Message ID | tencent_EE836CBFBC8AE545A1856CE7983C46237007@qq.com |
---|---|
State | Accepted |
Commit | 05438db02437e241a418e266a354bf4e7be7ac59 |
Headers | show |
Series | [FFmpeg-devel] libavcodec/hevc: reuse scale_store on idct32x32_neon | expand |
Context | Check | Description |
---|---|---|
yinshiyou/make_loongarch64 | success | Make finished |
yinshiyou/make_fate_loongarch64 | success | Make fate finished |
andriy/make_x86 | success | Make finished |
andriy/make_fate_x86 | success | Make fate finished |
On Fri, 24 Feb 2023, xufuji456 wrote: > --- > libavcodec/arm/hevcdsp_idct_neon.S | 18 ++---------------- > 1 file changed, 2 insertions(+), 16 deletions(-) > > diff --git a/libavcodec/arm/hevcdsp_idct_neon.S b/libavcodec/arm/hevcdsp_idct_neon.S > index 75795e6a6a..41ca3b83a8 100644 > --- a/libavcodec/arm/hevcdsp_idct_neon.S > +++ b/libavcodec/arm/hevcdsp_idct_neon.S > @@ -876,28 +876,14 @@ function func_tr_32x4_\name > movrel r9, trans + 32 > vld1.s16 {q0}, [r9, :128]! > vld1.s16 {q1}, [r9, :128] > - > - bl tr_block1 > - > add r4, sp, #2048 > - vld1.s16 {q14-q15}, [r4, :128]! > - butterfly32 q14, q10, q15, q11 > - scale32 d22, d23, d20, d21, q1, q14, q10, q15, \shift > - > - vld1.s16 {q14-q15}, [r4, :128]! > - butterfly32 q14, q12, q15, q13 > - scale32 d2, d3, d28, d29, q1, q14, q12, q15, \shift > > - transpose8_4x4 d22, d20, d2, d28 > - transpose8_4x4 d29, d3, d21, d23 > + bl tr_block1 > mov r1, r11 > mov r2, #64 > mov r8, #-64 > add r3, r11, #(56 + 3 * 64) > - store16 d22, d23, d20, d21, d2, d3, d28, d29, r8 > - > - @ reload multiplication coefficiens to q1 > - vld1.s16 {q1}, [r9, :128] > + scale_store \shift > > bl tr_block2 > add r1, r11, #8 > -- > 2.32.0 (Apple Git-132) LGTM, thanks - pushed now. // Martin
diff --git a/libavcodec/arm/hevcdsp_idct_neon.S b/libavcodec/arm/hevcdsp_idct_neon.S index 75795e6a6a..41ca3b83a8 100644 --- a/libavcodec/arm/hevcdsp_idct_neon.S +++ b/libavcodec/arm/hevcdsp_idct_neon.S @@ -876,28 +876,14 @@ function func_tr_32x4_\name movrel r9, trans + 32 vld1.s16 {q0}, [r9, :128]! vld1.s16 {q1}, [r9, :128] - - bl tr_block1 - add r4, sp, #2048 - vld1.s16 {q14-q15}, [r4, :128]! - butterfly32 q14, q10, q15, q11 - scale32 d22, d23, d20, d21, q1, q14, q10, q15, \shift - - vld1.s16 {q14-q15}, [r4, :128]! - butterfly32 q14, q12, q15, q13 - scale32 d2, d3, d28, d29, q1, q14, q12, q15, \shift - transpose8_4x4 d22, d20, d2, d28 - transpose8_4x4 d29, d3, d21, d23 + bl tr_block1 mov r1, r11 mov r2, #64 mov r8, #-64 add r3, r11, #(56 + 3 * 64) - store16 d22, d23, d20, d21, d2, d3, d28, d29, r8 - - @ reload multiplication coefficiens to q1 - vld1.s16 {q1}, [r9, :128] + scale_store \shift bl tr_block2 add r1, r11, #8