +ac_pt_MERGE_FDATA=$ac_cv_path_ac_pt_MERGE_FDATA +if test -n "$ac_pt_MERGE_FDATA"; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_pt_MERGE_FDATA" >&5 +$as_echo "$ac_pt_MERGE_FDATA" >&6; } +else + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } +fi + + if test "x$ac_pt_MERGE_FDATA" = x; then + MERGE_FDATA="''" + else + case $cross_compiling:$ac_tool_warned in +yes:) +{ $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: using cross tools not prefixed with host triplet" >&5 +$as_echo "$as_me: WARNING: using cross tools not prefixed with host triplet" >&2;} +ac_tool_warned=yes ;; +esac + MERGE_FDATA=$ac_pt_MERGE_FDATA + fi +else + MERGE_FDATA="$ac_cv_path_MERGE_FDATA" +fi + + if test -n "${MERGE_FDATA}" -a -x "${MERGE_FDATA}" + then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: \"Found merge-fdata\"" >&5 +$as_echo "\"Found merge-fdata\"" >&6; } + else + as_fn_error $? "merge-fdata is required for a --enable-bolt build but could not be found." "$LINENO" 5 + fi +fi + # Enable PGO flags. diff --git a/configure.ac b/configure.ac index 85d9e80..bab405e 100644 --- a/configure.ac +++ b/configure.ac @@ -1917,6 +1917,59 @@ if test "$Py_LTO" = 'true' ; then LDFLAGS_NODIST="$LDFLAGS_NODIST $LTOFLAGS" fi +# Enable bolt flags +Py_BOLT='false' +AC_MSG_CHECKING(for --enable-bolt) +AC_ARG_ENABLE(bolt, AS_HELP_STRING( + [--enable-bolt], + [enable usage of the llvm-bolt post-link optimizer (default is no)]), +[ +if test "$enableval" != no +then + Py_BOLT='true' + AC_MSG_RESULT(yes); +else + Py_BOLT='false' + AC_MSG_RESULT(no); +fi], +[AC_MSG_RESULT(no)]) + +AC_SUBST(PREBOLT_RULE) +if test "$Py_BOLT" = 'true' ; then + PREBOLT_RULE="${DEF_MAKE_ALL_RULE}" + DEF_MAKE_ALL_RULE="bolt-opt" + DEF_MAKE_RULE="build_all" + + # These flags are required for bolt to work: + CFLAGS_NODIST="$CFLAGS_NODIST -fno-reorder-blocks-and-partition" + LDFLAGS_NODIST="$LDFLAGS_NODIST -Wl,--emit-relocs" + + # These flags are required to get good performance from bolt: + CFLAGS_NODIST="$CFLAGS_NODIST -fno-pie" + # We want to add these no-pie flags to linking executables but not shared libraries: + LINKCC="$LINKCC -fno-pie -no-pie" + # Designate the DWARF version into 4 since the LLVM-BOLT does not support DWARF5 yet. + CFLAGS="$CFLAGS -gdwarf-4" + LDFLAGS="$LDFLAGS -gdwarf-4" + AC_SUBST(LLVM_BOLT) + AC_PATH_TOOL(LLVM_BOLT, llvm-bolt, '', ${llvm_path}) + if test -n "${LLVM_BOLT}" -a -x "${LLVM_BOLT}" + then + AC_MSG_RESULT("Found llvm-bolt") + else + AC_MSG_ERROR([llvm-bolt is required for a --enable-bolt build but could not be found.]) + fi + + AC_SUBST(MERGE_FDATA) + AC_PATH_TOOL(MERGE_FDATA, merge-fdata, '', ${llvm_path}) + if test -n "${MERGE_FDATA}" -a -x "${MERGE_FDATA}" + then + AC_MSG_RESULT("Found merge-fdata") + else + AC_MSG_ERROR([merge-fdata is required for a --enable-bolt build but could not be found.]) + fi +fi + # Enable PGO flags. AC_SUBST(PGO_PROF_GEN_FLAG) AC_SUBST(PGO_PROF_USE_FLAG) -- cgit v0.12