On Sun, 2 Mar 2014, Janne Grunau wrote:
Based on the aarch64 asm. CPU cycle counts on cortex-a9 compared to
gcc 4.8.2:
before: 475 decicycles in get_cabac_noinline, 67106035 runs, 2829 skips
after: 393 decicycles in get_cabac_noinline, 67106474 runs, 2390 skips
Overall speedup is above 2%. Code generated by clang 3.4 is slower on
the same hardware and the relative change is a little larger.
---
libavcodec/arm/cabac.h | 102 +++++++++++++++++++++++++++++++++++++++++++
libavcodec/cabac_functions.h | 3 ++
2 files changed, 105 insertions(+)
create mode 100644 libavcodec/arm/cabac.h
Both this and the aarch64 version look ok after a very cursory
readthrough.
// Martin
_______________________________________________
libav-devel mailing list
libav-devel@libav.org
https://lists.libav.org/mailman/listinfo/libav-devel
