From patchwork Mon Oct 9 06:01:20 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: kaustubh.raste@imgtec.com X-Patchwork-Id: 5492 Delivered-To: ffmpegpatchwork@gmail.com Received: by 10.2.161.90 with SMTP id m26csp2292694jah; Sun, 8 Oct 2017 23:00:19 -0700 (PDT) X-Google-Smtp-Source: AOwi7QDcB0D6DUt74LT2knDV/MIEe3LT09mQoIlX6ClHyZ07WMLUiV3yiNr9t7ao8B3V5MRRr9dK X-Received: by 10.28.107.150 with SMTP id a22mr7915225wmi.41.1507528818863; Sun, 08 Oct 2017 23:00:18 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1507528818; cv=none; d=google.com; s=arc-20160816; b=G0es/T8O4M1sOCsD3L1js8mFRiE1gPiPrpoF7Vtv2ecSlfCnUSI/3y67BFuLoNrmjj CBM8+PUTzE2RwHFgw6k4p+Yqwfe5idz3zRip3KWWSW442RaHw32RBe0rYr9Po4tbI3AZ L1XRVJHlZBKyDXrCAO2TKkjoK9yko7AbjdTaHBdk/tG3FdCp7L3bqyQM0BSQd4mMW0Pb CZGaMk8qDTFU9A4HPsvWQyxIbJ9dGXvRtAJOUZBVaID3iH+1XT/HpY0cOq4yrMylQCFL 0Ig37NLeUgUlWVKhk/DUU8XkGdY8rQES/aMJMaHlFHNvuHFE1PYprOT12T+nz9PwloLv ZgvQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:content-transfer-encoding:cc:reply-to :list-subscribe:list-help:list-post:list-archive:list-unsubscribe :list-id:precedence:subject:mime-version:message-id:date:to:from :delivered-to:arc-authentication-results; bh=0oJt0MhAzIgwR03ImZZdDQeTsCTnALM0wrxnzb3otRE=; b=KbaJkxn1ER0bYG+6Qgs5AmxGuMPukeMah6LXzrYif4HfBtSQ/+t3tj2U3vmGg9IPu4 oi0IQUHOHfsnZ1qNQkNIyQCD7t0FzBWBaF9VIDoXaaFwggzY8FNCl/gMDjvf/8FmRm3H 6HGPNEeRlZBkL8TxI9YouUAIEXiC5EqK8wEC6lm9CSUVoAQt89vQ9YKn+skF/JD09neg vW8/oKvrFr2KFMg3yI+pXBAMDIOtSDuQPisoCRVt6xv5TgmuXQs2QJvtLT0+WTWRFBZu Zo8QjQ/cnWPzC+vVKxZF/JzMMvgjzTagOAEcwhbbmNd6Va1tqBeOw12nySm5ZglpII0w 3SIg== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) smtp.mailfrom=ffmpeg-devel-bounces@ffmpeg.org Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org. [79.124.17.100]) by mx.google.com with ESMTP id 67si6096902wmu.32.2017.10.08.23.00.18; Sun, 08 Oct 2017 23:00:18 -0700 (PDT) Received-SPF: pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) client-ip=79.124.17.100; Authentication-Results: mx.google.com; spf=pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) smtp.mailfrom=ffmpeg-devel-bounces@ffmpeg.org Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 0EAF8680646; Mon, 9 Oct 2017 09:00:14 +0300 (EEST) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from mailapp01.imgtec.com (mailapp01.imgtec.com [195.59.15.196]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 5CC3268043D for ; Mon, 9 Oct 2017 09:00:07 +0300 (EEST) Received: from hhmail02.hh.imgtec.org (unknown [10.100.10.20]) by Forcepoint Email with ESMTPS id 779632FE7E230 for ; Mon, 9 Oct 2017 06:59:48 +0100 (IST) Received: from pudesk204.pu.imgtec.org (192.168.91.13) by hhmail02.hh.imgtec.org (10.100.10.20) with Microsoft SMTP Server (TLS) id 14.3.361.1; Mon, 9 Oct 2017 06:59:49 +0100 From: To: Date: Mon, 9 Oct 2017 11:31:20 +0530 Message-ID: <1507528880-4340-1-git-send-email-kaustubh.raste@imgtec.com> X-Mailer: git-send-email 1.7.9.5 MIME-Version: 1.0 X-Originating-IP: [192.168.91.13] Subject: [FFmpeg-devel] [PATCH] avcodec/mips: preload data in hevc sao edge 135 degree filter msa functions X-BeenThere: ffmpeg-devel@ffmpeg.org X-Mailman-Version: 2.1.20 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: Kaustubh Raste Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" From: Kaustubh Raste Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_lpf_sao_msa.c | 194 ++++++++++++++++++++++++------------ 1 file changed, 132 insertions(+), 62 deletions(-) diff --git a/libavcodec/mips/hevc_lpf_sao_msa.c b/libavcodec/mips/hevc_lpf_sao_msa.c index c192265..5b5537a 100644 --- a/libavcodec/mips/hevc_lpf_sao_msa.c +++ b/libavcodec/mips/hevc_lpf_sao_msa.c @@ -2226,23 +2226,24 @@ static void hevc_sao_edge_filter_135degree_4width_msa(uint8_t *dst, int32_t height) { uint8_t *src_orig; - int32_t h_cnt; uint32_t dst_val0, dst_val1; - v8i16 edge_idx = { 1, 2, 0, 3, 4, 0, 0, 0 }; + v16i8 edge_idx = { 1, 2, 0, 3, 4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }; v16u8 const1 = (v16u8) __msa_ldi_b(1); - v16i8 zero = { 0 }; + v16i8 offset, sao_offset = LD_SB(sao_offset_val); v16i8 src_zero0, src_zero1, dst0; v16u8 cmp_minus10, diff_minus10, cmp_minus11, diff_minus11; v16u8 src_minus10, src10, src_minus11, src11; - v8i16 offset_mask0, offset_mask1, sao_offset, src00, src01; + v8i16 offset_mask0, offset_mask1; - sao_offset = LD_SH(sao_offset_val); + sao_offset = __msa_pckev_b(sao_offset, sao_offset); src_orig = src - 1; + /* load in advance */ LD_UB2(src_orig - src_stride, src_stride, src_minus10, src_minus11); + LD_UB2(src_orig + src_stride, src_stride, src10, src11); - for (h_cnt = (height >> 1); h_cnt--;) { - LD_UB2(src_orig + src_stride, src_stride, src10, src11); + for (height -= 2; height; height -= 2) { + src_orig += (src_stride << 1); SLDI_B2_0_SB(src_minus11, src10, src_zero0, src_zero1, 1); SLDI_B2_0_UB(src_minus10, src_minus11, src_minus10, src_minus11, 2); @@ -2265,19 +2266,22 @@ static void hevc_sao_edge_filter_135degree_4width_msa(uint8_t *dst, offset_mask0 = (v8i16) (__msa_hadd_u_h(diff_minus10, diff_minus10) + 2); offset_mask1 = (v8i16) (__msa_hadd_u_h(diff_minus11, diff_minus11) + 2); - VSHF_H2_SH(edge_idx, edge_idx, sao_offset, sao_offset, offset_mask0, - offset_mask0, offset_mask0, offset_mask0); - VSHF_H2_SH(edge_idx, edge_idx, sao_offset, sao_offset, offset_mask1, - offset_mask1, offset_mask1, offset_mask1); - ILVEV_B2_SH(src_zero0, zero, src_zero1, zero, src00, src01); - ADD2(offset_mask0, src00, offset_mask1, src01, offset_mask0, - offset_mask1); - CLIP_SH2_0_255(offset_mask0, offset_mask1); - dst0 = __msa_pckev_b((v16i8) offset_mask1, (v16i8) offset_mask0); + offset = __msa_pckev_b((v16i8) offset_mask1, (v16i8) offset_mask0); + dst0 = __msa_pckev_b((v16i8) src_zero1, (v16i8) src_zero0); + + VSHF_B2_SB(edge_idx, edge_idx, sao_offset, sao_offset, offset, offset, + offset, offset); + + dst0 = (v16i8) __msa_xori_b((v16u8) dst0, 128); + dst0 = __msa_adds_s_b(dst0, offset); + dst0 = (v16i8) __msa_xori_b((v16u8) dst0, 128); src_minus10 = src10; src_minus11 = src11; + /* load in advance */ + LD_UB2(src_orig + src_stride, src_stride, src10, src11); + dst_val0 = __msa_copy_u_w((v4i32) dst0, 0); dst_val1 = __msa_copy_u_w((v4i32) dst0, 2); @@ -2286,8 +2290,46 @@ static void hevc_sao_edge_filter_135degree_4width_msa(uint8_t *dst, SW(dst_val1, dst); dst += dst_stride; - src_orig += (src_stride << 1); } + + SLDI_B2_0_SB(src_minus11, src10, src_zero0, src_zero1, 1); + SLDI_B2_0_UB(src_minus10, src_minus11, src_minus10, src_minus11, 2); + + ILVR_B2_UB(src10, src_minus10, src11, src_minus11, src_minus10, + src_minus11); + ILVR_B2_SB(src_zero0, src_zero0, src_zero1, src_zero1, src_zero0, + src_zero1); + + cmp_minus10 = ((v16u8) src_zero0 == src_minus10); + diff_minus10 = __msa_nor_v(cmp_minus10, cmp_minus10); + cmp_minus10 = (src_minus10 < (v16u8) src_zero0); + diff_minus10 = __msa_bmnz_v(diff_minus10, const1, cmp_minus10); + + cmp_minus11 = ((v16u8) src_zero1 == src_minus11); + diff_minus11 = __msa_nor_v(cmp_minus11, cmp_minus11); + cmp_minus11 = (src_minus11 < (v16u8) src_zero1); + diff_minus11 = __msa_bmnz_v(diff_minus11, const1, cmp_minus11); + + offset_mask0 = (v8i16) (__msa_hadd_u_h(diff_minus10, diff_minus10) + 2); + offset_mask1 = (v8i16) (__msa_hadd_u_h(diff_minus11, diff_minus11) + 2); + + offset = __msa_pckev_b((v16i8) offset_mask1, (v16i8) offset_mask0); + dst0 = __msa_pckev_b((v16i8) src_zero1, (v16i8) src_zero0); + + VSHF_B2_SB(edge_idx, edge_idx, sao_offset, sao_offset, offset, offset, + offset, offset); + + dst0 = (v16i8) __msa_xori_b((v16u8) dst0, 128); + dst0 = __msa_adds_s_b(dst0, offset); + dst0 = (v16i8) __msa_xori_b((v16u8) dst0, 128); + + dst_val0 = __msa_copy_u_w((v4i32) dst0, 0); + dst_val1 = __msa_copy_u_w((v4i32) dst0, 2); + + SW(dst_val0, dst); + dst += dst_stride; + SW(dst_val1, dst); + dst += dst_stride; } static void hevc_sao_edge_filter_135degree_8width_msa(uint8_t *dst, @@ -2298,23 +2340,24 @@ static void hevc_sao_edge_filter_135degree_8width_msa(uint8_t *dst, int32_t height) { uint8_t *src_orig; - int32_t h_cnt; uint64_t dst_val0, dst_val1; - v8i16 edge_idx = { 1, 2, 0, 3, 4, 0, 0, 0 }; + v16i8 edge_idx = { 1, 2, 0, 3, 4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }; v16u8 const1 = (v16u8) __msa_ldi_b(1); - v16i8 zero = { 0 }; - v16i8 src_zero0, src_zero1, dst0, dst1; + v16i8 offset, sao_offset = LD_SB(sao_offset_val); v16u8 cmp_minus10, diff_minus10, cmp_minus11, diff_minus11; v16u8 src_minus10, src10, src_minus11, src11; - v8i16 sao_offset, src00, offset_mask0, src01, offset_mask1; + v16i8 src_zero0, src_zero1, dst0; + v8i16 offset_mask0, offset_mask1; - sao_offset = LD_SH(sao_offset_val); + sao_offset = __msa_pckev_b(sao_offset, sao_offset); src_orig = src - 1; + /* load in advance */ LD_UB2(src_orig - src_stride, src_stride, src_minus10, src_minus11); + LD_UB2(src_orig + src_stride, src_stride, src10, src11); - for (h_cnt = (height >> 1); h_cnt--;) { - LD_UB2(src_orig + src_stride, src_stride, src10, src11); + for (height -= 2; height; height -= 2) { + src_orig += (src_stride << 1); SLDI_B2_0_SB(src_minus11, src10, src_zero0, src_zero1, 1); SLDI_B2_0_UB(src_minus10, src_minus11, src_minus10, src_minus11, 2); @@ -2336,30 +2379,68 @@ static void hevc_sao_edge_filter_135degree_8width_msa(uint8_t *dst, offset_mask0 = (v8i16) (__msa_hadd_u_h(diff_minus10, diff_minus10) + 2); offset_mask1 = (v8i16) (__msa_hadd_u_h(diff_minus11, diff_minus11) + 2); - VSHF_H2_SH(edge_idx, edge_idx, sao_offset, sao_offset, offset_mask0, - offset_mask0, offset_mask0, offset_mask0); - VSHF_H2_SH(edge_idx, edge_idx, sao_offset, sao_offset, offset_mask1, - offset_mask1, offset_mask1, offset_mask1); - ILVEV_B2_SH(src_zero0, zero, src_zero1, zero, src00, src01); - ADD2(offset_mask0, src00, offset_mask1, src01, offset_mask0, - offset_mask1); - CLIP_SH2_0_255(offset_mask0, offset_mask1); - PCKEV_B2_SB(offset_mask0, offset_mask0, offset_mask1, offset_mask1, - dst0, dst1); + offset = __msa_pckev_b((v16i8) offset_mask1, (v16i8) offset_mask0); + dst0 = __msa_pckev_b((v16i8) src_zero1, (v16i8) src_zero0); + + VSHF_B2_SB(edge_idx, edge_idx, sao_offset, sao_offset, offset, offset, + offset, offset); + + dst0 = (v16i8) __msa_xori_b((v16u8) dst0, 128); + dst0 = __msa_adds_s_b(dst0, offset); + dst0 = (v16i8) __msa_xori_b((v16u8) dst0, 128); src_minus10 = src10; src_minus11 = src11; + /* load in advance */ + LD_UB2(src_orig + src_stride, src_stride, src10, src11); + dst_val0 = __msa_copy_u_d((v2i64) dst0, 0); - dst_val1 = __msa_copy_u_d((v2i64) dst1, 0); + dst_val1 = __msa_copy_u_d((v2i64) dst0, 1); SD(dst_val0, dst); dst += dst_stride; SD(dst_val1, dst); dst += dst_stride; - - src_orig += (src_stride << 1); } + + SLDI_B2_0_SB(src_minus11, src10, src_zero0, src_zero1, 1); + SLDI_B2_0_UB(src_minus10, src_minus11, src_minus10, src_minus11, 2); + ILVR_B2_UB(src10, src_minus10, src11, src_minus11, src_minus10, + src_minus11); + ILVR_B2_SB(src_zero0, src_zero0, src_zero1, src_zero1, src_zero0, + src_zero1); + + cmp_minus10 = ((v16u8) src_zero0 == src_minus10); + diff_minus10 = __msa_nor_v(cmp_minus10, cmp_minus10); + cmp_minus10 = (src_minus10 < (v16u8) src_zero0); + diff_minus10 = __msa_bmnz_v(diff_minus10, const1, cmp_minus10); + + cmp_minus11 = ((v16u8) src_zero1 == src_minus11); + diff_minus11 = __msa_nor_v(cmp_minus11, cmp_minus11); + cmp_minus11 = (src_minus11 < (v16u8) src_zero1); + diff_minus11 = __msa_bmnz_v(diff_minus11, const1, cmp_minus11); + + offset_mask0 = (v8i16) (__msa_hadd_u_h(diff_minus10, diff_minus10) + 2); + offset_mask1 = (v8i16) (__msa_hadd_u_h(diff_minus11, diff_minus11) + 2); + + offset = __msa_pckev_b((v16i8) offset_mask1, (v16i8) offset_mask0); + dst0 = __msa_pckev_b((v16i8) src_zero1, (v16i8) src_zero0); + + VSHF_B2_SB(edge_idx, edge_idx, sao_offset, sao_offset, offset, offset, + offset, offset); + + dst0 = (v16i8) __msa_xori_b((v16u8) dst0, 128); + dst0 = __msa_adds_s_b(dst0, offset); + dst0 = (v16i8) __msa_xori_b((v16u8) dst0, 128); + + dst_val0 = __msa_copy_u_d((v2i64) dst0, 0); + dst_val1 = __msa_copy_u_d((v2i64) dst0, 1); + + SD(dst_val0, dst); + dst += dst_stride; + SD(dst_val1, dst); + dst += dst_stride; } static void hevc_sao_edge_filter_135degree_16multiple_msa(uint8_t *dst, @@ -2372,7 +2453,7 @@ static void hevc_sao_edge_filter_135degree_16multiple_msa(uint8_t *dst, int32_t height) { uint8_t *src_orig, *dst_orig; - int32_t h_cnt, v_cnt; + int32_t v_cnt; v16i8 edge_idx = { 1, 2, 0, 3, 4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }; v16u8 const1 = (v16u8) __msa_ldi_b(1); v16u8 dst0, dst1, dst2, dst3; @@ -2383,20 +2464,18 @@ static void hevc_sao_edge_filter_135degree_16multiple_msa(uint8_t *dst, v16u8 src_plus10, src_plus11, src_plus12, src_plus13; v16i8 src_minus12, src_minus13, src_zero0, src_zero1, src_zero2, src_zero3; v16i8 offset_mask0, offset_mask1, offset_mask2, offset_mask3, sao_offset; - v8i16 src0, src1, src2, src3, src4, src5, src6, src7; - v8i16 temp0, temp1, temp2, temp3, temp4, temp5, temp6, temp7; sao_offset = LD_SB(sao_offset_val); sao_offset = __msa_pckev_b(sao_offset, sao_offset); - for (h_cnt = (height >> 2); h_cnt--;) { + for (; height; height -= 4) { src_orig = src - 1; dst_orig = dst; - LD_UB4(src_orig, src_stride, - src_minus11, src_plus10, src_plus11, src_plus12); + LD_UB4(src_orig, src_stride, src_minus11, src_plus10, src_plus11, + src_plus12); - for (v_cnt = 0; v_cnt < (width >> 4); v_cnt++) { + for (v_cnt = 0; v_cnt < width; v_cnt += 16) { src_minus10 = LD_UB(src_orig + 2 - src_stride); LD_UB4(src_orig + 16, src_stride, src10, src11, src12, src13); src_plus13 = LD_UB(src_orig + (src_stride << 2)); @@ -2463,23 +2542,14 @@ static void hevc_sao_edge_filter_135degree_16multiple_msa(uint8_t *dst, VSHF_B2_SB(edge_idx, edge_idx, sao_offset, sao_offset, offset_mask3, offset_mask3, offset_mask3, offset_mask3); - UNPCK_UB_SH(src_zero0, src0, src1); - UNPCK_SB_SH(offset_mask0, temp0, temp1); - UNPCK_UB_SH(src_zero1, src2, src3); - UNPCK_SB_SH(offset_mask1, temp2, temp3); - UNPCK_UB_SH(src_zero2, src4, src5); - UNPCK_SB_SH(offset_mask2, temp4, temp5); - UNPCK_UB_SH(src_zero3, src6, src7); - UNPCK_SB_SH(offset_mask3, temp6, temp7); - - ADD4(temp0, src0, temp1, src1, temp2, src2, temp3, src3, temp0, - temp1, temp2, temp3); - ADD4(temp4, src4, temp5, src5, temp6, src6, temp7, src7, temp4, - temp5, temp6, temp7); - CLIP_SH4_0_255(temp0, temp1, temp2, temp3); - CLIP_SH4_0_255(temp4, temp5, temp6, temp7); - PCKEV_B4_UB(temp1, temp0, temp3, temp2, temp5, temp4, temp7, temp6, - dst0, dst1, dst2, dst3); + XORI_B4_128_SB(src_zero0, src_zero1, src_zero2, src_zero3); + + dst0 = (v16u8) __msa_adds_s_b((v16i8) src_zero0, offset_mask0); + dst1 = (v16u8) __msa_adds_s_b((v16i8) src_zero1, offset_mask1); + dst2 = (v16u8) __msa_adds_s_b((v16i8) src_zero2, offset_mask2); + dst3 = (v16u8) __msa_adds_s_b((v16i8) src_zero3, offset_mask3); + + XORI_B4_128_UB(dst0, dst1, dst2, dst3); src_minus11 = src10; src_plus10 = src11;