* [FFmpeg-devel] libavfilter/x86/vf_convolution.asm- fix missing decelerator for AVX512ICL sobel
@ 2023-02-24 3:00 Felix LeClair
2023-02-24 13:09 ` Kieran Kunhya
2023-02-24 13:51 ` James Darnley
0 siblings, 2 replies; 6+ messages in thread
From: Felix LeClair @ 2023-02-24 3:00 UTC (permalink / raw)
To: ffmpeg-devel
[-- Attachment #1: Type: text/plain, Size: 189 bytes --]
Fixes: Compilation of Sobel with AVX512ICL
Caused: Comment left without deleniator in AVX512ICL version of SOBEL
Testing:Confirmed working on AVX512 Alderlake (AKA SPR without AMX)
[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #2: 0001-libavfilter-x86-vf_convolution.asm.patch --]
[-- Type: text/x-patch; name="0001-libavfilter-x86-vf_convolution.asm.patch", Size: 1213 bytes --]
From 2b12db24d2bbe8a1544a9a7f3a08e1a693a6c2ce Mon Sep 17 00:00:00 2001
From: "Felix LeClair (FCLC)" <felix.leclair123@hotmail.com>
Date: Thu, 23 Feb 2023 21:36:32 -0500
Subject: [PATCH] libavfilter/x86/vf_convolution.asm
Fixes: Compilation of Sobel with AVX512ICL
Caused: Comment left without deleniator in AVX512ICL version of SOBEL
Testing:Confirmed working on AVX512 Alderlake (AKA SPR without AMX)
Signed-off-by: Felix LeClair (FCLC) <felix.leclair123@hotmail.com>
---
libavfilter/x86/vf_convolution.asm | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/libavfilter/x86/vf_convolution.asm b/libavfilter/x86/vf_convolution.asm
index 9ac9ef5d73..8b85897819 100644
--- a/libavfilter/x86/vf_convolution.asm
+++ b/libavfilter/x86/vf_convolution.asm
@@ -232,8 +232,8 @@ cglobal filter_sobel, 4, 15, 7, dst, width, rdiv, bias, matrix, ptr, c0, c1, c2,
psubd m4, m5
vpermb m3, m6, m3
mova m5, m4
- vpdpbusd m4, m2, [sobel_mulA] {1to16}
- vpdpbusd m5, m3, [sobel_mulB] {1to16}
+ vpdpbusd m4, m2, [sobel_mulA]; {1to16}
+ vpdpbusd m5, m3, [sobel_mulB]; {1to16}
cvtdq2ps m4, m4
mulps m4, m4
--
2.34.1
[-- Attachment #3: Type: text/plain, Size: 251 bytes --]
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [FFmpeg-devel] libavfilter/x86/vf_convolution.asm- fix missing decelerator for AVX512ICL sobel
2023-02-24 3:00 [FFmpeg-devel] libavfilter/x86/vf_convolution.asm- fix missing decelerator for AVX512ICL sobel Felix LeClair
@ 2023-02-24 13:09 ` Kieran Kunhya
2023-02-24 13:51 ` James Darnley
1 sibling, 0 replies; 6+ messages in thread
From: Kieran Kunhya @ 2023-02-24 13:09 UTC (permalink / raw)
To: FFmpeg development discussions and patches
On Fri, 24 Feb 2023 at 03:00, Felix LeClair <felix.leclair123@hotmail.com>
wrote:
> Fixes: Compilation of Sobel with AVX512ICL
> Caused: Comment left without deleniator in AVX512ICL version of SOBEL
>
> Testing:Confirmed working on AVX512 Alderlake (AKA SPR without AMX)
>
Seems fine, bit weird that FATE didn't pick it up.
Kieran
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [FFmpeg-devel] libavfilter/x86/vf_convolution.asm- fix missing decelerator for AVX512ICL sobel
2023-02-24 3:00 [FFmpeg-devel] libavfilter/x86/vf_convolution.asm- fix missing decelerator for AVX512ICL sobel Felix LeClair
2023-02-24 13:09 ` Kieran Kunhya
@ 2023-02-24 13:51 ` James Darnley
2023-02-24 13:51 ` James Darnley
2023-02-24 15:12 ` Felix LeClair
1 sibling, 2 replies; 6+ messages in thread
From: James Darnley @ 2023-02-24 13:51 UTC (permalink / raw)
To: ffmpeg-devel
On 2/24/23 04:00, Felix LeClair wrote:
> Fixes: Compilation of Sobel with AVX512ICL
> Caused: Comment left without deleniator in AVX512ICL version of SOBEL
>
> Testing:Confirmed working on AVX512 Alderlake (AKA SPR without AMX)
> diff --git a/libavfilter/x86/vf_convolution.asm b/libavfilter/x86/vf_convolution.asm
> index 9ac9ef5d73..8b85897819 100644
> --- a/libavfilter/x86/vf_convolution.asm
> +++ b/libavfilter/x86/vf_convolution.asm
> @@ -232,8 +232,8 @@ cglobal filter_sobel, 4, 15, 7, dst, width, rdiv, bias, matrix, ptr, c0, c1, c2,
> psubd m4, m5
> vpermb m3, m6, m3
> mova m5, m4
> - vpdpbusd m4, m2, [sobel_mulA] {1to16}
> - vpdpbusd m5, m3, [sobel_mulB] {1to16}
> + vpdpbusd m4, m2, [sobel_mulA]; {1to16}
> + vpdpbusd m5, m3, [sobel_mulB]; {1to16}
>
> cvtdq2ps m4, m4
> mulps m4, m4
Fix compilation with what?
I'm not familiar with the sobel algorith/function so I can't say whether
the code is correct. However those constants are only dword sized and
that is how you do a memory broadcast with avx512(icl). Furthermore
testing your change on an icl system results in a failure in checkasm.
So what program and what version fails to assemble that?
[re-sending to list]
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [FFmpeg-devel] libavfilter/x86/vf_convolution.asm- fix missing decelerator for AVX512ICL sobel
2023-02-24 13:51 ` James Darnley
@ 2023-02-24 13:51 ` James Darnley
2023-02-24 15:12 ` Felix LeClair
1 sibling, 0 replies; 6+ messages in thread
From: James Darnley @ 2023-02-24 13:51 UTC (permalink / raw)
To: ffmpeg-devel
On 2/24/23 04:00, Felix LeClair wrote:
> Fixes: Compilation of Sobel with AVX512ICL
> Caused: Comment left without deleniator in AVX512ICL version of SOBEL
>
> Testing:Confirmed working on AVX512 Alderlake (AKA SPR without AMX)
> diff --git a/libavfilter/x86/vf_convolution.asm b/libavfilter/x86/vf_convolution.asm
> index 9ac9ef5d73..8b85897819 100644
> --- a/libavfilter/x86/vf_convolution.asm
> +++ b/libavfilter/x86/vf_convolution.asm
> @@ -232,8 +232,8 @@ cglobal filter_sobel, 4, 15, 7, dst, width, rdiv, bias, matrix, ptr, c0, c1, c2,
> psubd m4, m5
> vpermb m3, m6, m3
> mova m5, m4
> - vpdpbusd m4, m2, [sobel_mulA] {1to16}
> - vpdpbusd m5, m3, [sobel_mulB] {1to16}
> + vpdpbusd m4, m2, [sobel_mulA]; {1to16}
> + vpdpbusd m5, m3, [sobel_mulB]; {1to16}
>
> cvtdq2ps m4, m4
> mulps m4, m4
Fix compilation with what?
I'm not familiar with the sobel algorith/function so I can't say whether
the code is correct. However those constants are only dword sized and
that is how you do a memory broadcast with avx512(icl). Furthermore
testing your change on an icl system results in a failure in checkasm.
So what program and what version fails to assemble that?
[re-sending to list]
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [FFmpeg-devel] libavfilter/x86/vf_convolution.asm- fix missing decelerator for AVX512ICL sobel
2023-02-24 13:51 ` James Darnley
2023-02-24 13:51 ` James Darnley
@ 2023-02-24 15:12 ` Felix LeClair
2023-02-24 15:45 ` Felix LeClair
1 sibling, 1 reply; 6+ messages in thread
From: Felix LeClair @ 2023-02-24 15:12 UTC (permalink / raw)
To: FFmpeg development discussions and patches
Without patch I hit:
```
CC libavdevice/version.o
AR libavdevice/libavdevice.a
CC libavfilter/version.o
X86ASM libavfilter/x86/vf_convolution.o
libavfilter/x86/vf_convolution.asm:302: error: operation size not specified
libavfilter/x86/vf_convolution.asm:235: ... from macro `FILTER_SOBEL' defined here
libavfilter/x86/vf_convolution.asm:302: error: operation size not specified
libavfilter/x86/vf_convolution.asm:236: ... from macro `FILTER_SOBEL' defined here
make: *** [ffbuild/common.mak:103: libavfilter/x86/vf_convolution.o] Error 1
```
During compilation of commit ac6eec1fc258efce219e4fccb84312a1b13a7a23
With
make config
./configure --samples=fate-suite --enable-gpl --enable-ladspa --enable-libass --enable-libcodec2 --enable-libdav1d --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzvbi --enable-lv2 --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libx264 --enable-opencl --enable-nonfree --enable-libsvtav1 --disable-stripping --cpu=sapphire-rapids --enable-pic
Kernel 6.2.0, NASM 2.16, GCC 12.1.1
________________________________
From: ffmpeg-devel <ffmpeg-devel-bounces@ffmpeg.org> on behalf of James Darnley <james.darnley@gmail.com>
Sent: February 24, 2023 8:51 AM
To: ffmpeg-devel@ffmpeg.org <ffmpeg-devel@ffmpeg.org>
Subject: Re: [FFmpeg-devel] libavfilter/x86/vf_convolution.asm- fix missing decelerator for AVX512ICL sobel
On 2/24/23 04:00, Felix LeClair wrote:
> Fixes: Compilation of Sobel with AVX512ICL
> Caused: Comment left without deleniator in AVX512ICL version of SOBEL
>
> Testing:Confirmed working on AVX512 Alderlake (AKA SPR without AMX)
> diff --git a/libavfilter/x86/vf_convolution.asm b/libavfilter/x86/vf_convolution.asm
> index 9ac9ef5d73..8b85897819 100644
> --- a/libavfilter/x86/vf_convolution.asm
> +++ b/libavfilter/x86/vf_convolution.asm
> @@ -232,8 +232,8 @@ cglobal filter_sobel, 4, 15, 7, dst, width, rdiv, bias, matrix, ptr, c0, c1, c2,
> psubd m4, m5
> vpermb m3, m6, m3
> mova m5, m4
> - vpdpbusd m4, m2, [sobel_mulA] {1to16}
> - vpdpbusd m5, m3, [sobel_mulB] {1to16}
> + vpdpbusd m4, m2, [sobel_mulA]; {1to16}
> + vpdpbusd m5, m3, [sobel_mulB]; {1to16}
>
> cvtdq2ps m4, m4
> mulps m4, m4
Fix compilation with what?
I'm not familiar with the sobel algorith/function so I can't say whether
the code is correct. However those constants are only dword sized and
that is how you do a memory broadcast with avx512(icl). Furthermore
testing your change on an icl system results in a failure in checkasm.
So what program and what version fails to assemble that?
[re-sending to list]
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [FFmpeg-devel] libavfilter/x86/vf_convolution.asm- fix missing decelerator for AVX512ICL sobel
2023-02-24 15:12 ` Felix LeClair
@ 2023-02-24 15:45 ` Felix LeClair
0 siblings, 0 replies; 6+ messages in thread
From: Felix LeClair @ 2023-02-24 15:45 UTC (permalink / raw)
To: FFmpeg development discussions and patches
Disregard-found to be an issue in nasm 2.16RC, fixed with upstream 2.16.01
________________________________
From: ffmpeg-devel <ffmpeg-devel-bounces@ffmpeg.org> on behalf of Felix LeClair <felix.leclair123@hotmail.com>
Sent: February 24, 2023 10:12 AM
To: FFmpeg development discussions and patches <ffmpeg-devel@ffmpeg.org>
Subject: Re: [FFmpeg-devel] libavfilter/x86/vf_convolution.asm- fix missing decelerator for AVX512ICL sobel
Without patch I hit:
```
CC libavdevice/version.o
AR libavdevice/libavdevice.a
CC libavfilter/version.o
X86ASM libavfilter/x86/vf_convolution.o
libavfilter/x86/vf_convolution.asm:302: error: operation size not specified
libavfilter/x86/vf_convolution.asm:235: ... from macro `FILTER_SOBEL' defined here
libavfilter/x86/vf_convolution.asm:302: error: operation size not specified
libavfilter/x86/vf_convolution.asm:236: ... from macro `FILTER_SOBEL' defined here
make: *** [ffbuild/common.mak:103: libavfilter/x86/vf_convolution.o] Error 1
```
During compilation of commit ac6eec1fc258efce219e4fccb84312a1b13a7a23
With
make config
./configure --samples=fate-suite --enable-gpl --enable-ladspa --enable-libass --enable-libcodec2 --enable-libdav1d --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzvbi --enable-lv2 --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libx264 --enable-opencl --enable-nonfree --enable-libsvtav1 --disable-stripping --cpu=sapphire-rapids --enable-pic
Kernel 6.2.0, NASM 2.16, GCC 12.1.1
________________________________
From: ffmpeg-devel <ffmpeg-devel-bounces@ffmpeg.org> on behalf of James Darnley <james.darnley@gmail.com>
Sent: February 24, 2023 8:51 AM
To: ffmpeg-devel@ffmpeg.org <ffmpeg-devel@ffmpeg.org>
Subject: Re: [FFmpeg-devel] libavfilter/x86/vf_convolution.asm- fix missing decelerator for AVX512ICL sobel
On 2/24/23 04:00, Felix LeClair wrote:
> Fixes: Compilation of Sobel with AVX512ICL
> Caused: Comment left without deleniator in AVX512ICL version of SOBEL
>
> Testing:Confirmed working on AVX512 Alderlake (AKA SPR without AMX)
> diff --git a/libavfilter/x86/vf_convolution.asm b/libavfilter/x86/vf_convolution.asm
> index 9ac9ef5d73..8b85897819 100644
> --- a/libavfilter/x86/vf_convolution.asm
> +++ b/libavfilter/x86/vf_convolution.asm
> @@ -232,8 +232,8 @@ cglobal filter_sobel, 4, 15, 7, dst, width, rdiv, bias, matrix, ptr, c0, c1, c2,
> psubd m4, m5
> vpermb m3, m6, m3
> mova m5, m4
> - vpdpbusd m4, m2, [sobel_mulA] {1to16}
> - vpdpbusd m5, m3, [sobel_mulB] {1to16}
> + vpdpbusd m4, m2, [sobel_mulA]; {1to16}
> + vpdpbusd m5, m3, [sobel_mulB]; {1to16}
>
> cvtdq2ps m4, m4
> mulps m4, m4
Fix compilation with what?
I'm not familiar with the sobel algorith/function so I can't say whether
the code is correct. However those constants are only dword sized and
that is how you do a memory broadcast with avx512(icl). Furthermore
testing your change on an icl system results in a failure in checkasm.
So what program and what version fails to assemble that?
[re-sending to list]
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2023-02-24 15:46 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2023-02-24 3:00 [FFmpeg-devel] libavfilter/x86/vf_convolution.asm- fix missing decelerator for AVX512ICL sobel Felix LeClair
2023-02-24 13:09 ` Kieran Kunhya
2023-02-24 13:51 ` James Darnley
2023-02-24 13:51 ` James Darnley
2023-02-24 15:12 ` Felix LeClair
2023-02-24 15:45 ` Felix LeClair
Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
This inbox may be cloned and mirrored by anyone:
git clone --mirror https://master.gitmailbox.com/ffmpegdev/0 ffmpegdev/git/0.git
# If you have public-inbox 1.1+ installed, you may
# initialize and index your mirror using the following commands:
public-inbox-init -V2 ffmpegdev ffmpegdev/ https://master.gitmailbox.com/ffmpegdev \
ffmpegdev@gitmailbox.com
public-inbox-index ffmpegdev
Example config snippet for mirrors.
AGPL code for this site: git clone https://public-inbox.org/public-inbox.git