From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org [79.124.17.100]) by master.gitmailbox.com (Postfix) with ESMTP id 211B1471FB for ; Sat, 30 Dec 2023 14:01:54 +0000 (UTC) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 3E68D68CC45; Sat, 30 Dec 2023 16:01:53 +0200 (EET) Received: from mail-qv1-f51.google.com (mail-qv1-f51.google.com [209.85.219.51]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id E376A68CB57 for ; Sat, 30 Dec 2023 16:01:46 +0200 (EET) Received: by mail-qv1-f51.google.com with SMTP id 6a1803df08f44-67f9fac086bso54105426d6.3 for ; Sat, 30 Dec 2023 06:01:46 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1703944905; x=1704549705; darn=ffmpeg.org; h=to:subject:message-id:date:from:in-reply-to:references:mime-version :from:to:cc:subject:date:message-id:reply-to; bh=qBPEpB2qTwv4jIJBP/OfToTMpE5tfTpGyKZZqDhdy3Y=; b=hPRjZAsHHHwmhCzcnD/4LUTU2IYjXYp86VXyPuBl/ztizsqOpSvRMpqatw8kIU2sNJ NxvN5/SMVlLiQfZ/Lwg1+l6wGXwG4kO0JBhC3a5qONYmL8+o2OXvTG2ewnrwGy2SPbq3 iD/lyN6kDKdVXMWdHgPemEUIII5T7bm+irsF2bWUNt8IguCwa4nFhAlrPWWzhtxKGvMI 9pLrwwa3WWvzNdLjBrIR06MxL3FwkwOFCJgvxwdy5aJGpEubV0NOz4ZtN63AFoEX8Wvn qXl38e7xheoZIB3FC0DT0lTqqkbDm2/o6caa35y+WPRIZrm4cZ2AbKgKIL/ABpGtpswP ujTA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1703944905; x=1704549705; h=to:subject:message-id:date:from:in-reply-to:references:mime-version :x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=qBPEpB2qTwv4jIJBP/OfToTMpE5tfTpGyKZZqDhdy3Y=; b=TGaZC+xS9VhPHKoadimK6zXveXzZBhMqEls6O35uwFhxK2uoJruY8zb7Cj0Al6YWba 3d8I6kbVmHDBfkUhJIvQ2p9iDAOo2hIBe8tnZHqWPntYvRcsUUhNySjG3h0cgG+/gKez nlBnK9vnfh+UOZHoFtzV2mAgO29R6Q5qQH5md6SEPIEiBjZAQqD6/2Y/CegGMUSj02Fx WHmk0uMTrFRG+cuRjpUD/RXG82nzae/s6FTCVs1vPB1S1Lbo2BN4pBQWDombZOKXbxbh 6KIg4TLLMlCjRP3E/G/frlkHPlycv8WNq/lv5Uz99iJC9AI0dHZqZD4eZhFWWx1Xm+U6 6zXg== X-Gm-Message-State: AOJu0YxR3mjjrSSm2FAsO1Z2VMlfgayvTODM7pOdx7DjJdnWeo2Sl3k5 Vn451GD2QqFi5spK1UBUb5AYgOtcB5Sz/WCRhhN5+yp7yaFoumdt X-Google-Smtp-Source: AGHT+IFqbH67vbNIHPxAajQtU98dVe40Ti+5KWHzLSzgksBAMN7avZAxfaoLij0aC0G09zwvaDjoNFNxyUUKoDK51wk= X-Received: by 2002:a05:6214:181:b0:67f:d681:f7e6 with SMTP id q1-20020a056214018100b0067fd681f7e6mr11153008qvr.122.1703944905572; Sat, 30 Dec 2023 06:01:45 -0800 (PST) MIME-Version: 1.0 References: In-Reply-To: From: flow gg Date: Sat, 30 Dec 2023 22:01:34 +0800 Message-ID: To: FFmpeg development discussions and patches Content-Type: multipart/mixed; boundary="000000000000d073c4060dba9620" X-Content-Filtered-By: Mailman/MimeDel 2.1.29 Subject: Re: [FFmpeg-devel] [PATCH 3/3] lavc/svq1enc: R-V V ssd_int8_vs_int16 X-BeenThere: ffmpeg-devel@ffmpeg.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: FFmpeg development discussions and patches List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Reply-To: FFmpeg development discussions and patches Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" Archived-At: List-Archive: List-Post: --000000000000d073c4060dba9620 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable flow gg =E4=BA=8E2023=E5=B9=B412=E6=9C=8830=E6=97=A5= =E5=91=A8=E5=85=AD 22:00=E5=86=99=E9=81=93=EF=BC=9A > > At a quick glance, it won't work if the input length is not a multiple > of the vector length. > > Why? I tried 1024, 32*3, 32*7 and all passed the test. > > > Also do you really need to extend accumulators to 32 bits? > > It won't overflow after the test is changed, so it's not needed anymore. > I have modified it in this reply. > > R=C3=A9mi Denis-Courmont =E4=BA=8E2023=E5=B9=B412=E6=9C= =8830=E6=97=A5=E5=91=A8=E5=85=AD 20:15=E5=86=99=E9=81=93=EF=BC=9A > >> >> >> Le 29 d=C3=A9cembre 2023 12:57:20 GMT+01:00, flow gg a >> =C3=A9crit : >> >C908 >> >ssd_int8_vs_int16_c: 207.7 >> >ssd_int8_vs_int16_rvv_i32: 28.0 >> >> At a quick glance, it won't work if the input length is not a multiple o= f >> the vector length. >> >> Also do you really need to extend accumulators to 32 bits? >> _______________________________________________ >> 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". >> > --000000000000d073c4060dba9620 Content-Type: text/x-patch; charset="US-ASCII"; name="0003-lavc-svq1enc-R-V-V-ssd_int8_vs_int16.patch" Content-Disposition: attachment; filename="0003-lavc-svq1enc-R-V-V-ssd_int8_vs_int16.patch" Content-Transfer-Encoding: base64 Content-ID: X-Attachment-Id: f_lqs4sltk0 RnJvbSA3YmIzNWI1NGE0ZTU3ODg0ODY2MGIxNDM3Yjk2MzMzZGQ3NDBjYmQzIE1vbiBTZXAgMTcg MDA6MDA6MDAgMjAwMQpGcm9tOiBzdW55dWVjaGkgPHN1bnl1ZWNoaUBpc2Nhcy5hYy5jbj4KRGF0 ZTogRnJpLCAyOSBEZWMgMjAyMyAxMzoyNzozMSArMDgwMApTdWJqZWN0OiBbUEFUQ0ggMy8zXSBs YXZjL3N2cTFlbmM6IFItViBWIHNzZF9pbnQ4X3ZzX2ludDE2CgpDOTA4CnNzZF9pbnQ4X3ZzX2lu dDE2X2M6IDIwNy43CnNzZF9pbnQ4X3ZzX2ludDE2X3J2dl9pMzI6IDE3LjcKLS0tCiBsaWJhdmNv ZGVjL3Jpc2N2L01ha2VmaWxlICAgICAgfCAgMiArKwogbGliYXZjb2RlYy9yaXNjdi9zdnFlbmNf aW5pdC5jIHwgNDEgKysrKysrKysrKysrKysrKysrKysrKysrKysrKysrKwogbGliYXZjb2RlYy9y aXNjdi9zdnFlbmNfcnZ2LlMgIHwgNDQgKysrKysrKysrKysrKysrKysrKysrKysrKysrKysrKysr KwogbGliYXZjb2RlYy9zdnExZW5jLmMgICAgICAgICAgIHwgIDIgKysKIGxpYmF2Y29kZWMvc3Zx MWVuY2RzcC5oICAgICAgICB8ICAxICsKIDUgZmlsZXMgY2hhbmdlZCwgOTAgaW5zZXJ0aW9ucygr KQogY3JlYXRlIG1vZGUgMTAwNjQ0IGxpYmF2Y29kZWMvcmlzY3Yvc3ZxZW5jX2luaXQuYwogY3Jl YXRlIG1vZGUgMTAwNjQ0IGxpYmF2Y29kZWMvcmlzY3Yvc3ZxZW5jX3J2di5TCgpkaWZmIC0tZ2l0 IGEvbGliYXZjb2RlYy9yaXNjdi9NYWtlZmlsZSBiL2xpYmF2Y29kZWMvcmlzY3YvTWFrZWZpbGUK aW5kZXggN2YyNTNiYmExMi4uNGUxNGMzZDA5NCAxMDA2NDQKLS0tIGEvbGliYXZjb2RlYy9yaXNj di9NYWtlZmlsZQorKysgYi9saWJhdmNvZGVjL3Jpc2N2L01ha2VmaWxlCkBAIC00Niw2ICs0Niw4 IEBAIFJWVi1PQkpTLSQoQ09ORklHX09QVVNfREVDT0RFUikgKz0gcmlzY3Yvb3B1c2RzcF9ydnYu bwogT0JKUy0kKENPTkZJR19QSVhCTE9DS0RTUCkgKz0gcmlzY3YvcGl4YmxvY2tkc3BfaW5pdC5v CiBSVi1PQkpTLSQoQ09ORklHX1BJWEJMT0NLRFNQKSArPSByaXNjdi9waXhibG9ja2RzcF9ydmku bwogUlZWLU9CSlMtJChDT05GSUdfUElYQkxPQ0tEU1ApICs9IHJpc2N2L3BpeGJsb2NrZHNwX3J2 di5vCitPQkpTLSQoQ09ORklHX1NWUTFfRU5DT0RFUikgKz0gcmlzY3Yvc3ZxZW5jX2luaXQubwor UlZWLU9CSlMtJChDT05GSUdfU1ZRMV9FTkNPREVSKSArPSByaXNjdi9zdnFlbmNfcnZ2Lm8KIE9C SlMtJChDT05GSUdfVEFLX0RFQ09ERVIpICs9IHJpc2N2L3Rha2RzcF9pbml0Lm8KIFJWVi1PQkpT LSQoQ09ORklHX1RBS19ERUNPREVSKSArPSByaXNjdi90YWtkc3BfcnZ2Lm8KIE9CSlMtJChDT05G SUdfVVRWSURFT19ERUNPREVSKSArPSByaXNjdi91dHZpZGVvZHNwX2luaXQubwpkaWZmIC0tZ2l0 IGEvbGliYXZjb2RlYy9yaXNjdi9zdnFlbmNfaW5pdC5jIGIvbGliYXZjb2RlYy9yaXNjdi9zdnFl bmNfaW5pdC5jCm5ldyBmaWxlIG1vZGUgMTAwNjQ0CmluZGV4IDAwMDAwMDAwMDAuLmY0YzM5ODk2 MGMKLS0tIC9kZXYvbnVsbAorKysgYi9saWJhdmNvZGVjL3Jpc2N2L3N2cWVuY19pbml0LmMKQEAg LTAsMCArMSw0MSBAQAorLyoKKyAqIENvcHlyaWdodCAoYykgMjAyMyBJbnN0aXR1ZSBvZiBTb2Z0 d2FyZSBDaGluZXNlIEFjYWRlbXkgb2YgU2NpZW5jZXMgKElTQ0FTKS4KKyAqCisgKiBUaGlzIGZp bGUgaXMgcGFydCBvZiBGRm1wZWcuCisgKgorICogRkZtcGVnIGlzIGZyZWUgc29mdHdhcmU7IHlv dSBjYW4gcmVkaXN0cmlidXRlIGl0IGFuZC9vcgorICogbW9kaWZ5IGl0IHVuZGVyIHRoZSB0ZXJt cyBvZiB0aGUgR05VIExlc3NlciBHZW5lcmFsIFB1YmxpYworICogTGljZW5zZSBhcyBwdWJsaXNo ZWQgYnkgdGhlIEZyZWUgU29mdHdhcmUgRm91bmRhdGlvbjsgZWl0aGVyCisgKiB2ZXJzaW9uIDIu MSBvZiB0aGUgTGljZW5zZSwgb3IgKGF0IHlvdXIgb3B0aW9uKSBhbnkgbGF0ZXIgdmVyc2lvbi4K KyAqCisgKiBGRm1wZWcgaXMgZGlzdHJpYnV0ZWQgaW4gdGhlIGhvcGUgdGhhdCBpdCB3aWxsIGJl IHVzZWZ1bCwKKyAqIGJ1dCBXSVRIT1VUIEFOWSBXQVJSQU5UWTsgd2l0aG91dCBldmVuIHRoZSBp bXBsaWVkIHdhcnJhbnR5IG9mCisgKiBNRVJDSEFOVEFCSUxJVFkgb3IgRklUTkVTUyBGT1IgQSBQ QVJUSUNVTEFSIFBVUlBPU0UuICBTZWUgdGhlIEdOVQorICogTGVzc2VyIEdlbmVyYWwgUHVibGlj IExpY2Vuc2UgZm9yIG1vcmUgZGV0YWlscy4KKyAqCisgKiBZb3Ugc2hvdWxkIGhhdmUgcmVjZWl2 ZWQgYSBjb3B5IG9mIHRoZSBHTlUgTGVzc2VyIEdlbmVyYWwgUHVibGljCisgKiBMaWNlbnNlIGFs b25nIHdpdGggRkZtcGVnOyBpZiBub3QsIHdyaXRlIHRvIHRoZSBGcmVlIFNvZnR3YXJlCisgKiBG b3VuZGF0aW9uLCBJbmMuLCA1MSBGcmFua2xpbiBTdHJlZXQsIEZpZnRoIEZsb29yLCBCb3N0b24s IE1BIDAyMTEwLTEzMDEgVVNBCisgKi8KKworI2luY2x1ZGUgImNvbmZpZy5oIgorCisjaW5jbHVk ZSAibGliYXZ1dGlsL2F0dHJpYnV0ZXMuaCIKKyNpbmNsdWRlICJsaWJhdnV0aWwvY3B1LmgiCisj aW5jbHVkZSAibGliYXZjb2RlYy9zdnExZW5jZHNwLmgiCisKK2ludCBmZl9zc2RfaW50OF92c19p bnQxNl9ydnYoY29uc3QgaW50OF90ICpwaXgxLCBjb25zdCBpbnQxNl90ICpwaXgyLAorICAgICAg ICAgICAgICAgICAgICAgICAgICAgICAgaW50cHRyX3Qgc2l6ZSk7CisKK2F2X2NvbGQgdm9pZCBm Zl9zdnExZW5jX2luaXRfcmlzY3YoU1ZRMUVuY0RTUENvbnRleHQgKmMpCit7CisjaWYgSEFWRV9S VlYKKyAgICBpbnQgZmxhZ3MgPSBhdl9nZXRfY3B1X2ZsYWdzKCk7CisKKyAgICBpZiAoZmxhZ3Mg JiBBVl9DUFVfRkxBR19SVlZfSTMyKSB7CisgICAgICAgIGlmIChmbGFncyAmIEFWX0NQVV9GTEFH X1JWQl9BRERSKSB7CisgICAgICAgICAgICBjLT5zc2RfaW50OF92c19pbnQxNiA9IGZmX3NzZF9p bnQ4X3ZzX2ludDE2X3J2djsKKyAgICAgICAgfQorICAgIH0KKyNlbmRpZgorfQpkaWZmIC0tZ2l0 IGEvbGliYXZjb2RlYy9yaXNjdi9zdnFlbmNfcnZ2LlMgYi9saWJhdmNvZGVjL3Jpc2N2L3N2cWVu Y19ydnYuUwpuZXcgZmlsZSBtb2RlIDEwMDY0NAppbmRleCAwMDAwMDAwMDAwLi5jNTI5MTNjMmU3 Ci0tLSAvZGV2L251bGwKKysrIGIvbGliYXZjb2RlYy9yaXNjdi9zdnFlbmNfcnZ2LlMKQEAgLTAs MCArMSw0NCBAQAorLyoKKyAqIENvcHlyaWdodCAoYykgMjAyMyBJbnN0aXR1ZSBvZiBTb2Z0d2Fy ZSBDaGluZXNlIEFjYWRlbXkgb2YgU2NpZW5jZXMgKElTQ0FTKS4KKyAqCisgKiBUaGlzIGZpbGUg aXMgcGFydCBvZiBGRm1wZWcuCisgKgorICogRkZtcGVnIGlzIGZyZWUgc29mdHdhcmU7IHlvdSBj YW4gcmVkaXN0cmlidXRlIGl0IGFuZC9vcgorICogbW9kaWZ5IGl0IHVuZGVyIHRoZSB0ZXJtcyBv ZiB0aGUgR05VIExlc3NlciBHZW5lcmFsIFB1YmxpYworICogTGljZW5zZSBhcyBwdWJsaXNoZWQg YnkgdGhlIEZyZWUgU29mdHdhcmUgRm91bmRhdGlvbjsgZWl0aGVyCisgKiB2ZXJzaW9uIDIuMSBv ZiB0aGUgTGljZW5zZSwgb3IgKGF0IHlvdXIgb3B0aW9uKSBhbnkgbGF0ZXIgdmVyc2lvbi4KKyAq CisgKiBGRm1wZWcgaXMgZGlzdHJpYnV0ZWQgaW4gdGhlIGhvcGUgdGhhdCBpdCB3aWxsIGJlIHVz ZWZ1bCwKKyAqIGJ1dCBXSVRIT1VUIEFOWSBXQVJSQU5UWTsgd2l0aG91dCBldmVuIHRoZSBpbXBs aWVkIHdhcnJhbnR5IG9mCisgKiBNRVJDSEFOVEFCSUxJVFkgb3IgRklUTkVTUyBGT1IgQSBQQVJU SUNVTEFSIFBVUlBPU0UuICBTZWUgdGhlIEdOVQorICogTGVzc2VyIEdlbmVyYWwgUHVibGljIExp Y2Vuc2UgZm9yIG1vcmUgZGV0YWlscy4KKyAqCisgKiBZb3Ugc2hvdWxkIGhhdmUgcmVjZWl2ZWQg YSBjb3B5IG9mIHRoZSBHTlUgTGVzc2VyIEdlbmVyYWwgUHVibGljCisgKiBMaWNlbnNlIGFsb25n IHdpdGggRkZtcGVnOyBpZiBub3QsIHdyaXRlIHRvIHRoZSBGcmVlIFNvZnR3YXJlCisgKiBGb3Vu ZGF0aW9uLCBJbmMuLCA1MSBGcmFua2xpbiBTdHJlZXQsIEZpZnRoIEZsb29yLCBCb3N0b24sIE1B IDAyMTEwLTEzMDEgVVNBCisgKi8KKworI2luY2x1ZGUgImxpYmF2dXRpbC9yaXNjdi9hc20uUyIK KworZnVuYyBmZl9zc2RfaW50OF92c19pbnQxNl9ydnYsIHp2ZTMyeAorICAgICAgICB2c2V0dmxp ICAgICB0MCwgemVybywgZTMyLCBtOCwgdGEsIG1hCisgICAgICAgIHZtdi52LnggICAgIHYyNCwg emVybworMToKKyAgICAgICAgdnNldHZsaSAgICAgIHQwLCBhMiwgZTgsIG0yLCB0YSwgbWEKKyAg ICAgICAgdmxlOC52ICAgICAgIHYwLCAoYTApCisgICAgICAgIHN1YiAgICAgICAgICBhMiwgYTIs IHQwCisgICAgICAgIHZzZXR2bGkgICAgICB6ZXJvLCB0MCwgZTE2LCBtNCwgdGEsIG1hCisgICAg ICAgIHZsZTE2LnYgICAgICB2OCwgKGExKQorICAgICAgICB2c2V4dC52ZjIgICAgdjE2LCB2MAor ICAgICAgICB2c3ViLnZ2ICAgICAgdjE2LCB2MTYsIHY4CisgICAgICAgIGFkZCAgICAgICAgICBh MCwgYTAsIHQwCisgICAgICAgIHZ3bWFjYy52diAgICB2MjQsIHYxNiwgdjE2CisgICAgICAgIHNo MWFkZCAgICAgICBhMSwgdDAsIGExCisgICAgICAgIGJuZXogICAgICAgICBhMiwgMWIKKyAgICAg ICAgdnNldHZsaSAgICAgIHQwLCB6ZXJvLCBlMzIsIG04LCB0YSwgbWEKKyAgICAgICAgdm12LnMu eCAgICAgIHYwLCB6ZXJvCisgICAgICAgIHZyZWRzdW0udnMgICB2MCwgdjI0LCB2MAorICAgICAg ICB2bXYueC5zICAgICAgYTAsIHYwCisKKyAgICAgICAgcmV0CitlbmRmdW5jCmRpZmYgLS1naXQg YS9saWJhdmNvZGVjL3N2cTFlbmMuYyBiL2xpYmF2Y29kZWMvc3ZxMWVuYy5jCmluZGV4IDBkZWE0 MDVkZWMuLjZlN2VhMTJhYTcgMTAwNjQ0Ci0tLSBhL2xpYmF2Y29kZWMvc3ZxMWVuYy5jCisrKyBi L2xpYmF2Y29kZWMvc3ZxMWVuYy5jCkBAIC03NjYsNiArNzY2LDggQEAgdm9pZCBmZl9zdnExZW5j X2luaXQoU1ZRMUVuY0RTUENvbnRleHQgKmMpCiAKICNpZiBBUkNIX1BQQwogICAgIGZmX3N2cTFl bmNfaW5pdF9wcGMoYyk7CisjZWxpZiBBUkNIX1JJU0NWCisgICAgZmZfc3ZxMWVuY19pbml0X3Jp c2N2KGMpOwogI2VsaWYgQVJDSF9YODYKICAgICBmZl9zdnExZW5jX2luaXRfeDg2KGMpOwogI2Vu ZGlmCmRpZmYgLS1naXQgYS9saWJhdmNvZGVjL3N2cTFlbmNkc3AuaCBiL2xpYmF2Y29kZWMvc3Zx MWVuY2RzcC5oCmluZGV4IDYxOGJmODQ2M2IuLjVkZmEzNWNjNjIgMTAwNjQ0Ci0tLSBhL2xpYmF2 Y29kZWMvc3ZxMWVuY2RzcC5oCisrKyBiL2xpYmF2Y29kZWMvc3ZxMWVuY2RzcC5oCkBAIC0zMCw2 ICszMCw3IEBAIHR5cGVkZWYgc3RydWN0IFNWUTFFbmNEU1BDb250ZXh0IHsKIAogdm9pZCBmZl9z dnExZW5jX2luaXQoU1ZRMUVuY0RTUENvbnRleHQgKmMpOwogdm9pZCBmZl9zdnExZW5jX2luaXRf cHBjKFNWUTFFbmNEU1BDb250ZXh0ICpjKTsKK3ZvaWQgZmZfc3ZxMWVuY19pbml0X3Jpc2N2KFNW UTFFbmNEU1BDb250ZXh0ICpjKTsKIHZvaWQgZmZfc3ZxMWVuY19pbml0X3g4NihTVlExRW5jRFNQ Q29udGV4dCAqYyk7CiAKICNlbmRpZiAvKiBBVkNPREVDX1NWUTFFTkNEU1BfSCAqLwotLSAKMi40 My4wCgo= --000000000000d073c4060dba9620 Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ 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". --000000000000d073c4060dba9620--