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 444294A21B for ; Mon, 25 Mar 2024 15:03:47 +0000 (UTC) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 5CF8268D57C; Mon, 25 Mar 2024 17:02:58 +0200 (EET) Received: from mail-lj1-f171.google.com (mail-lj1-f171.google.com [209.85.208.171]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id B0BE968D505 for ; Mon, 25 Mar 2024 17:02:52 +0200 (EET) Received: by mail-lj1-f171.google.com with SMTP id 38308e7fff4ca-2d6c8d741e8so31790491fa.3 for ; Mon, 25 Mar 2024 08:02:52 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=martin-st.20230601.gappssmtp.com; s=20230601; t=1711378971; x=1711983771; darn=ffmpeg.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=y149jlwhaCuGR1CXHDUXnqyiLs7Hu94LuuEx7Lnxqpo=; b=P61ofUcjpEzbmsYcGjuf/jp0lH74MWOPp826aQVd9HwhGuz7ldORE3T0dcyIsSH8Mu IogHeLZYKFfH5w/dqeaKtEhqt+ZtrVEX+JYyhe51xeK49Y3x9ngfvbIWEO62FZXcXsJZ wfJDn80dVPCZRRmsW55ICMiNoprAIOQColWeJ7mHtetyfQfXiDyXAMSbSmk7wxlog7Zy VycHqoQ0lTd/kz90WuwzvuyMp9e0lgMq3PkegsYoqjYUjO0A7QDiQHkmNhsfzvxQ+UUY PwZDrYQ9NbnSISvW1VvuWsS4ddUmS2iojmUemkxD8lTrkmdW5wF2sJH9cpG5U/sdjEsf 5n2w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1711378971; x=1711983771; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=y149jlwhaCuGR1CXHDUXnqyiLs7Hu94LuuEx7Lnxqpo=; b=Vg+GpvZ3DprYubAUpCRjiakCtZomVKPzAztppdPs1oMTeHBTXgAs/3Hr7PVks5neci steoUCKt2FVclOrNllz0jVhvIFVi95b70eoW/0Y7NVTCS+JmK5qccTbKcFGjuSt6HaSA 6WNFHBfiwP6HYK1vHLhnfRfhBV1ZtPErlXQCivQYxkuNTCJ8ZeoeHN4mjCJASYJJZLtY 5494YNcpr4h4VOmsLmXc20sh6KUAK1hPNYcDbTtqIY0EY7kfcCRzCGvob7PivCMD4Btj SZFmUmuZHvrrzRvSRop3l2Nx5gyqJzUzkY/T0xOb6y6NR7RidJhZ9EznrNrKOnOlxyPh m4gw== X-Gm-Message-State: AOJu0YwKxxXhdMQ8oJOFO4zNeRu8BMRXr2YCY3lgbK48f68TsUgdq+Zo o0hUgUkMAp4qGcW6xYLMJ7cdS/N00Sy6V+Zv/mTc3Xc6tGbnAkvCG4qWe///ov8814xltfEmBIl SCUEt X-Google-Smtp-Source: AGHT+IGV/wnSplv6nCoIfp8IZOU2LireozvuNx6sfq290hZXcTpHWkP4w4pHylNCe7t6KhwZAADzQw== X-Received: by 2002:a2e:90c2:0:b0:2d6:b9d3:ef40 with SMTP id o2-20020a2e90c2000000b002d6b9d3ef40mr4709532ljg.29.1711378971220; Mon, 25 Mar 2024 08:02:51 -0700 (PDT) Received: from localhost (host-114-191.parnet.fi. [77.234.114.191]) by smtp.gmail.com with ESMTPSA id h7-20020a05651c124700b002d46df91965sm1488565ljh.80.2024.03.25.08.02.50 (version=TLS1 cipher=AES128-SHA bits=128/128); Mon, 25 Mar 2024 08:02:50 -0700 (PDT) From: =?UTF-8?q?Martin=20Storsj=C3=B6?= To: ffmpeg-devel@ffmpeg.org Date: Mon, 25 Mar 2024 17:02:31 +0200 Message-Id: <20240325150243.59058-10-martin@martin.st> X-Mailer: git-send-email 2.39.3 (Apple Git-146) In-Reply-To: <20240325150243.59058-1-martin@martin.st> References: <20240325150243.59058-1-martin@martin.st> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH 09/21] aarch64: hevc: Reorder epel_hv functions to prepare for templating 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: Logan Lyu , "J . Dekker" 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: This is a pure reordering of code without changing anything in the individual functions. --- libavcodec/aarch64/hevcdsp_epel_neon.S | 971 +++++++++++++------------ 1 file changed, 497 insertions(+), 474 deletions(-) diff --git a/libavcodec/aarch64/hevcdsp_epel_neon.S b/libavcodec/aarch64/hevcdsp_epel_neon.S index 6be171ece1..2088630da1 100644 --- a/libavcodec/aarch64/hevcdsp_epel_neon.S +++ b/libavcodec/aarch64/hevcdsp_epel_neon.S @@ -2173,21 +2173,9 @@ function ff_hevc_put_hevc_epel_h64_8_neon_i8mm, export=1 ret endfunc +DISABLE_I8MM +#endif -function ff_hevc_put_hevc_epel_hv4_8_neon_i8mm, export=1 - add w10, w3, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - stp x5, x30, [sp, #-32]! - stp x0, x3, [sp, #16] - add x0, sp, #32 - sub x1, x1, x2 - add w3, w3, #3 - bl X(ff_hevc_put_hevc_epel_h4_8_neon_i8mm) - ldp x0, x3, [sp, #16] - ldp x5, x30, [sp], #32 - b hevc_put_hevc_epel_hv4_8_end_neon -endfunc function hevc_put_hevc_epel_hv4_8_end_neon load_epel_filterh x5, x4 @@ -2207,21 +2195,6 @@ function hevc_put_hevc_epel_hv4_8_end_neon 2: ret endfunc -function ff_hevc_put_hevc_epel_hv6_8_neon_i8mm, export=1 - add w10, w3, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - stp x5, x30, [sp, #-32]! - stp x0, x3, [sp, #16] - add x0, sp, #32 - sub x1, x1, x2 - add w3, w3, #3 - bl X(ff_hevc_put_hevc_epel_h6_8_neon_i8mm) - ldp x0, x3, [sp, #16] - ldp x5, x30, [sp], #32 - b hevc_put_hevc_epel_hv6_8_end_neon -endfunc - function hevc_put_hevc_epel_hv6_8_end_neon load_epel_filterh x5, x4 mov x5, #120 @@ -2243,21 +2216,6 @@ function hevc_put_hevc_epel_hv6_8_end_neon 2: ret endfunc -function ff_hevc_put_hevc_epel_hv8_8_neon_i8mm, export=1 - add w10, w3, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - stp x5, x30, [sp, #-32]! - stp x0, x3, [sp, #16] - add x0, sp, #32 - sub x1, x1, x2 - add w3, w3, #3 - bl X(ff_hevc_put_hevc_epel_h8_8_neon_i8mm) - ldp x0, x3, [sp, #16] - ldp x5, x30, [sp], #32 - b hevc_put_hevc_epel_hv8_8_end_neon -endfunc - function hevc_put_hevc_epel_hv8_8_end_neon load_epel_filterh x5, x4 mov x10, #(MAX_PB_SIZE * 2) @@ -2277,21 +2235,6 @@ function hevc_put_hevc_epel_hv8_8_end_neon 2: ret endfunc -function ff_hevc_put_hevc_epel_hv12_8_neon_i8mm, export=1 - add w10, w3, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - stp x5, x30, [sp, #-32]! - stp x0, x3, [sp, #16] - add x0, sp, #32 - sub x1, x1, x2 - add w3, w3, #3 - bl X(ff_hevc_put_hevc_epel_h12_8_neon_i8mm) - ldp x0, x3, [sp, #16] - ldp x5, x30, [sp], #32 - b hevc_put_hevc_epel_hv12_8_end_neon -endfunc - function hevc_put_hevc_epel_hv12_8_end_neon load_epel_filterh x5, x4 mov x5, #112 @@ -2313,21 +2256,6 @@ function hevc_put_hevc_epel_hv12_8_end_neon 2: ret endfunc -function ff_hevc_put_hevc_epel_hv16_8_neon_i8mm, export=1 - add w10, w3, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - stp x5, x30, [sp, #-32]! - stp x0, x3, [sp, #16] - add x0, sp, #32 - sub x1, x1, x2 - add w3, w3, #3 - bl X(ff_hevc_put_hevc_epel_h16_8_neon_i8mm) - ldp x0, x3, [sp, #16] - ldp x5, x30, [sp], #32 - b hevc_put_hevc_epel_hv16_8_end_neon -endfunc - function hevc_put_hevc_epel_hv16_8_end_neon load_epel_filterh x5, x4 mov x10, #(MAX_PB_SIZE * 2) @@ -2348,21 +2276,6 @@ function hevc_put_hevc_epel_hv16_8_end_neon 2: ret endfunc -function ff_hevc_put_hevc_epel_hv24_8_neon_i8mm, export=1 - add w10, w3, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - stp x5, x30, [sp, #-32]! - stp x0, x3, [sp, #16] - add x0, sp, #32 - sub x1, x1, x2 - add w3, w3, #3 - bl X(ff_hevc_put_hevc_epel_h24_8_neon_i8mm) - ldp x0, x3, [sp, #16] - ldp x5, x30, [sp], #32 - b hevc_put_hevc_epel_hv24_8_end_neon -endfunc - function hevc_put_hevc_epel_hv24_8_end_neon load_epel_filterh x5, x4 mov x10, #(MAX_PB_SIZE * 2) @@ -2385,6 +2298,99 @@ function hevc_put_hevc_epel_hv24_8_end_neon 2: ret endfunc +#if HAVE_I8MM +ENABLE_I8MM + +function ff_hevc_put_hevc_epel_hv4_8_neon_i8mm, export=1 + add w10, w3, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + stp x5, x30, [sp, #-32]! + stp x0, x3, [sp, #16] + add x0, sp, #32 + sub x1, x1, x2 + add w3, w3, #3 + bl X(ff_hevc_put_hevc_epel_h4_8_neon_i8mm) + ldp x0, x3, [sp, #16] + ldp x5, x30, [sp], #32 + b hevc_put_hevc_epel_hv4_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_hv6_8_neon_i8mm, export=1 + add w10, w3, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + stp x5, x30, [sp, #-32]! + stp x0, x3, [sp, #16] + add x0, sp, #32 + sub x1, x1, x2 + add w3, w3, #3 + bl X(ff_hevc_put_hevc_epel_h6_8_neon_i8mm) + ldp x0, x3, [sp, #16] + ldp x5, x30, [sp], #32 + b hevc_put_hevc_epel_hv6_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_hv8_8_neon_i8mm, export=1 + add w10, w3, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + stp x5, x30, [sp, #-32]! + stp x0, x3, [sp, #16] + add x0, sp, #32 + sub x1, x1, x2 + add w3, w3, #3 + bl X(ff_hevc_put_hevc_epel_h8_8_neon_i8mm) + ldp x0, x3, [sp, #16] + ldp x5, x30, [sp], #32 + b hevc_put_hevc_epel_hv8_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_hv12_8_neon_i8mm, export=1 + add w10, w3, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + stp x5, x30, [sp, #-32]! + stp x0, x3, [sp, #16] + add x0, sp, #32 + sub x1, x1, x2 + add w3, w3, #3 + bl X(ff_hevc_put_hevc_epel_h12_8_neon_i8mm) + ldp x0, x3, [sp, #16] + ldp x5, x30, [sp], #32 + b hevc_put_hevc_epel_hv12_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_hv16_8_neon_i8mm, export=1 + add w10, w3, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + stp x5, x30, [sp, #-32]! + stp x0, x3, [sp, #16] + add x0, sp, #32 + sub x1, x1, x2 + add w3, w3, #3 + bl X(ff_hevc_put_hevc_epel_h16_8_neon_i8mm) + ldp x0, x3, [sp, #16] + ldp x5, x30, [sp], #32 + b hevc_put_hevc_epel_hv16_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_hv24_8_neon_i8mm, export=1 + add w10, w3, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + stp x5, x30, [sp, #-32]! + stp x0, x3, [sp, #16] + add x0, sp, #32 + sub x1, x1, x2 + add w3, w3, #3 + bl X(ff_hevc_put_hevc_epel_h24_8_neon_i8mm) + ldp x0, x3, [sp, #16] + ldp x5, x30, [sp], #32 + b hevc_put_hevc_epel_hv24_8_end_neon +endfunc + function ff_hevc_put_hevc_epel_hv32_8_neon_i8mm, export=1 stp x4, x5, [sp, #-64]! stp x2, x3, [sp, #16] @@ -2453,24 +2459,8 @@ function ff_hevc_put_hevc_epel_hv64_8_neon_i8mm, export=1 ret endfunc -function ff_hevc_put_hevc_epel_uni_hv4_8_neon_i8mm, export=1 - add w10, w4, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - str x30, [sp, #-48]! - stp x4, x6, [sp, #16] - stp x0, x1, [sp, #32] - add x0, sp, #48 - sub x1, x2, x3 - mov x2, x3 - add w3, w4, #3 - mov x4, x5 - bl X(ff_hevc_put_hevc_epel_h4_8_neon_i8mm) - ldp x4, x6, [sp, #16] - ldp x0, x1, [sp, #32] - ldr x30, [sp], #48 - b hevc_put_hevc_epel_uni_hv4_8_end_neon -endfunc +DISABLE_I8MM +#endif function hevc_put_hevc_epel_uni_hv4_8_end_neon load_epel_filterh x6, x5 @@ -2490,25 +2480,6 @@ function hevc_put_hevc_epel_uni_hv4_8_end_neon 2: ret endfunc -function ff_hevc_put_hevc_epel_uni_hv6_8_neon_i8mm, export=1 - add w10, w4, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - str x30, [sp, #-48]! - stp x4, x6, [sp, #16] - stp x0, x1, [sp, #32] - add x0, sp, #48 - sub x1, x2, x3 - mov x2, x3 - add w3, w4, #3 - mov x4, x5 - bl X(ff_hevc_put_hevc_epel_h6_8_neon_i8mm) - ldp x4, x6, [sp, #16] - ldp x0, x1, [sp, #32] - ldr x30, [sp], #48 - b hevc_put_hevc_epel_uni_hv6_8_end_neon -endfunc - function hevc_put_hevc_epel_uni_hv6_8_end_neon load_epel_filterh x6, x5 sub x1, x1, #4 @@ -2530,25 +2501,6 @@ function hevc_put_hevc_epel_uni_hv6_8_end_neon 2: ret endfunc -function ff_hevc_put_hevc_epel_uni_hv8_8_neon_i8mm, export=1 - add w10, w4, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - str x30, [sp, #-48]! - stp x4, x6, [sp, #16] - stp x0, x1, [sp, #32] - add x0, sp, #48 - sub x1, x2, x3 - mov x2, x3 - add w3, w4, #3 - mov x4, x5 - bl X(ff_hevc_put_hevc_epel_h8_8_neon_i8mm) - ldp x4, x6, [sp, #16] - ldp x0, x1, [sp, #32] - ldr x30, [sp], #48 - b hevc_put_hevc_epel_uni_hv8_8_end_neon -endfunc - function hevc_put_hevc_epel_uni_hv8_8_end_neon load_epel_filterh x6, x5 mov x10, #(MAX_PB_SIZE * 2) @@ -2568,25 +2520,6 @@ function hevc_put_hevc_epel_uni_hv8_8_end_neon 2: ret endfunc -function ff_hevc_put_hevc_epel_uni_hv12_8_neon_i8mm, export=1 - add w10, w4, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - str x30, [sp, #-48]! - stp x4, x6, [sp, #16] - stp x0, x1, [sp, #32] - add x0, sp, #48 - sub x1, x2, x3 - mov x2, x3 - add w3, w4, #3 - mov x4, x5 - bl X(ff_hevc_put_hevc_epel_h12_8_neon_i8mm) - ldp x4, x6, [sp, #16] - ldp x0, x1, [sp, #32] - ldr x30, [sp], #48 - b hevc_put_hevc_epel_uni_hv12_8_end_neon -endfunc - function hevc_put_hevc_epel_uni_hv12_8_end_neon load_epel_filterh x6, x5 sub x1, x1, #8 @@ -2610,25 +2543,6 @@ function hevc_put_hevc_epel_uni_hv12_8_end_neon 2: ret endfunc -function ff_hevc_put_hevc_epel_uni_hv16_8_neon_i8mm, export=1 - add w10, w4, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - str x30, [sp, #-48]! - stp x4, x6, [sp, #16] - stp x0, x1, [sp, #32] - add x0, sp, #48 - sub x1, x2, x3 - mov x2, x3 - add w3, w4, #3 - mov x4, x5 - bl X(ff_hevc_put_hevc_epel_h16_8_neon_i8mm) - ldp x4, x6, [sp, #16] - ldp x0, x1, [sp, #32] - ldr x30, [sp], #48 - b hevc_put_hevc_epel_uni_hv16_8_end_neon -endfunc - function hevc_put_hevc_epel_uni_hv16_8_end_neon load_epel_filterh x6, x5 mov x10, #(MAX_PB_SIZE * 2) @@ -2651,25 +2565,6 @@ function hevc_put_hevc_epel_uni_hv16_8_end_neon 2: ret endfunc -function ff_hevc_put_hevc_epel_uni_hv24_8_neon_i8mm, export=1 - add w10, w4, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - str x30, [sp, #-48]! - stp x4, x6, [sp, #16] - stp x0, x1, [sp, #32] - add x0, sp, #48 - sub x1, x2, x3 - mov x2, x3 - add w3, w4, #3 - mov x4, x5 - bl X(ff_hevc_put_hevc_epel_h24_8_neon_i8mm) - ldp x4, x6, [sp, #16] - ldp x0, x1, [sp, #32] - ldr x30, [sp], #48 - b hevc_put_hevc_epel_uni_hv24_8_end_neon -endfunc - function hevc_put_hevc_epel_uni_hv24_8_end_neon load_epel_filterh x6, x5 mov x10, #(MAX_PB_SIZE * 2) @@ -2695,6 +2590,123 @@ function hevc_put_hevc_epel_uni_hv24_8_end_neon 2: ret endfunc +#if HAVE_I8MM +ENABLE_I8MM + +function ff_hevc_put_hevc_epel_uni_hv4_8_neon_i8mm, export=1 + add w10, w4, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + str x30, [sp, #-48]! + stp x4, x6, [sp, #16] + stp x0, x1, [sp, #32] + add x0, sp, #48 + sub x1, x2, x3 + mov x2, x3 + add w3, w4, #3 + mov x4, x5 + bl X(ff_hevc_put_hevc_epel_h4_8_neon_i8mm) + ldp x4, x6, [sp, #16] + ldp x0, x1, [sp, #32] + ldr x30, [sp], #48 + b hevc_put_hevc_epel_uni_hv4_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_uni_hv6_8_neon_i8mm, export=1 + add w10, w4, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + str x30, [sp, #-48]! + stp x4, x6, [sp, #16] + stp x0, x1, [sp, #32] + add x0, sp, #48 + sub x1, x2, x3 + mov x2, x3 + add w3, w4, #3 + mov x4, x5 + bl X(ff_hevc_put_hevc_epel_h6_8_neon_i8mm) + ldp x4, x6, [sp, #16] + ldp x0, x1, [sp, #32] + ldr x30, [sp], #48 + b hevc_put_hevc_epel_uni_hv6_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_uni_hv8_8_neon_i8mm, export=1 + add w10, w4, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + str x30, [sp, #-48]! + stp x4, x6, [sp, #16] + stp x0, x1, [sp, #32] + add x0, sp, #48 + sub x1, x2, x3 + mov x2, x3 + add w3, w4, #3 + mov x4, x5 + bl X(ff_hevc_put_hevc_epel_h8_8_neon_i8mm) + ldp x4, x6, [sp, #16] + ldp x0, x1, [sp, #32] + ldr x30, [sp], #48 + b hevc_put_hevc_epel_uni_hv8_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_uni_hv12_8_neon_i8mm, export=1 + add w10, w4, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + str x30, [sp, #-48]! + stp x4, x6, [sp, #16] + stp x0, x1, [sp, #32] + add x0, sp, #48 + sub x1, x2, x3 + mov x2, x3 + add w3, w4, #3 + mov x4, x5 + bl X(ff_hevc_put_hevc_epel_h12_8_neon_i8mm) + ldp x4, x6, [sp, #16] + ldp x0, x1, [sp, #32] + ldr x30, [sp], #48 + b hevc_put_hevc_epel_uni_hv12_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_uni_hv16_8_neon_i8mm, export=1 + add w10, w4, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + str x30, [sp, #-48]! + stp x4, x6, [sp, #16] + stp x0, x1, [sp, #32] + add x0, sp, #48 + sub x1, x2, x3 + mov x2, x3 + add w3, w4, #3 + mov x4, x5 + bl X(ff_hevc_put_hevc_epel_h16_8_neon_i8mm) + ldp x4, x6, [sp, #16] + ldp x0, x1, [sp, #32] + ldr x30, [sp], #48 + b hevc_put_hevc_epel_uni_hv16_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_uni_hv24_8_neon_i8mm, export=1 + add w10, w4, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + str x30, [sp, #-48]! + stp x4, x6, [sp, #16] + stp x0, x1, [sp, #32] + add x0, sp, #48 + sub x1, x2, x3 + mov x2, x3 + add w3, w4, #3 + mov x4, x5 + bl X(ff_hevc_put_hevc_epel_h24_8_neon_i8mm) + ldp x4, x6, [sp, #16] + ldp x0, x1, [sp, #32] + ldr x30, [sp], #48 + b hevc_put_hevc_epel_uni_hv24_8_end_neon +endfunc + function ff_hevc_put_hevc_epel_uni_hv32_8_neon_i8mm, export=1 stp x5, x6, [sp, #-64]! stp x3, x4, [sp, #16] @@ -3098,6 +3110,8 @@ function ff_hevc_put_hevc_epel_uni_w_h64_8_neon_i8mm, export=1 b.hi 1b ret endfunc +DISABLE_I8MM +#endif .macro epel_uni_w_hv_start mov x15, x5 //denom @@ -3202,28 +3216,6 @@ endfunc -function ff_hevc_put_hevc_epel_uni_w_hv4_8_neon_i8mm, export=1 - epel_uni_w_hv_start - sxtw x4, w4 - - add x10, x4, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - str x30, [sp, #-48]! - stp x4, x6, [sp, #16] - stp x0, x1, [sp, #32] - add x0, sp, #48 - sub x1, x2, x3 - mov x2, x3 - add x3, x4, #3 - mov x4, x5 - bl X(ff_hevc_put_hevc_epel_h4_8_neon_i8mm) - ldp x4, x6, [sp, #16] - ldp x0, x1, [sp, #32] - ldr x30, [sp], #48 - b hevc_put_hevc_epel_uni_w_hv4_8_end_neon -endfunc - function hevc_put_hevc_epel_uni_w_hv4_8_end_neon load_epel_filterh x6, x5 mov x10, #(MAX_PB_SIZE * 2) @@ -3273,28 +3265,6 @@ function hevc_put_hevc_epel_uni_w_hv4_8_end_neon ret endfunc -function ff_hevc_put_hevc_epel_uni_w_hv6_8_neon_i8mm, export=1 - epel_uni_w_hv_start - sxtw x4, w4 - - add x10, x4, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - str x30, [sp, #-48]! - stp x4, x6, [sp, #16] - stp x0, x1, [sp, #32] - add x0, sp, #48 - sub x1, x2, x3 - mov x2, x3 - add x3, x4, #3 - mov x4, x5 - bl X(ff_hevc_put_hevc_epel_h6_8_neon_i8mm) - ldp x4, x6, [sp, #16] - ldp x0, x1, [sp, #32] - ldr x30, [sp], #48 - b hevc_put_hevc_epel_uni_w_hv6_8_end_neon -endfunc - function hevc_put_hevc_epel_uni_w_hv6_8_end_neon load_epel_filterh x6, x5 sub x1, x1, #4 @@ -3349,28 +3319,6 @@ function hevc_put_hevc_epel_uni_w_hv6_8_end_neon ret endfunc -function ff_hevc_put_hevc_epel_uni_w_hv8_8_neon_i8mm, export=1 - epel_uni_w_hv_start - sxtw x4, w4 - - add x10, x4, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - str x30, [sp, #-48]! - stp x4, x6, [sp, #16] - stp x0, x1, [sp, #32] - add x0, sp, #48 - sub x1, x2, x3 - mov x2, x3 - add x3, x4, #3 - mov x4, x5 - bl X(ff_hevc_put_hevc_epel_h8_8_neon_i8mm) - ldp x4, x6, [sp, #16] - ldp x0, x1, [sp, #32] - ldr x30, [sp], #48 - b hevc_put_hevc_epel_uni_w_hv8_8_end_neon -endfunc - function hevc_put_hevc_epel_uni_w_hv8_8_end_neon load_epel_filterh x6, x5 mov x10, #(MAX_PB_SIZE * 2) @@ -3420,28 +3368,6 @@ function hevc_put_hevc_epel_uni_w_hv8_8_end_neon ret endfunc -function ff_hevc_put_hevc_epel_uni_w_hv12_8_neon_i8mm, export=1 - epel_uni_w_hv_start - sxtw x4, w4 - - add x10, x4, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - str x30, [sp, #-48]! - stp x4, x6, [sp, #16] - stp x0, x1, [sp, #32] - add x0, sp, #48 - sub x1, x2, x3 - mov x2, x3 - add x3, x4, #3 - mov x4, x5 - bl X(ff_hevc_put_hevc_epel_h12_8_neon_i8mm) - ldp x4, x6, [sp, #16] - ldp x0, x1, [sp, #32] - ldr x30, [sp], #48 - b hevc_put_hevc_epel_uni_w_hv12_8_end_neon -endfunc - function hevc_put_hevc_epel_uni_w_hv12_8_end_neon load_epel_filterh x6, x5 sub x1, x1, #8 @@ -3504,28 +3430,6 @@ function hevc_put_hevc_epel_uni_w_hv12_8_end_neon ret endfunc -function ff_hevc_put_hevc_epel_uni_w_hv16_8_neon_i8mm, export=1 - epel_uni_w_hv_start - sxtw x4, w4 - - add x10, x4, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - str x30, [sp, #-48]! - stp x4, x6, [sp, #16] - stp x0, x1, [sp, #32] - add x0, sp, #48 - sub x1, x2, x3 - mov x2, x3 - add x3, x4, #3 - mov x4, x5 - bl X(ff_hevc_put_hevc_epel_h16_8_neon_i8mm) - ldp x4, x6, [sp, #16] - ldp x0, x1, [sp, #32] - ldr x30, [sp], #48 - b hevc_put_hevc_epel_uni_w_hv16_8_end_neon -endfunc - function hevc_put_hevc_epel_uni_w_hv16_8_end_neon load_epel_filterh x6, x5 mov x10, #(MAX_PB_SIZE * 2) @@ -3587,28 +3491,6 @@ function hevc_put_hevc_epel_uni_w_hv16_8_end_neon ret endfunc -function ff_hevc_put_hevc_epel_uni_w_hv24_8_neon_i8mm, export=1 - epel_uni_w_hv_start - sxtw x4, w4 - - add x10, x4, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - str x30, [sp, #-48]! - stp x4, x6, [sp, #16] - stp x0, x1, [sp, #32] - add x0, sp, #48 - sub x1, x2, x3 - mov x2, x3 - add x3, x4, #3 - mov x4, x5 - bl X(ff_hevc_put_hevc_epel_h24_8_neon_i8mm) - ldp x4, x6, [sp, #16] - ldp x0, x1, [sp, #32] - ldr x30, [sp], #48 - b hevc_put_hevc_epel_uni_w_hv24_8_end_neon -endfunc - function hevc_put_hevc_epel_uni_w_hv24_8_end_neon load_epel_filterh x6, x5 mov x10, #(MAX_PB_SIZE * 2) @@ -3686,6 +3568,141 @@ function hevc_put_hevc_epel_uni_w_hv24_8_end_neon ret endfunc +#if HAVE_I8MM +ENABLE_I8MM + +function ff_hevc_put_hevc_epel_uni_w_hv4_8_neon_i8mm, export=1 + epel_uni_w_hv_start + sxtw x4, w4 + + add x10, x4, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + str x30, [sp, #-48]! + stp x4, x6, [sp, #16] + stp x0, x1, [sp, #32] + add x0, sp, #48 + sub x1, x2, x3 + mov x2, x3 + add x3, x4, #3 + mov x4, x5 + bl X(ff_hevc_put_hevc_epel_h4_8_neon_i8mm) + ldp x4, x6, [sp, #16] + ldp x0, x1, [sp, #32] + ldr x30, [sp], #48 + b hevc_put_hevc_epel_uni_w_hv4_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_uni_w_hv6_8_neon_i8mm, export=1 + epel_uni_w_hv_start + sxtw x4, w4 + + add x10, x4, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + str x30, [sp, #-48]! + stp x4, x6, [sp, #16] + stp x0, x1, [sp, #32] + add x0, sp, #48 + sub x1, x2, x3 + mov x2, x3 + add x3, x4, #3 + mov x4, x5 + bl X(ff_hevc_put_hevc_epel_h6_8_neon_i8mm) + ldp x4, x6, [sp, #16] + ldp x0, x1, [sp, #32] + ldr x30, [sp], #48 + b hevc_put_hevc_epel_uni_w_hv6_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_uni_w_hv8_8_neon_i8mm, export=1 + epel_uni_w_hv_start + sxtw x4, w4 + + add x10, x4, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + str x30, [sp, #-48]! + stp x4, x6, [sp, #16] + stp x0, x1, [sp, #32] + add x0, sp, #48 + sub x1, x2, x3 + mov x2, x3 + add x3, x4, #3 + mov x4, x5 + bl X(ff_hevc_put_hevc_epel_h8_8_neon_i8mm) + ldp x4, x6, [sp, #16] + ldp x0, x1, [sp, #32] + ldr x30, [sp], #48 + b hevc_put_hevc_epel_uni_w_hv8_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_uni_w_hv12_8_neon_i8mm, export=1 + epel_uni_w_hv_start + sxtw x4, w4 + + add x10, x4, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + str x30, [sp, #-48]! + stp x4, x6, [sp, #16] + stp x0, x1, [sp, #32] + add x0, sp, #48 + sub x1, x2, x3 + mov x2, x3 + add x3, x4, #3 + mov x4, x5 + bl X(ff_hevc_put_hevc_epel_h12_8_neon_i8mm) + ldp x4, x6, [sp, #16] + ldp x0, x1, [sp, #32] + ldr x30, [sp], #48 + b hevc_put_hevc_epel_uni_w_hv12_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_uni_w_hv16_8_neon_i8mm, export=1 + epel_uni_w_hv_start + sxtw x4, w4 + + add x10, x4, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + str x30, [sp, #-48]! + stp x4, x6, [sp, #16] + stp x0, x1, [sp, #32] + add x0, sp, #48 + sub x1, x2, x3 + mov x2, x3 + add x3, x4, #3 + mov x4, x5 + bl X(ff_hevc_put_hevc_epel_h16_8_neon_i8mm) + ldp x4, x6, [sp, #16] + ldp x0, x1, [sp, #32] + ldr x30, [sp], #48 + b hevc_put_hevc_epel_uni_w_hv16_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_uni_w_hv24_8_neon_i8mm, export=1 + epel_uni_w_hv_start + sxtw x4, w4 + + add x10, x4, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + str x30, [sp, #-48]! + stp x4, x6, [sp, #16] + stp x0, x1, [sp, #32] + add x0, sp, #48 + sub x1, x2, x3 + mov x2, x3 + add x3, x4, #3 + mov x4, x5 + bl X(ff_hevc_put_hevc_epel_h24_8_neon_i8mm) + ldp x4, x6, [sp, #16] + ldp x0, x1, [sp, #32] + ldr x30, [sp], #48 + b hevc_put_hevc_epel_uni_w_hv24_8_end_neon +endfunc + function ff_hevc_put_hevc_epel_uni_w_hv32_8_neon_i8mm, export=1 ldp x15, x16, [sp] mov x17, #16 @@ -3769,26 +3786,9 @@ function ff_hevc_put_hevc_epel_uni_w_hv64_8_neon_i8mm, export=1 ret endfunc +DISABLE_I8MM +#endif -function ff_hevc_put_hevc_epel_bi_hv4_8_neon_i8mm, export=1 - add w10, w5, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - stp x7, x30, [sp, #-48]! - stp x4, x5, [sp, #16] - stp x0, x1, [sp, #32] - add x0, sp, #48 - sub x1, x2, x3 - mov x2, x3 - add w3, w5, #3 - mov x4, x6 - mov x5, x7 - bl X(ff_hevc_put_hevc_epel_h4_8_neon_i8mm) - ldp x4, x5, [sp, #16] - ldp x0, x1, [sp, #32] - ldp x7, x30, [sp], #48 - b hevc_put_hevc_epel_bi_hv4_8_end_neon -endfunc function hevc_put_hevc_epel_bi_hv4_8_end_neon load_epel_filterh x7, x6 @@ -3810,26 +3810,6 @@ function hevc_put_hevc_epel_bi_hv4_8_end_neon 2: ret endfunc -function ff_hevc_put_hevc_epel_bi_hv6_8_neon_i8mm, export=1 - add w10, w5, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - stp x7, x30, [sp, #-48]! - stp x4, x5, [sp, #16] - stp x0, x1, [sp, #32] - add x0, sp, #48 - sub x1, x2, x3 - mov x2, x3 - add w3, w5, #3 - mov x4, x6 - mov x5, x7 - bl X(ff_hevc_put_hevc_epel_h6_8_neon_i8mm) - ldp x4, x5, [sp, #16] - ldp x0, x1, [sp, #32] - ldp x7, x30, [sp], #48 - b hevc_put_hevc_epel_bi_hv6_8_end_neon -endfunc - function hevc_put_hevc_epel_bi_hv6_8_end_neon load_epel_filterh x7, x6 sub x1, x1, #4 @@ -3853,26 +3833,6 @@ function hevc_put_hevc_epel_bi_hv6_8_end_neon 2: ret endfunc -function ff_hevc_put_hevc_epel_bi_hv8_8_neon_i8mm, export=1 - add w10, w5, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - stp x7, x30, [sp, #-48]! - stp x4, x5, [sp, #16] - stp x0, x1, [sp, #32] - add x0, sp, #48 - sub x1, x2, x3 - mov x2, x3 - add w3, w5, #3 - mov x4, x6 - mov x5, x7 - bl X(ff_hevc_put_hevc_epel_h8_8_neon_i8mm) - ldp x4, x5, [sp, #16] - ldp x0, x1, [sp, #32] - ldp x7, x30, [sp], #48 - b hevc_put_hevc_epel_bi_hv8_8_end_neon -endfunc - function hevc_put_hevc_epel_bi_hv8_8_end_neon load_epel_filterh x7, x6 mov x10, #(MAX_PB_SIZE * 2) @@ -3894,26 +3854,6 @@ function hevc_put_hevc_epel_bi_hv8_8_end_neon 2: ret endfunc -function ff_hevc_put_hevc_epel_bi_hv12_8_neon_i8mm, export=1 - add w10, w5, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - stp x7, x30, [sp, #-48]! - stp x4, x5, [sp, #16] - stp x0, x1, [sp, #32] - add x0, sp, #48 - sub x1, x2, x3 - mov x2, x3 - add w3, w5, #3 - mov x4, x6 - mov x5, x7 - bl X(ff_hevc_put_hevc_epel_h12_8_neon_i8mm) - ldp x4, x5, [sp, #16] - ldp x0, x1, [sp, #32] - ldp x7, x30, [sp], #48 - b hevc_put_hevc_epel_bi_hv12_8_end_neon -endfunc - function hevc_put_hevc_epel_bi_hv12_8_end_neon load_epel_filterh x7, x6 sub x1, x1, #8 @@ -3940,26 +3880,6 @@ function hevc_put_hevc_epel_bi_hv12_8_end_neon 2: ret endfunc -function ff_hevc_put_hevc_epel_bi_hv16_8_neon_i8mm, export=1 - add w10, w5, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - stp x7, x30, [sp, #-48]! - stp x4, x5, [sp, #16] - stp x0, x1, [sp, #32] - add x0, sp, #48 - sub x1, x2, x3 - mov x2, x3 - add w3, w5, #3 - mov x4, x6 - mov x5, x7 - bl X(ff_hevc_put_hevc_epel_h16_8_neon_i8mm) - ldp x4, x5, [sp, #16] - ldp x0, x1, [sp, #32] - ldp x7, x30, [sp], #48 - b hevc_put_hevc_epel_bi_hv16_8_end_neon -endfunc - function hevc_put_hevc_epel_bi_hv16_8_end_neon load_epel_filterh x7, x6 mov x10, #(MAX_PB_SIZE * 2) @@ -3985,26 +3905,6 @@ function hevc_put_hevc_epel_bi_hv16_8_end_neon 2: ret endfunc -function ff_hevc_put_hevc_epel_bi_hv24_8_neon_i8mm, export=1 - add w10, w5, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - stp x7, x30, [sp, #-48]! - stp x4, x5, [sp, #16] - stp x0, x1, [sp, #32] - add x0, sp, #48 - sub x1, x2, x3 - mov x2, x3 - add w3, w5, #3 - mov x4, x6 - mov x5, x7 - bl X(ff_hevc_put_hevc_epel_h24_8_neon_i8mm) - ldp x4, x5, [sp, #16] - ldp x0, x1, [sp, #32] - ldp x7, x30, [sp], #48 - b hevc_put_hevc_epel_bi_hv24_8_end_neon -endfunc - function hevc_put_hevc_epel_bi_hv24_8_end_neon load_epel_filterh x7, x6 mov x10, #(MAX_PB_SIZE * 2) @@ -4034,27 +3934,6 @@ function hevc_put_hevc_epel_bi_hv24_8_end_neon 2: ret endfunc -function ff_hevc_put_hevc_epel_bi_hv32_8_neon_i8mm, export=1 - str d8, [sp, #-16]! - add w10, w5, #3 - lsl x10, x10, #7 - sub sp, sp, x10 // tmp_array - stp x7, x30, [sp, #-48]! - stp x4, x5, [sp, #16] - stp x0, x1, [sp, #32] - add x0, sp, #48 - sub x1, x2, x3 - mov x2, x3 - add w3, w5, #3 - mov x4, x6 - mov x5, x7 - bl X(ff_hevc_put_hevc_epel_h32_8_neon_i8mm) - ldp x4, x5, [sp, #16] - ldp x0, x1, [sp, #32] - ldp x7, x30, [sp], #48 - b hevc_put_hevc_epel_bi_hv32_8_end_neon -endfunc - function hevc_put_hevc_epel_bi_hv32_8_end_neon load_epel_filterh x7, x6 mov x10, #(MAX_PB_SIZE * 2) @@ -4089,6 +3968,150 @@ function hevc_put_hevc_epel_bi_hv32_8_end_neon ret endfunc +#if HAVE_I8MM +ENABLE_I8MM + +function ff_hevc_put_hevc_epel_bi_hv4_8_neon_i8mm, export=1 + add w10, w5, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + stp x7, x30, [sp, #-48]! + stp x4, x5, [sp, #16] + stp x0, x1, [sp, #32] + add x0, sp, #48 + sub x1, x2, x3 + mov x2, x3 + add w3, w5, #3 + mov x4, x6 + mov x5, x7 + bl X(ff_hevc_put_hevc_epel_h4_8_neon_i8mm) + ldp x4, x5, [sp, #16] + ldp x0, x1, [sp, #32] + ldp x7, x30, [sp], #48 + b hevc_put_hevc_epel_bi_hv4_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_bi_hv6_8_neon_i8mm, export=1 + add w10, w5, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + stp x7, x30, [sp, #-48]! + stp x4, x5, [sp, #16] + stp x0, x1, [sp, #32] + add x0, sp, #48 + sub x1, x2, x3 + mov x2, x3 + add w3, w5, #3 + mov x4, x6 + mov x5, x7 + bl X(ff_hevc_put_hevc_epel_h6_8_neon_i8mm) + ldp x4, x5, [sp, #16] + ldp x0, x1, [sp, #32] + ldp x7, x30, [sp], #48 + b hevc_put_hevc_epel_bi_hv6_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_bi_hv8_8_neon_i8mm, export=1 + add w10, w5, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + stp x7, x30, [sp, #-48]! + stp x4, x5, [sp, #16] + stp x0, x1, [sp, #32] + add x0, sp, #48 + sub x1, x2, x3 + mov x2, x3 + add w3, w5, #3 + mov x4, x6 + mov x5, x7 + bl X(ff_hevc_put_hevc_epel_h8_8_neon_i8mm) + ldp x4, x5, [sp, #16] + ldp x0, x1, [sp, #32] + ldp x7, x30, [sp], #48 + b hevc_put_hevc_epel_bi_hv8_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_bi_hv12_8_neon_i8mm, export=1 + add w10, w5, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + stp x7, x30, [sp, #-48]! + stp x4, x5, [sp, #16] + stp x0, x1, [sp, #32] + add x0, sp, #48 + sub x1, x2, x3 + mov x2, x3 + add w3, w5, #3 + mov x4, x6 + mov x5, x7 + bl X(ff_hevc_put_hevc_epel_h12_8_neon_i8mm) + ldp x4, x5, [sp, #16] + ldp x0, x1, [sp, #32] + ldp x7, x30, [sp], #48 + b hevc_put_hevc_epel_bi_hv12_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_bi_hv16_8_neon_i8mm, export=1 + add w10, w5, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + stp x7, x30, [sp, #-48]! + stp x4, x5, [sp, #16] + stp x0, x1, [sp, #32] + add x0, sp, #48 + sub x1, x2, x3 + mov x2, x3 + add w3, w5, #3 + mov x4, x6 + mov x5, x7 + bl X(ff_hevc_put_hevc_epel_h16_8_neon_i8mm) + ldp x4, x5, [sp, #16] + ldp x0, x1, [sp, #32] + ldp x7, x30, [sp], #48 + b hevc_put_hevc_epel_bi_hv16_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_bi_hv24_8_neon_i8mm, export=1 + add w10, w5, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + stp x7, x30, [sp, #-48]! + stp x4, x5, [sp, #16] + stp x0, x1, [sp, #32] + add x0, sp, #48 + sub x1, x2, x3 + mov x2, x3 + add w3, w5, #3 + mov x4, x6 + mov x5, x7 + bl X(ff_hevc_put_hevc_epel_h24_8_neon_i8mm) + ldp x4, x5, [sp, #16] + ldp x0, x1, [sp, #32] + ldp x7, x30, [sp], #48 + b hevc_put_hevc_epel_bi_hv24_8_end_neon +endfunc + +function ff_hevc_put_hevc_epel_bi_hv32_8_neon_i8mm, export=1 + str d8, [sp, #-16]! + add w10, w5, #3 + lsl x10, x10, #7 + sub sp, sp, x10 // tmp_array + stp x7, x30, [sp, #-48]! + stp x4, x5, [sp, #16] + stp x0, x1, [sp, #32] + add x0, sp, #48 + sub x1, x2, x3 + mov x2, x3 + add w3, w5, #3 + mov x4, x6 + mov x5, x7 + bl X(ff_hevc_put_hevc_epel_h32_8_neon_i8mm) + ldp x4, x5, [sp, #16] + ldp x0, x1, [sp, #32] + ldp x7, x30, [sp], #48 + b hevc_put_hevc_epel_bi_hv32_8_end_neon +endfunc + function ff_hevc_put_hevc_epel_bi_hv48_8_neon_i8mm, export=1 stp x6, x7, [sp, #-80]! stp x4, x5, [sp, #16] -- 2.39.3 (Apple Git-146) _______________________________________________ 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".