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 92DF542979 for ; Mon, 10 Jan 2022 14:59:05 +0000 (UTC) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id EBAC468AE77; Mon, 10 Jan 2022 16:59:03 +0200 (EET) Received: from mail-ed1-f74.google.com (mail-ed1-f74.google.com [209.85.208.74]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 64EFC68ACF5 for ; Mon, 10 Jan 2022 16:58:57 +0200 (EET) Received: by mail-ed1-f74.google.com with SMTP id q15-20020a056402518f00b003f87abf9c37so10328055edd.15 for ; Mon, 10 Jan 2022 06:58:57 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; h=date:in-reply-to:message-id:mime-version:references:subject:from:to :cc; bh=Wwj+Sc9WmUDQyhLfHao/MLUaiJbRA7EqbvhSw1acUSY=; b=jq7e29rfJHILMiGjhYSYYCjnYqqllHTRFDarvSxPNAj4UfDMx+CChh9HYruEvf17wb SKofJCQTMlctx6KweF0pcjJNTS1Ub6jfbzV4uFWBXaizteb/DJfsENKEYAzGkKN7FA/M bWFme7h+Prvz7NabkwoBVYu+UrE33DtNbG+astOToi9Nqd3hrDjKS/qUnX7dO1sZ05za uOGthaloDEqpKzA+nIgimuyV/DdfOibC8WKXM4UO9cmplzzl3jQ3YhLEYA7qFMBOVSAr fKz5ZBul8np5P2aULBQY6u4Sa12yuL/7shP9qXXA40poFwJpAegy2akAucpXCfYVVtXs pelA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:date:in-reply-to:message-id:mime-version :references:subject:from:to:cc; bh=Wwj+Sc9WmUDQyhLfHao/MLUaiJbRA7EqbvhSw1acUSY=; b=wXQwdkJeUwfDGbRT91b6EzCmc040OOOjG0PON6gzDbF3psEIZa3CpNDwGx5NtAzREa pD78sr7gNu/Tg9kItbUrerQ3QR1vpcKazAzDKZTCVJMqQeMoCTZdQlWDHVv0l07Tcgea Eb+KWckYRgODP1Aw1/pH4s9rW6MafUlsz4Rd6th8lcZdzAjOm7Gy3RdhwjFfEVIRdcGR Lwjpn1as0czStSiMIgnvUAB/j04lAFIvcTednPucvF9JVoS7JN3FvIWDof27GylHTEqS r9GNtZf/1T2LILH//MvBHgOAuDNc46CN7ZMBYjuJ1oEU64THCaQl6gA68RDTwiIyggwl 1t7A== X-Gm-Message-State: AOAM533D2ZkrcQmaF2sxfWh3AeNDnQmgGVfzlQSkh0N/h6t3UmVU9IP7 TZTA2LXL4fO6H94Vb9evnT2ECF6fSbMwwthhM/gw29Ff4+e4T+OZzLXhIRkX0oXSizQQZgEy7yh V5dSJuZC33vpzbJqqF2ZXy0DEKgTqsNK6Npb17UQ3PdM/H8SC3ceXcFQKJpsupuR1ITnIxMs= X-Google-Smtp-Source: ABdhPJwBOu9u/eGwIrGOPtqVB/8CprwtFYjkXu221reXRwMkU5jXpb8retDk2NScFTopuyCGkmRH5UZrLC4Dlzg= X-Received: from alankelly0.zrh.corp.google.com ([2a00:79e0:61:301:b61d:d4c4:5dce:c0af]) (user=alankelly job=sendgmr) by 2002:a05:6402:3551:: with SMTP id f17mr70743edd.64.1641826736686; Mon, 10 Jan 2022 06:58:56 -0800 (PST) Date: Mon, 10 Jan 2022 15:58:34 +0100 In-Reply-To: <20220110145836.3449558-1-alankelly@google.com> Message-Id: <20220110145836.3449558-2-alankelly@google.com> Mime-Version: 1.0 References: <20220110145836.3449558-1-alankelly@google.com> X-Mailer: git-send-email 2.34.1.575.g55b058a8bb-goog From: Alan Kelly To: ffmpeg-devel@ffmpeg.org Subject: [FFmpeg-devel] [PATCH 2/4] libswscale: Avx2 hscale can process any input of size which is a multiple of 4. 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 Cc: Alan Kelly Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" Archived-At: List-Archive: List-Post: The main loop processes blocks of 16 pixels. The tail processes blocks of size 4. --- libswscale/x86/scale_avx2.asm | 48 +++++++++++++++++++++++++++++++++-- 1 file changed, 46 insertions(+), 2 deletions(-) diff --git a/libswscale/x86/scale_avx2.asm b/libswscale/x86/scale_avx2.asm index 20acdbd633..dc42abb100 100644 --- a/libswscale/x86/scale_avx2.asm +++ b/libswscale/x86/scale_avx2.asm @@ -53,6 +53,9 @@ cglobal hscale8to15_%1, 7, 9, 16, pos0, dst, w, srcmem, filter, fltpos, fltsize, mova m14, [four] shr fltsized, 2 %endif + cmp wq, 16 + jl .tail_loop + mov countq, 0x10 .loop: movu m1, [fltposq] movu m2, [fltposq+32] @@ -97,11 +100,52 @@ cglobal hscale8to15_%1, 7, 9, 16, pos0, dst, w, srcmem, filter, fltpos, fltsize, vpsrad m6, 7 vpackssdw m5, m5, m6 vpermd m5, m15, m5 - vmovdqu [dstq + countq * 2], m5 + vmovdqu [dstq], m5 + add dstq, 0x20 add fltposq, 0x40 add countq, 0x10 cmp countq, wq - jl .loop + jle .loop + + sub countq, 0x10 + cmp countq, wq + jge .end + +.tail_loop: + movu xm1, [fltposq] +%ifidn %1, X4 + pxor xm9, xm9 + pxor xm10, xm10 + xor innerq, innerq +.tail_innerloop: +%endif + vpcmpeqd xm13, xm13 + vpgatherdd xm3,[srcmemq + xm1], xm13 + vpunpcklbw xm5, xm3, xm0 + vpunpckhbw xm6, xm3, xm0 + vpmaddwd xm5, xm5, [filterq] + vpmaddwd xm6, xm6, [filterq + 16] + add filterq, 0x20 +%ifidn %1, X4 + paddd xm9, xm5 + paddd xm10, xm6 + paddd xm1, xm14 + add innerq, 1 + cmp innerq, fltsizeq + jl .tail_innerloop + vphaddd xm5, xm9, xm10 +%else + vphaddd xm5, xm5, xm6 +%endif + vpsrad xm5, 7 + vpackssdw xm5, xm5, xm5 + vmovq [dstq], xm5 + add dstq, 0x8 + add fltposq, 0x10 + add countq, 0x4 + cmp countq, wq + jl .tail_loop +.end: REP_RET %endmacro -- 2.34.1.575.g55b058a8bb-goog _______________________________________________ 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".