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 7243C4ADE6 for ; Mon, 24 Jun 2024 11:37:50 +0000 (UTC) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 221E368D62E; Mon, 24 Jun 2024 14:37:29 +0300 (EEST) Received: from out203-205-221-236.mail.qq.com (out203-205-221-236.mail.qq.com [203.205.221.236]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id EA2FA68D5D2 for ; Mon, 24 Jun 2024 14:37:18 +0300 (EEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=foxmail.com; s=s201512; t=1719229029; bh=/iGVJt5I+DiDIVip4gouw18Bfj3JgI92LjXcvJTojTc=; h=From:To:Cc:Subject:Date:In-Reply-To:References; b=S/XTcPQp4WyCSZ51v7/2PTPfURu19MlynElfLQNF8ZTsg/wZM59Qiz3ixjJfhI645 hAeWTkm04qJr0FhVRUqMv0hppVlkN2AqcDr4sZfWw/m8pzQGhYvq2O5m4bnpoEq+aH z6aruciTFN7/IWzXjlQktblnacsbKSpt7s+xwj4k= Received: from ZHILIZHAO-MB1.tencent.com ([119.147.10.191]) by newxmesmtplogicsvrszb9-1.qq.com (NewEsmtp) with SMTP id 9438A032; Mon, 24 Jun 2024 19:37:03 +0800 X-QQ-mid: xmsmtpt1719229027tcnxwvj1a Message-ID: X-QQ-XMAILINFO: NvH2zBBgt3uTwffz0RAPyBC6By0CLoM6HdUanZVJYkL8YiShQ9i94HAzaZPpJB 2YerpdvIzqtj3Q0YGrcVz33JXPHuc1ODs+RRFWhjW4LOOKEhPmdUco0MBg/enIgW0IS+6j4MTS2O 0rxtVbl4TnC1Gwe/S0K/TtbxWs5bYSs5rxNiZ9Eu1ZFknePqmPBqt912Xs226vlddBr03YgP2voY nRU4MUmkYIjOIMf9B79bYm67DEBEfqSmivN2DGG2DfpWi+zndPdjIN+jenUJisVv7dbn2J7N7iLR a/XFDHn6E04115lk9gqc4ee79U4UjUdZCh6euBehVKhXhFl+6sovbocCMR5ZEBgemv8hjj96hw9z r63jYlK/319zvKY2rJhkeSgrDdWJX2eGhuIy9V/5xIdjIksickvdg8BzXCdLQuAY4MCfw1OpFV9X MW5neTdoiu4OG8o/VvQv85k81p4s4zQzbmmc8uJ4jrpUWQ9So6bGFiuFyI2nWEIfHzwKqS+NwEoN aU9aF5s6FVq3xwNfAMY+G4u8lFdKPanD63iqvDN1iq1K3AuDmHrABC74j1ZHvpFepnedWvwbM3FA nlUeCHKTtmTDxdZpYu2Fjq7aqRTXQPpA8mDJ8LEL4PBBwHBec2NE9tBfXsRrEFkpwS1nisQYRc7b x3mzdqQfzZK8fyyHrNrcQE8m5AlEdfhnUSonuUoXkUTD6/MA/2j9m/EDcMsXTrb1pY3g3GViYPGq XgChjR/N8b8U7FxH0sx+OPuuhstocyv1bkJT4MC2Lo87AVkcvslbO9+KZ58OKSEepamESPV/WWgs cFPT1nBjgdpzKimvg93hTEn2QPgA46vY8FVqqSpsC7r1mnL7nesmvy55BzG9F7W8Clq/bQjgbTkm Hc35xFhs16H3defTfkQTzm+oKN+71C+92CVp08U62SZ6+dWFkWY3uGcwAarzQ23qsbfuh+gIDxu1 Je92/X1PCW96mtAEgWPOpEEW/6yXfYCP+vndxCKZz/2kXVRgkrsNViZhpx30UIodkuN45gJGA= X-QQ-XMRINFO: OD9hHCdaPRBwq3WW+NvGbIU= From: Zhao Zhili To: ffmpeg-devel@ffmpeg.org Date: Mon, 24 Jun 2024 19:37:01 +0800 X-OQ-MSGID: <20240624113701.94616-3-quinkblack@foxmail.com> X-Mailer: git-send-email 2.42.0 In-Reply-To: <20240624113701.94616-1-quinkblack@foxmail.com> References: <20240624113701.94616-1-quinkblack@foxmail.com> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH v3 3/3] swscale/aarch64: Add argb/abgr to yuv 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: Zhao Zhili 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: From: Zhao Zhili Test on Apple M1 with kperf: : -O3 : -O3 -fno-vectorize abgr_to_uv_8_c : 19.4 : 26.1 abgr_to_uv_8_neon : 29.9 : 51.1 abgr_to_uv_128_c : 146.4 : 558.9 abgr_to_uv_128_neon : 85.1 : 83.4 abgr_to_uv_1080_c : 1162.6 : 4786.4 abgr_to_uv_1080_neon : 819.6 : 826.6 abgr_to_uv_1920_c : 2063.6 : 8492.1 abgr_to_uv_1920_neon : 1435.1 : 1447.1 abgr_to_uv_half_8_c : 16.4 : 11.4 abgr_to_uv_half_8_neon : 35.6 : 20.4 abgr_to_uv_half_128_c : 108.6 : 359.4 abgr_to_uv_half_128_neon : 75.4 : 42.6 abgr_to_uv_half_1080_c : 883.4 : 2885.6 abgr_to_uv_half_1080_neon : 460.6 : 481.1 abgr_to_uv_half_1920_c : 1553.6 : 5106.9 abgr_to_uv_half_1920_neon : 817.6 : 820.4 abgr_to_y_8_c : 6.1 : 26.4 abgr_to_y_8_neon : 40.6 : 6.4 abgr_to_y_128_c : 99.9 : 390.1 abgr_to_y_128_neon : 67.4 : 55.9 abgr_to_y_1080_c : 735.9 : 3170.4 abgr_to_y_1080_neon : 534.6 : 536.6 abgr_to_y_1920_c : 1279.4 : 6016.4 abgr_to_y_1920_neon : 932.6 : 927.6 --- libswscale/aarch64/input.S | 114 ++++++++++++++++++++++++++++------- libswscale/aarch64/swscale.c | 17 ++++++ 2 files changed, 110 insertions(+), 21 deletions(-) diff --git a/libswscale/aarch64/input.S b/libswscale/aarch64/input.S index 6d2c6034bb..f4d587fed0 100644 --- a/libswscale/aarch64/input.S +++ b/libswscale/aarch64/input.S @@ -34,6 +34,16 @@ uxtl2 v24.8h, v18.16b // v24: b .endm +.macro argb_to_yuv_load_rgb src + ld4 { v16.16b, v17.16b, v18.16b, v19.16b }, [\src] + uxtl v21.8h, v19.8b // v21: b + uxtl2 v24.8h, v19.16b // v24: b + uxtl v19.8h, v17.8b // v19: r + uxtl v20.8h, v18.8b // v20: g + uxtl2 v22.8h, v17.16b // v22: r + uxtl2 v23.8h, v18.16b // v23: g +.endm + .macro rgb_to_yuv_product r, g, b, dst1, dst2, dst, coef0, coef1, coef2, right_shift mov \dst1\().16b, v6.16b // dst1 = const_offset mov \dst2\().16b, v6.16b // dst2 = const_offset @@ -55,7 +65,7 @@ function ff_bgr24ToY_neon, export=1 ret endfunc -.macro rgbToY_neon fmt, element +.macro rgbToY_neon fmt, element, alpha_first=0 function ff_\fmt\()ToY_neon, export=1 cmp w4, #0 // check width > 0 ldp w10, w11, [x5] // w10: ry, w11: gy @@ -72,7 +82,11 @@ function ff_\fmt\()ToY_neon, export=1 dup v2.8h, w12 b.lt 2f 1: + .if \alpha_first + argb_to_yuv_load_rgb x1 + .else rgb_to_yuv_load_rgb x1, \element + .endif rgb_to_yuv_product v19, v20, v21, v25, v26, v16, v0, v1, v2, #9 rgb_to_yuv_product v22, v23, v24, v27, v28, v17, v0, v1, v2, #9 sub w4, w4, #16 // width -= 16 @@ -82,9 +96,15 @@ function ff_\fmt\()ToY_neon, export=1 b.ge 1b cbz x4, 3f 2: + .if \alpha_first + ldrb w13, [x1, #1] // w13: r + ldrb w14, [x1, #2] // w14: g + ldrb w15, [x1, #3] // w15: b + .else ldrb w13, [x1] // w13: r ldrb w14, [x1, #1] // w14: g ldrb w15, [x1, #2] // w15: b + .endif smaddl x13, w13, w10, x9 // x13 = ry * r + const_offset smaddl x13, w14, w11, x13 // x13 += gy * g @@ -101,6 +121,16 @@ endfunc rgbToY_neon fmt=rgb24, element=3 +function ff_abgr32ToY_neon, export=1 + cmp w4, #0 // check width > 0 + ldp w12, w11, [x5] // w12: ry, w11: gy + ldr w10, [x5, #8] // w10: by + b.gt 4f + ret +endfunc + +rgbToY_neon fmt=argb32, element=4, alpha_first=1 + function ff_bgra32ToY_neon, export=1 cmp w4, #0 // check width > 0 ldp w12, w11, [x5] // w12: ry, w11: gy @@ -138,7 +168,21 @@ function ff_bgr24ToUV_half_neon, export=1 b 4f endfunc -.macro rgbToUV_half_neon fmt, element +.macro rgb_load_add_half off_r1, off_r2, off_g1, off_g2, off_b1, off_b2 + ldrb w2, [x3, #\off_r1] // w2: r1 + ldrb w4, [x3, #\off_r2] // w4: r2 + add w2, w2, w4 // w2 = r1 + r2 + + ldrb w4, [x3, #\off_g1] // w4: g1 + ldrb w7, [x3, #\off_g2] // w7: g2 + add w4, w4, w7 // w4 = g1 + g2 + + ldrb w7, [x3, #\off_b1] // w7: b1 + ldrb w8, [x3, #\off_b2] // w8: b2 + add w7, w7, w8 // w7 = b1 + b2 +.endm + +.macro rgbToUV_half_neon fmt, element, alpha_first=0 function ff_\fmt\()ToUV_half_neon, export=1 cmp w5, #0 // check width > 0 b.le 3f @@ -156,9 +200,15 @@ function ff_\fmt\()ToUV_half_neon, export=1 .else ld4 { v16.16b, v17.16b, v18.16b, v19.16b }, [x3] .endif + .if \alpha_first + uaddlp v21.8h, v19.16b + uaddlp v20.8h, v18.16b + uaddlp v19.8h, v17.16b + .else uaddlp v19.8h, v16.16b // v19: r uaddlp v20.8h, v17.16b // v20: g uaddlp v21.8h, v18.16b // v21: b + .endif rgb_to_yuv_product v19, v20, v21, v22, v23, v16, v0, v1, v2, #10 rgb_to_yuv_product v19, v20, v21, v24, v25, v17, v3, v4, v5, #10 @@ -170,27 +220,15 @@ function ff_\fmt\()ToUV_half_neon, export=1 b.ge 1b cbz w5, 3f 2: - ldrb w2, [x3] // w2: r1 - ldrb w4, [x3, #\element] // w4: r2 - add w2, w2, w4 // w2 = r1 + r2 - +.if \alpha_first + rgb_load_add_half 1, 5, 2, 6, 3, 7 +.else .if \element == 3 - ldrb w4, [x3, #1] // w4: g1 - ldrb w7, [x3, #4] // w7: g2 - add w4, w4, w7 // w4 = g1 + g2 - - ldrb w7, [x3, #2] // w7: b1 - ldrb w8, [x3, #5] // w8: b2 - add w7, w7, w8 // w7 = b1 + b2 + rgb_load_add_half 0, 3, 1, 4, 2, 5 .else - ldrb w4, [x3, #1] // w4: g1 - ldrb w7, [x3, #5] // w7: g2 - add w4, w4, w7 // w4 = g1 + g2 - - ldrb w7, [x3, #2] // w7: b1 - ldrb w8, [x3, #6] // w8: b2 - add w7, w7, w8 // w7 = b1 + b2 + rgb_load_add_half 0, 4, 1, 5, 2, 6 .endif +.endif smaddl x8, w2, w10, x9 // dst_u = ru * r + const_offset smaddl x8, w4, w11, x8 // dst_u += gu * g @@ -214,6 +252,18 @@ endfunc rgbToUV_half_neon fmt=rgb24, element=3 +function ff_abgr32ToUV_half_neon, export=1 + cmp w5, #0 // check width > 0 + b.le 3f + + ldp w12, w11, [x6, #12] + ldp w10, w15, [x6, #20] + ldp w14, w13, [x6, #28] + b 4f +endfunc + +rgbToUV_half_neon fmt=argb32, element=4, alpha_first=1 + function ff_bgra32ToUV_half_neon, export=1 cmp w5, #0 // check width > 0 b.le 3f @@ -236,7 +286,7 @@ function ff_bgr24ToUV_neon, export=1 b 4f endfunc -.macro rgbToUV_neon fmt, element +.macro rgbToUV_neon fmt, element, alpha_first=0 function ff_\fmt\()ToUV_neon, export=1 cmp w5, #0 // check width > 0 b.le 3f @@ -249,7 +299,11 @@ function ff_\fmt\()ToUV_neon, export=1 rgb_set_uv_coeff half=0 b.lt 2f 1: + .if \alpha_first + argb_to_yuv_load_rgb x3 + .else rgb_to_yuv_load_rgb x3, \element + .endif rgb_to_yuv_product v19, v20, v21, v25, v26, v16, v0, v1, v2, #9 rgb_to_yuv_product v22, v23, v24, v27, v28, v17, v0, v1, v2, #9 rgb_to_yuv_product v19, v20, v21, v25, v26, v18, v3, v4, v5, #9 @@ -262,9 +316,15 @@ function ff_\fmt\()ToUV_neon, export=1 b.ge 1b cbz w5, 3f 2: + .if \alpha_first + ldrb w16, [x3, #1] // w16: r + ldrb w17, [x3, #2] // w17: g + ldrb w4, [x3, #3] // w4: b + .else ldrb w16, [x3] // w16: r ldrb w17, [x3, #1] // w17: g ldrb w4, [x3, #2] // w4: b + .endif smaddl x8, w16, w10, x9 // x8 = ru * r + const_offset smaddl x8, w17, w11, x8 // x8 += gu * g @@ -287,6 +347,18 @@ endfunc rgbToUV_neon fmt=rgb24, element=3 +function ff_abgr32ToUV_neon, export=1 + cmp w5, #0 // check width > 0 + b.le 3f + + ldp w12, w11, [x6, #12] + ldp w10, w15, [x6, #20] + ldp w14, w13, [x6, #28] + b 4f +endfunc + +rgbToUV_neon fmt=argb32, element=4, alpha_first=1 + function ff_bgra32ToUV_neon, export=1 cmp w5, #0 // check width > 0 b.le 3f diff --git a/libswscale/aarch64/swscale.c b/libswscale/aarch64/swscale.c index 92af662014..eb907284e7 100644 --- a/libswscale/aarch64/swscale.c +++ b/libswscale/aarch64/swscale.c @@ -211,6 +211,8 @@ void ff_##name##ToUV_half_neon(uint8_t *, uint8_t *, const uint8_t *, \ const uint8_t *, const uint8_t *, int w, \ uint32_t *coeffs, void *) +NEON_INPUT(abgr32); +NEON_INPUT(argb32); NEON_INPUT(bgr24); NEON_INPUT(bgra32); NEON_INPUT(rgb24); @@ -248,6 +250,21 @@ av_cold void ff_sws_init_swscale_aarch64(SwsContext *c) c->yuv2planeX = ff_yuv2planeX_8_neon; } switch (c->srcFormat) { + case AV_PIX_FMT_ABGR: + c->lumToYV12 = ff_abgr32ToY_neon; + if (c->chrSrcHSubSample) + c->chrToYV12 = ff_abgr32ToUV_half_neon; + else + c->chrToYV12 = ff_abgr32ToUV_neon; + break; + + case AV_PIX_FMT_ARGB: + c->lumToYV12 = ff_argb32ToY_neon; + if (c->chrSrcHSubSample) + c->chrToYV12 = ff_argb32ToUV_half_neon; + else + c->chrToYV12 = ff_argb32ToUV_neon; + break; case AV_PIX_FMT_BGR24: c->lumToYV12 = ff_bgr24ToY_neon; if (c->chrSrcHSubSample) -- 2.42.0 _______________________________________________ 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".