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 AAD8D45F18 for ; Wed, 15 Nov 2023 23:05:01 +0000 (UTC) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id AB6E068CCA8; Thu, 16 Nov 2023 01:04:58 +0200 (EET) Received: from mail-yb1-f177.google.com (mail-yb1-f177.google.com [209.85.219.177]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 194E368CBA0 for ; Thu, 16 Nov 2023 01:04:52 +0200 (EET) Received: by mail-yb1-f177.google.com with SMTP id 3f1490d57ef6-da41e70e334so149641276.3 for ; Wed, 15 Nov 2023 15:04:52 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1700089490; x=1700694290; 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=X8m7MKab+tApnJZctlWWTd/n3bmOwJk74evuMWR6xMI=; b=W6rDRIJOpuDoNz7M+Q/i2aRJOl0GJkT/gJkXqY8aoieLBrsPkQLSefHJwHtf4d5VWp mrWL9ojUc4KDI4Mmz9BcAHBy5Ged5+fF77Voy2JTXqea/OUGwrO/OxqnkMSxovW/KyYh psy5YO3qbVN1tMrvqcYQH34cBpXaUjSaRbOGfFW5CE/OLgHlLEMh21bbLFQKhG8z0LYv KE+or0XBUhTif85AIBHouWlTCNU/OZPgKjP7oU4+UNaqkIqZeLV2g3I/T39w3xJfxv1Q Vfo/eOA9YJpc/7/kEGU2XdVCZNXlzSkolauaL1uDCgtoy4UrjkqfFlrn10ZnW9aRpxXo M9UQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1700089490; x=1700694290; 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=X8m7MKab+tApnJZctlWWTd/n3bmOwJk74evuMWR6xMI=; b=dh3Z0ZaTIcsbrKbivnroR9dHolcQEC9eT/X8oDRrwi37PSy0wyS3g4lOahKrbCTeGk MonBuOHxNvnwFMTlw4/2pLQlM0CVyWUtlM1PGrtGHIXL1Whi33KqQS8/EQvPKs5VvNHD RVdGHcHYlGIDWVvNSA3VxvnqC5XqgwGtaG+mpnwVXc3rEnNeu+VmugirhYA/oVsnFhAf TaEYoPbKNNYRdojXfWwH9PoeNEtKx/uLHdOXMpadj10gN3dlivsr8o47Hpm+MntKsdax n/hBz2DiqFli8S5Vw1BLLO5HdXkzqQETzlFd0GaunkZVOSn5NK8iZzQIe9UQYOA+yc4J nmWQ== X-Gm-Message-State: AOJu0Yyy/KDvilAJxHi7n1JlNi1WyET4J5X/NERsIzdrxc3dSTrqxugI nlSukbxD6rz2bLBkN5M3vO8eLXm0vRuM+CqPSu6tYB9GeQn4fj7N X-Google-Smtp-Source: AGHT+IE+Hcz6W4eS0ktENN4QW3HVXxLPCAfQBLab/USo5wYrmSPwBk21PQcK6X9JSfofhCt4nFx6A7/PE0d6dIZSKw4= X-Received: by 2002:a25:768a:0:b0:d7b:90c6:683c with SMTP id r132-20020a25768a000000b00d7b90c6683cmr14080952ybc.26.1700089490145; Wed, 15 Nov 2023 15:04:50 -0800 (PST) MIME-Version: 1.0 References: <3257813.aeNJFYEL58@basile.remlab.net> <2333300.bBitlWAPyq@basile.remlab.net> In-Reply-To: <2333300.bBitlWAPyq@basile.remlab.net> From: flow gg Date: Thu, 16 Nov 2023 07:04:38 +0800 Message-ID: To: FFmpeg development discussions and patches Content-Type: multipart/mixed; boundary="00000000000025cf3e060a38eea4" X-Content-Filtered-By: Mailman/MimeDel 2.1.29 Subject: Re: [FFmpeg-devel] [PATCH] af_afir: RISC-V V fcmul_add 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: --00000000000025cf3e060a38eea4 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Okay, I have modified them to 64 and added some descriptions. R=C3=A9mi Denis-Courmont =E4=BA=8E2023=E5=B9=B411=E6=9C= =8815=E6=97=A5=E5=91=A8=E4=B8=89 23:06=E5=86=99=E9=81=93=EF=BC=9A > Le keskiviikkona 15. marraskuuta 2023, 10.59.55 EET flow gg a =C3=A9crit = : > > Okay, I have updated these issues in the patch. > > It does not assemble but I can fix it locally. The narrowing shift > trickery > require Zve64x, or rather Zve64f in this case. > > The performance improvement is much better on newer hardware: > fcmul_add_c: 4891.2 > fcmul_add_rvv_f64: 2399.5 > > FWIW, VLSEG2E32.V remains slightly worse than with shifting: > fcmul_add_c: 4891.2 > fcmul_add_rvv_f32: 2877.5 > > -- > =E9=9B=B7=E7=B1=B3=E2=80=A7=E5=BE=B7=E5=B0=BC-=E5=BA=93=E5=B0=94=E8=92=99 > http://www.remlab.net/ > > > > _______________________________________________ > 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". > --00000000000025cf3e060a38eea4 Content-Type: text/x-patch; charset="US-ASCII"; name="af_afir-RISC-V-V-fcmul_add.patch" Content-Disposition: attachment; filename="af_afir-RISC-V-V-fcmul_add.patch" Content-Transfer-Encoding: base64 Content-ID: X-Attachment-Id: f_lp0da93v0 RnJvbSA2Yjg4ZmJmOWI5NGMwOTg4NDExOTdjOWZjYjQ2NzAwNjE3N2VlNGM2IE1vbiBTZXAgMTcg MDA6MDA6MDAgMjAwMQpGcm9tOiBzdW55dWVjaGkgPHN1bnl1ZWNoaUBpc2Nhcy5hYy5jbj4KRGF0 ZTogRnJpLCAzIE5vdiAyMDIzIDEwOjM1OjUzICswODAwClN1YmplY3Q6IFtQQVRDSF0gYWZfYWZp cjogUklTQy1WIFYgZmNtdWxfYWRkCgpTZWdtZW50ZWQgbG9hZHMgYXJlIHNsb3csIHNvIGhlcmUg d2UgdXNlIHVuaXQtc3RyaWRlZCBsb2FkIGFuZCBuYXJyb3dpbmcgc2hpZnRzLgoKYzkxMDoKZmNt dWxfYWRkX2M6IDIxNzkKZmNtdWxfYWRkX3J2dl9mNjQ6IDE2NTIKCmM5MDg6CmZjbXVsX2FkZF9j OiA0ODkxLjIKZmNtdWxfYWRkX3J2dl9mNjQ6IDIzOTkuNQotLS0KIGxpYmF2ZmlsdGVyL2FmX2Fm aXJkc3AuaCAgICAgICAgIHwgIDUgKystCiBsaWJhdmZpbHRlci9yaXNjdi9NYWtlZmlsZSAgICAg ICB8ICAyICsrCiBsaWJhdmZpbHRlci9yaXNjdi9hZl9hZmlyX2luaXQuYyB8IDQyICsrKysrKysr KysrKysrKysrKysrKysrKwogbGliYXZmaWx0ZXIvcmlzY3YvYWZfYWZpcl9ydnYuUyAgfCA1NSAr KysrKysrKysrKysrKysrKysrKysrKysrKysrKysrKwogNCBmaWxlcyBjaGFuZ2VkLCAxMDMgaW5z ZXJ0aW9ucygrKSwgMSBkZWxldGlvbigtKQogY3JlYXRlIG1vZGUgMTAwNjQ0IGxpYmF2ZmlsdGVy L3Jpc2N2L01ha2VmaWxlCiBjcmVhdGUgbW9kZSAxMDA2NDQgbGliYXZmaWx0ZXIvcmlzY3YvYWZf YWZpcl9pbml0LmMKIGNyZWF0ZSBtb2RlIDEwMDY0NCBsaWJhdmZpbHRlci9yaXNjdi9hZl9hZmly X3J2di5TCgpkaWZmIC0tZ2l0IGEvbGliYXZmaWx0ZXIvYWZfYWZpcmRzcC5oIGIvbGliYXZmaWx0 ZXIvYWZfYWZpcmRzcC5oCmluZGV4IDQyMDg1MDEzOTMuLjgyN2UwNjdhOWIgMTAwNjQ0Ci0tLSBh L2xpYmF2ZmlsdGVyL2FmX2FmaXJkc3AuaAorKysgYi9saWJhdmZpbHRlci9hZl9hZmlyZHNwLmgK QEAgLTMzLDYgKzMzLDcgQEAgdHlwZWRlZiBzdHJ1Y3QgQXVkaW9GSVJEU1BDb250ZXh0IHsKICAg ICAgICAgICAgICAgICAgICAgICBwdHJkaWZmX3QgbGVuKTsKIH0gQXVkaW9GSVJEU1BDb250ZXh0 OwogCit2b2lkIGZmX2FmaXJfaW5pdF9yaXNjdihBdWRpb0ZJUkRTUENvbnRleHQgKnMpOwogdm9p ZCBmZl9hZmlyX2luaXRfeDg2KEF1ZGlvRklSRFNQQ29udGV4dCAqcyk7CiAKIHN0YXRpYyB2b2lk IGZjbXVsX2FkZF9jKGZsb2F0ICpzdW0sIGNvbnN0IGZsb2F0ICp0LCBjb25zdCBmbG9hdCAqYywg cHRyZGlmZl90IGxlbikKQEAgLTc0LDcgKzc1LDkgQEAgc3RhdGljIGF2X3VudXNlZCB2b2lkIGZm X2FmaXJfaW5pdChBdWRpb0ZJUkRTUENvbnRleHQgKmRzcCkKICAgICBkc3AtPmZjbXVsX2FkZCA9 IGZjbXVsX2FkZF9jOwogICAgIGRzcC0+ZGNtdWxfYWRkID0gZGNtdWxfYWRkX2M7CiAKLSNpZiBB UkNIX1g4NgorI2lmIEFSQ0hfUklTQ1YKKyAgICBmZl9hZmlyX2luaXRfcmlzY3YoZHNwKTsKKyNl bGlmIEFSQ0hfWDg2CiAgICAgZmZfYWZpcl9pbml0X3g4Nihkc3ApOwogI2VuZGlmCiB9CmRpZmYg LS1naXQgYS9saWJhdmZpbHRlci9yaXNjdi9NYWtlZmlsZSBiL2xpYmF2ZmlsdGVyL3Jpc2N2L01h a2VmaWxlCm5ldyBmaWxlIG1vZGUgMTAwNjQ0CmluZGV4IDAwMDAwMDAwMDAuLjBiOTY4YTljMGQK LS0tIC9kZXYvbnVsbAorKysgYi9saWJhdmZpbHRlci9yaXNjdi9NYWtlZmlsZQpAQCAtMCwwICsx LDIgQEAKK09CSlMgKz0gcmlzY3YvYWZfYWZpcl9pbml0Lm8KK1JWVi1PQkpTICs9IHJpc2N2L2Fm X2FmaXJfcnZ2Lm8KZGlmZiAtLWdpdCBhL2xpYmF2ZmlsdGVyL3Jpc2N2L2FmX2FmaXJfaW5pdC5j IGIvbGliYXZmaWx0ZXIvcmlzY3YvYWZfYWZpcl9pbml0LmMKbmV3IGZpbGUgbW9kZSAxMDA2NDQK aW5kZXggMDAwMDAwMDAwMC4uNTJhYTE4YzEyNgotLS0gL2Rldi9udWxsCisrKyBiL2xpYmF2Zmls dGVyL3Jpc2N2L2FmX2FmaXJfaW5pdC5jCkBAIC0wLDAgKzEsNDIgQEAKKy8qCisgKiBDb3B5cmln aHQgKGMpIDIwMjMgSW5zdGl0dWUgb2YgU29mdHdhcmUgQ2hpbmVzZSBBY2FkZW15IG9mIFNjaWVu Y2VzIChJU0NBUykuCisgKgorICogVGhpcyBmaWxlIGlzIHBhcnQgb2YgRkZtcGVnLgorICoKKyAq IEZGbXBlZyBpcyBmcmVlIHNvZnR3YXJlOyB5b3UgY2FuIHJlZGlzdHJpYnV0ZSBpdCBhbmQvb3IK KyAqIG1vZGlmeSBpdCB1bmRlciB0aGUgdGVybXMgb2YgdGhlIEdOVSBMZXNzZXIgR2VuZXJhbCBQ dWJsaWMKKyAqIExpY2Vuc2UgYXMgcHVibGlzaGVkIGJ5IHRoZSBGcmVlIFNvZnR3YXJlIEZvdW5k YXRpb247IGVpdGhlcgorICogdmVyc2lvbiAyLjEgb2YgdGhlIExpY2Vuc2UsIG9yIChhdCB5b3Vy IG9wdGlvbikgYW55IGxhdGVyIHZlcnNpb24uCisgKgorICogRkZtcGVnIGlzIGRpc3RyaWJ1dGVk IGluIHRoZSBob3BlIHRoYXQgaXQgd2lsbCBiZSB1c2VmdWwsCisgKiBidXQgV0lUSE9VVCBBTlkg V0FSUkFOVFk7IHdpdGhvdXQgZXZlbiB0aGUgaW1wbGllZCB3YXJyYW50eSBvZgorICogTUVSQ0hB TlRBQklMSVRZIG9yIEZJVE5FU1MgRk9SIEEgUEFSVElDVUxBUiBQVVJQT1NFLiAgU2VlIHRoZSBH TlUKKyAqIExlc3NlciBHZW5lcmFsIFB1YmxpYyBMaWNlbnNlIGZvciBtb3JlIGRldGFpbHMuCisg KgorICogWW91IHNob3VsZCBoYXZlIHJlY2VpdmVkIGEgY29weSBvZiB0aGUgR05VIExlc3NlciBH ZW5lcmFsIFB1YmxpYworICogTGljZW5zZSBhbG9uZyB3aXRoIEZGbXBlZzsgaWYgbm90LCB3cml0 ZSB0byB0aGUgRnJlZSBTb2Z0d2FyZQorICogRm91bmRhdGlvbiwgSW5jLiwgNTEgRnJhbmtsaW4g U3RyZWV0LCBGaWZ0aCBGbG9vciwgQm9zdG9uLCBNQSAwMjExMC0xMzAxIFVTQQorICovCisKKyNp bmNsdWRlIDxzdGRpbnQuaD4KKworI2luY2x1ZGUgImNvbmZpZy5oIgorI2luY2x1ZGUgImxpYmF2 dXRpbC9hdHRyaWJ1dGVzLmgiCisjaW5jbHVkZSAibGliYXZ1dGlsL2NwdS5oIgorI2luY2x1ZGUg ImxpYmF2ZmlsdGVyL2FmX2FmaXJkc3AuaCIKKwordm9pZCBmZl9mY211bF9hZGRfcnZ2KGZsb2F0 ICpzdW0sIGNvbnN0IGZsb2F0ICp0LCBjb25zdCBmbG9hdCAqYywKKyAgICAgICAgICAgICAgICAg ICAgICAgcHRyZGlmZl90IGxlbik7CisKK2F2X2NvbGQgdm9pZCBmZl9hZmlyX2luaXRfcmlzY3Yo QXVkaW9GSVJEU1BDb250ZXh0ICpzKQoreworI2lmIEhBVkVfUlZWCisgICAgaW50IGZsYWdzID0g YXZfZ2V0X2NwdV9mbGFncygpOworCisgICAgaWYgKGZsYWdzICYgQVZfQ1BVX0ZMQUdfUlZWX0Y2 NCkgeworICAgICAgICBpZiAoZmxhZ3MgJiBBVl9DUFVfRkxBR19SVkJfQUREUikgeworICAgICAg ICAgICAgcy0+ZmNtdWxfYWRkID0gZmZfZmNtdWxfYWRkX3J2djsKKyAgICAgICAgfQorICAgIH0K KyNlbmRpZgorfQpkaWZmIC0tZ2l0IGEvbGliYXZmaWx0ZXIvcmlzY3YvYWZfYWZpcl9ydnYuUyBi L2xpYmF2ZmlsdGVyL3Jpc2N2L2FmX2FmaXJfcnZ2LlMKbmV3IGZpbGUgbW9kZSAxMDA2NDQKaW5k ZXggMDAwMDAwMDAwMC4uMDRlYzJlNTBkOAotLS0gL2Rldi9udWxsCisrKyBiL2xpYmF2ZmlsdGVy L3Jpc2N2L2FmX2FmaXJfcnZ2LlMKQEAgLTAsMCArMSw1NSBAQAorLyoKKyAqIENvcHlyaWdodCAo YykgMjAyMyBJbnN0aXR1ZSBvZiBTb2Z0d2FyZSBDaGluZXNlIEFjYWRlbXkgb2YgU2NpZW5jZXMg KElTQ0FTKS4KKyAqCisgKiBUaGlzIGZpbGUgaXMgcGFydCBvZiBGRm1wZWcuCisgKgorICogRkZt cGVnIGlzIGZyZWUgc29mdHdhcmU7IHlvdSBjYW4gcmVkaXN0cmlidXRlIGl0IGFuZC9vcgorICog bW9kaWZ5IGl0IHVuZGVyIHRoZSB0ZXJtcyBvZiB0aGUgR05VIExlc3NlciBHZW5lcmFsIFB1Ymxp YworICogTGljZW5zZSBhcyBwdWJsaXNoZWQgYnkgdGhlIEZyZWUgU29mdHdhcmUgRm91bmRhdGlv bjsgZWl0aGVyCisgKiB2ZXJzaW9uIDIuMSBvZiB0aGUgTGljZW5zZSwgb3IgKGF0IHlvdXIgb3B0 aW9uKSBhbnkgbGF0ZXIgdmVyc2lvbi4KKyAqCisgKiBGRm1wZWcgaXMgZGlzdHJpYnV0ZWQgaW4g dGhlIGhvcGUgdGhhdCBpdCB3aWxsIGJlIHVzZWZ1bCwKKyAqIGJ1dCBXSVRIT1VUIEFOWSBXQVJS QU5UWTsgd2l0aG91dCBldmVuIHRoZSBpbXBsaWVkIHdhcnJhbnR5IG9mCisgKiBNRVJDSEFOVEFC SUxJVFkgb3IgRklUTkVTUyBGT1IgQSBQQVJUSUNVTEFSIFBVUlBPU0UuICBTZWUgdGhlIEdOVQor ICogTGVzc2VyIEdlbmVyYWwgUHVibGljIExpY2Vuc2UgZm9yIG1vcmUgZGV0YWlscy4KKyAqCisg KiBZb3Ugc2hvdWxkIGhhdmUgcmVjZWl2ZWQgYSBjb3B5IG9mIHRoZSBHTlUgTGVzc2VyIEdlbmVy YWwgUHVibGljCisgKiBMaWNlbnNlIGFsb25nIHdpdGggRkZtcGVnOyBpZiBub3QsIHdyaXRlIHRv IHRoZSBGcmVlIFNvZnR3YXJlCisgKiBGb3VuZGF0aW9uLCBJbmMuLCA1MSBGcmFua2xpbiBTdHJl ZXQsIEZpZnRoIEZsb29yLCBCb3N0b24sIE1BIDAyMTEwLTEzMDEgVVNBCisgKi8KKworI2luY2x1 ZGUgImxpYmF2dXRpbC9yaXNjdi9hc20uUyIKKworLy8gIHZvaWQgZmZfZmNtdWxfYWRkKGZsb2F0 ICpzdW0sIGNvbnN0IGZsb2F0ICp0LCBjb25zdCBmbG9hdCAqYywgaW50IGxlbikKK2Z1bmMgZmZf ZmNtdWxfYWRkX3J2diwgenZlNjRmCisgICAgICAgIGxpICAgICAgICAgIHQxLCAzMgorMToKKyAg ICAgICAgdnNldHZsaSAgICAgdDAsIGEzLCBlMzIsIG00LCB0YSwgbWEKKyAgICAgICAgdmxlNjQu diAgICAgdjI0LCAoYTApCisgICAgICAgIHN1YiAgICAgICAgIGEzLCBhMywgdDAKKyAgICAgICAg dm5zcmwud3ggICAgdjE2LCB2MjQsIHplcm8KKyAgICAgICAgdm5zcmwud3ggICAgdjIwLCB2MjQs IHQxCisgICAgICAgIHZsZTY0LnYgICAgIHYyNCwgKGExKQorICAgICAgICBzaDNhZGQgICAgICBh MSwgdDAsIGExCisgICAgICAgIHZuc3JsLnd4ICAgIHYwLCB2MjQsIHplcm8KKyAgICAgICAgdm5z cmwud3ggICAgdjQsIHYyNCwgdDEKKyAgICAgICAgdmxlNjQudiAgICAgdjI0LCAoYTIpCisgICAg ICAgIHNoM2FkZCAgICAgIGEyLCB0MCwgYTIKKyAgICAgICAgdm5zcmwud3ggICAgdjgsIHYyNCwg emVybworICAgICAgICB2bnNybC53eCAgICB2MTIsIHYyNCwgdDEKKyAgICAgICAgdmZtYWNjLnZ2 ICAgdjE2LCB2MCwgdjgKKyAgICAgICAgdmZtYWNjLnZ2ICAgdjIwLCB2NCwgdjgKKyAgICAgICAg dmZubXNhYy52diAgdjE2LCB2NCwgdjEyCisgICAgICAgIHZmbWFjYy52diAgIHYyMCwgdjAsIHYx MgorICAgICAgICB2c3NlZzJlMzIudiB2MTYsIChhMCkKKyAgICAgICAgc2gzYWRkICAgICAgYTAs IHQwLCBhMAorICAgICAgICBiZ3R6ICAgICAgICBhMywgMWIKKworICAgICAgICBmbHcgICAgICAg ICBmYTAsIDAoYTEpCisgICAgICAgIGZsdyAgICAgICAgIGZhMSwgMChhMikKKyAgICAgICAgZmx3 ICAgICAgICAgZmEyLCAwKGEwKQorICAgICAgICBmbWFkZC5zICAgICBmYTIsIGZhMCwgZmExLCBm YTIKKyAgICAgICAgZnN3ICAgICAgICAgZmEyLCAwKGEwKQorCisgICAgICAgIHJldAorZW5kZnVu YwotLSAKMi40Mi4xCgo= --00000000000025cf3e060a38eea4 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". --00000000000025cf3e060a38eea4--