@ -1378,48 +1378,48 @@ static av_always_inline void iadst16_1d(const dctcoef *in, ptrdiff_t stride,
dctint t0a , t1a , t2a , t3a , t4a , t5a , t6a , t7a ;
dctint t8a , t9a , t10a , t11a , t12a , t13a , t14a , t15a ;
t0 = IN ( 15 ) * 16364 + IN ( 0 ) * 804 ;
t1 = IN ( 15 ) * 804 - IN ( 0 ) * 16364 ;
t2 = IN ( 13 ) * 15893 + IN ( 2 ) * 3981 ;
t3 = IN ( 13 ) * 3981 - IN ( 2 ) * 15893 ;
t4 = IN ( 11 ) * 14811 + IN ( 4 ) * 7005 ;
t5 = IN ( 11 ) * 7005 - IN ( 4 ) * 14811 ;
t6 = IN ( 9 ) * 13160 + IN ( 6 ) * 9760 ;
t7 = IN ( 9 ) * 9760 - IN ( 6 ) * 13160 ;
t8 = IN ( 7 ) * 11003 + IN ( 8 ) * 12140 ;
t9 = IN ( 7 ) * 12140 - IN ( 8 ) * 11003 ;
t10 = IN ( 5 ) * 8423 + IN ( 10 ) * 14053 ;
t11 = IN ( 5 ) * 14053 - IN ( 10 ) * 8423 ;
t12 = IN ( 3 ) * 5520 + IN ( 12 ) * 15426 ;
t13 = IN ( 3 ) * 15426 - IN ( 12 ) * 5520 ;
t14 = IN ( 1 ) * 2404 + IN ( 14 ) * 16207 ;
t15 = IN ( 1 ) * 16207 - IN ( 14 ) * 2404 ;
t0a = ( t0 + t8 + ( 1 < < 13 ) ) > > 14 ;
t1a = ( t1 + t9 + ( 1 < < 13 ) ) > > 14 ;
t2a = ( t2 + t10 + ( 1 < < 13 ) ) > > 14 ;
t3a = ( t3 + t11 + ( 1 < < 13 ) ) > > 14 ;
t4a = ( t4 + t12 + ( 1 < < 13 ) ) > > 14 ;
t5a = ( t5 + t13 + ( 1 < < 13 ) ) > > 14 ;
t6a = ( t6 + t14 + ( 1 < < 13 ) ) > > 14 ;
t7a = ( t7 + t15 + ( 1 < < 13 ) ) > > 14 ;
t8a = ( t0 - t8 + ( 1 < < 13 ) ) > > 14 ;
t9a = ( t1 - t9 + ( 1 < < 13 ) ) > > 14 ;
t10a = ( t2 - t10 + ( 1 < < 13 ) ) > > 14 ;
t11a = ( t3 - t11 + ( 1 < < 13 ) ) > > 14 ;
t12a = ( t4 - t12 + ( 1 < < 13 ) ) > > 14 ;
t13a = ( t5 - t13 + ( 1 < < 13 ) ) > > 14 ;
t14a = ( t6 - t14 + ( 1 < < 13 ) ) > > 14 ;
t15a = ( t7 - t15 + ( 1 < < 13 ) ) > > 14 ;
t8 = t8a * 16069 + t9a * 3196 ;
t9 = t8a * 3196 - t9a * 16069 ;
t10 = t10a * 9102 + t11a * 13623 ;
t11 = t10a * 13623 - t11a * 9102 ;
t12 = t13a * 16069 - t12a * 3196 ;
t13 = t13a * 3196 + t12a * 16069 ;
t14 = t15a * 9102 - t14a * 13623 ;
t15 = t15a * 13623 + t14a * 9102 ;
t0 = IN ( 15 ) * 16364U + IN ( 0 ) * 804U ;
t1 = IN ( 15 ) * 804U - IN ( 0 ) * 16364U ;
t2 = IN ( 13 ) * 15893U + IN ( 2 ) * 3981U ;
t3 = IN ( 13 ) * 3981U - IN ( 2 ) * 15893U ;
t4 = IN ( 11 ) * 14811U + IN ( 4 ) * 7005U ;
t5 = IN ( 11 ) * 7005U - IN ( 4 ) * 14811U ;
t6 = IN ( 9 ) * 13160U + IN ( 6 ) * 9760U ;
t7 = IN ( 9 ) * 9760U - IN ( 6 ) * 13160U ;
t8 = IN ( 7 ) * 11003U + IN ( 8 ) * 12140U ;
t9 = IN ( 7 ) * 12140U - IN ( 8 ) * 11003U ;
t10 = IN ( 5 ) * 8423U + IN ( 10 ) * 14053U ;
t11 = IN ( 5 ) * 14053U - IN ( 10 ) * 8423U ;
t12 = IN ( 3 ) * 5520U + IN ( 12 ) * 15426U ;
t13 = IN ( 3 ) * 15426U - IN ( 12 ) * 5520U ;
t14 = IN ( 1 ) * 2404U + IN ( 14 ) * 16207U ;
t15 = IN ( 1 ) * 16207U - IN ( 14 ) * 2404U ;
t0a = ( dctint ) ( ( 1U < < 13 ) + t0 + t8 ) > > 14 ;
t1a = ( dctint ) ( ( 1U < < 13 ) + t1 + t9 ) > > 14 ;
t2a = ( dctint ) ( ( 1U < < 13 ) + t2 + t10 ) > > 14 ;
t3a = ( dctint ) ( ( 1U < < 13 ) + t3 + t11 ) > > 14 ;
t4a = ( dctint ) ( ( 1U < < 13 ) + t4 + t12 ) > > 14 ;
t5a = ( dctint ) ( ( 1U < < 13 ) + t5 + t13 ) > > 14 ;
t6a = ( dctint ) ( ( 1U < < 13 ) + t6 + t14 ) > > 14 ;
t7a = ( dctint ) ( ( 1U < < 13 ) + t7 + t15 ) > > 14 ;
t8a = ( dctint ) ( ( 1U < < 13 ) + t0 - t8 ) > > 14 ;
t9a = ( dctint ) ( ( 1U < < 13 ) + t1 - t9 ) > > 14 ;
t10a = ( dctint ) ( ( 1U < < 13 ) + t2 - t10 ) > > 14 ;
t11a = ( dctint ) ( ( 1U < < 13 ) + t3 - t11 ) > > 14 ;
t12a = ( dctint ) ( ( 1U < < 13 ) + t4 - t12 ) > > 14 ;
t13a = ( dctint ) ( ( 1U < < 13 ) + t5 - t13 ) > > 14 ;
t14a = ( dctint ) ( ( 1U < < 13 ) + t6 - t14 ) > > 14 ;
t15a = ( dctint ) ( ( 1U < < 13 ) + t7 - t15 ) > > 14 ;
t8 = t8a * 16069U + t9a * 3196U ;
t9 = t8a * 3196U - t9a * 16069U ;
t10 = t10a * 9102U + t11a * 13623U ;
t11 = t10a * 13623U - t11a * 9102U ;
t12 = t13a * 16069U - t12a * 3196U ;
t13 = t13a * 3196U + t12a * 16069U ;
t14 = t15a * 9102U - t14a * 13623U ;
t15 = t15a * 13623U + t14a * 9102U ;
t0 = t0a + t4a ;
t1 = t1a + t5a ;
@ -1429,49 +1429,49 @@ static av_always_inline void iadst16_1d(const dctcoef *in, ptrdiff_t stride,
t5 = t1a - t5a ;
t6 = t2a - t6a ;
t7 = t3a - t7a ;
t8a = ( t8 + t12 + ( 1 < < 13 ) ) > > 14 ;
t9a = ( t9 + t13 + ( 1 < < 13 ) ) > > 14 ;
t10a = ( t10 + t14 + ( 1 < < 13 ) ) > > 14 ;
t11a = ( t11 + t15 + ( 1 < < 13 ) ) > > 14 ;
t12a = ( t8 - t12 + ( 1 < < 13 ) ) > > 14 ;
t13a = ( t9 - t13 + ( 1 < < 13 ) ) > > 14 ;
t14a = ( t10 - t14 + ( 1 < < 13 ) ) > > 14 ;
t15a = ( t11 - t15 + ( 1 < < 13 ) ) > > 14 ;
t4a = t4 * 15137 + t5 * 6270 ;
t5a = t4 * 6270 - t5 * 15137 ;
t6a = t7 * 15137 - t6 * 6270 ;
t7a = t7 * 6270 + t6 * 15137 ;
t12 = t12a * 15137 + t13a * 6270 ;
t13 = t12a * 6270 - t13a * 15137 ;
t14 = t15a * 15137 - t14a * 6270 ;
t15 = t15a * 6270 + t14a * 15137 ;
t8a = ( dctint ) ( ( 1U < < 13 ) + t8 + t12 ) > > 14 ;
t9a = ( dctint ) ( ( 1U < < 13 ) + t9 + t13 ) > > 14 ;
t10a = ( dctint ) ( ( 1U < < 13 ) + t10 + t14 ) > > 14 ;
t11a = ( dctint ) ( ( 1U < < 13 ) + t11 + t15 ) > > 14 ;
t12a = ( dctint ) ( ( 1U < < 13 ) + t8 - t12 ) > > 14 ;
t13a = ( dctint ) ( ( 1U < < 13 ) + t9 - t13 ) > > 14 ;
t14a = ( dctint ) ( ( 1U < < 13 ) + t10 - t14 ) > > 14 ;
t15a = ( dctint ) ( ( 1U < < 13 ) + t11 - t15 ) > > 14 ;
t4a = t4 * 15137U + t5 * 6270U ;
t5a = t4 * 6270U - t5 * 15137U ;
t6a = t7 * 15137U - t6 * 6270U ;
t7a = t7 * 6270U + t6 * 15137U ;
t12 = t12a * 15137U + t13a * 6270U ;
t13 = t12a * 6270U - t13a * 15137U ;
t14 = t15a * 15137U - t14a * 6270U ;
t15 = t15a * 6270U + t14a * 15137U ;
out [ 0 ] = t0 + t2 ;
out [ 15 ] = - ( t1 + t3 ) ;
t2a = t0 - t2 ;
t3a = t1 - t3 ;
out [ 3 ] = - ( ( t4a + t6a + ( 1 < < 13 ) ) > > 14 ) ;
out [ 12 ] = ( t5a + t7a + ( 1 < < 13 ) ) > > 14 ;
t6 = ( t4a - t6a + ( 1 < < 13 ) ) > > 14 ;
t7 = ( t5a - t7a + ( 1 < < 13 ) ) > > 14 ;
out [ 3 ] = - ( ( dctint ) ( ( 1U < < 13 ) + t4a + t6a ) > > 14 ) ;
out [ 12 ] = ( dctint ) ( ( 1U < < 13 ) + t5a + t7a ) > > 14 ;
t6 = ( dctint ) ( ( 1U < < 13 ) + t4a - t6a ) > > 14 ;
t7 = ( dctint ) ( ( 1U < < 13 ) + t5a - t7a ) > > 14 ;
out [ 1 ] = - ( t8a + t10a ) ;
out [ 14 ] = t9a + t11a ;
t10 = t8a - t10a ;
t11 = t9a - t11a ;
out [ 2 ] = ( t12 + t14 + ( 1 < < 13 ) ) > > 14 ;
out [ 13 ] = - ( ( t13 + t15 + ( 1 < < 13 ) ) > > 14 ) ;
t14a = ( t12 - t14 + ( 1 < < 13 ) ) > > 14 ;
t15a = ( t13 - t15 + ( 1 < < 13 ) ) > > 14 ;
out [ 7 ] = ( ( t2a + t3a ) * - 11585 + ( 1 < < 13 ) ) > > 14 ;
out [ 8 ] = ( ( t2a - t3a ) * 11585 + ( 1 < < 13 ) ) > > 14 ;
out [ 4 ] = ( ( t7 + t6 ) * 11585 + ( 1 < < 13 ) ) > > 14 ;
out [ 11 ] = ( ( t7 - t6 ) * 11585 + ( 1 < < 13 ) ) > > 14 ;
out [ 6 ] = ( ( t11 + t10 ) * 11585 + ( 1 < < 13 ) ) > > 14 ;
out [ 9 ] = ( ( t11 - t10 ) * 11585 + ( 1 < < 13 ) ) > > 14 ;
out [ 5 ] = ( ( t14a + t15a ) * - 11585 + ( 1 < < 13 ) ) > > 14 ;
out [ 10 ] = ( ( t14a - t15a ) * 11585 + ( 1 < < 13 ) ) > > 14 ;
out [ 2 ] = ( dctint ) ( ( 1U < < 13 ) + t12 + t14 ) > > 14 ;
out [ 13 ] = - ( ( dctint ) ( ( 1U < < 13 ) + t13 + t15 ) > > 14 ) ;
t14a = ( dctint ) ( ( 1U < < 13 ) + t12 - t14 ) > > 14 ;
t15a = ( dctint ) ( ( 1U < < 13 ) + t13 - t15 ) > > 14 ;
out [ 7 ] = ( dctint ) ( - ( t2a + t3a ) * 11585U + ( 1 < < 13 ) ) > > 14 ;
out [ 8 ] = ( dctint ) ( ( t2a - t3a ) * 11585U + ( 1 < < 13 ) ) > > 14 ;
out [ 4 ] = ( dctint ) ( ( t7 + t6 ) * 11585U + ( 1 < < 13 ) ) > > 14 ;
out [ 11 ] = ( dctint ) ( ( t7 - t6 ) * 11585U + ( 1 < < 13 ) ) > > 14 ;
out [ 6 ] = ( dctint ) ( ( t11 + t10 ) * 11585U + ( 1 < < 13 ) ) > > 14 ;
out [ 9 ] = ( dctint ) ( ( t11 - t10 ) * 11585U + ( 1 < < 13 ) ) > > 14 ;
out [ 5 ] = ( dctint ) ( - ( t14a + t15a ) * 11585U + ( 1 < < 13 ) ) > > 14 ;
out [ 10 ] = ( dctint ) ( ( t14a - t15a ) * 11585U + ( 1 < < 13 ) ) > > 14 ;
}
itxfm_wrap ( 16 , 6 )