Ping.
> 2024年5月15日 16:57，金波 写道：
>
> Look good to me.
>
> 2024-05-08 18:07:49 "yinshiyou-hf" 写道：
>> Compile with '--disable-lasx', ‘lumRangeFromJpeg_lasx’ undeclared.
>> ---
>> libswscale/loongarch/swscale_init_loongarch.c | 2 ++
>> 1 file changed, 2 insertions(+)
>>
>> diff --git a/libswscale
[PATCH 1/3] configure: Add support for loongarch.
[PATCH 2/3] avcodec: [loongarch] optimize get_cabac.
[PATCH 3/3] avcodec: [loongarch] Optimize decode_significance.
___
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinf
For la464 cpu: ./configure --cpu=la464
With cross-compiler:
./configure --cross-prefix=loongarch64-linux-gnu- \
--enable-cross-compile --arch=loongarch64 \
--target-os=linux --cpu=la464
---
Changelog | 1 +
configure | 17 +
2 files changed, 18 insertions(+)
diff --git a/Changelo
b/libavcodec/loongarch/cabac.h
new file mode 100644
index 00..71e8ba3be7
--- /dev/null
+++ b/libavcodec/loongarch/cabac.h
@@ -0,0 +1,254 @@
+/*
+ * Loongson optimized cabac
+ *
+ * Copyright (c) 2020 Loongson Technology Corporation Limited
+ * Contributed by Shiyou Yin
+ *
From: Hao Chen
Decoding 1080P H264 from 168fps to 170fps.
Signed-off-by: Shiyou Yin
---
libavcodec/h264_cabac.c | 2 +
libavcodec/loongarch/h264_cabac.c | 140 ++
2 files changed, 142 insertions(+)
create mode 100644 libavcodec/loongarch/h264_cabac.c
b/libavcodec/loongarch/cabac.h
new file mode 100644
index 00..e1c946fe16
--- /dev/null
+++ b/libavcodec/loongarch/cabac.h
@@ -0,0 +1,238 @@
+/*
+ * Loongson optimized cabac
+ *
+ * Copyright (c) 2020 Loongson Technology Corporation Limited
+ * Contributed by Shiyou Yin
+ *
V2:
1. rebase.
2. Change Author email from yinshi...@loongson.cn to
yinshiyou...@loongson.cn for 1/3 2/3.
3. Refine 2/3.
[PATCH v2 1/3] configure: Add support for loongarch.
[PATCH v2 2/3] avcodec: [loongarch] optimize get_cabac.
[PATCH v2 3/3] avcodec: [loongarch] Optimize decode_significance.
_
For la464 cpu: ./configure --cpu=la464
With cross-compiler:
./configure --cross-prefix=loongarch64-linux-gnu- \
--enable-cross-compile --arch=loongarch64 \
--target-os=linux --cpu=la464
---
Changelog | 1 +
configure | 23 +++
2 files changed, 24 inser
From: Hao Chen
Decoding 1080P H264 from 168fps to 170fps.
Signed-off-by: Shiyou Yin
---
libavcodec/h264_cabac.c | 2 +
libavcodec/loongarch/h264_cabac.c | 140 ++
2 files changed, 142 insertions(+)
create mode 100644 libavcodec/loongarch/h264_cabac.c
In function ff_dct_unquantize_mpeg2_intra_mmi,
addr0 shoudn't be changed before storage operation.
---
libavcodec/mips/mpegvideo_mmi.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/libavcodec/mips/mpegvideo_mmi.c b/libavcodec/mips/mpegvideo_mmi.c
index 18058e4..e4aba08 100644
Loongson 3A4000 and 2k1000 has supported MSA2.0.
This patch optimized SAD_UB2_UH,UNPCK_R_SH_SW,UNPCK_SB_SH and UNPCK_SH_SW with
MSA2.0 instruction.
---
configure | 5 +
libavutil/mips/generic_macros_msa.h | 42 ++---
2 files changed,
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of
>YunQiang Su
>Sent: Tuesday, July 2, 2019 11:53 AM
>To: ffmpeg-devel@ffmpeg.org
>Cc: YunQiang Su
>Subject: [FFmpeg-devel] [PATCH] MIPS: replace addi with addiu
>
>addi/daddi ar
Ensure the address accesed by gssqc1/gslqc1 are 16-bits memory-aligned.
---
libavcodec/mips/h264dsp_mmi.c | 48 +---
libavcodec/mips/simple_idct_mmi.c | 51 +--
libavutil/mips/mmiutils.h | 2 +-
3 files changed, 51 in
From: gxw
Changing details as following:
1. Refine arguments of SLDI_Bn to make it easier to understand.
2. Remove SLDI_Bn_0, and use SLDI_Bn instead.
Signed-off-by: Shiyou Yin
---
libavcodec/mips/h264dsp_msa.c | 9 ++--
libavcodec/mips/h264qpel_msa.c | 64
Ensure the address accesed by gssqc1/gslqc1 are 16-bits memory-aligned.
---
libavcodec/mips/simple_idct_mmi.c | 2 +-
libavutil/mips/mmiutils.h | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/libavcodec/mips/simple_idct_mmi.c
b/libavcodec/mips/simple_idct_mmi.c
inde
>Why is "block" not aligned? Does the code for other architectures also use
>unaligned instructions for
>these?
Thank you for reminding me. After checking the struct H264SliceContext and
function call process, 'block' is find out as 16-bit aligned.
There are some refines in this patch, I will up
ps: Avoid instruction
>exception caused by gssqc1/gslqc1.
>
>Is there a mips maintainer? otherwise:
Since Manojkumar Bhosale stoped take care of mips section last year,
I applied to be the mips maintainer, and trying to be qualified. Will keep
learning and be rigorous.
>On 24.07.
Ensure the address accesed by gssqc1/gslqc1 are 16-bits memory-aligned.
---
libavcodec/mips/simple_idct_mmi.c | 2 +-
libavutil/mips/mmiutils.h | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/libavcodec/mips/simple_idct_mmi.c
b/libavcodec/mips/simple_idct_mmi.c
inde
1. Refine setting zero process in function ff_h264_add_pixels4_8_mmi and
ff_h264_idct_add_8_mmi.
2. Remove redundant setting zeor process in function ff_h264_idct_add_8_mmi
and ff_h264_idct8_add_8_mmi.
---
libavcodec/mips/h264dsp_mmi.c | 44 +--
1 file
ps: [loongson] refine process of
>setting block as 0 in
>h264dsp_mmi.
>
>On 26.07.2019, at 10:25, Shiyou Yin wrote:
>
>> 1. Refine setting zero process in function ff_h264_add_pixels4_8_mmi and
>> ff_h264_idct_add_8_mmi.
>
>"refine" is rather unspecific
In function ff_h264_add_pixels4_8_mmi, there is no need to reset '%[ftmp0]'
to 0, because it's value has never changed since the start of the asm block.
This patch remove the redundant 'xor' and set src to zero once it was loaded.
In function ff_h264_idct_add_8_mmi, 'block' is seted to zero twice.
Ensure the address accesed by gssqc1/gslqc1 are 16-byte aligned.
---
libavcodec/mips/simple_idct_mmi.c | 2 +-
libavutil/mips/mmiutils.h | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/libavcodec/mips/simple_idct_mmi.c
b/libavcodec/mips/simple_idct_mmi.c
index 7f4bb
ps: Avoid instruction
>exception caused by gssqc1/gslqc1.
>
>On 26.07.2019, at 07:18, Shiyou Yin wrote:
>
>> Ensure the address accesed by gssqc1/gslqc1 are 16-bits memory-aligned.
>
>Looks good to me if standard DECLARE_ALIGNED should work for stack on MIPS.
>(on x86 it u
ps: Avoid instruction
>exception caused by gssqc1/gslqc1.
>
>On 29.07.2019, at 11:54, "Shiyou Yin" wrote:
>>>
>> DECLARE_ALIGNED is defined in ' libavutil/mem.h ' and related to compiler.
>> No matter mips or x86,
>> it's definition is
Ensure the address accesed by gssqc1/gslqc1 are 16-byte aligned.
---
libavcodec/mips/simple_idct_mmi.c | 2 +-
libavutil/mips/mmiutils.h | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/libavcodec/mips/simple_idct_mmi.c
b/libavcodec/mips/simple_idct_mmi.c
index 7f4bb
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of gxw
>Sent: Tuesday, August 6, 2019 11:38 AM
>To: ffmpeg-devel@ffmpeg.org
>Subject: [FFmpeg-devel] [PATCH] avutil/mips: refactor msa SLDI_Bn_0 and
>SLDI_Bn macros.
>
>Changing
LGTM.
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of gxw
>Sent: Tuesday, August 6, 2019 7:11 PM
>To: ffmpeg-devel@ffmpeg.org
>Subject: [FFmpeg-devel] [PATCH v2] avutil/mips: refactor msa SLDI_Bn_0 and
>SLDI_Bn macros.
>
>
LGTM.
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of gxw
>Sent: Wednesday, August 7, 2019 5:52 PM
>To: ffmpeg-devel@ffmpeg.org
>Subject: [FFmpeg-devel] [PATCH v4] avutil/mips: refine msa macros CLIP_*.
>
>Changing details
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of
>Michael Niedermayer
>Sent: Friday, August 9, 2019 12:07 AM
>To: FFmpeg development discussions and patches
>Subject: Re: [FFmpeg-devel] [PATCH v4] avutil/mips: refine msa macr
---
libavutil/mips/generic_macros_msa.h | 2 --
1 file changed, 2 deletions(-)
diff --git a/libavutil/mips/generic_macros_msa.h
b/libavutil/mips/generic_macros_msa.h
index 9ac0583..219ff07 100644
--- a/libavutil/mips/generic_macros_msa.h
+++ b/libavutil/mips/generic_macros_msa.h
@@ -2523,8 +2523
gt;no-expensive-optimizations
>
>On Wed, Aug 22, 2018 at 06:11:15PM +0800, Shiyou Yin wrote:
>> >-Original Message-
>> >From: ffmpeg-devel-boun...@ffmpeg.org
>> >[mailto:ffmpeg-devel-boun...@ffmpeg.org] On Behalf Of Michael
>> >Niedermayer
>> >S
>> Hi Michael, please help to review the following updates.
>>
>>
>> diff --git a/configure b/configure
>> index b9c9d0b..08cf48e 100755
>> --- a/configure
>> +++ b/configure
>> @@ -4796,15 +4796,24 @@ elif enabled mips; then
>> disable mipsfpu
>> disable mipsdsp
>
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of
>Shiyou Yin
>Sent: Saturday, August 25, 2018 11:04 AM
>To: 'FFmpeg development discussions and patches'
>Subject: Re: [FFmpeg-devel] [PATCH 1/
Performance of mpeg4 decoding improved about 23%(from 128fps to 158fps, tested
on loongson 3A3000).
Reoptimized following functions with mmi.
1. ff_simple_idct_put_8_mmi
2. ff_simple_idct_add_8_mmi
3. ff_simple_idct_8_mmi
Change-Id: I109939240d31ccb74127431c92daabcbc3f3aa03
---
libavcodec/mips/i
Reoptimize function ff_put_h264_chroma_mc8_mmi and ff_avg_h264_chroma_mc8_mmi.
Performance of h264 decoding improved about 5%(from 69fps to 73fps, tested on
loongson 3A3000).
Change-Id: Iccd7f4e480b2d0bfc47e4d409874c4adb77416cc
---
libavcodec/mips/h264chroma_mmi.c | 744 -
Optimized memset with mmi in following functions:
1. ff_h264_add_pixels4_8_mmi.
2. ff_h264_idct_add_8_mmi.
3. ff_h264_idct8_add_8_mmi.
This optimization improved h264 decoding performance about 1fps(tested on
loongson 3A3000).
Change-Id: I4e8b75510e6a34b4c80f84ad784b00377570c4ec
---
libavcodec/
codec/mips: [loongson] reoptimize
>h264_chroma_mc8_mmi v2.
>
>On Thu, Aug 30, 2018 at 02:24:04PM +0800, Shiyou Yin wrote:
>> Reoptimize function ff_put_h264_chroma_mc8_mmi and
>> ff_avg_h264_chroma_mc8_mmi.
>> Performance of h264 decoding improved about 5%(from 69fps to 7
Performance of mpeg4 decoding improved about 23%(from 128fps to 158fps, tested
on loongson 3A3000).
Reoptimized following functions with mmi.
1. ff_simple_idct_put_8_mmi
2. ff_simple_idct_add_8_mmi
3. ff_simple_idct_8_mmi
---
libavcodec/mips/idctdsp_init_mips.c |7 +-
libavcodec/mips/idctdsp_
Reoptimize function ff_put_h264_chroma_mc8_mmi and ff_avg_h264_chroma_mc8_mmi.
Performance of h264 decoding improved about 5%(from 69fps to 73fps, tested on
loongson 3A3000).
---
libavcodec/mips/h264chroma_mmi.c | 744 ---
1 file changed, 455 insertions(+), 289
Optimized memset with mmi in following functions:
1. ff_h264_add_pixels4_8_mmi.
2. ff_h264_idct_add_8_mmi.
3. ff_h264_idct8_add_8_mmi.
This optimization improved h264 decoding performance about 1.3%(tested on
loongson 3A3000).
---
libavcodec/mips/h264dsp_mmi.c | 30 +-
Failed case: mss2-wmv
In following functions, pmullh was used to multiply two 16-bit data, this will
cause data overflow.
1. ff_vc1_inv_trans_8x8_dc_mmi
2. ff_vc1_inv_trans_8x8_mmi
3. ff_vc1_inv_trans_8x4_mmi
4. ff_vc1_inv_trans_4x8_mmi
5. ff_vc1_inv_trans_4x4_mmi
---
libavcodec/mips/vc1dsp_mmi.c
Simplify the usage of intermediate variable addr in following functions:
1. ff_put_pixels4_8_mmi
2. ff_put_pixels8_8_mmi
3. ff_put_pixels16_8_mmi
4. ff_avg_pixels16_8_mmi.
---
libavcodec/mips/hpeldsp_mmi.c | 181 --
1 file changed, 87 insertions(+), 94 delet
Simplify the usage of intermediate variable addr and remove unused variable
all64
in following functions:
1. ff_put_pixels_clamped_mmi
2. ff_put_signed_pixels_clamped_mmi
3. ff_add_pixels_clamped_mmi
This optimization speed up mpeg4 decode about 2% on loongson platform(tested
with 3A3000).
---
-off-by: Shiyou Yin
---
libavcodec/mips/vp8dsp_mmi.c | 402 +++
libavutil/mips/mmiutils.h| 28 +++
2 files changed, 394 insertions(+), 36 deletions(-)
diff --git a/libavcodec/mips/vp8dsp_mmi.c b/libavcodec/mips/vp8dsp_mmi.c
index f972628..b24a87a 100644
Simplify macro TRANSPOSE_4H in mmiutils.h and add TRANSPOSE_8B as a common
macro.
---
libavcodec/mips/vc1dsp_mmi.c | 12 +++
libavcodec/mips/vp8dsp_mmi.c | 72 +
libavutil/mips/mmiutils.h| 84
3 files changed
Constraint "g" means compiler can store variable in memory or register.
When we use constraint "g" for a variable and this variable was operated by
instruction which only support register operands may lead "invalid operands"
error.
---
libavcodec/mips/vc1dsp_mmi.c | 6 +++---
1 file changed, 3 in
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of
>Shiyou Yin
>Sent: Wednesday, September 5, 2018 6:31 PM
>To: ffmpeg-devel@ffmpeg.org
>Cc: gxw
>Subject: [FFmpeg-devel] [PATCH 2/2] avcodec/mips:
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of
>Shiyou Yin
>Sent: Thursday, September 6, 2018 4:11 PM
>To: ffmpeg-devel@ffmpeg.org
>Subject: [FFmpeg-devel] [PATCH 1/2] avcodec/mips: [loongson]
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of
>Shiyou Yin
>Sent: Thursday, September 6, 2018 4:11 PM
>To: ffmpeg-devel@ffmpeg.org
>Subject: [FFmpeg-devel] [PATCH 2/2] avutil/mips: [loongson] simplify
Failed case: svq3-watermark
When minimum loop count of following functions are greater than parameter h
passed to them, svq3-watermark failed.
1. ff_put_pixels4_8_mmi
2. ff_avg_pixels4_8_mmi
3. ff_put_pixels4_l2_8_mmi
4. ff_avg_pixels4_l2_8_mmi
---
libavcodec/mips/hpeldsp_mmi.c | 112 +---
Combined 1st and 2nd loop into one inline asm in function
ff_vc1_inv_trans_8x8_mmi to
reduce memory operation, and made some small optimization in
ff_vc1_inv_trans_4x8_mmi.
---
libavcodec/mips/vc1dsp_mmi.c | 227 ++-
1 file changed, 94 insertions(+), 133 d
le mode 100644
index 000..82cee29
--- /dev/null
+++ b/libavcodec/mips/cabac.h
@@ -0,0 +1,119 @@
+/*
+ * Loongson SIMD optimized h264chroma
+ *
+ * Copyright (c) 2018 Loongson Technology Corporation Limited
+ * Copyright (c) 2018 Shiyou Yin
+ *
+ * This file is part of FFmpeg.
+ *
+ * FFmpeg is fr
Remove invalid operation in the case x and y all equal 0,
this refine made about 2% speedup for H264 decode on loongson platform.
---
libavcodec/mips/h264chroma_mmi.c | 970 +--
1 file changed, 426 insertions(+), 544 deletions(-)
diff --git a/libavcodec/mips/h2
Remove invalid operation in the case x and y all equal 0,
this refine made about 2% speedup for H264 decode on loongson platform.
---
libavcodec/mips/h264chroma_mmi.c | 970 +--
1 file changed, 426 insertions(+), 544 deletions(-)
diff --git a/libavcodec/mips/h2
Remove invalid operation in the case x and y all equal 0,
this refine made about 2% speedup for H264 decode on loongson platform.
---
libavcodec/mips/h264chroma_mmi.c | 970 +--
1 file changed, 426 insertions(+), 544 deletions(-)
diff --git a/libavcodec/mips/h2
mipsfpu supported by loongson 3a2000,3a3000,3a4000,2k1000, Fate tests passed.
---
configure | 1 -
1 file changed, 1 deletion(-)
diff --git a/configure b/configure
index 3e9222e..54b7e11 100755
--- a/configure
+++ b/configure
@@ -4848,7 +4848,6 @@ elif enabled mips; then
enable f
The MSA optimization has been refined in commit 93218c2 and ce0a52e.
It is better than MMI version now.
Speed of decoding H264: 4.83x ==> 4.89x (tested on 3A4000).
---
libavcodec/mips/h264chroma_init_mips.c | 19 +--
1 file changed, 9 insertions(+), 10 deletions(-)
diff --git a/li
v2: Fixed a build error in [PATCH 2/5].
v3: add patch 4/5.
[PATCH v3 1/5] avcodec/mips: Restore the initialization sequence of
[PATCH v3 2/5] avcodec/mips: Refine get_cabac_inline_mips.
[PATCH v3 3/5] avcodec/mips: Optimize function ff_h264_loop_filter_strength_msa.
[PATCH v3 4/5] avcodec/mips: Re
(c) 2018 Shiyou Yin
+ * Contributed by Shiyou Yin
+ *Gu Xiwei(guxiwei...@loongson.cn)
*
* This file is part of FFmpeg.
*
@@ -25,18 +26,18 @@
#define AVCODEC_MIPS_CABAC_H
#include "libavcodec/cabac.h"
-#include "libavutil/mips/asmdefs.h"
+#include &qu
From: gxw
Speed of decoding H264 1080P: 5.05x ==> 5.13x
Signed-off-by: Shiyou Yin
---
libavcodec/mips/Makefile| 3 +-
libavcodec/mips/h264_deblock_msa.c | 153
libavcodec/mips/h264dsp_init_mips.c | 2 +
libavcodec/mips/h264dsp_mip
From: gxw
Using mask to avoid judgment, H264 4K decoding speed
improved about 0.1fps tested on 3A4000
Signed-off-by: Shiyou Yin
---
libavcodec/mips/h264dsp_msa.c | 465 --
1 file changed, 171 insertions(+), 294 deletions(-)
diff --git a/libavcodec/mips
MSA2 optimizations are attached to MSA macros in generic_macros_msa.h.
It's difficult to do runtime check for them. Remove this part of code
can make it more robust. H264 1080p decoding: 5.13x==>5.12x.
---
configure | 7 +--
libavutil/mips/generic_macros_msa.h | 37 -
(c) 2018 Shiyou Yin
+ * Contributed by Shiyou Yin
+ *Gu Xiwei(guxiwei...@loongson.cn)
*
* This file is part of FFmpeg.
*
@@ -25,18 +26,18 @@
#define AVCODEC_MIPS_CABAC_H
#include "libavcodec/cabac.h"
-#include "libavutil/mips/asmdefs.h"
+#include &qu
The MSA optimization has been refined in commit 93218c2 and ce0a52e.
It is better than MMI version now.
Speed of decoding H264: 4.83x ==> 4.89x (tested on 3A4000).
---
libavcodec/mips/h264chroma_init_mips.c | 19 +--
1 file changed, 9 insertions(+), 10 deletions(-)
diff --git a/li
v2: Fixed a build error in [PATCH 2/5].
v3: add patch 4/5.
v4: Fix bug in 2/5 caused by instruction 'lhu' on BIGENDIAN environment.
[PATCH v4 1/5] avcodec/mips: Restore the initialization sequence of
[PATCH v4 2/5] avcodec/mips: Refine get_cabac_inline_mips.
[PATCH v4 3/5] avcodec/mips: Optimize f
From: gxw
Using mask to avoid judgment, H264 4K decoding speed
improved about 0.1fps tested on 3A4000
Signed-off-by: Shiyou Yin
---
libavcodec/mips/h264dsp_msa.c | 465 --
1 file changed, 171 insertions(+), 294 deletions(-)
diff --git a/libavcodec/mips
From: gxw
Speed of decoding H264 1080P: 5.05x ==> 5.13x
Signed-off-by: Shiyou Yin
---
libavcodec/mips/Makefile| 3 +-
libavcodec/mips/h264_deblock_msa.c | 153
libavcodec/mips/h264dsp_init_mips.c | 2 +
libavcodec/mips/h264dsp_mip
MSA2 optimizations are attached to MSA macros in generic_macros_msa.h.
It's difficult to do runtime check for them. Remove this part of code
can make it more robust. H264 1080p decoding: 5.13x==>5.12x.
---
configure | 7 +--
libavutil/mips/generic_macros_msa.h | 37 -
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of
>Jiaxun Yang
>Sent: Tuesday, May 26, 2020 5:48 PM
>To: ffmpeg-devel@ffmpeg.org
>Cc: yinshi...@loongson.cn; Jiaxun Yang
>Subject: [FFmpeg-devel] [PATCH 1/3] ffbuild: Refine MI
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of
>Jiaxun Yang
>Sent: Tuesday, May 26, 2020 5:48 PM
>To: ffmpeg-devel@ffmpeg.org
>Cc: yinshi...@loongson.cn; Jiaxun Yang
>Subject: [FFmpeg-devel] [PATCH 1/3] ffbuild: Refine MIPS
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of
>Shiyou Yin
>Sent: Sunday, May 31, 2020 11:33 AM
>To: 'FFmpeg development discussions and patches'
>Cc: yinshi...@loongson.cn
>Subject: Re:
For your convenience, I add the previous comments into this patch.
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of
>Jiaxun Yang
>Sent: Tuesday, June 2, 2020 10:15 PM
>To: ffmpeg-devel@ffmpeg.org
>Cc: yinshi...@loongson.cn;
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of
>Jiaxun Yang
>Sent: Saturday, June 6, 2020 3:34 PM
>To: ffmpeg-devel@ffmpeg.org
>Cc: yinshi...@loongson.cn; Jiaxun Yang
>Subject: [FFmpeg-devel] [PATCH v3 1/4] ffbuild: Refine
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of
>Jiaxun Yang
>Sent: Monday, June 8, 2020 11:30 AM
>To: ffmpeg-devel@ffmpeg.org
>Cc: yinshi...@loongson.cn; Jiaxun Yang
>Subject: [FFmpeg-devel] [PATCH v4 1/4] ffbuild: Refine M
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of
>Jiaxun Yang
>Sent: Monday, June 8, 2020 11:30 AM
>To: ffmpeg-devel@ffmpeg.org
>Cc: yinshi...@loongson.cn; Jiaxun Yang
>Subject: [FFmpeg-devel] [PATCH v4 2/4] libavutils: Add p
>-Original Message-
>From: jiaxun.y...@flygoat.com [mailto:jiaxun.y...@flygoat.com]
>Sent: Tuesday, June 9, 2020 2:03 AM
>To: FFmpeg development discussions and patches; Shiyou Yin; 'FFmpeg
>development discussions and
>patches'
>Subject: Re: [FFmpeg-devel]
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of
>jiaxun.y...@flygoat.com
>Sent: Tuesday, June 9, 2020 1:59 PM
>To: Shiyou Yin; 'FFmpeg development discussions and patches'
>Subject: R
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of
>Jiaxun Yang
>Sent: Monday, June 8, 2020 11:32 AM
>To: ffmpeg-devel@ffmpeg.org
>Cc: yinshi...@loongson.cn; Jiaxun Yang
>Subject: [FFmpeg-devel] [PATCH v4 3/4] libavutil: Detect
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of
>Jiaxun Yang
>Sent: Monday, June 8, 2020 11:32 AM
>To: ffmpeg-devel@ffmpeg.org
>Cc: yinshi...@loongson.cn; Jiaxun Yang
>Subject: [FFmpeg-devel] [PATCH v4 4/4] libavcodec: Enabl
The indentation of code dose not reflect the if block structure in
'apply_ltp_mips', and this will generate a warnning when build with
'-Wall' or '-Wmisleading-indentation'.
---
libavcodec/mips/aacdec_mips.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/libavcodec/mips/
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of gxw
>Sent: Saturday, October 12, 2019 10:48 AM
>To: ffmpeg-devel@ffmpeg.org
>Subject: [FFmpeg-devel] [PATCH] avcodec/mips: Fixed four warnings in vc1dsp
>
>Change the stride ar
>diff --git a/libavcodec/mips/vc1dsp_msa.c b/libavcodec/mips/vc1dsp_msa.c
>new file mode 100644
>index 000..1619ea4
>--- /dev/null
>+++ b/libavcodec/mips/vc1dsp_msa.c
>@@ -0,0 +1,483 @@
>+/*
>+ * Loongson SIMD optimized vc1dsp
>+ *
>+ * Copyright (c) 2019 Loongson Technology Corporation Limited
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of gxw
>Sent: Monday, October 21, 2019 3:57 PM
>To: ffmpeg-devel@ffmpeg.org
>Subject: [FFmpeg-devel] [PATCH v2] avcodec/mips: msa optimizations for vc1dsp
>
>Performance of WMV3 d
Set initialization order of MSA after MMI to make it work on loongson
platform(msa is supported by loongson2k、3a4000 etc.).
---
libavcodec/mips/blockdsp_init_mips.c| 6 +++---
libavcodec/mips/h264chroma_init_mips.c | 6 +++---
libavcodec/mips/h264dsp_init_mips.c | 6 +++---
libavcodec/mi
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of gxw
>Sent: Tuesday, December 18, 2018 9:15 AM
>To: ffmpeg-devel@ffmpeg.org
>Cc: gxw
>Subject: [FFmpeg-devel] [PATCH] avcodec/mips: [loongson] fix failed case:
>hevc-conformance
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of gxw
>Sent: Tuesday, December 18, 2018 9:15 AM
>To: ffmpeg-devel@ffmpeg.org
>Cc: gxw
>Subject: [FFmpeg-devel] [PATCH] avcodec/mips: [loongson] fix failed case:
>hevc-conformance
CDSP_MIPS_H
diff --git a/libavcodec/mips/hevcdsp_mmi.c b/libavcodec/mips/hevcdsp_mmi.c
new file mode 100644
index 000..e9403c5
--- /dev/null
+++ b/libavcodec/mips/hevcdsp_mmi.c
@@ -0,0 +1,135 @@
+/*
+ * Copyright (c) 2019 Shiyou Yin (yinshiyou...@loongson.cn)
+ *
+ * This file is part of FFmpeg.
Optimize put_hevc_qpel_bi_hv_8 with mmi in the case width=4/8/12/16/24/32/48/64.
This optimization improved HEVC decoding performance 11.4%(2.01x to 2.24x,
tested on loongson 3A3000).
---
libavcodec/mips/hevcdsp_init_mips.c | 9 ++
libavcodec/mips/hevcdsp_mips.h | 12 +-
libavcodec/mips/h
Optimize put_hevc_qpel_hv_8 with mmi in the case width=4/8/12/16/24/32/48/64.
This optimization improved HEVC decoding performance 11%(1.81x to 2.01x, tested
on loongson 3A3000).
---
libavcodec/mips/hevcdsp_init_mips.c | 9 ++
libavcodec/mips/hevcdsp_mips.h | 37 +--
libavcodec/mips/h
Optimize put_hevc_qpel_bi_h_8 with mmi in the case width=4/8/12/16/24/32/48/64.
This optimization improved HEVC decoding performance 2.1%(2.34x to 2.39x,
tested on loongson 3A3000).
---
libavcodec/mips/hevcdsp_init_mips.c | 9 +++
libavcodec/mips/hevcdsp_mips.h | 9 +++
libavcodec/mips/h
Optimize put_hevc_qpel_uni_hv_8 with mmi in the case
width=4/8/12/16/24/32/48/64.
This optimization improved HEVC decoding performance 2.7%(2.24x to 2.30x,
tested on loongson 3A3000).
---
libavcodec/mips/hevcdsp_init_mips.c | 9 ++
libavcodec/mips/hevcdsp_mips.h | 21
libavcodec/mip
Optimize put_hevc_epel_bi_hv_8 with mmi in the case width=4/8/12/16/24/32.
This optimization improved HEVC decoding performance 1.7%(2.30x to 2.34x,
tested on loongson 3A3000).
---
libavcodec/mips/hevcdsp_init_mips.c | 7 ++
libavcodec/mips/hevcdsp_mips.h | 6 ++
libavcodec/mips/hevcdsp_
Optimize put_hevc_qpel_h_8 with mmi in the case width=4/8/12/16/24/32/48/64.
This optimization improved HEVC decoding performance 2%(2.39x to 2.44x, tested
on loongson 3A3000).
---
libavcodec/mips/hevcdsp_init_mips.c | 9
libavcodec/mips/hevcdsp_mips.h | 9
libavcodec/mips/hevcds
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of gxw
>Sent: Tuesday, February 12, 2019 6:56 PM
>To: ffmpeg-devel@ffmpeg.org
>Cc: gxw
>Subject: [FFmpeg-devel] [PATCH] avcodec/mips: [loongson] optimize theora
>decoding with mm
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of gxw
>Sent: Tuesday, February 19, 2019 11:02 AM
>To: ffmpeg-devel@ffmpeg.org
>Cc: gxw
>Subject: [FFmpeg-devel] [PATCH] avcodec/mips: [loongson] mmi optimizations for
>VP9 put a
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of gxw
>Sent: Thursday, February 21, 2019 8:39 PM
>To: ffmpeg-devel@ffmpeg.org
>Cc: gxw
>Subject: [FFmpeg-devel] [PATCH v2] avcodec/mips: [loongson] mmi optimizations
>for VP9
>-Original Message-
>From: ffmpeg-devel-boun...@ffmpeg.org [mailto:ffmpeg-devel-boun...@ffmpeg.org]
>On Behalf Of gxw
>Sent: Monday, February 25, 2019 6:14 PM
>To: ffmpeg-devel@ffmpeg.org
>Cc: gxw
>Subject: [FFmpeg-devel] [PATCH v3] avcodec/mips: [loongson] mmi optimizations
>for VP9 put
> 2024年3月16日 11:03，Shiyou Yin 写道：
>
> [PATCH 1/3] swscale: [LA] Optimize range convert for yuvj420p.
> [PATCH 2/3] swscale: [LA] Optimize yuv2plane1_8_c.
> [PATCH 3/3] swscale: [LA] Optimize swscale funcs in input.c
>
> ___
&
> 2024年3月27日 03:31，Michael Niedermayer 写道：
>
> On Tue, Mar 26, 2024 at 11:11:00AM +0800, Shiyou Yin wrote:
>>
>>> 2024年3月16日 11:03，Shiyou Yin 写道：
>>>
>>> [PATCH 1/3] swscale: [LA] Optimize range convert for yuvj420p.
>>> [PATCH 2/3] sw
Compile with '--disable-lasx', ‘lumRangeFromJpeg_lasx’ undeclared.
---
libswscale/loongarch/swscale_init_loongarch.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/libswscale/loongarch/swscale_init_loongarch.c
b/libswscale/loongarch/swscale_init_loongarch.c
index 3a5a7ee856..4af62ad9f8 100
1 - 100 of 187 matches
Mail list logo
