Mercurial > libavcodec.hg
changeset 5562:0074dd43ae5e libavcodec
Simplify and optimize the 4th vertical lifting step of the SSE2 code (untested)
This also reduces the needed headroom in that step by 1 bit
| author | michael |
|---|---|
| date | Tue, 21 Aug 2007 00:03:18 +0000 |
| parents | 225867be27f7 |
| children | 538d55152d09 |
| files | i386/snowdsp_mmx.c |
| diffstat | 1 files changed, 1 insertions(+), 2 deletions(-) [+] |
line wrap: on
line diff
--- a/i386/snowdsp_mmx.c Tue Aug 21 00:02:19 2007 +0000 +++ b/i386/snowdsp_mmx.c Tue Aug 21 00:03:18 2007 +0000 @@ -498,9 +498,8 @@ snow_vertical_compose_sse2_store(REG_c,"xmm0","xmm2","xmm4","xmm6") snow_vertical_compose_sse2_add(REG_S,"xmm0","xmm2","xmm4","xmm6") snow_vertical_compose_sse2_move("xmm0","xmm2","xmm4","xmm6","xmm1","xmm3","xmm5","xmm7") - snow_vertical_compose_sse2_r2r_add("xmm0","xmm2","xmm4","xmm6","xmm0","xmm2","xmm4","xmm6") + snow_vertical_compose_sse2_sra("1","xmm0","xmm2","xmm4","xmm6") snow_vertical_compose_sse2_r2r_add("xmm1","xmm3","xmm5","xmm7","xmm0","xmm2","xmm4","xmm6") - snow_vertical_compose_sse2_sra("1","xmm0","xmm2","xmm4","xmm6") snow_vertical_compose_sse2_add(REG_a,"xmm0","xmm2","xmm4","xmm6") snow_vertical_compose_sse2_store(REG_a,"xmm0","xmm2","xmm4","xmm6")