Le 26 mai 2025 00:37:08 GMT+03:00, Michael Niedermayer
a écrit :
>Hi Rémi
>
>On Sat, May 24, 2025 at 07:10:57PM +0300, Rémi Denis-Courmont wrote:
>> Le torstaina 22. toukokuuta 2025, 9.32.18 Itä-Euroopan kesäaika Jiawei a
>> écrit
>> :
>> > > The RISC-V autovectorised output looks like it has
Hi Rémi
On Sat, May 24, 2025 at 07:10:57PM +0300, Rémi Denis-Courmont wrote:
> Le torstaina 22. toukokuuta 2025, 9.32.18 Itä-Euroopan kesäaika Jiawei a
> écrit
> :
> > > The RISC-V autovectorised output looks like it has a warning "Odd
> > > rotation angle" which is not present in the non-autove
Le torstaina 22. toukokuuta 2025, 9.32.18 Itä-Euroopan kesäaika Jiawei a écrit
:
> > The RISC-V autovectorised output looks like it has a warning "Odd
> > rotation angle" which is not present in the non-autovectorised output.
>
> I found this occured when using '-ffast-math' in RISC-V, also occur
Hi,
Le 21 mai 2025 09:17:50 GMT+03:00, Jiawei a écrit :
>This patch modifies the FFmpeg build system to remove the explicit disabling
>of GCC's auto-vectorization feature.
>
>Modern GCC versions (>= 10.0) have demonstrated stable auto-vectorization
>capabilities through extensive optimizations in
Here is a particularly bad example of autovectorisation across many
compilers:
https://gcc.godbolt.org/z/rjEqzf1hh
Kieran
Admittedly, in some cases, enabling vectorization is not the optimal
solution.
But the question is the limitation is only added on gcc side.For LLVM
clang, there are no
On Thu, 22 May 2025, 07:32 Jiawei, wrote:
> 在 2025/5/22 2:21, Frank Plowman 写道:
> > On 21/05/2025 11:17, Jiawei wrote:
> >> 在 2025/5/21 14:52, Nicolas George 写道:
> >>> Jiawei (HE12025-05-21):
> particularly improving
> performance on x86_64 (AVX), AR
在 2025/5/22 2:21, Frank Plowman 写道:
On 21/05/2025 11:17, Jiawei wrote:
在 2025/5/21 14:52, Nicolas George 写道:
Jiawei (HE12025-05-21):
particularly improving
performance on x86_64 (AVX), ARM64 (SVE) and RISC-V(RVV) architectures.
Benchmark needed.
Rega
On 21/05/2025 11:17, Jiawei wrote:
>
> 在 2025/5/21 14:52, Nicolas George 写道:
>> Jiawei (HE12025-05-21):
>>> particularly improving
>>> performance on x86_64 (AVX), ARM64 (SVE) and RISC-V(RVV) architectures.
>> Benchmark needed.
>>
>> Regards,
>
>
> Hi Nicola
> -Original Message-
> From: ffmpeg-devel On Behalf Of Martin
> Storsjö
> Sent: Mittwoch, 21. Mai 2025 14:22
> To: FFmpeg development discussions and patches
> Subject: Re: [FFmpeg-devel] gcc: Remove auto-vectorization limitation.
>
> On Wed, 21 May 2025,
On Wed, 21 May 2025, Andreas Rheinhardt wrote:
Martin Storsjö:
On Wed, 21 May 2025, Andreas Rheinhardt wrote:
Jiawei:
This patch modifies the FFmpeg build system to remove the explicit
disabling
of GCC's auto-vectorization feature.
Modern GCC versions (>= 10.0) have demonstrated stable auto
Martin Storsjö:
> On Wed, 21 May 2025, Andreas Rheinhardt wrote:
>
>> Jiawei:
>>> This patch modifies the FFmpeg build system to remove the explicit
>>> disabling
>>> of GCC's auto-vectorization feature.
>>>
>>> Modern GCC versions (>= 10.0) have demonstrated stable auto-
>>> vectorization
>>> cap
On Wed, 21 May 2025, Andreas Rheinhardt wrote:
Jiawei:
This patch modifies the FFmpeg build system to remove the explicit disabling
of GCC's auto-vectorization feature.
Modern GCC versions (>= 10.0) have demonstrated stable auto-vectorization
capabilities through extensive optimizations in loo
On Wed, May 21, 2025 at 06:32:49PM +0800, Jiawei wrote:
>
> 在 2025/5/21 15:46, Michael Niedermayer 写道:
> > On Wed, May 21, 2025 at 02:17:50PM +0800, Jiawei wrote:
> > > This patch modifies the FFmpeg build system to remove the explicit
> > > disabling
> > > of GCC's auto-vectorization feature.
>
Jiawei:
> This patch modifies the FFmpeg build system to remove the explicit disabling
> of GCC's auto-vectorization feature.
>
> Modern GCC versions (>= 10.0) have demonstrated stable auto-vectorization
> capabilities through extensive optimizations in loop analysis and SIMD
> code generation. Th
在 2025/5/21 15:46, Michael Niedermayer 写道:
On Wed, May 21, 2025 at 02:17:50PM +0800, Jiawei wrote:
This patch modifies the FFmpeg build system to remove the explicit disabling
of GCC's auto-vectorization feature.
Modern GCC versions (>= 10.0) have demonstrated stable auto-vectorization
capabil
在 2025/5/21 17:04, Zhao Zhili 写道:
On May 21, 2025, at 14:17, Jiawei wrote:
This patch modifies the FFmpeg build system to remove the explicit disabling
of GCC's auto-vectorization feature.
Modern GCC versions (>= 10.0) have demonstrated stable auto-vectorization
capabilities through extensi
在 2025/5/21 14:52, Nicolas George 写道:
Jiawei (HE12025-05-21):
particularly improving
performance on x86_64 (AVX), ARM64 (SVE) and RISC-V(RVV) architectures.
Benchmark needed.
Regards,
Hi Nicolas,
Since I am a gcc developer, I'm not so familiar wi
> -原始邮件-
> 发件人: "Nicolas George"
> 发送时间: 2025-05-21 14:52:12 (星期三)
> 收件人: "FFmpeg development discussions and patches"
> 抄送:
> 主题: Re: [FFmpeg-devel] gcc: Remove auto-vectorization limitation.
>
> Jiawei (HE12025-05-21):
> >
> -原始邮件-
> 发件人: "Nicolas George"
> 发送时间: 2025-05-21 14:52:12 (星期三)
> 收件人: "FFmpeg development discussions and patches"
> 抄送:
> 主题: Re: [FFmpeg-devel] gcc: Remove auto-vectorization limitation.
>
> Jiawei (HE12025-05-21):
> >
> On May 21, 2025, at 14:17, Jiawei wrote:
>
> This patch modifies the FFmpeg build system to remove the explicit disabling
> of GCC's auto-vectorization feature.
>
> Modern GCC versions (>= 10.0) have demonstrated stable auto-vectorization
> capabilities through extensive optimizations in loo
On Wed, May 21, 2025 at 02:17:50PM +0800, Jiawei wrote:
> This patch modifies the FFmpeg build system to remove the explicit disabling
> of GCC's auto-vectorization feature.
>
> Modern GCC versions (>= 10.0) have demonstrated stable auto-vectorization
> capabilities through extensive optimizations
Jiawei (HE12025-05-21):
> particularly improving
> performance on x86_64 (AVX), ARM64 (SVE) and RISC-V(RVV) architectures.
Benchmark needed.
Regards,
--
Nicolas George
___
ffmpeg-devel mailing list
ffmpeg-deve
This patch modifies the FFmpeg build system to remove the explicit disabling
of GCC's auto-vectorization feature.
Modern GCC versions (>= 10.0) have demonstrated stable auto-vectorization
capabilities through extensive optimizations in loop analysis and SIMD
code generation. The explicit -fno-tree
23 matches
Mail list logo
