diff options
author | lhchavez <lhchavez@lhchavez.com> | 2020-12-18 06:50:22 -0800 |
---|---|---|
committer | lhchavez <lhchavez@lhchavez.com> | 2020-12-23 18:18:16 -0800 |
commit | 83265b3e2c6b10370c2fea304be33db78f653761 (patch) | |
tree | 656af27d57d28c7534a59ae216519689a3bf470b /deps | |
parent | fe41e5823986aff01054b7db4b869b2896ea4c30 (diff) | |
download | libgit2-83265b3e2c6b10370c2fea304be33db78f653761.tar.gz |
zlib: Add support for building with Chromium's zlib implementation
This change builds libgit2 using Chromium's zlib implementation by
invoking cmake with `-DUSE_BUNDLED_ZLIB=ON -DUSE_CHROMIUM_ZLIB=ON`,
which is ~10% faster than the bundled zlib for the core::zstream suite.
This version of zlib has some optimizations:
a) Decompression (Intel+ARM): inflate_fast, adler32, crc32, etc.
b) Compression (Intel): fill_window, longest_match, hash function, etc.
Due to the introduction of SIMD optimizations, and to get the maximum
performance out of this fork of zlib, this requires an x86_64 processor
with SSE4.2 and CLMUL (anything Westmere or later, ~2010). The Chromium
zlib implementation also supports ARM with NEON, but it has not been
enabled in this patch.
Performance
===========
TL;DR: Running just `./libgit2_clar -score::zstream` 100 times in a loop
took 0:56.30 before and 0:50.67 after (~10% reduction!).
The bundled and system zlib implementations on an Ubuntu Focal system
perform relatively similar (the bundled one is marginally better due to
the compiler being able to inline some functions), so only the bundled
and Chromium zlibs were compared.
For a more balanced comparison (to ensure that nothing regressed
overall), `libgit2_clar` under `perf` was also run, and the zlib-related
functions were compared.
Bundled
-------
```shell
cmake \
-DUSE_BUNDLED_ZLIB=ON \
-DUSE_CHROMIUM_ZLIB=OFF \
-DCMAKE_BUILD_TYPE="RelWithDebInfo" \
-DCMAKE_C_FLAGS="-fPIC -fno-omit-frame-pointer" \
-GNinja \
..
ninja
perf record --call-graph=dwarf ./libgit2_clar
perf report --children
```
```
Samples: 87K of event 'cycles', Event count (approx.): 75923450603
Children Self Command Shared Objec Symbol
+ 4.14% 0.01% libgit2_clar libgit2_clar [.] git_zstream_get_output_chunk
+ 2.91% 0.00% libgit2_clar libgit2_clar [.] git_zstream_get_output
+ 0.69% 0.00% libgit2_clar libgit2_clar [.] git_zstream_get_output (inlined)
0.17% 0.00% libgit2_clar libgit2_clar [.] git_zstream_init
0.02% 0.00% libgit2_clar libgit2_clar [.] git_zstream_reset
0.00% 0.00% libgit2_clar libgit2_clar [.] git_zstream_eos
0.00% 0.00% libgit2_clar libgit2_clar [.] git_zstream_done
0.00% 0.00% libgit2_clar libgit2_clar [.] git_zstream_free (inlined)
Samples: 87K of event 'cycles', Event count (approx.): 75923450603
Children Self Command Shared Objec Symbol
+ 3.12% 0.01% libgit2_clar libgit2_clar [.] deflate
+ 2.65% 1.48% libgit2_clar libgit2_clar [.] deflate_slow
+ 1.60% 0.55% libgit2_clar libgit2_clar [.] inflate
+ 0.53% 0.00% libgit2_clar libgit2_clar [.] write_deflate
0.49% 0.36% libgit2_clar libgit2_clar [.] inflate_fast
0.46% 0.02% libgit2_clar libgit2_clar [.] deflate_fast
0.19% 0.19% libgit2_clar libgit2_clar [.] inflate_table
0.16% 0.01% libgit2_clar libgit2_clar [.] inflateInit_
0.15% 0.00% libgit2_clar libgit2_clar [.] inflateInit2_ (inlined)
0.10% 0.00% libgit2_clar libgit2_clar [.] deflateInit_
0.10% 0.00% libgit2_clar libgit2_clar [.] deflateInit2_
0.03% 0.00% libgit2_clar libgit2_clar [.] deflateReset (inlined)
0.02% 0.00% libgit2_clar libgit2_clar [.] deflateReset
0.02% 0.00% libgit2_clar libgit2_clar [.] inflateEnd
0.02% 0.00% libgit2_clar libgit2_clar [.] deflateEnd
0.01% 0.00% libgit2_clar libgit2_clar [.] deflateResetKeep
0.01% 0.01% libgit2_clar libgit2_clar [.] inflateReset2
0.01% 0.00% libgit2_clar libgit2_clar [.] deflateReset (inlined)
0.00% 0.00% libgit2_clar libgit2_clar [.] inflateStateCheck (inlined)
0.00% 0.00% libgit2_clar libgit2_clar [.] inflateReset (inlined)
0.00% 0.00% libgit2_clar libgit2_clar [.] inflateStateCheck (inlined)
0.00% 0.00% libgit2_clar libgit2_clar [.] deflateStateCheck (inlined)
0.00% 0.00% libgit2_clar libgit2_clar [.] inflateResetKeep (inlined)
```
Chromium
--------
```shell
cmake \
-DUSE_BUNDLED_ZLIB=ON \
-DUSE_CHROMIUM_ZLIB=ON \
-DCMAKE_BUILD_TYPE="RelWithDebInfo" \
-DCMAKE_C_FLAGS="-fPIC -fno-omit-frame-pointer" \
-GNinja \
..
ninja
perf record --call-graph=dwarf ./libgit2_clar
perf report --children
```
```
Samples: 97K of event 'cycles', Event count (approx.): 80862210917
Children Self Command Shared Objec Symbol
+ 3.31% 0.00% libgit2_clar libgit2_clar [.] git_zstream_get_output_chunk
+ 2.27% 0.01% libgit2_clar libgit2_clar [.] git_zstream_get_output
+ 0.55% 0.00% libgit2_clar libgit2_clar [.] git_zstream_get_output (inlined)
0.18% 0.00% libgit2_clar libgit2_clar [.] git_zstream_init
0.02% 0.00% libgit2_clar libgit2_clar [.] git_zstream_reset
0.00% 0.00% libgit2_clar libgit2_clar [.] git_zstream_free (inlined)
0.00% 0.00% libgit2_clar libgit2_clar [.] git_zstream_done
0.00% 0.00% libgit2_clar libgit2_clar [.] git_zstream_free
Samples: 97K of event 'cycles', Event count (approx.): 80862210917
Children Self Command Shared Objec Symbol
+ 2.55% 0.01% libgit2_clar libgit2_clar [.] deflate
+ 2.25% 1.41% libgit2_clar libgit2_clar [.] deflate_slow
+ 1.10% 0.52% libgit2_clar libgit2_clar [.] inflate
0.36% 0.00% libgit2_clar libgit2_clar [.] write_deflate
0.30% 0.03% libgit2_clar libgit2_clar [.] deflate_fast
0.28% 0.15% libgit2_clar libgit2_clar [.] inflate_fast_chunk_
0.19% 0.19% libgit2_clar libgit2_clar [.] inflate_table
0.17% 0.01% libgit2_clar libgit2_clar [.] inflateInit_
0.16% 0.00% libgit2_clar libgit2_clar [.] inflateInit2_ (inlined)
0.15% 0.00% libgit2_clar libgit2_clar [.] deflateInit_
0.15% 0.00% libgit2_clar libgit2_clar [.] deflateInit2_
0.11% 0.01% libgit2_clar libgit2_clar [.] adler32_z
0.09% 0.09% libgit2_clar libgit2_clar [.] adler32_simd_
0.05% 0.00% libgit2_clar libgit2_clar [.] deflateReset (inlined)
0.05% 0.00% libgit2_clar libgit2_clar [.] deflate_read_buf
0.03% 0.00% libgit2_clar libgit2_clar [.] inflateEnd
0.02% 0.00% libgit2_clar libgit2_clar [.] deflateReset
0.01% 0.00% libgit2_clar libgit2_clar [.] deflateEnd
0.01% 0.01% libgit2_clar libgit2_clar [.] inflateReset2
0.01% 0.00% libgit2_clar libgit2_clar [.] inflateReset (inlined)
0.00% 0.00% libgit2_clar libgit2_clar [.] adler32
0.00% 0.00% libgit2_clar libgit2_clar [.] inflateResetKeep (inlined)
0.00% 0.00% libgit2_clar libgit2_clar [.] deflateResetKeep
0.00% 0.00% libgit2_clar libgit2_clar [.] inflateStateCheck (inlined)
0.00% 0.00% libgit2_clar libgit2_clar [.] inflateStateCheck (inlined)
0.00% 0.00% libgit2_clar libgit2_clar [.] inflateStateCheck (inlined)
0.00% 0.00% libgit2_clar libgit2_clar [.] deflateStateCheck (inlined)
```
Diffstat (limited to 'deps')
-rw-r--r-- | deps/chromium-zlib/CMakeLists.txt | 101 |
1 files changed, 101 insertions, 0 deletions
diff --git a/deps/chromium-zlib/CMakeLists.txt b/deps/chromium-zlib/CMakeLists.txt new file mode 100644 index 000000000..bbb35d4e6 --- /dev/null +++ b/deps/chromium-zlib/CMakeLists.txt @@ -0,0 +1,101 @@ +# CMake build script for the bundled Chromium zlib implementation. So far, it +# is only supported for x86_64 processors with CLMUL, SSE3, SSE4.2. +# +# TODO: The Chromium build file (in deps/chromium-zlib/zlib/BUILD.gn) supports +# more platforms (like ARM with NEON), more can be enabled as needed. + +CMAKE_MINIMUM_REQUIRED(VERSION 3.11) + +include(FetchContent) +include(FindGit) + +# Ensure that the git binary is present to download the sources. +find_package(Git) +IF(NOT Git_FOUND) + message(FATAL_ERROR "git is required to download the Chromium zlib sources") +ENDIF() + +FetchContent_Populate(chromium_zlib_src + GIT_REPOSITORY https://chromium.googlesource.com/chromium/src/third_party/zlib.git + GIT_TAG 2c183c9f93a328bfb3121284da13cf89a0f7e64a + QUIET +) + +# The Chromium build globally disables some warnings. +disable_warnings(implicit-fallthrough) +disable_warnings(unused-function) +disable_warnings(unused-parameter) +disable_warnings(sign-compare) +disable_warnings(declaration-after-statement) +disable_warnings(missing-declarations) + +# -O3 is also set by the Chromium configuration and has been deemed safe enough +# for them. +SET(CMAKE_C_FLAGS_RELWITHDEBINFO "-O3 -g -DNDEBUG") +SET(CMAKE_C_FLAGS_RELEASE "-O3 -DNDEBUG") + +# Common definitions. +add_definitions( + -DSTDC + -DNO_GZIP + -DZLIB_IMPLEMENTATION +) +list(APPEND SRC_ZLIB + "${chromium_zlib_src_SOURCE_DIR}/adler32.c" + "${chromium_zlib_src_SOURCE_DIR}/chromeconf.h" + "${chromium_zlib_src_SOURCE_DIR}/compress.c" + "${chromium_zlib_src_SOURCE_DIR}/contrib/optimizations/insert_string.h" + "${chromium_zlib_src_SOURCE_DIR}/cpu_features.c" + "${chromium_zlib_src_SOURCE_DIR}/cpu_features.h" + "${chromium_zlib_src_SOURCE_DIR}/crc32.c" + "${chromium_zlib_src_SOURCE_DIR}/crc32.h" + "${chromium_zlib_src_SOURCE_DIR}/deflate.c" + "${chromium_zlib_src_SOURCE_DIR}/deflate.h" + "${chromium_zlib_src_SOURCE_DIR}/gzclose.c" + "${chromium_zlib_src_SOURCE_DIR}/gzguts.h" + "${chromium_zlib_src_SOURCE_DIR}/gzlib.c" + "${chromium_zlib_src_SOURCE_DIR}/gzread.c" + "${chromium_zlib_src_SOURCE_DIR}/gzwrite.c" + "${chromium_zlib_src_SOURCE_DIR}/infback.c" + "${chromium_zlib_src_SOURCE_DIR}/inffast.c" + "${chromium_zlib_src_SOURCE_DIR}/inffast.h" + "${chromium_zlib_src_SOURCE_DIR}/inffixed.h" + "${chromium_zlib_src_SOURCE_DIR}/inflate.h" + "${chromium_zlib_src_SOURCE_DIR}/inftrees.c" + "${chromium_zlib_src_SOURCE_DIR}/inftrees.h" + "${chromium_zlib_src_SOURCE_DIR}/trees.c" + "${chromium_zlib_src_SOURCE_DIR}/trees.h" + "${chromium_zlib_src_SOURCE_DIR}/uncompr.c" + "${chromium_zlib_src_SOURCE_DIR}/zconf.h" + "${chromium_zlib_src_SOURCE_DIR}/zlib.h" + "${chromium_zlib_src_SOURCE_DIR}/zutil.c" + "${chromium_zlib_src_SOURCE_DIR}/zutil.h" +) + +# x86_64-specific optimizations +string(APPEND CMAKE_C_FLAGS " -mssse3 -msse4.2 -mpclmul") +add_definitions( + -DCHROMIUM_ZLIB_NO_CHROMECONF + -DX86_NOT_WINDOWS + -DADLER32_SIMD_SSSE3 + -DCRC32_SIMD_SSE42_PCLMUL + -DDEFLATE_FILL_WINDOW_SSE2 + -DINFLATE_CHUNK_READ_64LE + -DINFLATE_CHUNK_SIMD_SSE2 +) +list(APPEND SRC_ZLIB + "${chromium_zlib_src_SOURCE_DIR}/adler32_simd.c" + "${chromium_zlib_src_SOURCE_DIR}/adler32_simd.h" + "${chromium_zlib_src_SOURCE_DIR}/contrib/optimizations/chunkcopy.h" + "${chromium_zlib_src_SOURCE_DIR}/contrib/optimizations/inffast_chunk.c" + "${chromium_zlib_src_SOURCE_DIR}/contrib/optimizations/inffast_chunk.h" + "${chromium_zlib_src_SOURCE_DIR}/contrib/optimizations/inflate.c" + "${chromium_zlib_src_SOURCE_DIR}/crc32_simd.c" + "${chromium_zlib_src_SOURCE_DIR}/crc32_simd.h" + "${chromium_zlib_src_SOURCE_DIR}/crc_folding.c" + "${chromium_zlib_src_SOURCE_DIR}/fill_window_sse.c" +) + +list(SORT SRC_ZLIB) +include_directories("${chromium_zlib_src_SOURCE_DIR}") +add_library(chromium_zlib OBJECT ${SRC_ZLIB}) |