mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-14 15:54:15 +08:00
7416cdc9b9
After the update to zstd-1.4.10 passing -O3 is no longer necessary to get good performance from zstd. Using the default optimization level -O2 is sufficient to get good performance. I've measured no significant change to compression speed, and a ~1% decompression speed loss, which is acceptable. This fixes the reported parisc -Wframe-larger-than=1536 errors [0]. The gcc-8-hppa-linux-gnu compiler performed very poorly with -O3, generating stacks that are ~3KB. With -O2 these same functions generate stacks in the < 100B, completely fixing the problem. Function size deltas are listed below: ZSTD_compressBlock_fast_extDict_generic: 3800 -> 68 ZSTD_compressBlock_fast: 2216 -> 40 ZSTD_compressBlock_fast_dictMatchState: 1848 -> 64 ZSTD_compressBlock_doubleFast_extDict_generic: 3744 -> 76 ZSTD_fillDoubleHashTable: 3252 -> 0 ZSTD_compressBlock_doubleFast: 5856 -> 36 ZSTD_compressBlock_doubleFast_dictMatchState: 5380 -> 84 ZSTD_copmressBlock_lazy2: 2420 -> 72 Additionally, this improves the reported code bloat [1]. With gcc-11 bloat-o-meter shows an 80KB code size improvement: ``` > ../scripts/bloat-o-meter vmlinux.old vmlinux add/remove: 31/8 grow/shrink: 24/155 up/down: 25734/-107924 (-82190) Total: Before=6418562, After=6336372, chg -1.28% ``` Compared to before the zstd-1.4.10 update we see a total code size regression of 105KB, down from 374KB at v5.16-rc1: ``` > ../scripts/bloat-o-meter vmlinux.old vmlinux add/remove: 292/62 grow/shrink: 56/88 up/down: 235009/-127487 (107522) Total: Before=6228850, After=6336372, chg +1.73% ``` [0] https://lkml.org/lkml/2021/11/15/710 [1] https://lkml.org/lkml/2021/11/14/189 Link: https://lore.kernel.org/r/20211117014949.1169186-4-nickrterrell@gmail.com/ Link: https://lore.kernel.org/r/20211117201459.1194876-4-nickrterrell@gmail.com/ Reported-by: Geert Uytterhoeven <geert@linux-m68k.org> Tested-by: Geert Uytterhoeven <geert@linux-m68k.org> Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Nick Terrell <terrelln@fb.com>
45 lines
1.4 KiB
Makefile
45 lines
1.4 KiB
Makefile
# SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause
|
|
# ################################################################
|
|
# Copyright (c) Facebook, Inc.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under both the BSD-style license (found in the
|
|
# LICENSE file in the root directory of this source tree) and the GPLv2 (found
|
|
# in the COPYING file in the root directory of this source tree).
|
|
# You may select, at your option, one of the above-listed licenses.
|
|
# ################################################################
|
|
obj-$(CONFIG_ZSTD_COMPRESS) += zstd_compress.o
|
|
obj-$(CONFIG_ZSTD_DECOMPRESS) += zstd_decompress.o
|
|
|
|
zstd_compress-y := \
|
|
zstd_compress_module.o \
|
|
common/debug.o \
|
|
common/entropy_common.o \
|
|
common/error_private.o \
|
|
common/fse_decompress.o \
|
|
common/zstd_common.o \
|
|
compress/fse_compress.o \
|
|
compress/hist.o \
|
|
compress/huf_compress.o \
|
|
compress/zstd_compress.o \
|
|
compress/zstd_compress_literals.o \
|
|
compress/zstd_compress_sequences.o \
|
|
compress/zstd_compress_superblock.o \
|
|
compress/zstd_double_fast.o \
|
|
compress/zstd_fast.o \
|
|
compress/zstd_lazy.o \
|
|
compress/zstd_ldm.o \
|
|
compress/zstd_opt.o \
|
|
|
|
zstd_decompress-y := \
|
|
zstd_decompress_module.o \
|
|
common/debug.o \
|
|
common/entropy_common.o \
|
|
common/error_private.o \
|
|
common/fse_decompress.o \
|
|
common/zstd_common.o \
|
|
decompress/huf_decompress.o \
|
|
decompress/zstd_ddict.o \
|
|
decompress/zstd_decompress.o \
|
|
decompress/zstd_decompress_block.o \
|