summaryrefslogtreecommitdiff
path: root/NEWS
diff options
context:
space:
mode:
authorH.J. Lu <hjl.tools@gmail.com>2015-01-30 06:50:20 -0800
committerH.J. Lu <hjl.tools@gmail.com>2015-01-30 15:37:58 -0800
commit5f3d0b78e011d2a72f9e88b0e9ef5bc081d18f97 (patch)
tree8eabf127206283d2421bc40b6bc44e123e346598 /NEWS
parentb658fdd82b4524cf6a39881d092caa23f63d93ac (diff)
Use AVX unaligned memcpy only if AVX2 is available
memcpy with unaligned 256-bit AVX register loads/stores are slow on older processorsl like Sandy Bridge. This patch adds bit_AVX_Fast_Unaligned_Load and sets it only when AVX2 is available. [BZ #17801] * sysdeps/x86_64/multiarch/init-arch.c (__init_cpu_features): Set the bit_AVX_Fast_Unaligned_Load bit for AVX2. * sysdeps/x86_64/multiarch/init-arch.h (bit_AVX_Fast_Unaligned_Load): New. (index_AVX_Fast_Unaligned_Load): Likewise. (HAS_AVX_FAST_UNALIGNED_LOAD): Likewise. * sysdeps/x86_64/multiarch/memcpy.S (__new_memcpy): Check the bit_AVX_Fast_Unaligned_Load bit instead of the bit_AVX_Usable bit. * sysdeps/x86_64/multiarch/memcpy_chk.S (__memcpy_chk): Likewise. * sysdeps/x86_64/multiarch/mempcpy.S (__mempcpy): Likewise. * sysdeps/x86_64/multiarch/mempcpy_chk.S (__mempcpy_chk): Likewise. * sysdeps/x86_64/multiarch/memmove.c (__libc_memmove): Replace HAS_AVX with HAS_AVX_FAST_UNALIGNED_LOAD. * sysdeps/x86_64/multiarch/memmove_chk.c (__memmove_chk): Likewise.
Diffstat (limited to 'NEWS')
-rw-r--r--NEWS4
1 files changed, 2 insertions, 2 deletions
diff --git a/NEWS b/NEWS
index 8e2729bddd..c91b9fc58a 100644
--- a/NEWS
+++ b/NEWS
@@ -17,8 +17,8 @@ Version 2.21
17601, 17608, 17616, 17625, 17630, 17633, 17634, 17635, 17647, 17653,
17657, 17658, 17664, 17665, 17668, 17682, 17702, 17717, 17719, 17722,
17723, 17724, 17725, 17732, 17733, 17744, 17745, 17746, 17747, 17748,
- 17775, 17777, 17780, 17781, 17782, 17791, 17793, 17796, 17797, 17803,
- 17806, 17834, 17844, 17848, 17868, 17869, 17870, 17885, 17892.
+ 17775, 17777, 17780, 17781, 17782, 17791, 17793, 17796, 17797, 17801,
+ 17803, 17806, 17834, 17844, 17848, 17868, 17869, 17870, 17885, 17892.
* A new semaphore algorithm has been implemented in generic C code for all
machines. Previous custom assembly implementations of semaphore were