diff options
| author | Igor Zamyatin <igor.zamyatin@intel.com> | 2014-03-13 11:10:22 -0700 |
|---|---|---|
| committer | H.J. Lu <hjl.tools@gmail.com> | 2014-03-13 11:19:08 -0700 |
| commit | 2d63a517e4084ec80403cd9f278690fa8b676cc4 (patch) | |
| tree | d5d5dd025d9a59bd41fedf9c16799271b5dbb722 /sysdeps/x86_64/Makefile | |
| parent | 44c4e5d598bfcbb309f05ceb7a57ab02662e7f34 (diff) | |
| download | glibc-2d63a517e4084ec80403cd9f278690fa8b676cc4.tar glibc-2d63a517e4084ec80403cd9f278690fa8b676cc4.tar.gz glibc-2d63a517e4084ec80403cd9f278690fa8b676cc4.tar.bz2 glibc-2d63a517e4084ec80403cd9f278690fa8b676cc4.zip | |
Save and restore AVX-512 zmm registers to x86-64 ld.so
AVX-512 ISA adds 512-bit zmm registers. This patch updates
_dl_runtime_profile to pass zmm registers to run-time audit. It also
changes _dl_x86_64_save_sse and _dl_x86_64_restore_sse to upport zmm
registers, which are called when only when RTLD_PREPARE_FOREIGN_CALL
is used. Its performance impact is minimum.
* config.h.in (HAVE_AVX512_SUPPORT): New #undef.
(HAVE_AVX512_ASM_SUPPORT): Likewise.
* sysdeps/x86_64/bits/link.h (La_x86_64_zmm): New.
(La_x86_64_vector): Add zmm.
* sysdeps/x86_64/Makefile (tests): Add tst-audit10.
(modules-names): Add tst-auditmod10a and tst-auditmod10b.
($(objpfx)tst-audit10): New target.
($(objpfx)tst-audit10.out): Likewise.
(tst-audit10-ENV): New.
(AVX512-CFLAGS): Likewise.
(CFLAGS-tst-audit10.c): Likewise.
(CFLAGS-tst-auditmod10a.c): Likewise.
(CFLAGS-tst-auditmod10b.c): Likewise.
* sysdeps/x86_64/configure.ac: Set config-cflags-avx512,
HAVE_AVX512_SUPPORT and HAVE_AVX512_ASM_SUPPORT.
* sysdeps/x86_64/configure: Regenerated.
* sysdeps/x86_64/dl-trampoline.S (_dl_runtime_profile): Add
AVX-512 zmm register support.
(_dl_x86_64_save_sse): Likewise.
(_dl_x86_64_restore_sse): Likewise.
* sysdeps/x86_64/dl-trampoline.h: Updated to support different
size vector registers.
* sysdeps/x86_64/link-defines.sym (YMM_SIZE): New.
(ZMM_SIZE): Likewise.
* sysdeps/x86_64/tst-audit10.c: New file.
* sysdeps/x86_64/tst-auditmod10a.c: Likewise.
* sysdeps/x86_64/tst-auditmod10b.c: Likewise.
Diffstat (limited to 'sysdeps/x86_64/Makefile')
| -rw-r--r-- | sysdeps/x86_64/Makefile | 15 |
1 files changed, 13 insertions, 2 deletions
diff --git a/sysdeps/x86_64/Makefile b/sysdeps/x86_64/Makefile index 08db331923..58900a5c28 100644 --- a/sysdeps/x86_64/Makefile +++ b/sysdeps/x86_64/Makefile @@ -38,7 +38,7 @@ tests-pie += $(quad-pie-test) $(objpfx)tst-quad1pie: $(objpfx)tst-quadmod1pie.o $(objpfx)tst-quad2pie: $(objpfx)tst-quadmod2pie.o -tests += tst-audit3 tst-audit4 tst-audit5 +tests += tst-audit3 tst-audit4 tst-audit5 tst-audit10 ifeq (yes,$(config-cflags-avx)) tests += tst-audit6 tst-audit7 endif @@ -46,7 +46,8 @@ 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-auditmod7a tst-auditmod7b \ + tst-auditmod10a tst-auditmod10b $(objpfx)tst-audit3: $(objpfx)tst-auditmod3a.so $(objpfx)tst-audit3.out: $(objpfx)tst-auditmod3b.so @@ -69,6 +70,10 @@ $(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: $(objpfx)tst-auditmod10a.so +$(objpfx)tst-audit10.out: $(objpfx)tst-auditmod10b.so +tst-audit10-ENV = LD_AUDIT=$(objpfx)tst-auditmod10b.so + ifeq (yes,$(config-cflags-avx)) AVX-CFLAGS=-mavx ifeq (yes,$(config-cflags-novzeroupper)) @@ -81,6 +86,12 @@ CFLAGS-tst-auditmod6b.c += $(AVX-CFLAGS) CFLAGS-tst-auditmod6c.c += $(AVX-CFLAGS) CFLAGS-tst-auditmod7b.c += $(AVX-CFLAGS) endif +ifeq (yes,$(config-cflags-avx512)) +AVX512-CFLAGS = -mavx512f +CFLAGS-tst-audit10.c += $(AVX512-CFLAGS) +CFLAGS-tst-auditmod10a.c += $(AVX512-CFLAGS) +CFLAGS-tst-auditmod10b.c += $(AVX512-CFLAGS) +endif endif ifeq ($(subdir),csu) |