Age | Commit message (Collapse) | Author |
|
GCC added support for -mfma4 in version 4.5. Thus the configure tests
for this support are obsolete, and this patch removes them.
Tested for x86_64 and x86 (testsuite, and that installed stripped
shared libraries are unchanged by this patch).
* sysdeps/i386/configure.ac (libc_cv_cc_fma4): Remove configure
test.
* sysdeps/i386/configure: Regenerated.
* sysdeps/x86_64/configure.ac (libc_cv_cc_fma4): Remove configure
test.
* sysdeps/x86_64/configure: Regenerated.
* sysdeps/x86_64/fpu/multiarch/Makefile [$(have-mfma4) = yes]:
Make code unconditional.
* sysdeps/x86_64/fpu/multiarch/e_asin.c [HAVE_FMA4_SUPPORT]:
Likewise.
* sysdeps/x86_64/fpu/multiarch/e_atan2.c [HAVE_FMA4_SUPPORT]:
Likewise.
[!HAVE_FMA4_SUPPORT]: Remove conditional code.
* sysdeps/x86_64/fpu/multiarch/e_exp.c [HAVE_FMA4_SUPPORT]: Make
code unconditional.
[!HAVE_FMA4_SUPPORT]: Remove conditional code.
* sysdeps/x86_64/fpu/multiarch/e_log.c [HAVE_FMA4_SUPPORT]: Make
code unconditional.
[!HAVE_FMA4_SUPPORT]: Remove conditional code.
* sysdeps/x86_64/fpu/multiarch/e_pow.c [HAVE_FMA4_SUPPORT]: Make
code unconditional.
* sysdeps/x86_64/fpu/multiarch/s_atan.c [HAVE_FMA4_SUPPORT]: Make
code unconditional.
[!HAVE_FMA4_SUPPORT]: Remove conditional code.
* sysdeps/x86_64/fpu/multiarch/s_fma.c [HAVE_FMA4_SUPPORT]: Make
code unconditional.
[!HAVE_FMA4_SUPPORT]: Remove conditional code.
* sysdeps/x86_64/fpu/multiarch/s_fmaf.c [HAVE_FMA4_SUPPORT]: Make
code unconditional.
[!HAVE_FMA4_SUPPORT]: Remove conditional code.
* sysdeps/x86_64/fpu/multiarch/s_sin.c [HAVE_FMA4_SUPPORT]: Make
code unconditional.
[!HAVE_FMA4_SUPPORT]: Remove conditional code.
* sysdeps/x86_64/fpu/multiarch/s_tan.c [HAVE_FMA4_SUPPORT]: Make
code unconditional.
[!HAVE_FMA4_SUPPORT]: Remove conditional code.
* config.h.in (HAVE_FMA4_SUPPORT): Remove #undef.
|
|
GCC added support for -mavx and -msse2avx in version 4.4. Thus the
configure tests for this support are obsolete, and this patch removes
them.
Tested for x86_64 and x86 (testsuite, and that installed stripped
shared libraries are unchanged by this patch).
* sysdeps/i386/configure.ac (libc_cv_cc_avx): Remove configure
test.
(libc_cv_cc_sse2avx): Likewise.
* sysdeps/i386/configure: Regenerated.
* sysdeps/i386/i686/multiarch/Makefile
[$(subdir)$(config-cflags-avx) = mathyes]: Change conditional to
[$(subdir) = math].
* sysdeps/i386/i686/multiarch/s_fma-fma.c [HAVE_AVX_SUPPORT]: Make
code unconditional.
* sysdeps/i386/i686/multiarch/s_fma.c [HAVE_AVX_SUPPORT]:
Likewise.
* sysdeps/i386/i686/multiarch/s_fmaf-fma.c [HAVE_AVX_SUPPORT]:
Likewise.
* sysdeps/i386/i686/multiarch/s_fmaf.c [HAVE_AVX_SUPPORT]:
Likewise.
* sysdeps/x86_64/configure.ac (libc_cv_cc_avx): Remove configure
test.
(libc_cv_cc_sse2avx): Likewise.
* sysdeps/x86_64/configure: Regenerated.
* sysdeps/x86_64/Makefile [$(config-cflags-avx) = yes]: Make code
unconditional.
* sysdeps/x86_64/dl-trampoline.h (_dl_runtime_profile)
[HAVE_AVX_SUPPORT || HAVE_AVX512_ASM_SUPPORT]: Make code
unconditional.
(_dl_runtime_profile)
[!(HAVE_AVX_SUPPORT || HAVE_AVX512_ASM_SUPPORT)]: Remove
conditional code.
* sysdeps/x86_64/fpu/multiarch/Makefile
[$(config-cflags-sse2avx) = yes]: Make code unconditional.
* sysdeps/x86_64/fpu/multiarch/e_atan2.c
[HAVE_FMA4_SUPPORT || HAVE_AVX_SUPPORT]: Likewise.
* sysdeps/x86_64/fpu/multiarch/e_exp.c
[HAVE_FMA4_SUPPORT || HAVE_AVX_SUPPORT]: Likewise.
* sysdeps/x86_64/fpu/multiarch/e_log.c
[HAVE_FMA4_SUPPORT || HAVE_AVX_SUPPORT]: Likewise.
* sysdeps/x86_64/fpu/multiarch/s_atan.c
[HAVE_FMA4_SUPPORT || HAVE_AVX_SUPPORT]: Likewise.
* sysdeps/x86_64/fpu/multiarch/s_fma.c [HAVE_AVX_SUPPORT]:
Likewise.
* sysdeps/x86_64/fpu/multiarch/s_fmaf.c [HAVE_AVX_SUPPORT]:
Likewise.
* sysdeps/x86_64/fpu/multiarch/s_sin.c
[HAVE_FMA4_SUPPORT || HAVE_AVX_SUPPORT]: Likewise.
* sysdeps/x86_64/fpu/multiarch/s_tan.c
[HAVE_FMA4_SUPPORT || HAVE_AVX_SUPPORT]: Likewise.
* sysdeps/x86_64/multiarch/strcmp.S [HAVE_AVX_SUPPORT]: Likewise.
* config.h.in (HAVE_AVX_SUPPORT): Remove #undef.
(HAVE_SSE2AVX_SUPPORT): Likewise.
|
|
This patch updates x86_64 multiarch functions to use the newly defined
HAS_CPU_FEATURE, HAS_ARCH_FEATURE and LOAD_RTLD_GLOBAL_RO_RDX from
<cpu-features.h>.
* sysdeps/x86_64/fpu/multiarch/e_asin.c: Replace HAS_XXX with
HAS_CPU_FEATURE/HAS_ARCH_FEATURE (XXX).
* sysdeps/x86_64/fpu/multiarch/e_atan2.c: Likewise.
* sysdeps/x86_64/fpu/multiarch/e_exp.c: Likewise.
* sysdeps/x86_64/fpu/multiarch/e_log.c: Likewise.
* sysdeps/x86_64/fpu/multiarch/e_pow.c: Likewise.
* sysdeps/x86_64/fpu/multiarch/s_atan.c: Likewise.
* sysdeps/x86_64/fpu/multiarch/s_fma.c: Likewise.
* sysdeps/x86_64/fpu/multiarch/s_fmaf.c: Likewise.
* sysdeps/x86_64/fpu/multiarch/s_sin.c: Likewise.
* sysdeps/x86_64/fpu/multiarch/s_tan.c: Likewise.
* sysdeps/x86_64/fpu/multiarch/s_ceil.S: Use
LOAD_RTLD_GLOBAL_RO_RDX and HAS_CPU_FEATURE (SSE4_1).
* sysdeps/x86_64/fpu/multiarch/s_ceilf.S: Likewise.
* sysdeps/x86_64/fpu/multiarch/s_floor.S: Likewise.
* sysdeps/x86_64/fpu/multiarch/s_floorf.S: Likewise.
* sysdeps/x86_64/fpu/multiarch/s_nearbyint.S : Likewise.
* sysdeps/x86_64/fpu/multiarch/s_nearbyintf.S: Likewise.
* sysdeps/x86_64/fpu/multiarch/s_rintf.S: Likewise.
* sysdeps/x86_64/fpu/multiarch/s_rintf.S : Likewise.
* sysdeps/x86_64/multiarch/ifunc-impl-list.c: Likewise.
* sysdeps/x86_64/multiarch/sched_cpucount.c: Likewise.
* sysdeps/x86_64/multiarch/strstr.c: Likewise.
* sysdeps/x86_64/multiarch/memmove.c: Likewise.
* sysdeps/x86_64/multiarch/memmove_chk.c: Likewise.
* sysdeps/x86_64/multiarch/test-multiarch.c: Likewise.
* sysdeps/x86_64/multiarch/memcmp.S: Remove __init_cpu_features
call. Add LOAD_RTLD_GLOBAL_RO_RDX. Replace HAS_XXX with
HAS_CPU_FEATURE/HAS_ARCH_FEATURE (XXX).
* sysdeps/x86_64/multiarch/memcpy.S: Likewise.
* sysdeps/x86_64/multiarch/memcpy_chk.S: Likewise.
* sysdeps/x86_64/multiarch/mempcpy.S: Likewise.
* sysdeps/x86_64/multiarch/mempcpy_chk.S: Likewise.
* sysdeps/x86_64/multiarch/memset.S: Likewise.
* sysdeps/x86_64/multiarch/memset_chk.S: Likewise.
* sysdeps/x86_64/multiarch/strcat.S: Likewise.
* sysdeps/x86_64/multiarch/strchr.S: Likewise.
* sysdeps/x86_64/multiarch/strcmp.S: Likewise.
* sysdeps/x86_64/multiarch/strcpy.S: Likewise.
* sysdeps/x86_64/multiarch/strcspn.S: Likewise.
* sysdeps/x86_64/multiarch/strspn.S: Likewise.
* sysdeps/x86_64/multiarch/wcscpy.S: Likewise.
* sysdeps/x86_64/multiarch/wmemcmp.S: Likewise.
|
|
|
|
There is no problem with strcmp, it doesn't use the YMM registers.
The math routines might since gcc perhaps generates such code.
Introduce bit_YMM_USBALE and use it in the math routines.
|
|
|
|
|