aarch64: vp9itxfm: Reorder iadst16 coeffs

This matches the order they are in the 16 bpp version.

There they are in this order, to make sure we access them in the
same order they are declared, easing loading only half of the
coefficients at a time.

This makes the 8 bpp version match the 16 bpp version better.

Signed-off-by: Martin Storsjö <martin@martin.st>

libavcodec/aarch64/vp9itxfm_neon.S

@@ -37,8 +37,8 @@ idct_coeffs:
 endconst
 
 const iadst16_coeffs, align=4
-        .short  16364, 804, 15893, 3981, 14811, 7005, 13160, 9760
-        .short  11003, 12140, 8423, 14053, 5520, 15426, 2404, 16207
+        .short  16364, 804, 15893, 3981, 11003, 12140, 8423, 14053
+        .short  14811, 7005, 13160, 9760, 5520, 15426, 2404, 16207
 endconst
 
 // out1 = ((in1 + in2) * v0[0] + (1 << 13)) >> 14
@@ -628,19 +628,19 @@ function iadst16
         ld1             {v0.8h,v1.8h}, [x11]
 
         dmbutterfly_l   v6,  v7,  v4,  v5,  v31, v16, v0.h[1], v0.h[0]   // v6,v7   = t1,   v4,v5   = t0
-        dmbutterfly_l   v10, v11, v8,  v9,  v23, v24, v1.h[1], v1.h[0]   // v10,v11 = t9,   v8,v9   = t8
+        dmbutterfly_l   v10, v11, v8,  v9,  v23, v24, v0.h[5], v0.h[4]   // v10,v11 = t9,   v8,v9   = t8
         dbutterfly_n    v31, v24, v6,  v7,  v10, v11, v12, v13, v10, v11 // v31     = t1a,  v24     = t9a
         dmbutterfly_l   v14, v15, v12, v13, v29, v18, v0.h[3], v0.h[2]   // v14,v15 = t3,   v12,v13 = t2
         dbutterfly_n    v16, v23, v4,  v5,  v8,  v9,  v6,  v7,  v8,  v9  // v16     = t0a,  v23     = t8a
 
-        dmbutterfly_l   v6,  v7,  v4,  v5,  v21, v26, v1.h[3], v1.h[2]   // v6,v7   = t11,  v4,v5   = t10
+        dmbutterfly_l   v6,  v7,  v4,  v5,  v21, v26, v0.h[7], v0.h[6]   // v6,v7   = t11,  v4,v5   = t10
         dbutterfly_n    v29, v26, v14, v15, v6,  v7,  v8,  v9,  v6,  v7  // v29     = t3a,  v26     = t11a
-        dmbutterfly_l   v10, v11, v8,  v9,  v27, v20, v0.h[5], v0.h[4]   // v10,v11 = t5,   v8,v9   = t4
+        dmbutterfly_l   v10, v11, v8,  v9,  v27, v20, v1.h[1], v1.h[0]   // v10,v11 = t5,   v8,v9   = t4
         dbutterfly_n    v18, v21, v12, v13, v4,  v5,  v6,  v7,  v4,  v5  // v18     = t2a,  v21     = t10a
 
         dmbutterfly_l   v14, v15, v12, v13, v19, v28, v1.h[5], v1.h[4]   // v14,v15 = t13,  v12,v13 = t12
         dbutterfly_n    v20, v28, v10, v11, v14, v15, v4,  v5,  v14, v15 // v20     = t5a,  v28     = t13a
-        dmbutterfly_l   v6,  v7,  v4,  v5,  v25, v22, v0.h[7], v0.h[6]   // v6,v7   = t7,   v4,v5   = t6
+        dmbutterfly_l   v6,  v7,  v4,  v5,  v25, v22, v1.h[3], v1.h[2]   // v6,v7   = t7,   v4,v5   = t6
         dbutterfly_n    v27, v19, v8,  v9,  v12, v13, v10, v11, v12, v13 // v27     = t4a,  v19     = t12a
 
         dmbutterfly_l   v10, v11, v8,  v9,  v17, v30, v1.h[7], v1.h[6]   // v10,v11 = t15,  v8,v9   = t14