From patchwork Mon Jan 2 12:17:56 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [6/6] aarch64: vp9mc: Calculate less unused data in the 4 pixel wide horizontal filter X-Patchwork-Submitter: =?utf-8?q?Martin_Storsj=C3=B6?= X-Patchwork-Id: 62548 Message-Id: <1483359476-4641-6-git-send-email-martin@martin.st> To: libav-devel@libav.org Date: Mon, 2 Jan 2017 14:17:56 +0200 From: =?utf-8?q?Martin_Storsj=C3=B6?= List-Id: libav development No measured speedup on an Cortex A53, but other cores might benefit. --- libavcodec/aarch64/vp9mc_neon.S | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/libavcodec/aarch64/vp9mc_neon.S b/libavcodec/aarch64/vp9mc_neon.S index 99f1809..95ed26c 100644 --- a/libavcodec/aarch64/vp9mc_neon.S +++ b/libavcodec/aarch64/vp9mc_neon.S @@ -202,9 +202,12 @@ endfunc ext v23.16b, \src5\().16b, \src6\().16b, #(2*\offset) mla \dst2\().8h, v21.8h, v0.h[\offset] mla \dst4\().8h, v23.8h, v0.h[\offset] -.else +.elseif \size == 8 mla \dst1\().8h, v20.8h, v0.h[\offset] mla \dst3\().8h, v22.8h, v0.h[\offset] +.else + mla \dst1\().4h, v20.4h, v0.h[\offset] + mla \dst3\().4h, v22.4h, v0.h[\offset] .endif .endm // The same as above, but don't accumulate straight into the @@ -219,16 +222,24 @@ endfunc ext v23.16b, \src5\().16b, \src6\().16b, #(2*\offset) mul v21.8h, v21.8h, v0.h[\offset] mul v23.8h, v23.8h, v0.h[\offset] -.else +.elseif \size == 8 mul v20.8h, v20.8h, v0.h[\offset] mul v22.8h, v22.8h, v0.h[\offset] +.else + mul v20.4h, v20.4h, v0.h[\offset] + mul v22.4h, v22.4h, v0.h[\offset] .endif +.if \size == 4 + sqadd \dst1\().4h, \dst1\().4h, v20.4h + sqadd \dst3\().4h, \dst3\().4h, v22.4h +.else sqadd \dst1\().8h, \dst1\().8h, v20.8h sqadd \dst3\().8h, \dst3\().8h, v22.8h .if \size >= 16 sqadd \dst2\().8h, \dst2\().8h, v21.8h sqadd \dst4\().8h, \dst4\().8h, v23.8h .endif +.endif .endm