|
|
@@ -30,7 +30,7 @@ function ff_resample_common_apply_filter_x4_float_neon, export=1
|
|
|
faddp v0.4s, v0.4s, v0.4s // pair adding of the 4x32-bit accumulated values
|
|
|
faddp v0.4s, v0.4s, v0.4s // pair adding of the 4x32-bit accumulated values
|
|
|
st1 {v0.s}[0], [x0], #4 // write accumulator
|
|
|
- ret
|
|
|
+ ret
|
|
|
endfunc
|
|
|
|
|
|
function ff_resample_common_apply_filter_x8_float_neon, export=1
|
|
|
@@ -46,7 +46,7 @@ function ff_resample_common_apply_filter_x8_float_neon, export=1
|
|
|
faddp v0.4s, v0.4s, v0.4s // pair adding of the 4x32-bit accumulated values
|
|
|
faddp v0.4s, v0.4s, v0.4s // pair adding of the 4x32-bit accumulated values
|
|
|
st1 {v0.s}[0], [x0], #4 // write accumulator
|
|
|
- ret
|
|
|
+ ret
|
|
|
endfunc
|
|
|
|
|
|
function ff_resample_common_apply_filter_x4_s16_neon, export=1
|
|
|
@@ -59,7 +59,7 @@ function ff_resample_common_apply_filter_x4_s16_neon, export=1
|
|
|
addp v0.4s, v0.4s, v0.4s // pair adding of the 4x32-bit accumulated values
|
|
|
addp v0.4s, v0.4s, v0.4s // pair adding of the 4x32-bit accumulated values
|
|
|
st1 {v0.s}[0], [x0], #4 // write accumulator
|
|
|
- ret
|
|
|
+ ret
|
|
|
endfunc
|
|
|
|
|
|
function ff_resample_common_apply_filter_x8_s16_neon, export=1
|
|
|
@@ -73,5 +73,5 @@ function ff_resample_common_apply_filter_x8_s16_neon, export=1
|
|
|
addp v0.4s, v0.4s, v0.4s // pair adding of the 4x32-bit accumulated values
|
|
|
addp v0.4s, v0.4s, v0.4s // pair adding of the 4x32-bit accumulated values
|
|
|
st1 {v0.s}[0], [x0], #4 // write accumulator
|
|
|
- ret
|
|
|
+ ret
|
|
|
endfunc
|