[Pixman] [PATCH v5 0/4] Two ARMv6 optimizations

Pekka Paalanen ppaalanen at gmail.com
Wed Apr 9 06:25:28 PDT 2014

From: Pekka Paalanen <pekka.paalanen at collabora.co.uk>


this is a re-send of the two series that ended with
"ARMv6: Add fast path for over_n_8888_8888_ca" and
"ARMv6: Add fast path for in_reverse_8888_8888", i.e.
combined into one series, just like I benchmarked them.

The bug in over_n_8888_8888_ca has been fixed.

Ben Avison (4):
  ARMv6: Support for very variable-hungry composite operations
  ARMv6: Add fast path for over_n_8888_8888_ca
  ARMv6: Add fast path flag to force no preload of destination buffer
  ARMv6: Add fast path for in_reverse_8888_8888

 pixman/pixman-arm-simd-asm.S | 370 +++++++++++++++++++++++++++++++++++++++++++
 pixman/pixman-arm-simd-asm.h |  80 +++++++++-
 pixman/pixman-arm-simd.c     |  15 ++
 3 files changed, 459 insertions(+), 6 deletions(-)


More information about the Pixman mailing list