mirror of
https://sourceware.org/git/glibc.git
synced 2024-12-29 05:51:10 +00:00
64b8b6516b
Implemented:
wcscat-evex (+ 905 bytes)
wcscpy-evex (+ 674 bytes)
wcpcpy-evex (+ 709 bytes)
wcsncpy-evex (+1358 bytes)
wcpncpy-evex (+1467 bytes)
wcsncat-evex (+1213 bytes)
Performance Changes:
Times are from N = 10 runs of the benchmark suite and are reported
as geometric mean of all ratios of New Implementation / Best Old
Implementation. Best Old Implementation was determined with the
highest ISA implementation.
wcscat-evex -> 0.991
wcscpy-evex -> 0.587
wcpcpy-evex -> 0.695
wcsncpy-evex -> 0.719
wcpncpy-evex -> 0.694
wcsncat-evex -> 0.979
Code Size Changes:
This change increase the size of libc.so by ~6.3kb bytes. For
reference the patch optimizing the normal strcpy family functions
decreases libc.so by ~5.7kb.
Full check passes on x86-64 and build succeeds for all ISA levels w/
and w/o multiarch.
215 lines
6.7 KiB
Makefile
215 lines
6.7 KiB
Makefile
# The i387 `long double' is a distinct type we support.
|
|
long-double-fcts = yes
|
|
|
|
ifeq ($(subdir),csu)
|
|
gen-as-const-headers += link-defines.sym
|
|
endif
|
|
|
|
ifeq ($(subdir),gmon)
|
|
sysdep_routines += _mcount
|
|
# We cannot compile _mcount.S with -pg because that would create
|
|
# recursive calls when ENTRY is used. Just copy the normal static
|
|
# object.
|
|
sysdep_noprof += _mcount
|
|
endif
|
|
|
|
ifeq ($(subdir),string)
|
|
sysdep_routines += \
|
|
strcasecmp_l-nonascii \
|
|
strcspn-generic \
|
|
strncase_l-nonascii \
|
|
strpbrk-generic \
|
|
strspn-generic \
|
|
varshift \
|
|
# sysdep_routines
|
|
gen-as-const-headers += locale-defines.sym
|
|
tests += \
|
|
tst-rsi-strlen
|
|
endif
|
|
|
|
ifeq ($(subdir),elf)
|
|
# There is no good reason to use MMX in x86-64 ld.so with GCC.
|
|
CFLAGS-.os += $(if $(filter $(@F),$(patsubst %,%.os,$(all-rtld-routines))),\
|
|
-mno-mmx)
|
|
|
|
sysdep-dl-routines += tlsdesc dl-tlsdesc tls_get_addr
|
|
|
|
tests += ifuncmain8
|
|
modules-names += ifuncmod8
|
|
|
|
$(objpfx)ifuncmain8: $(objpfx)ifuncmod8.so
|
|
|
|
tests += tst-quad1 tst-quad2
|
|
modules-names += tst-quadmod1 tst-quadmod2
|
|
|
|
$(objpfx)tst-quad1: $(objpfx)tst-quadmod1.so
|
|
$(objpfx)tst-quad2: $(objpfx)tst-quadmod2.so
|
|
|
|
quad-pie-test += tst-quad1pie tst-quad2pie
|
|
tests += $(quad-pie-test)
|
|
tests-pie += $(quad-pie-test)
|
|
test-extras += tst-quadmod1pie tst-quadmod2pie
|
|
extra-test-objs += tst-quadmod1pie.o tst-quadmod2pie.o
|
|
|
|
$(objpfx)tst-quad1pie: $(objpfx)tst-quadmod1pie.o
|
|
$(objpfx)tst-quad2pie: $(objpfx)tst-quadmod2pie.o
|
|
|
|
CFLAGS-tst-quad1pie.c = $(PIE-ccflag)
|
|
CFLAGS-tst-quad2pie.c = $(PIE-ccflag)
|
|
|
|
ifneq (no,$(have-tunables))
|
|
tests += tst-platform-1
|
|
modules-names += tst-platformmod-1 x86_64/tst-platformmod-2
|
|
extra-test-objs += tst-platformmod-2.o
|
|
CFLAGS-tst-platform-1.c = -mno-avx
|
|
CFLAGS-tst-platformmod-1.c = -mno-avx
|
|
CFLAGS-tst-platformmod-2.c = -mno-avx
|
|
LDFLAGS-tst-platformmod-2.so = -Wl,-soname,tst-platformmod-2.so
|
|
$(objpfx)tst-platform-1: $(objpfx)tst-platformmod-1.so
|
|
$(objpfx)tst-platform-1.out: $(objpfx)x86_64/tst-platformmod-2.so
|
|
# Turn off AVX512F and AVX2 so that GLRO(dl_platform) is
|
|
# always set to x86_64.
|
|
tst-platform-1-ENV = LD_PRELOAD=$(objpfx)\$$PLATFORM/tst-platformmod-2.so \
|
|
GLIBC_TUNABLES=glibc.cpu.hwcaps=-AVX512F,-AVX2
|
|
endif
|
|
|
|
tests += tst-audit3 tst-audit4 tst-audit5 tst-audit6 tst-audit7 \
|
|
tst-audit10 tst-sse tst-avx tst-avx512
|
|
test-extras += tst-audit4-aux tst-audit10-aux \
|
|
tst-avx-aux tst-avx512-aux
|
|
extra-test-objs += tst-audit4-aux.o tst-audit10-aux.o \
|
|
tst-avx-aux.o tst-avx512-aux.o
|
|
|
|
ifeq ($(have-insert),yes)
|
|
tests += tst-split-dynreloc
|
|
LDFLAGS-tst-split-dynreloc = -Wl,-T,$(..)sysdeps/x86_64/tst-split-dynreloc.lds
|
|
tst-split-dynreloc-ENV = LD_BIND_NOW=1
|
|
endif
|
|
|
|
modules-names += tst-auditmod3a tst-auditmod3b \
|
|
tst-auditmod4a tst-auditmod4b \
|
|
tst-auditmod5a tst-auditmod5b \
|
|
tst-auditmod6a tst-auditmod6b tst-auditmod6c \
|
|
tst-auditmod7a tst-auditmod7b \
|
|
tst-auditmod10a tst-auditmod10b \
|
|
tst-ssemod tst-avxmod tst-avx512mod
|
|
|
|
$(objpfx)tst-audit3: $(objpfx)tst-auditmod3a.so
|
|
$(objpfx)tst-audit3.out: $(objpfx)tst-auditmod3b.so
|
|
tst-audit3-ENV = LD_AUDIT=$(objpfx)tst-auditmod3b.so
|
|
|
|
$(objpfx)tst-audit4: $(objpfx)tst-audit4-aux.o $(objpfx)tst-auditmod4a.so
|
|
$(objpfx)tst-audit4.out: $(objpfx)tst-auditmod4b.so
|
|
tst-audit4-ENV = LD_AUDIT=$(objpfx)tst-auditmod4b.so
|
|
|
|
$(objpfx)tst-audit5: $(objpfx)tst-auditmod5a.so
|
|
$(objpfx)tst-audit5.out: $(objpfx)tst-auditmod5b.so
|
|
tst-audit5-ENV = LD_AUDIT=$(objpfx)tst-auditmod5b.so
|
|
|
|
$(objpfx)tst-audit6: $(objpfx)tst-auditmod6a.so
|
|
$(objpfx)tst-audit6.out: $(objpfx)tst-auditmod6b.so \
|
|
$(objpfx)tst-auditmod6c.so
|
|
tst-audit6-ENV = LD_AUDIT=$(objpfx)tst-auditmod6b.so:$(objpfx)tst-auditmod6c.so
|
|
|
|
$(objpfx)tst-audit7: $(objpfx)tst-auditmod7a.so
|
|
$(objpfx)tst-audit7.out: $(objpfx)tst-auditmod7b.so
|
|
tst-audit7-ENV = LD_AUDIT=$(objpfx)tst-auditmod7b.so
|
|
|
|
$(objpfx)tst-audit10: $(objpfx)tst-audit10-aux.o $(objpfx)tst-auditmod10a.so
|
|
$(objpfx)tst-audit10.out: $(objpfx)tst-auditmod10b.so
|
|
tst-audit10-ENV = LD_AUDIT=$(objpfx)tst-auditmod10b.so
|
|
|
|
$(objpfx)tst-sse: $(objpfx)tst-ssemod.so
|
|
$(objpfx)tst-avx: $(objpfx)tst-avx-aux.o $(objpfx)tst-avxmod.so
|
|
$(objpfx)tst-avx512: $(objpfx)tst-avx512-aux.o $(objpfx)tst-avx512mod.so
|
|
|
|
AVX-CFLAGS=-mavx -mno-vzeroupper
|
|
CFLAGS-tst-audit4-aux.c += $(AVX-CFLAGS)
|
|
CFLAGS-tst-auditmod4a.c += $(AVX-CFLAGS)
|
|
CFLAGS-tst-auditmod4b.c += $(AVX-CFLAGS)
|
|
CFLAGS-tst-auditmod6b.c += $(AVX-CFLAGS)
|
|
CFLAGS-tst-auditmod6c.c += $(AVX-CFLAGS)
|
|
CFLAGS-tst-auditmod7b.c += $(AVX-CFLAGS)
|
|
CFLAGS-tst-avx-aux.c += $(AVX-CFLAGS)
|
|
CFLAGS-tst-avxmod.c += $(AVX-CFLAGS)
|
|
AVX512-CFLAGS = -mavx512f
|
|
CFLAGS-tst-audit10-aux.c += $(AVX512-CFLAGS)
|
|
CFLAGS-tst-auditmod10a.c += $(AVX512-CFLAGS)
|
|
CFLAGS-tst-auditmod10b.c += $(AVX512-CFLAGS)
|
|
CFLAGS-tst-avx512-aux.c += $(AVX512-CFLAGS)
|
|
CFLAGS-tst-avx512mod.c += $(AVX512-CFLAGS)
|
|
|
|
$(objpfx)tst-glibc-hwcaps: $(objpfx)libmarkermod2-1.so \
|
|
$(objpfx)libmarkermod3-1.so $(objpfx)libmarkermod4-1.so
|
|
$(objpfx)tst-glibc-hwcaps.out: \
|
|
$(objpfx)libmarkermod2.so \
|
|
$(objpfx)glibc-hwcaps/x86-64-v2/libmarkermod2.so \
|
|
$(objpfx)libmarkermod3.so \
|
|
$(objpfx)glibc-hwcaps/x86-64-v2/libmarkermod3.so \
|
|
$(objpfx)glibc-hwcaps/x86-64-v3/libmarkermod3.so \
|
|
$(objpfx)libmarkermod4.so \
|
|
$(objpfx)glibc-hwcaps/x86-64-v2/libmarkermod4.so \
|
|
$(objpfx)glibc-hwcaps/x86-64-v3/libmarkermod4.so \
|
|
$(objpfx)glibc-hwcaps/x86-64-v4/libmarkermod4.so \
|
|
|
|
$(objpfx)glibc-hwcaps/x86-64-v2/libmarkermod2.so: $(objpfx)libmarkermod2-2.so
|
|
$(make-target-directory)
|
|
cp $< $@
|
|
$(objpfx)glibc-hwcaps/x86-64-v2/libmarkermod3.so: $(objpfx)libmarkermod3-2.so
|
|
$(make-target-directory)
|
|
cp $< $@
|
|
$(objpfx)glibc-hwcaps/x86-64-v3/libmarkermod3.so: $(objpfx)libmarkermod3-3.so
|
|
$(make-target-directory)
|
|
cp $< $@
|
|
$(objpfx)glibc-hwcaps/x86-64-v2/libmarkermod4.so: $(objpfx)libmarkermod4-2.so
|
|
$(make-target-directory)
|
|
cp $< $@
|
|
$(objpfx)glibc-hwcaps/x86-64-v3/libmarkermod4.so: $(objpfx)libmarkermod4-3.so
|
|
$(make-target-directory)
|
|
cp $< $@
|
|
$(objpfx)glibc-hwcaps/x86-64-v4/libmarkermod4.so: $(objpfx)libmarkermod4-4.so
|
|
$(make-target-directory)
|
|
cp $< $@
|
|
|
|
ifeq (no,$(build-hardcoded-path-in-tests))
|
|
# This is an ld.so.cache test, and RPATH/RUNPATH in the executable
|
|
# interferes with its test objectives.
|
|
tests-container += tst-glibc-hwcaps-cache
|
|
endif
|
|
|
|
tests-internal += tst-x86-64-tls-1
|
|
|
|
endif # $(subdir) == elf
|
|
|
|
ifeq ($(subdir),csu)
|
|
gen-as-const-headers += tlsdesc.sym rtld-offsets.sym
|
|
endif
|
|
|
|
ifeq ($(subdir),wcsmbs)
|
|
|
|
sysdep_routines += \
|
|
wcpcpy-generic \
|
|
wcpncpy-generic \
|
|
wcscat-generic \
|
|
wcscpy-generic \
|
|
wcsncat-generic \
|
|
wcsncmp-generic \
|
|
wcsncpy-generic \
|
|
wcsnlen-generic \
|
|
# sysdep_routines
|
|
|
|
tests += \
|
|
tst-rsi-wcslen
|
|
endif
|
|
|
|
do-tests-clean common-mostlyclean: tst-x86_64-1-clean
|
|
|
|
.PHONY: tst-x86_64-1-clean
|
|
tst-x86_64-1-clean:
|
|
-rm -rf $(objpfx)x86_64
|
|
|
|
$(objpfx)x86_64/tst-platformmod-2.os: $(objpfx)tst-platformmod-2.os
|
|
$(make-target-directory)
|
|
rm -f $@
|
|
ln $< $@
|