| commit | a46f5459c3f5da8700e1ed34d4ed0fd4480e6ff3 | [log] [tgz] |
|---|---|---|
| author | Andrew Russell <anrussell@google.com> | Mon Mar 03 07:38:02 2014 -0800 |
| committer | Andrew Russell <anrussell@google.com> | Mon Mar 03 14:25:42 2014 -0800 |
| tree | 50310254266c7855bd37f07f365c5f3c73a6ef5a | |
| parent | 5ee16cc075dea7ed8b36e013adbeca7a84125ee3 [diff] |
improved speed of 4x4 sse2 fdct. * speed improvment of 30 percent achieved * multiplies and adds remain the same * non-arithmetic instructions minimized by hand, by: -expanding 2 pass loop -removing irrelivant "shuffles" -combining last two rounding steps * further improvments may be possible Change-Id: Idec2c3f52910c48e6a0e0f9aefed5cae31b0b8c0