Merge commit 'c0bd865ad60da31282c5d8e1000c98366249c31e'

[ffmpeg] / libavcodec / aarch64 / vp8dsp_neon.S

diff --git a/libavcodec/aarch64/vp8dsp_neon.S b/libavcodec/aarch64/vp8dsp_neon.S
index aefe8fdcde9af68a5e1abae1d4d853f14eb79af1..4bbf16d1a4c7f1db75bec8fa8785e03510b8d1a2 100644 (file)
--- a/libavcodec/aarch64/vp8dsp_neon.S
+++ b/libavcodec/aarch64/vp8dsp_neon.S
@@ -92,8 +92,8 @@ function ff_vp8_idct_add_neon, export=1
         smull           v27.4s, v3.4h,  v4.h[0]
         sqdmulh         v20.4h, v1.4h,  v4.h[1]
         sqdmulh         v23.4h, v3.4h,  v4.h[1]
-        sqshrn          v21.4h, v26.4s, #16
-        sqshrn          v22.4h, v27.4s, #16
+        shrn            v21.4h, v26.4s, #16
+        shrn            v22.4h, v27.4s, #16
         add             v21.4h, v21.4h, v1.4h
         add             v22.4h, v22.4h, v3.4h
 
@@ -117,44 +117,45 @@ function ff_vp8_idct_add_neon, export=1
         st1             {v29.16b},  [x1]
         sqdmulh         v21.4h,     v1.4h,  v4.h[1]
         sqdmulh         v23.4h,     v3.4h,  v4.h[1]
-        sqshrn          v20.4h,     v26.4s, #16
-        sqshrn          v22.4h,     v27.4s, #16
+        shrn            v20.4h,     v26.4s, #16
+        shrn            v22.4h,     v27.4s, #16
         add             v20.4h,     v20.4h, v1.4h
         add             v22.4h,     v22.4h, v3.4h
         add             v16.4h,     v0.4h,  v2.4h
         sub             v17.4h,     v0.4h,  v2.4h
 
         add             v18.4h,     v20.4h, v23.4h
-        ld1             {v24.d}[0], [x0],   x2
-        zip1            v16.2d,     v16.2d, v17.2d
-        sub             v19.4h,     v21.4h, v22.4h
-        ld1             {v25.d}[0], [x0],   x2
-        zip1            v18.2d,     v18.2d, v19.2d
-        add             v0.8h,      v16.8h, v18.8h
-        ld1             {v25.d}[1], [x0],   x2
-        sub             v1.8h,      v16.8h, v18.8h
-        ld1             {v24.d}[1], [x0],   x2
-        srshr           v0.8h,      v0.8h,  #3
-        trn1            v24.4s,     v24.4s, v25.4s
-        srshr           v1.8h,      v1.8h,  #3
+        ld1             {v24.s}[0], [x0],   x2
+        sub             v19.4h, v21.4h, v22.4h
+        ld1             {v25.s}[0], [x0],   x2
+        add             v0.4h,      v16.4h, v18.4h
+        add             v1.4h,      v17.4h, v19.4h
+        ld1             {v26.s}[0], [x0],   x2
+        sub             v3.4h,      v16.4h, v18.4h
+        sub             v2.4h,      v17.4h, v19.4h
+        ld1             {v27.s}[0], [x0],   x2
+        srshr           v0.4h,      v0.4h,  #3
+        srshr           v1.4h,      v1.4h,  #3
+        srshr           v2.4h,      v2.4h,  #3
+        srshr           v3.4h,      v3.4h,  #3
+
         sub             x0,  x0,  x2,  lsl #2
 
-        ext             v1.16b, v1.16b, v1.16b, #8
-        trn1            v3.2d,  v0.2d,  v1.2d
-        trn2            v0.2d,  v0.2d,  v1.2d
-        trn1            v1.8h,  v3.8h,  v0.8h
-        trn2            v3.8h,  v3.8h,  v0.8h
-        uzp1            v0.4s,  v1.4s,  v3.4s
-        uzp2            v1.4s,  v3.4s,  v1.4s
+        transpose_4x4H  v0, v1, v2, v3, v5, v6, v7, v16
 
         uaddw           v0.8h,  v0.8h, v24.8b
-        uaddw2          v1.8h,  v1.8h, v24.16b
+        uaddw           v1.8h,  v1.8h, v25.8b
+        uaddw           v2.8h,  v2.8h, v26.8b
+        uaddw           v3.8h,  v3.8h, v27.8b
         sqxtun          v0.8b,  v0.8h
-        sqxtun2         v0.16b, v1.8h
+        sqxtun          v1.8b,  v1.8h
+        sqxtun          v2.8b,  v2.8h
+        sqxtun          v3.8b,  v3.8h
+
         st1             {v0.s}[0],  [x0], x2
-        st1             {v0.s}[1],  [x0], x2
-        st1             {v0.s}[3],  [x0], x2
-        st1             {v0.s}[2],  [x0], x2
+        st1             {v1.s}[0],  [x0], x2
+        st1             {v2.s}[0],  [x0], x2
+        st1             {v3.s}[0],  [x0], x2
 
         ret
 endfunc
@@ -769,23 +770,6 @@ endfunc
         sqrshrun2       \d0\().16b, v22.8h, #7
 .endm
 
-.macro  vp8_epel8_v6    d0,  s0,  s1,  s2, s3, s4, s5
-        uxtl            \s2\().8h, \s2\().8b
-        uxtl            \s3\().8h, \s3\().8b
-        uxtl            \s1\().8h, \s1\().8b
-        uxtl            \s4\().8h, \s4\().8b
-        uxtl            \s0\().8h, \s0\().8b
-        uxtl            \s5\().8h, \s5\().8b
-        mul             \s2\().8h, \s2\().8h, v0.h[2]
-        mul             \s3\().8h, \s3\().8h, v0.h[3]
-        mls             \s2\().8h, \s1\().8h, v0.h[1]
-        mls             \s3\().8h, \s4\().8h, v0.h[4]
-        mla             \s2\().8h, \s0\().8h, v0.h[0]
-        mla             \s3\().8h, \s5\().8h, v0.h[5]
-        sqadd           \s3\().8h, \s2\().8h, \s3\().8h
-        sqrshrun        \d0\().8b, \s3\().8h, #7
-.endm
-
 .macro  vp8_epel8_v6_y2 d0, d1, s0, s1, s2, s3, s4, s5, s6
         uxtl            \s0\().8h, \s0\().8b
         uxtl            \s3\().8h, \s3\().8b
@@ -942,15 +926,18 @@ function ff_put_vp8_epel16_h6v6_neon, export=1
 2:
         ld1             {v1.8b - v4.8b},    [x7], #32
         ld1             {v16.8b - v19.8b},  [x7], #32
-        ld1             {v20.8b - v23.8b},  [x7]
-        sub             x7,  x7,  #48
+        ld1             {v20.8b - v23.8b},  [x7], #32
+        ld1             {v24.8b - v25.8b},  [x7]
+        sub             x7,  x7,  #64
 
-        vp8_epel8_v6    v5, v1, v3, v16, v18, v20, v22
-        vp8_epel8_v6    v2, v2, v4, v17, v19, v21, v23
-        trn1            v2.2d, v5.2d, v2.2d
+        vp8_epel8_v6_y2 v1, v3, v1, v3, v16, v18, v20, v22, v24
+        vp8_epel8_v6_y2 v2, v4, v2, v4, v17, v19, v21, v23, v25
+        trn1            v1.2d, v1.2d, v2.2d
+        trn1            v3.2d, v3.2d, v4.2d
 
-        st1             {v2.16b}, [x0], x1
-        subs            x4, x4, #1
+        st1             {v1.16b}, [x0], x1
+        st1             {v3.16b}, [x0], x1
+        subs            x4, x4, #2
         b.ne            2b
 
         add             sp,  sp,  #336+16