> -原始邮件-
> 发件人: jinbo
> 发送时间:2023-12-28 16:21:05 (星期四)
> 收件人: ffmpeg-devel@ffmpeg.org
> 抄送: yuanhecai
> 主题: [FFmpeg-devel] [PATCH v3 7/7] avcodec/hevc: Add ff_hevc_idct_32x32_lasx
> asm opt
>
> From: yuanhecai
>
> tests/checkasm/checkasm:
>
> C LSX
-原始邮件-
发件人: "Michael Niedermayer"
发送时间: 2023-12-22 03:17:28 (星期五)
收件人: "FFmpeg development discussions and patches"
主题: [FFmpeg-devel] FFmpeg 6.1.1
Hi all
I will probably make a 6.1.1 release in maybe 1-3 weeks due to bug/fixes
in it.
if you want something in it, please backport it
> -原始邮件-
> 发件人: jinbo
> 发送时间:2023-12-28 16:20:59 (星期四)
> 收件人: ffmpeg-devel@ffmpeg.org
> 抄送: jinbo
> 主题: [FFmpeg-devel] [PATCH v3 1/7] avcodec/hevc: Add init for sao_edge_filter
>
> Forgot to init c->sao_edge_filter[idx] when idx=0/1/2/3.
> After this patch, the speedup of decoding H265
> -原始邮件-
> 发件人: jinbo
> 发送时间:2023-12-27 12:50:19 (星期三)
> 收件人: ffmpeg-devel@ffmpeg.org
> 抄送: yuanhecai
> 主题: [FFmpeg-devel] [PATCH v2 7/7] avcodec/hevc: Add ff_hevc_idct_32x32_lasx
> asm opt
> +
> +.macro malloc_space number
> +li.w t0, \number
> +sub.d
> -原始邮件-
> 发件人: jinbo
> 发送时间:2023-12-27 12:50:15 (星期三)
> 收件人: ffmpeg-devel@ffmpeg.org
> 抄送: jinbo
> 主题: [FFmpeg-devel] [PATCH v2 3/7] avcodec/hevc: Add
> pel_uni_w_pixels4/6/8/12/16/24/32/48/64 asm opt
>
> +
> +.macro HEVC_PEL_UNI_W_PIXELS8_LSX src0, dst0, w
> +vldrepl.d vr0,
> -原始邮件-
> 发件人: "Hao Chen"
> 发送时间:2023-05-04 16:49:47 (星期四)
> 收件人: ffmpeg-devel@ffmpeg.org
> 抄送: "Shiyou Yin"
> 主题: [FFmpeg-devel] [PATCH v1 1/6] avcodec/la: add LSX optimization for h264
> idct.
>
> diff --git a/libavcodec/loongarch/h264dsp_lasx.h
>
> -原始邮件-
> 发件人: "Hao Chen"
> 发送时间:2022-09-09 17:00:23 (星期五)
> 收件人: ffmpeg-devel@ffmpeg.org
> 抄送:
> 主题: [FFmpeg-devel] Add LoongArch SIMD optimization in swscale lib.
>
> v2: Some modifications were made according to the comments of the reviewers.
> v3: Update and run CI test again.
>
Thanks for your respose, The remote debuggable machine is available from
loongson cloud for free.
BTW, we can donate machine to enthusiasts. contact me please.
Hi,
Glad to hear there have some optimize code for loongarch.
In my view, a remote debuggable machine may help more people focus
> -原始邮件-
> 发件人: "Jin Bo"
> 发送时间: 2021-08-03 12:05:21 (星期二)
> 收件人: ffmpeg-devel@ffmpeg.org
> 抄送:
> 主题: [FFmpeg-devel] [PATCH v2] configure: [loongson] adjust MMI check in
> configure
>
> After standardizing the use of 'pxor' in commit 'ebedd26', FFmpeg
> build failed with upstream
> -原始邮件-
> 发件人: "Jiaxun Yang"
> 发送时间: 2021-08-02 13:40:54 (星期一)
> 收件人: "FFmpeg development discussions and patches" ,
> yinshiyou...@loongson.cn
> 抄送:
> 主题: Re: [FFmpeg-devel] [PATCH] avcodec/mips: Support old style mmi
> instruction mnemonics
>
>
> 在 2021/7/29 20:26, Jiaxun Yang 写道:
> -原始邮件-
> 发件人: "Jiaxun Yang"
> 发送时间: 2021-07-29 14:32:35 (星期四)
> 收件人: ffmpeg-devel@ffmpeg.org
> 抄送: yinshiyou...@loongson.cn, "Jiaxun Yang"
> 主题: [PATCH] avcodec/mips: Support old style mmi instruction mnemonics
>
> Loongson had renamed serval instruction mnemonics to distinguish
>
-原始邮件-
发件人: "Jiaxun Yang"
发送时间: 2021-07-23 17:27:18 (星期五)
收件人: yinshiyou...@loongson.cn, "FFmpeg development discussions and
patches"
抄送: "金波"
主题: Re: [FFmpeg-devel] [PATCH v1] configure: fix mmi check
在 2021/7/23 17:23, yinshiyou...@loongson.cn 写道:
-原始邮件-
-原始邮件-
发件人: "Jiaxun Yang"
发送时间: 2021-07-23 10:34:37 (星期五)
收件人: ffmpeg-devel@ffmpeg.org
抄送:
主题: Re: [FFmpeg-devel] [PATCH v1] configure: fix mmi check
在 2021/7/23 上午9:39, Jin Bo 写道:
pxor is loongson media extension instruction, it's not
supported yet on upstream gcc
-原始邮件-
发件人: "Jiaxun Yang"
发送时间: 2021-07-23 13:53:40 (星期五)
收件人: ffmpeg-devel@ffmpeg.org
抄送: yinshiyou...@loongson.cn, "Jiaxun Yang"
主题: [PATCH v3 0/4] avcodec Loongson-2 MMI fixes
Get MMI optimizations build for Loongson-2 again.
Tested on Loongson-2 and Loongson-3A.
---
v2:
-原始邮件-
发件人: "Jiaxun Yang"
发送时间: 2021-07-22 21:59:03 (星期四)
收件人: ffmpeg-devel@ffmpeg.org
抄送:
主题: Re: [FFmpeg-devel] [PATCH v2 2/5] avutil/mips: Extract load store with
shift C1 pair marco
在 2021/7/22 下午7:55, yinshiyou...@loongson.cn 写道:
-原始邮件-
发件人: "Jiaxun Yang"
-原始邮件-
发件人: "Jiaxun Yang"
发送时间: 2021-07-22 17:14:17 (星期四)
收件人: yinshiyou...@loongson.cn, "FFmpeg development discussions and
patches"
抄送: "Jin Bo" , xuchueng...@loongson.cn
主题: Re: [FFmpeg-devel] [PATCH] Revert "libavcodec/mips: Fix specification
of instruction name"
在
-原始邮件-
发件人: "Jiaxun Yang"
发送时间: 2021-07-21 17:19:10 (星期三)
收件人: ffmpeg-devel@ffmpeg.org
抄送: yinshiyou...@loongson.cn, "Jiaxun Yang"
主题: [FFmpeg-devel] [PATCH v2 2/5] avutil/mips: Extract load store with
shift C1 pair marco
We're doing some fancy hacks with load store with shift
-原始邮件-
发件人: "Jiaxun Yang"
发送时间: 2021-07-21 17:39:22 (星期三)
收件人: ffmpeg-devel@ffmpeg.org
抄送: yinshiyou...@loongson.cn, "Jin Bo" , "Jiaxun Yang"
主题: [FFmpeg-devel] [PATCH] Revert "libavcodec/mips: Fix specification of
instruction name"
This reverts commit
-原始邮件-
发件人: "Jin Bo"
发送时间: 2021-05-28 10:04:41 (星期五)
收件人: ffmpeg-devel@ffmpeg.org
抄送: "Jin Bo"
主题: [FFmpeg-devel] [PATCH 3/3] libavcodec/mips: Fix fate errors reported
by clang
The data width of gsldrc1/gsldlc1 should be 8 bytes wide.
Signed-off-by: Jin Bo
---
-原始邮件-
发件人: "Jin Bo"
发送时间: 2021-05-28 10:04:40 (星期五)
收件人: ffmpeg-devel@ffmpeg.org
抄送: "Jin Bo"
主题: [FFmpeg-devel] [PATCH 2/3] libavcodec/mips: Fix build errors reported
by clang
Clang is more strict on the type of asm operands, float or double
type variable should use
I hered from the previous mantainer for mips that he was no longer part of mips
company,and as a result, my patch was still pending review.
Will ffmpeg community asign new mantainer for mips? If so, I hope I can be one
of the candidates. I have uploaded some loongson optimization patchs for
> 2018-07-11 11:45 GMT+02:00, Shiyou Yin :
> > Reoptimized following functions with mmi.
> > 1. ff_simple_idct_put_mmi
> > 2. ff_simple_idct_add_mmi
> > 3. ff_simple_idct_mmi (rename to ff_simple_idct_8_mmi)
>
> Are the new functions faster? Easier to maintain?
> More future-proof?
>
> Please
> 2018-07-11 11:44 GMT+02:00, Shiyou Yin :
> > Revert expensive optimizations in gcc O3 optimization for loongson.
> > The bug in gcc-4.9.x has been fixed in gcc master branch.
> > Loongson released gcc-4.9.3-3.fc21.loongson with this patch.
>
> I believe the title of the patch can be clarified
> > From: gxw
> >
> > Optimize vp8 loop filter with mmi, four functions optimized:
> > 1. ff_vp8_h_loop_filter8uv_mmi.
> > 2. ff_vp8_v_loop_filter8uv_mmi.
> > 3. ff_vp8_h_loop_filter16_mmi.
> > 4. ff_vp8_v_loop_filter16_mmi.
> >
> > Vp8 decoding speed improved about 50%(from 73fps to 110fps,
Is there anyone reviewing my patch? I sent 9 patchs about 20 days ago, but only
one patch received reply at June 14.
___
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
> +
> +void ff_simple_idct_put_mmi(uint8_t *dest, int line_size, int16_t *block)
> +{
> +ff_simple_idct_8_mmi(block);
> +ff_put_pixels_clamped_mmi(block, dest, line_size);
> +}
> +void ff_simple_idct_add_mmi(uint8_t *dest, int line_size, int16_t *block)
> +{
> +
> -原始邮件-
> 发件人: "Shiyou Yin"
> 发送时间: 2018-06-19 14:21:10 (星期二)
> 收件人: ffmpeg-devel@ffmpeg.org
> 抄送: gxw
> 主题: [FFmpeg-devel] [PATCH] avcodec/mips: [loongson] optimize vp8 decoding in
> vp8dsp.
>
> From: gxw
>
> Optimize vp8 decoding with mmi in function:
> 1.
>
> 2018-06-14 9:36 GMT+02:00, Shiyou Yin :
> > From: gxw
> >
> > Optimize vp8 decoding with mmi in function:
> > 1. ff_vp8_h_loop_filter8uv_mmi.
> > 2. ff_vp8_v_loop_filter8uv_mmi.
> > 3. ff_vp8_h_loop_filter16_mmi.
> > 4. ff_vp8_v_loop_filter16_mmi.
>
> Please add some numbers about the
28 matches
Mail list logo
