From patchwork Tue Sep 4 08:05:33 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Shiyou Yin X-Patchwork-Id: 10227 Delivered-To: ffmpegpatchwork@gmail.com Received: by 2002:a02:12c4:0:0:0:0:0 with SMTP id 65-v6csp3583132jap; Tue, 4 Sep 2018 01:05:49 -0700 (PDT) X-Google-Smtp-Source: ANB0VdbJLbKD375rxsbPd9Vo+zYk+Ra+X5HaM+qQlfxqwcXJc/Nz3wjFqN9W/V27WqvcAfi1M9Ep X-Received: by 2002:a5d:4d52:: with SMTP id a18-v6mr21769786wru.40.1536048348995; Tue, 04 Sep 2018 01:05:48 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1536048348; cv=none; d=google.com; s=arc-20160816; b=HpJBcpUkqIpohsEHCZ6Q5esizb0600zU2beUxTvqiemqnhGcnmFuQ0qQhlg6IklSc6 /51QsHCTmWvzjl6Pgz6VwP8YV/Pt11EfVJDNENSVdjAFuLf45qOtRNEOzXkKDpZlmIA/ gePQ/1o1dVjW9GmMA5Q/VymTVeaSBmG26JPNjHYLWq2V+eJ0XrdvcPVXc8LRtL14DxC3 1zOPZEEJHvDWsAfyH1WtVZ/NmWsunE+Gp1bDD4CeI+Gv5kOr6uXBOPmRI7HJjTBcBngf saduzfc2Gawge9PqKQwPk6LXJc330nFtV3JS8sNZmldcRn7UT9XrVmJaXqxNjNPoO7H8 ZVbg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:content-transfer-encoding:mime-version:reply-to :list-subscribe:list-help:list-post:list-archive:list-unsubscribe :list-id:precedence:subject:message-id:date:to:from:delivered-to :arc-authentication-results; bh=sX8JQig4IK5bQjkh+DJVoCiFIp+2KuCPllrnAiE0XX4=; b=tus8N8EqwLHw4EpOcPB3V55HAJgdzXoUWRk2Nx4DXU4FBzG+2ypyXlM3O0i9U558MZ I1CTrY+qW/XFc+TSC8NhaJASS9rOyxdKc9aHIzWQoRrSTcMjjRhWDNXbxjiwZUYX6OZ5 K56mMsIPPQcZlWFbsNCuH5cgRT1hoBXI2Gt4yMUxnazm0rIbS8kvGugQKZ7GrBFU8LpE RqRASiOvvI4Z7lWAOCXPeePQyHh0Tj/TXJ1o2fi/RqIyp11QkuA3jaGTMGaWSFsXFx4L zxvGlh3e4LfFHDUfeW/IEXy3hBe1AttdPFsaklmtG/H1AvB+G6ZxyQ2yNmrBLoCI8/Xg UG8A== 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 t14-v6si10624799wmt.161.2018.09.04.01.05.47; Tue, 04 Sep 2018 01:05:48 -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 BC0CB689DF7; Tue, 4 Sep 2018 11:05:39 +0300 (EEST) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from mail.loongson.cn (mail.loongson.cn [114.242.206.163]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 971276806CC for ; Tue, 4 Sep 2018 11:05:31 +0300 (EEST) Received: from localhost (unknown [210.45.123.188]) by mail (Coremail) with SMTP id QMiowPCxaeSyPI5bm74MAA--.56407S3; Tue, 04 Sep 2018 16:05:06 +0800 (CST) From: Shiyou Yin To: ffmpeg-devel@ffmpeg.org Date: Tue, 4 Sep 2018 16:05:33 +0800 Message-Id: <1536048333-17991-1-git-send-email-yinshiyou-hf@loongson.cn> X-Mailer: git-send-email 2.1.0 X-CM-TRANSID: QMiowPCxaeSyPI5bm74MAA--.56407S3 X-Coremail-Antispam: 1UD129KBjvJXoW3uw43CrWxtFW7CF43tw17Awb_yoWkAr4Dpa y8Arn5Z3ZF9F45Xa17Jw1UCFy3Zr4vyr4Sk34qgF10v395tFn7Xr4xGr93GrWYka4ayF4D JF1UAa4Sk3s8GF7anT9S1TB71UUUUU7qnTZGkaVYY2UrUUUUjbIjqfuFe4nvWSU5nxnvy2 9KBjDU0xBIdaVrnRJUUUkmb4IE77IF4wAFF20E14v26r1j6r4UM7CY07I20VC2zVCF04k2 6cxKx2IYs7xG6rWj6s0DM7CIcVAFz4kK6r1j6r18M28lY4IEw2IIxxk0rwA2F7IY1VAKz4 vEj48ve4kI8wA2z4x0Y4vE2Ix0cI8IcVAFwI0_Gr0_Xr1l84ACjcxK6xIIjxv20xvEc7Cj xVAFwI0_Cr0_Gr1UM28EF7xvwVC2z280aVAFwI0_Gr1j6F4UJwA2z4x0Y4vEx4A2jsIEc7 CjxVAFwI0_Cr1j6rxdM2AIxVAIcxkEcVAq07x20xvEncxIr21l5I8CrVACY4xI64kE6c02 F40Ex7xfMcIj6xIIjxv20xvE14v26r106r15McIj6I8E87Iv67AKxVWUJVW8JwAm72CE4I kC6x0Yz7v_Jr0_Gr1lF7xvr2IYc2Ij64vIr41lF7xvr2IYc2Ij64vIr40E4x8a64kEw24l c2xSY4AK67AK6r43MxAIw28IcxkI7VAKI48JMxC20s026xCaFVCjc4AY6r1j6r4UMI8I3I 0E5I8CrVAFwI0_Jr0_Jr4lx2IqxVCjr7xvwVAFwI0_JrI_JrWlx4CE17CEb7AF67AKxVWU JVWUXwCI42IY6xIIjxv20xvE14v26r1j6r1xMIIF0xvE2Ix0cI8IcVCY1x0267AKxVWUJV W8JwCI42IY6xAIw20EY4v20xvaj40_Wr1j6rW3Jr1lIxAIcVC2z280aVAFwI0_Jr0_Gr1l IxAIcVC2z280aVCY1x0267AKxVWUJVW8JbIYCTnIWIevJa73UjIFyTuYvjxUcjXdUUUUU X-CM-SenderInfo: p1lq2x5l1r3gtki6z05rqj20fqof0/ Subject: [FFmpeg-devel] [PATCH] avcodec/mips: [loongson] simplify the usage of intermediate variable addr. 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 MIME-Version: 1.0 Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" Simplify the usage of intermediate variable addr in following functions: 1. ff_put_pixels4_8_mmi 2. ff_put_pixels8_8_mmi 3. ff_put_pixels16_8_mmi 4. ff_avg_pixels16_8_mmi. --- libavcodec/mips/hpeldsp_mmi.c | 181 ++++++++++++++++++++---------------------- 1 file changed, 87 insertions(+), 94 deletions(-) diff --git a/libavcodec/mips/hpeldsp_mmi.c b/libavcodec/mips/hpeldsp_mmi.c index 2dbef22..db2fa10 100644 --- a/libavcodec/mips/hpeldsp_mmi.c +++ b/libavcodec/mips/hpeldsp_mmi.c @@ -29,36 +29,35 @@ void ff_put_pixels4_8_mmi(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h) { - double ftmp[2]; - mips_reg addr[2]; + double ftmp[4]; DECLARE_VAR_LOW32; - DECLARE_VAR_ADDRT; __asm__ volatile ( - PTR_ADDU "%[addr1], %[line_size], %[line_size] \n\t" "1: \n\t" - PTR_ADDU "%[addr0], %[pixels], %[line_size] \n\t" MMI_ULWC1(%[ftmp0], %[pixels], 0x00) - MMI_ULWC1(%[ftmp1], %[addr0], 0x00) - MMI_SWC1(%[ftmp0], %[block], 0x00) - MMI_SWXC1(%[ftmp1], %[block], %[line_size], 0x00) - PTR_ADDU "%[pixels], %[pixels], %[addr1] \n\t" - PTR_ADDU "%[block], %[block], %[addr1] \n\t" + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + MMI_ULWC1(%[ftmp1], %[pixels], 0x00) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + MMI_ULWC1(%[ftmp2], %[pixels], 0x00) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + MMI_ULWC1(%[ftmp3], %[pixels], 0x00) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + + PTR_ADDI "%[h], %[h], -0x04 \n\t" - PTR_ADDU "%[addr0], %[pixels], %[line_size] \n\t" - MMI_ULWC1(%[ftmp0], %[pixels], 0x00) - MMI_ULWC1(%[ftmp1], %[addr0], 0x00) MMI_SWC1(%[ftmp0], %[block], 0x00) - MMI_SWXC1(%[ftmp1], %[block], %[line_size], 0x00) - PTR_ADDU "%[pixels], %[pixels], %[addr1] \n\t" - PTR_ADDU "%[block], %[block], %[addr1] \n\t" + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + MMI_SWC1(%[ftmp1], %[block], 0x00) + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + MMI_SWC1(%[ftmp2], %[block], 0x00) + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + MMI_SWC1(%[ftmp3], %[block], 0x00) + PTR_ADDU "%[block], %[block], %[line_size] \n\t" - PTR_ADDI "%[h], %[h], -0x04 \n\t" "bnez %[h], 1b \n\t" : [ftmp0]"=&f"(ftmp[0]), [ftmp1]"=&f"(ftmp[1]), + [ftmp2]"=&f"(ftmp[2]), [ftmp3]"=&f"(ftmp[3]), RESTRICT_ASM_LOW32 - RESTRICT_ASM_ADDRT - [addr0]"=&r"(addr[0]), [addr1]"=&r"(addr[1]), [block]"+&r"(block), [pixels]"+&r"(pixels), [h]"+&r"(h) : [line_size]"r"((mips_reg)line_size) @@ -69,37 +68,35 @@ void ff_put_pixels4_8_mmi(uint8_t *block, const uint8_t *pixels, void ff_put_pixels8_8_mmi(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h) { - double ftmp[2]; - mips_reg addr[3]; + double ftmp[4]; DECLARE_VAR_ALL64; __asm__ volatile ( - PTR_ADDU "%[addr1], %[line_size], %[line_size] \n\t" "1: \n\t" MMI_ULDC1(%[ftmp0], %[pixels], 0x00) - PTR_ADDU "%[addr0], %[pixels], %[line_size] \n\t" - MMI_ULDC1(%[ftmp1], %[addr0], 0x00) - MMI_SDC1(%[ftmp0], %[block], 0x00) - PTR_ADDU "%[addr2], %[block], %[line_size] \n\t" - MMI_SDC1(%[ftmp1], %[addr2], 0x00) - PTR_ADDU "%[pixels], %[pixels], %[addr1] \n\t" - PTR_ADDU "%[block], %[block], %[addr1] \n\t" + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + MMI_ULDC1(%[ftmp1], %[pixels], 0x00) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + MMI_ULDC1(%[ftmp2], %[pixels], 0x00) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + MMI_ULDC1(%[ftmp3], %[pixels], 0x00) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + + PTR_ADDI "%[h], %[h], -0x04 \n\t" - MMI_ULDC1(%[ftmp0], %[pixels], 0x00) - PTR_ADDU "%[addr0], %[pixels], %[line_size] \n\t" - MMI_ULDC1(%[ftmp1], %[addr0], 0x00) MMI_SDC1(%[ftmp0], %[block], 0x00) - PTR_ADDU "%[addr2], %[block], %[line_size] \n\t" - MMI_SDC1(%[ftmp1], %[addr2], 0x00) - PTR_ADDU "%[pixels], %[pixels], %[addr1] \n\t" - PTR_ADDU "%[block], %[block], %[addr1] \n\t" + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + MMI_SDC1(%[ftmp1], %[block], 0x00) + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + MMI_SDC1(%[ftmp2], %[block], 0x00) + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + MMI_SDC1(%[ftmp3], %[block], 0x00) + PTR_ADDU "%[block], %[block], %[line_size] \n\t" - PTR_ADDI "%[h], %[h], -0x04 \n\t" "bnez %[h], 1b \n\t" : [ftmp0]"=&f"(ftmp[0]), [ftmp1]"=&f"(ftmp[1]), + [ftmp2]"=&f"(ftmp[2]), [ftmp3]"=&f"(ftmp[3]), RESTRICT_ASM_ALL64 - [addr0]"=&r"(addr[0]), [addr1]"=&r"(addr[1]), - [addr2]"=&r"(addr[2]), [block]"+&r"(block), [pixels]"+&r"(pixels), [h]"+&r"(h) : [line_size]"r"((mips_reg)line_size) @@ -110,45 +107,45 @@ void ff_put_pixels8_8_mmi(uint8_t *block, const uint8_t *pixels, void ff_put_pixels16_8_mmi(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h) { - double ftmp[4]; - mips_reg addr[2]; + double ftmp[8]; DECLARE_VAR_ALL64; - DECLARE_VAR_ADDRT; __asm__ volatile ( - PTR_ADDU "%[addr1], %[line_size], %[line_size] \n\t" - "1: \n\t" - PTR_ADDU "%[addr0], %[pixels], %[line_size] \n\t" + "1: \n\t" MMI_ULDC1(%[ftmp0], %[pixels], 0x00) MMI_ULDC1(%[ftmp2], %[pixels], 0x08) - MMI_ULDC1(%[ftmp1], %[addr0], 0x00) - MMI_ULDC1(%[ftmp3], %[addr0], 0x08) - MMI_SDC1(%[ftmp0], %[block], 0x00) - MMI_SDXC1(%[ftmp1], %[block], %[line_size], 0x00) - MMI_SDC1(%[ftmp2], %[block], 0x08) - MMI_SDXC1(%[ftmp3], %[block], %[line_size], 0x08) - PTR_ADDU "%[pixels], %[pixels], %[addr1] \n\t" - PTR_ADDU "%[block], %[block], %[addr1] \n\t" + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + MMI_ULDC1(%[ftmp1], %[pixels], 0x00) + MMI_ULDC1(%[ftmp3], %[pixels], 0x08) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + MMI_ULDC1(%[ftmp4], %[pixels], 0x00) + MMI_ULDC1(%[ftmp6], %[pixels], 0x08) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + MMI_ULDC1(%[ftmp5], %[pixels], 0x00) + MMI_ULDC1(%[ftmp7], %[pixels], 0x08) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + + PTR_ADDI "%[h], %[h], -0x04 \n\t" - PTR_ADDU "%[addr0], %[pixels], %[line_size] \n\t" - MMI_ULDC1(%[ftmp0], %[pixels], 0x00) - MMI_ULDC1(%[ftmp2], %[pixels], 0x08) - MMI_ULDC1(%[ftmp1], %[addr0], 0x00) - MMI_ULDC1(%[ftmp3], %[addr0], 0x08) MMI_SDC1(%[ftmp0], %[block], 0x00) - MMI_SDXC1(%[ftmp1], %[block], %[line_size], 0x00) MMI_SDC1(%[ftmp2], %[block], 0x08) - MMI_SDXC1(%[ftmp3], %[block], %[line_size], 0x08) - PTR_ADDU "%[pixels], %[pixels], %[addr1] \n\t" - PTR_ADDU "%[block], %[block], %[addr1] \n\t" - - PTR_ADDI "%[h], %[h], -0x04 \n\t" - "bnez %[h], 1b \n\t" + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + MMI_SDC1(%[ftmp1], %[block], 0x00) + MMI_SDC1(%[ftmp3], %[block], 0x08) + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + MMI_SDC1(%[ftmp4], %[block], 0x00) + MMI_SDC1(%[ftmp6], %[block], 0x08) + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + MMI_SDC1(%[ftmp5], %[block], 0x00) + MMI_SDC1(%[ftmp7], %[block], 0x08) + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + + "bnez %[h], 1b \n\t" : [ftmp0]"=&f"(ftmp[0]), [ftmp1]"=&f"(ftmp[1]), [ftmp2]"=&f"(ftmp[2]), [ftmp3]"=&f"(ftmp[3]), + [ftmp4]"=&f"(ftmp[4]), [ftmp5]"=&f"(ftmp[5]), + [ftmp6]"=&f"(ftmp[6]), [ftmp7]"=&f"(ftmp[7]), RESTRICT_ASM_ALL64 - RESTRICT_ASM_ADDRT - [addr0]"=&r"(addr[0]), [addr1]"=&r"(addr[1]), [block]"+&r"(block), [pixels]"+&r"(pixels), [h]"+&r"(h) : [line_size]"r"((mips_reg)line_size) @@ -264,65 +261,61 @@ void ff_avg_pixels16_8_mmi(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h) { double ftmp[8]; - mips_reg addr[3]; + mips_reg addr[1]; DECLARE_VAR_ALL64; - DECLARE_VAR_ADDRT; __asm__ volatile ( - PTR_ADDU "%[addr2], %[line_size], %[line_size] \n\t" "1: \n\t" + PTR_ADDI "%[h], %[h], -0x04 \n\t" MMI_ULDC1(%[ftmp0], %[pixels], 0x00) - PTR_ADDU "%[addr0], %[pixels], %[line_size] \n\t" MMI_ULDC1(%[ftmp4], %[pixels], 0x08) - PTR_ADDU "%[addr1], %[block], %[line_size] \n\t" - MMI_ULDC1(%[ftmp1], %[addr0], 0x00) - MMI_ULDC1(%[ftmp5], %[addr0], 0x08) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + MMI_ULDC1(%[ftmp1], %[pixels], 0x00) + MMI_ULDC1(%[ftmp5], %[pixels], 0x08) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" MMI_ULDC1(%[ftmp2], %[block], 0x00) MMI_ULDC1(%[ftmp6], %[block], 0x08) - MMI_ULDC1(%[ftmp3], %[addr1], 0x00) - MMI_ULDC1(%[ftmp7], %[addr1], 0x08) + PTR_ADDU "%[addr0], %[block], %[line_size] \n\t" + MMI_ULDC1(%[ftmp3], %[addr0], 0x00) + MMI_ULDC1(%[ftmp7], %[addr0], 0x08) "pavgb %[ftmp0], %[ftmp0], %[ftmp2] \n\t" "pavgb %[ftmp4], %[ftmp4], %[ftmp6] \n\t" "pavgb %[ftmp1], %[ftmp1], %[ftmp3] \n\t" "pavgb %[ftmp5], %[ftmp5], %[ftmp7] \n\t" MMI_SDC1(%[ftmp0], %[block], 0x00) - MMI_SDXC1(%[ftmp1], %[block], %[line_size], 0x00) MMI_SDC1(%[ftmp4], %[block], 0x08) - MMI_SDXC1(%[ftmp5], %[block], %[line_size], 0x08) - PTR_ADDU "%[pixels], %[pixels], %[addr2] \n\t" - PTR_ADDU "%[block], %[block], %[addr2] \n\t" + MMI_SDC1(%[ftmp1], %[addr0], 0x00) + MMI_SDC1(%[ftmp5], %[addr0], 0x08) + PTR_ADDU "%[block], %[addr0], %[line_size] \n\t" MMI_ULDC1(%[ftmp0], %[pixels], 0x00) - PTR_ADDU "%[addr0], %[pixels], %[line_size] \n\t" MMI_ULDC1(%[ftmp4], %[pixels], 0x08) - PTR_ADDU "%[addr1], %[block], %[line_size] \n\t" - MMI_ULDC1(%[ftmp1], %[addr0], 0x00) - MMI_ULDC1(%[ftmp5], %[addr0], 0x08) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + MMI_ULDC1(%[ftmp1], %[pixels], 0x00) + MMI_ULDC1(%[ftmp5], %[pixels], 0x08) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" MMI_ULDC1(%[ftmp2], %[block], 0x00) MMI_ULDC1(%[ftmp6], %[block], 0x08) - MMI_ULDC1(%[ftmp3], %[addr1], 0x00) - MMI_ULDC1(%[ftmp7], %[addr1], 0x08) + PTR_ADDU "%[addr0], %[block], %[line_size] \n\t" + MMI_ULDC1(%[ftmp3], %[addr0], 0x00) + MMI_ULDC1(%[ftmp7], %[addr0], 0x08) "pavgb %[ftmp0], %[ftmp0], %[ftmp2] \n\t" "pavgb %[ftmp4], %[ftmp4], %[ftmp6] \n\t" "pavgb %[ftmp1], %[ftmp1], %[ftmp3] \n\t" "pavgb %[ftmp5], %[ftmp5], %[ftmp7] \n\t" MMI_SDC1(%[ftmp0], %[block], 0x00) - MMI_SDXC1(%[ftmp1], %[block], %[line_size], 0x00) MMI_SDC1(%[ftmp4], %[block], 0x08) - MMI_SDXC1(%[ftmp5], %[block], %[line_size], 0x08) - PTR_ADDU "%[pixels], %[pixels], %[addr2] \n\t" - PTR_ADDU "%[block], %[block], %[addr2] \n\t" + MMI_SDC1(%[ftmp1], %[addr0], 0x00) + MMI_SDC1(%[ftmp5], %[addr0], 0x08) + PTR_ADDU "%[block], %[addr0], %[line_size] \n\t" - PTR_ADDI "%[h], %[h], -0x04 \n\t" "bnez %[h], 1b \n\t" : [ftmp0]"=&f"(ftmp[0]), [ftmp1]"=&f"(ftmp[1]), [ftmp2]"=&f"(ftmp[2]), [ftmp3]"=&f"(ftmp[3]), [ftmp4]"=&f"(ftmp[4]), [ftmp5]"=&f"(ftmp[5]), [ftmp6]"=&f"(ftmp[6]), [ftmp7]"=&f"(ftmp[7]), RESTRICT_ASM_ALL64 - RESTRICT_ASM_ADDRT - [addr0]"=&r"(addr[0]), [addr1]"=&r"(addr[1]), - [addr2]"=&r"(addr[2]), + [addr0]"=&r"(addr[0]), [block]"+&r"(block), [pixels]"+&r"(pixels), [h]"+&r"(h) : [line_size]"r"((mips_reg)line_size)