mirror of git://sourceware.org/git/glibc.git
345 lines
16 KiB
Makefile
345 lines
16 KiB
Makefile
ifeq ($(subdir),math)
|
|
|
|
#
|
|
# Only enable ifunc _Float128 support if the baseline cpu support
|
|
# is older than power9.
|
|
ifneq (yes,$(libc-submachine-power9))
|
|
do_f128_multiarch = yes
|
|
endif
|
|
|
|
#
|
|
# This is an ugly, but contained, mechanism to provide hardware optimized
|
|
# _Float128 and ldouble == ieee128 optimized routines for P9 and beyond
|
|
# hardware. At a very high level, we rely on ASM renames, and rarely
|
|
# macro renames to build two sets of _Float128 ABI, one with _power8 (the
|
|
# baseline powerpc64le cpu) and _power9 (the first powerpc64le cpu to introduce
|
|
# hardware support for _Float128).
|
|
#
|
|
# At a high level, we compile 3 files for each object file.
|
|
# 1. The baseline soft-float128, unsuffixed objects $(object).$(sfx)
|
|
# The symbols contained in these files is suffixed by _power8.
|
|
# 2. The hard-float128, power9, suffixed objects $(object)-power9.$(sfx).
|
|
# The symbols contained in these files is suffixed by _power9.
|
|
# 3. The IFUNC wrapper object to export ABI, $(object)-ifunc.$(sfx)
|
|
# This glues the above together and implements the ABI.
|
|
#
|
|
# 2 & 3 are automatically generated by Makefile rule. Placing the exported
|
|
# ABI into a separate file allows reuse of existing aliasing macros
|
|
# with minimal hassle.
|
|
#
|
|
#
|
|
# If the float128 ABI is expanded, and a new ifunc wrappers are desired,
|
|
# the following lists how to map new symbols from the shared headers into
|
|
# their local overrides here:
|
|
#
|
|
# float128_private.h
|
|
#
|
|
# is used to rename the ldouble == ieee128 object files. This takes
|
|
# it a step further and redirects symbols to a local name. This supports
|
|
# nearly all files in sysdeps/ieee754/float128, but not all _Float128
|
|
# objects. However, this is only meant to be used internally to support
|
|
# compilation of ldbl-128 into float128.
|
|
#
|
|
# math-type-macros-float128.h
|
|
#
|
|
# renames symbols which are generated via shared templated in math/.
|
|
#
|
|
# math_private.h
|
|
#
|
|
# provides internal declarations for common macros and functions which
|
|
# are called from within libm. Note, float128_private.h duplicates
|
|
# some of these declarations as these headers are generally not included
|
|
# in the same translation unit.
|
|
#
|
|
# The above is supported by several header files as described below:
|
|
#
|
|
# float128-ifunc.h
|
|
#
|
|
# provides support for generating the IFUNC objects in part 3 above.
|
|
# This header is only included with wrapper functions.
|
|
#
|
|
# float128-ifunc-macros.h
|
|
#
|
|
# disables all first-order float128 aliasing macros used in libm,
|
|
# and libm wrappers around libc-symbols.h.
|
|
#
|
|
# float128-ifunc-redirect-macros.h
|
|
#
|
|
# provides macros which implement the appending of the suffix to
|
|
# symbols what have been selected.
|
|
#
|
|
# float128-ifunc-redirects.h
|
|
#
|
|
# provides ASM redirects for symbols which are redirected in the
|
|
# private copy of math.h used by glibc, but not declared by math_private.h
|
|
#
|
|
# float128-ifunc-redirects-mp.h
|
|
#
|
|
# provides ASM redirects which are used by math_private.h (the -mp suffix)
|
|
# and the interposer float128_private.h discussed late.
|
|
#
|
|
# Notably, this enforces a slightly different mechanism for machine specific
|
|
# overrides. Optimizations for all targets must all be reachable from the same
|
|
# file. See the history to fmaf128 or sqrtf128 to understand how this looks
|
|
# in practice.
|
|
#
|
|
ifeq ($(do_f128_multiarch),yes)
|
|
|
|
f128-ifunc-calls = s_modff128 s_scalbnf128 s_frexpf128 s_ldexpf128
|
|
gen-libm-f128-ifunc-routines = \
|
|
e_acosf128 e_acoshf128 e_asinf128 e_atan2f128 e_atanhf128 e_coshf128 \
|
|
e_expf128 e_fmodf128 e_hypotf128 e_j0f128 e_j1f128 e_jnf128 \
|
|
e_lgammaf128_r e_logf128 e_log10f128 e_powf128 e_remainderf128 \
|
|
e_sinhf128 e_sqrtf128 e_gammaf128_r e_ilogbf128 k_tanf128 s_asinhf128 \
|
|
s_atanf128 s_cbrtf128 s_ceilf128 s_cosf128 s_erff128 s_expm1f128 \
|
|
s_fabsf128 s_floorf128 s_log1pf128 s_logbf128 \
|
|
s_rintf128 s_scalblnf128 s_sinf128 s_tanf128 \
|
|
s_tanhf128 s_truncf128 s_remquof128 e_log2f128 \
|
|
s_roundf128 s_nearbyintf128 s_sincosf128 s_fmaf128 s_lrintf128 \
|
|
s_llrintf128 s_lroundf128 s_llroundf128 e_exp10f128 \
|
|
$(f128-ifunc-calls) $(f128-ifunc-calls:s_%=m_%) x2y2m1f128 \
|
|
gamma_productf128 lgamma_negf128 lgamma_productf128 s_roundevenf128 \
|
|
cargf128 conjf128 cimagf128 crealf128 cabsf128 e_scalbf128 s_cacosf128 \
|
|
s_cacoshf128 s_ccosf128 s_ccoshf128 s_casinf128 s_csinf128 \
|
|
s_casinhf128 k_casinhf128 s_csinhf128 k_casinhf128 s_csinhf128 \
|
|
s_catanhf128 s_catanf128 s_ctanf128 s_ctanhf128 s_cexpf128 s_clogf128 \
|
|
s_cprojf128 s_csqrtf128 s_cpowf128 s_clog10f128 s_fdimf128 \
|
|
s_fmaxf128 s_fminf128 w_ilogbf128 w_llogbf128 \
|
|
w_log1pf128 w_scalblnf128 w_acosf128 \
|
|
w_acoshf128 w_asinf128 w_atan2f128 w_atanhf128 w_coshf128 w_exp10f128 \
|
|
w_exp2f128 w_fmodf128 w_hypotf128 w_j0f128 w_j1f128 w_jnf128 \
|
|
w_logf128 w_log10f128 w_log2f128 w_powf128 w_remainderf128 \
|
|
w_scalbf128 w_sinhf128 w_sqrtf128 w_tgammaf128 w_lgammaf128 \
|
|
w_lgammaf128_r w_expf128 e_exp2f128 \
|
|
k_sinf128 k_cosf128 k_sincosf128 e_rem_pio2f128
|
|
|
|
|
|
f128-march-routines-p9 = $(addsuffix -power9,$(gen-libm-f128-ifunc-routines))
|
|
f128-march-routines-ifunc = $(addsuffix -ifunc,$(gen-libm-f128-ifunc-routines))
|
|
f128-march-routines = $(f128-march-routines-p9) $(f128-march-routines-ifunc)
|
|
f128-march-cpus = power9
|
|
|
|
f128-march-calls-p9 = $(addsuffix -power9,$(f128-ifunc-calls))
|
|
f128-march-calls-ifunc = $(addsuffix -ifunc,$(f128-ifunc-calls))
|
|
f128-march-calls = $(f128-march-calls-p9) $(f128-march-calls-ifunc)
|
|
|
|
calls += $(f128-march-calls)
|
|
libm-routines += $(filter-out $(f128-march-calls), $(f128-march-routines))
|
|
generated += $(f128-march-routines)
|
|
|
|
CFLAGS-float128-ifunc.c += $(type-float128-CFLAGS) $(no-gnu-attribute-CFLAGS)
|
|
|
|
# Copy special CFLAGS for some functions
|
|
CFLAGS-s_modff128-power9.c += $(config-cflags-signaling-nans)
|
|
CFLAGS-m_modff128-power9.c += $(config-cflags-signaling-nans)
|
|
|
|
# Generate ifunc wrapper files and target specific wrappers around
|
|
# each routine above. Note, m_%.c files are fixed up to include
|
|
# s_%.c files. This is an artifact of the makefile rules which allow
|
|
# some files to be compiled for libc and libm.
|
|
$(objpfx)gen-float128-ifuncs.stmp: \
|
|
Makefile $(..)sysdeps/powerpc/powerpc64/le/fpu/multiarch/Makefile
|
|
$(make-target-directory)
|
|
for gcall in $(gen-libm-f128-ifunc-routines); do \
|
|
ifile="$${gcall}"; \
|
|
if [ $${gcall##m_} != $${gcall} ]; then \
|
|
ifile="s_$${gcall##m_}"; \
|
|
fi; \
|
|
for cpu in $(f128-march-cpus); do \
|
|
file=$(objpfx)$${gcall}-$${cpu}.c; \
|
|
{ \
|
|
echo "#include <$${ifile}.c>"; \
|
|
} > $${file}; \
|
|
done; \
|
|
name="$${gcall##?_}"; \
|
|
pfx="$${gcall%%_*}"; \
|
|
R=""; \
|
|
r=""; \
|
|
if [ $${gcall##m_} != $${gcall} ]; then \
|
|
pfx="s"; \
|
|
fi; \
|
|
if [ $${#pfx} != 1 ]; then \
|
|
pfx=""; \
|
|
else \
|
|
pfx="_$${pfx}"; \
|
|
fi; \
|
|
if [ $${name%%_r} != $${name} ]; then \
|
|
R="_R"; \
|
|
r="_r"; \
|
|
name="$${name%%_r}"; \
|
|
fi; \
|
|
name="$${name%%f128}"; \
|
|
decl="DECL_ALIAS$${pfx}_$${name}$${r}"; \
|
|
compat="GEN_COMPAT$${pfx}_$${name}$${r}"; \
|
|
declc="DECL_ALIAS$${R}$${pfx}"; \
|
|
{ \
|
|
echo "#include <float128-ifunc.h>"; \
|
|
echo "#ifndef $${decl}"; \
|
|
echo "# define $${decl}(f) $${declc} (f)"; \
|
|
echo "#endif"; \
|
|
echo "#ifndef $${compat}"; \
|
|
echo "# define $${compat}(f)"; \
|
|
echo "#endif"; \
|
|
echo "$${decl} ($${name});"; \
|
|
echo "$${compat} ($${name});"; \
|
|
} > $(objpfx)$${gcall}-ifunc.c; \
|
|
done; \
|
|
echo > $(@)
|
|
|
|
$(foreach f,$(f128-march-routines),$(objpfx)$(f).c): \
|
|
$(objpfx)gen-float128-ifuncs.stmp $(objpfx)gen-libm-templates.stmp
|
|
|
|
enable-f128-ifunc-CFLAGS = -D_F128_ENABLE_IFUNC $(no-gnu-attributes-CFLAGS) $(type-float128-CFLAGS)
|
|
|
|
# Enable IFUNC on baseline (power8) implementations
|
|
include $(o-iterator)
|
|
define o-iterator-doit
|
|
$(foreach f,$(gen-libm-f128-ifunc-routines),$(objpfx)$(f)$(o)): sysdep-CFLAGS += -D_F128_ENABLE_IFUNC
|
|
endef
|
|
object-suffixes-left := $(all-object-suffixes)
|
|
include $(o-iterator)
|
|
|
|
# Likewise, but for power9.
|
|
include $(o-iterator)
|
|
define o-iterator-doit
|
|
$(foreach f,$(f128-march-routines-p9),$(objpfx)$(f)$(o)): sysdep-CFLAGS += $$(enable-f128-ifunc-CFLAGS) -mcpu=power9
|
|
endef
|
|
object-suffixes-left := $(all-object-suffixes)
|
|
include $(o-iterator)
|
|
|
|
CFLAGS-w_acosf128-ifunc.c += -fno-builtin-acosf64x
|
|
CFLAGS-w_acoshf128-ifunc.c += -fno-builtin-acoshf64x
|
|
CFLAGS-w_asinf128-ifunc.c += -fno-builtin-asinf64x
|
|
CFLAGS-s_asinhf128-ifunc.c += -fno-builtin-asinhf64x
|
|
CFLAGS-s_atanf128-ifunc.c += -fno-builtin-atanf64x
|
|
CFLAGS-w_atan2f128-ifunc.c += -fno-builtin-atan2f64x
|
|
CFLAGS-w_atanhf128-ifunc.c += -fno-builtin-atanhf64x
|
|
CFLAGS-s_cabsf128-ifunc.c += -fno-builtin-cabsf64x
|
|
CFLAGS-s_cacosf128-ifunc.c += -fno-builtin-cacosf64x
|
|
CFLAGS-s_cacoshf128-ifunc.c += -fno-builtin-cacoshf64x
|
|
CFLAGS-s_canonicalizef128-ifunc.c += -fno-builtin-canonicalizef64x
|
|
CFLAGS-s_cargf128-ifunc.c += -fno-builtin-cargf64x
|
|
CFLAGS-s_casinf128-ifunc.c += -fno-builtin-casinf64x
|
|
CFLAGS-s_casinhf128-ifunc.c += -fno-builtin-casinhf64x
|
|
CFLAGS-s_catanf128-ifunc.c += -fno-builtin-catanf64x
|
|
CFLAGS-s_catanhf128-ifunc.c += -fno-builtin-catanhf64x
|
|
CFLAGS-s_cbrtf128-ifunc.c += -fno-builtin-cbrtf64x
|
|
CFLAGS-s_ccosf128-ifunc.c += -fno-builtin-ccosf64x
|
|
CFLAGS-s_ccoshf128-ifunc.c += -fno-builtin-ccoshf64x
|
|
CFLAGS-s_ceilf128-ifunc.c += -fno-builtin-ceilf64x
|
|
CFLAGS-s_cexpf128-ifunc.c += -fno-builtin-cexpf64x
|
|
CFLAGS-s_cimagf128-ifunc.c += -fno-builtin-cimagf64x
|
|
CFLAGS-s_clogf128-ifunc.c += -fno-builtin-clogf64x
|
|
CFLAGS-s_clog10f128-ifunc.c += -fno-builtin-clog10f64x
|
|
CFLAGS-s_conjf128-ifunc.c += -fno-builtin-conjf64x
|
|
CFLAGS-s_copysignf128-ifunc.c += -fno-builtin-copysignf64x
|
|
CFLAGS-s_cosf128-ifunc.c += -fno-builtin-cosf64x
|
|
CFLAGS-w_coshf128-ifunc.c += -fno-builtin-coshf64x
|
|
CFLAGS-s_cpowf128-ifunc.c += -fno-builtin-cpowf64x
|
|
CFLAGS-s_cprojf128-ifunc.c += -fno-builtin-cprojf64x
|
|
CFLAGS-s_crealf128-ifunc.c += -fno-builtin-crealf64x
|
|
CFLAGS-s_csinf128-ifunc.c += -fno-builtin-csinf64x
|
|
CFLAGS-s_csinhf128-ifunc.c += -fno-builtin-csinhf64x
|
|
CFLAGS-s_csqrtf128-ifunc.c += -fno-builtin-csqrtf64x
|
|
CFLAGS-s_ctanf128-ifunc.c += -fno-builtin-ctanf64x
|
|
CFLAGS-s_ctanhf128-ifunc.c += -fno-builtin-ctanhf64x
|
|
CFLAGS-s_daddf128-ifunc.c += -fno-builtin-f64addf64x
|
|
CFLAGS-s_ddivf128-ifunc.c += -fno-builtin-f64divf64x
|
|
CFLAGS-s_dfmaf128-ifunc.c += -fno-builtin-f64fmaf64x
|
|
CFLAGS-s_dmulf128-ifunc.c += -fno-builtin-f64mulf64x
|
|
CFLAGS-s_dsqrtf128-ifunc.c += -fno-builtin-f64sqrtf64x
|
|
CFLAGS-s_dsubf128-ifunc.c += -fno-builtin-f64subf64x
|
|
CFLAGS-s_erff128-ifunc.c += -fno-builtin-erff64x
|
|
CFLAGS-s_erfcf128-ifunc.c += -fno-builtin-erfcf64x
|
|
CFLAGS-e_expf128-ifunc.c += -fno-builtin-expf64x
|
|
CFLAGS-w_exp10f128-ifunc.c += -fno-builtin-exp10f64x
|
|
CFLAGS-e_exp2f128-ifunc.c += -fno-builtin-exp2f64x
|
|
CFLAGS-s_expm1f128-ifunc.c += -fno-builtin-expm1f64x
|
|
CFLAGS-s_fabsf128-ifunc.c += -fno-builtin-fabsf64x
|
|
CFLAGS-s_faddf128-ifunc.c += -fno-builtin-f32addf64x
|
|
CFLAGS-s_fdimf128-ifunc.c += -fno-builtin-fdimf64x
|
|
CFLAGS-s_fdivf128-ifunc.c += -fno-builtin-f32divf64x
|
|
CFLAGS-s_ffmaf128-ifunc.c += -fno-builtin-f32fmaf64x
|
|
CFLAGS-s_floorf128-ifunc.c += -fno-builtin-floorf64x
|
|
CFLAGS-s_fmaf128-ifunc.c += -fno-builtin-fmaf64x
|
|
CFLAGS-s_fmaxf128-ifunc.c += -fno-builtin-fmaxf64x
|
|
CFLAGS-s_fmaximumf128-ifunc.c += -fno-builtin-fmaximumf64x
|
|
CFLAGS-s_fmaximum_magf128-ifunc.c += -fno-builtin-fmaximum_magf64x
|
|
CFLAGS-s_fmaximum_mag_numf128-ifunc.c += -fno-builtin-fmaximum_mag_numf64x
|
|
CFLAGS-s_fmaximum_numf128-ifunc.c += -fno-builtin-fmaximum_numf64x
|
|
CFLAGS-s_fmaxmagf128-ifunc.c += -fno-builtin-fmaxmagf64x
|
|
CFLAGS-s_fminf128-ifunc.c += -fno-builtin-fminf64x
|
|
CFLAGS-s_fminimumf128-ifunc.c += -fno-builtin-fminimumf64x
|
|
CFLAGS-s_fminimum_magf128-ifunc.c += -fno-builtin-fminimum_magf64x
|
|
CFLAGS-s_fminimum_mag_numf128-ifunc.c += -fno-builtin-fminimum_mag_numf64x
|
|
CFLAGS-s_fminimum_numf128-ifunc.c += -fno-builtin-fminimum_numf64x
|
|
CFLAGS-s_fminmagf128-ifunc.c += -fno-builtin-fminmagf64x
|
|
CFLAGS-w_fmodf128-ifunc.c += -fno-builtin-fmodf64x
|
|
CFLAGS-s_fmulf128-ifunc.c += -fno-builtin-f32mulf64x
|
|
CFLAGS-s_frexpf128-ifunc.c += -fno-builtin-frexpf64x
|
|
CFLAGS-s_fromfpf128-ifunc.c += -fno-builtin-fromfpf64x
|
|
CFLAGS-s_fromfpxf128-ifunc.c += -fno-builtin-fromfpxf64x
|
|
CFLAGS-s_fsqrtf128-ifunc.c += -fno-builtin-f32sqrtf64x
|
|
CFLAGS-s_fsubf128-ifunc.c += -fno-builtin-f32subf64x
|
|
CFLAGS-s_getpayloadf128-ifunc.c += -fno-builtin-getpayloadf64x
|
|
CFLAGS-w_hypotf128-ifunc.c += -fno-builtin-hypotf64x
|
|
CFLAGS-w_ilogbf128-ifunc.c += -fno-builtin-ilogbf64x
|
|
CFLAGS-w_j0f128-ifunc.c += -fno-builtin-j0f64x
|
|
CFLAGS-w_j1f128-ifunc.c += -fno-builtin-j1f64x
|
|
CFLAGS-w_jnf128-ifunc.c += -fno-builtin-jnf64x
|
|
CFLAGS-s_ldexpf128-ifunc.c += -fno-builtin-ldexpf64x
|
|
CFLAGS-w_lgammaf128-ifunc.c += -fno-builtin-lgammaf64x
|
|
CFLAGS-w_lgammaf128_r-ifunc.c += -fno-builtin-lgammaf64x_r
|
|
CFLAGS-w_llogbf128-ifunc.c += -fno-builtin-llogbf64x
|
|
CFLAGS-s_llrintf128-ifunc.c += -fno-builtin-llrintf64x
|
|
CFLAGS-s_llroundf128-ifunc.c += -fno-builtin-llroundf64x
|
|
CFLAGS-e_logf128-ifunc.c += -fno-builtin-logf64x
|
|
CFLAGS-w_log10f128-ifunc.c += -fno-builtin-log10f64x
|
|
CFLAGS-w_log1pf128-ifunc.c += -fno-builtin-log1pf64x
|
|
CFLAGS-e_log2f128-ifunc.c += -fno-builtin-log2f64x
|
|
CFLAGS-s_logbf128-ifunc.c += -fno-builtin-logbf64x
|
|
CFLAGS-s_lrintf128-ifunc.c += -fno-builtin-lrintf64x
|
|
CFLAGS-s_lroundf128-ifunc.c += -fno-builtin-lroundf64x
|
|
CFLAGS-s_modff128-ifunc.c += -fno-builtin-modff64x
|
|
CFLAGS-s_nanf128-ifunc.c += -fno-builtin-nanf64x
|
|
CFLAGS-s_nearbyintf128-ifunc.c += -fno-builtin-nearbyintf64x
|
|
CFLAGS-s_nextafterf128-ifunc.c += -fno-builtin-nextafterf64x
|
|
CFLAGS-s_nextdownf128-ifunc.c += -fno-builtin-nextdownf64x
|
|
CFLAGS-s_nextupf128-ifunc.c += -fno-builtin-nextupf64x
|
|
CFLAGS-e_powf128-ifunc.c += -fno-builtin-powf64x
|
|
CFLAGS-w_remainderf128-ifunc.c += -fno-builtin-remainderf64x
|
|
CFLAGS-s_remquof128-ifunc.c += -fno-builtin-remquof64x
|
|
CFLAGS-s_rintf128-ifunc.c += -fno-builtin-rintf64x
|
|
CFLAGS-s_roundf128-ifunc.c += -fno-builtin-roundf64x
|
|
CFLAGS-s_roundevenf128-ifunc.c += -fno-builtin-roundevenf64x
|
|
CFLAGS-w_scalblnf128-ifunc.c += -fno-builtin-scalblnf64x
|
|
CFLAGS-s_scalbnf128-ifunc.c += -fno-builtin-scalbnf64x
|
|
CFLAGS-s_setpayloadf128-ifunc.c += -fno-builtin-setpayloadf64x
|
|
CFLAGS-s_setpayloadsigf128-ifunc.c += -fno-builtin-setpayloadsigf64x
|
|
CFLAGS-s_sinf128-ifunc.c += -fno-builtin-sinf64x
|
|
CFLAGS-s_sincosf128-ifunc.c += -fno-builtin-sincosf64x
|
|
CFLAGS-w_sinhf128-ifunc.c += -fno-builtin-sinhf64x
|
|
CFLAGS-w_sqrtf128-ifunc.c += -fno-builtin-sqrtf64x
|
|
CFLAGS-s_tanf128-ifunc.c += -fno-builtin-tanf64x
|
|
CFLAGS-s_tanhf128-ifunc.c += -fno-builtin-tanhf64x
|
|
CFLAGS-w_tgammaf128-ifunc.c += -fno-builtin-tgammaf64x
|
|
CFLAGS-s_totalorderf128-ifunc.c += -fno-builtin-totalorderf64x
|
|
CFLAGS-s_totalordermagf128-ifunc.c += -fno-builtin-totalordermagf64x
|
|
CFLAGS-s_truncf128-ifunc.c += -fno-builtin-truncf64x
|
|
CFLAGS-s_ufromfpf128-ifunc.c += -fno-builtin-ufromfpf64x
|
|
CFLAGS-s_ufromfpxf128-ifunc.c += -fno-builtin-ufromfpxf64x
|
|
CFLAGS-s_y0f128-ifunc.c += -fno-builtin-y0f64x
|
|
CFLAGS-s_y1f128-ifunc.c += -fno-builtin-y1f64x
|
|
CFLAGS-s_ynf128-ifunc.c += -fno-builtin-ynf64x
|
|
|
|
endif # do_f128_multiarch
|
|
|
|
libm-sysdep_routines += e_log-ppc64
|
|
|
|
ifeq ($(mcpu-power10), yes)
|
|
libm-sysdep_routines += e_log-power10
|
|
CFLAGS-e_log-power10.c += -mcpu=power10
|
|
endif
|
|
|
|
endif
|