From patchwork Thu Jun 14 07:19:59 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Shiyou Yin X-Patchwork-Id: 9405 Delivered-To: ffmpegpatchwork@gmail.com Received: by 2002:a02:11c:0:0:0:0:0 with SMTP id c28-v6csp1579149jad; Thu, 14 Jun 2018 00:20:10 -0700 (PDT) X-Google-Smtp-Source: ADUXVKKigWvTl1qg65Xhrm+pUj+MSOrcs3/SlTIQ3DSHfYBXNs68EP4DlxdusjP+xD+86D7Lu412 X-Received: by 2002:adf:8989:: with SMTP id x9-v6mr1066302wrx.78.1528960810350; Thu, 14 Jun 2018 00:20:10 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1528960810; cv=none; d=google.com; s=arc-20160816; b=apFM7NWdLMqkfvXanfMkZsTOiECLKX6QpDWx5qY9D8+rmVdVP5L/5MmDGgLIcu2GxA 4eqLyte6+RXF+amyXCEX2a54oNC5dUJPBtNFlk1g8XWIer3FGjAQ9fFW+iuKdKjx3NjF 1fQMq93yZePxe/DoURKcneTQ7lDue2I2MCChC7jDv8IvHPteEOUXfOPBbtlp8yA7K9W7 2SGI8ZfjFa80Sto//udE+LRqW2kiEWT23NQ39aF/cdkhtr4yxoIKu0h5JmTXRVSNm3/y yN87W1PC7bypCef/DYDGuO8M6jLv57VM+CvBD6grZOtr1ld5IU+cvD9pBeXuESxEEcEJ XErQ== 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:cc: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=OqLn9oqz7SXE7hd7ZroeVjp0JGyHpTLAXnpL9z117IM=; b=sc7T0BfIK1XOlwkF5EMJaw4ZqkP4fgk1B1FNj9OD/9kXGfw2stt0WWnUspX31AcBYR rCtlM+V9cvlud0rMV1EntCqplga06Rk7Dggb9+EQRvfToaQIILA4xAmNqj7B2wl6F4Cz H4nwzvwcv3FVGpg0Fu/CN8ESzog3jg2H5z88o9Pvv9T7RlS6R4cBfpxHEtOeslJcDgPt OoQlA76D9a/OIax27m5IlRL0FbzLZyAP2RExtmLhdN57xTKKRViCMnpSF+20tunOXivX MSTV7hWXfbcaFxWeIIvKBSqX34PJcKTcFu5Grg6SGRhm9hv3RAPp8b5XVR3DMwUsyWV/ ka0A== 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 q9-v6si3946764wrp.314.2018.06.14.00.20.10; Thu, 14 Jun 2018 00:20:10 -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 E696968AF13; Thu, 14 Jun 2018 10:19:17 +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 4AECD68AE33 for ; Thu, 14 Jun 2018 10:19:12 +0300 (EEST) Received: from localhost (unknown [202.141.160.96]) by mail (Coremail) with SMTP id QMiowPDxr2MxFiJbr313AA--.23278S3; Thu, 14 Jun 2018 15:16:01 +0800 (CST) From: Shiyou Yin To: ffmpeg-devel@ffmpeg.org Date: Thu, 14 Jun 2018 15:19:59 +0800 Message-Id: <1528960799-17669-1-git-send-email-yinshiyou-hf@loongson.cn> X-Mailer: git-send-email 2.1.0 X-CM-TRANSID: QMiowPDxr2MxFiJbr313AA--.23278S3 X-Coremail-Antispam: 1UD129KBjvJXoW3uw47KF18Xry8AryUKF1xKrg_yoWDZw45pa y8Ar1Fv3W2vF45Xa1UJw1UCF13ZF1DtFsakFyq9F10v3s3tFn7Xr4xGr93GrWYya4ayF4q yF1UAa4Sywn5Gr7anT9S1TB71UUUUUUqnTZGkaVYY2UrUUUUjbIjqfuFe4nvWSU5nxnvy2 9KBjDU0xBIdaVrnRJUUUvI14x267AKxVWUJVW8JwAFc2x0x2IEx4CE42xK8VAvwI8IcIk0 rVWrJVCq3wAFIxvE14AKwVWUJVWUGwA2ocxC64kIII0Yj41l84x0c7CEw4AK67xGY2AK02 1l84ACjcxK6xIIjxv20xvE14v26ryj6F1UM28EF7xvwVC0I7IYx2IY6xkF7I0E14v26r4j 6F4UM28EF7xvwVC2z280aVAFwI0_Gr1j6F4UJwA2z4x0Y4vEx4A2jsIEc7CjxVAFwI0_Cr 1j6rxdM2AIxVAIcxkEcVAq07x20xvEncxIr21l5I8CrVACY4xI64kE6c02F40Ex7xfMcIj 6xIIjxv20xvE14v26r126r1DMcIj6I8E87Iv67AKxVWUJVW8JwAm72CE4IkC6x0Yz7v_Jr 0_Gr1lF7xvr2IYc2Ij64vIr41lF7xvr2IYc2Ij64vIr40E4x8a64kEw24lF7I21c0EjII2 zVCS5cI20VAGYxC7MxkIecxEwVAFwVW8CwCF04k20xvY0x0EwIxGrwCFx2IqxVCFs4IE7x kEbVWUJVW8JwC20s026c02F40E14v26r1j6r18MI8I3I0E7480Y4vE14v26r106r1rMI8E 67AF67kF1VAFwI0_Jrv_JF1lIxAIcVC0I7IYx2IY67AKxVWUCVW8JwCI42IY6xIIjxv20x vEc7CjxVAFwI0_Gr0_Cr1lIxAIcVCF04k26cxKx2IYs7xG6r4j6FyUMIIF0xvEx4A2jsIE 14v26r1j6r4UMIIF0xvEx4A2jsIEc7CjxVAFwI0_Gr0_Gr1UYxBIdaVFxhVjvjDU0xZFpf 9x0JU2-eOUUUUU= X-CM-SenderInfo: p1lq2x5l1r3gtki6z05rqj20fqof0/ Subject: [FFmpeg-devel] [PATCH 7/7] avcodec/mips: [loongson] reoptimize put&add pixels with mmi v2. 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: Shiyou Yin MIME-Version: 1.0 Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" Reoptimize following functions with mmi: 1. ff_put_pixels4_8_mmi. 2. ff_put_pixels8_8_mmi. 3. ff_put_pixels16_8_mmi. 4. ff_add_pixels_clamped_mmi. Change-Id: I80bf76b4d8d79c32c6c1913fe80fd5a828e937f1 Signed-off-by: Shiyou Yin --- libavcodec/mips/hpeldsp_mmi.c | 133 +++++++++++++++++++----------------------- libavcodec/mips/idctdsp_mmi.c | 71 +++++++++------------- 2 files changed, 89 insertions(+), 115 deletions(-) diff --git a/libavcodec/mips/hpeldsp_mmi.c b/libavcodec/mips/hpeldsp_mmi.c index 1bba70e..3272367 100644 --- a/libavcodec/mips/hpeldsp_mmi.c +++ b/libavcodec/mips/hpeldsp_mmi.c @@ -29,36 +29,32 @@ 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]; 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 "%[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" + MMI_ULWC1($f0, %[pixels], 0x00) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + MMI_ULWC1($f1, %[pixels], 0x00) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + MMI_ULWC1($f2, %[pixels], 0x00) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + MMI_ULWC1($f3, %[pixels], 0x00) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" PTR_ADDI "%[h], %[h], -0x04 \n\t" + + MMI_SWC1($f0, %[block], 0x00) + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + MMI_SWC1($f1, %[block], 0x00) + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + MMI_SWC1($f2, %[block], 0x00) + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + MMI_SWC1($f3, %[block], 0x00) + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + "bnez %[h], 1b \n\t" - : [ftmp0]"=&f"(ftmp[0]), [ftmp1]"=&f"(ftmp[1]), - RESTRICT_ASM_LOW32 - RESTRICT_ASM_ADDRT - [addr0]"=&r"(addr[0]), [addr1]"=&r"(addr[1]), + : RESTRICT_ASM_LOW32 [block]"+&r"(block), [pixels]"+&r"(pixels), [h]"+&r"(h) : [line_size]"r"((mips_reg)line_size) @@ -69,37 +65,32 @@ 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]; 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" - - 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" + MMI_ULDC1($f0, %[pixels], 0x00) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + MMI_ULDC1($f1, %[pixels], 0x00) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + MMI_ULDC1($f2, %[pixels], 0x00) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + MMI_ULDC1($f3, %[pixels], 0x00) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" PTR_ADDI "%[h], %[h], -0x04 \n\t" + + MMI_SDC1($f0, %[block], 0x00) + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + MMI_SDC1($f1, %[block], 0x00) + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + MMI_SDC1($f2, %[block], 0x00) + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + MMI_SDC1($f3, %[block], 0x00) + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + "bnez %[h], 1b \n\t" - : [ftmp0]"=&f"(ftmp[0]), [ftmp1]"=&f"(ftmp[1]), - RESTRICT_ASM_ALL64 - [addr0]"=&r"(addr[0]), [addr1]"=&r"(addr[1]), - [addr2]"=&r"(addr[2]), + : RESTRICT_ASM_ALL64 [block]"+&r"(block), [pixels]"+&r"(pixels), [h]"+&r"(h) : [line_size]"r"((mips_reg)line_size) @@ -110,42 +101,40 @@ 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]; DECLARE_VAR_ALL64; __asm__ volatile ( "1: \n\t" - MMI_ULDC1(%[ftmp0], %[pixels], 0x00) - MMI_ULDC1(%[ftmp2], %[pixels], 0x08) + MMI_ULDC1($f0, %[pixels], 0x00) + MMI_ULDC1($f2, %[pixels], 0x08) PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" - MMI_ULDC1(%[ftmp1], %[pixels], 0x00) - MMI_ULDC1(%[ftmp3], %[pixels], 0x08) - MMI_SDC1(%[ftmp0], %[block], 0x00) - MMI_SDC1(%[ftmp2], %[block], 0x08) - PTR_ADDU "%[block], %[block], %[line_size] \n\t" - MMI_SDC1(%[ftmp1], %[block], 0x00) - MMI_SDC1(%[ftmp3], %[block], 0x08) + MMI_ULDC1($f1, %[pixels], 0x00) + MMI_ULDC1($f3, %[pixels], 0x08) PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" - PTR_ADDU "%[block], %[block], %[line_size] \n\t" - - MMI_ULDC1(%[ftmp0], %[pixels], 0x00) - MMI_ULDC1(%[ftmp2], %[pixels], 0x08) + MMI_ULDC1($f4, %[pixels], 0x00) + MMI_ULDC1($f6, %[pixels], 0x08) PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" - MMI_ULDC1(%[ftmp1], %[pixels], 0x00) - MMI_ULDC1(%[ftmp3], %[pixels], 0x08) - MMI_SDC1(%[ftmp0], %[block], 0x00) - MMI_SDC1(%[ftmp2], %[block], 0x08) - PTR_ADDU "%[block], %[block], %[line_size] \n\t" - MMI_SDC1(%[ftmp1], %[block], 0x00) - MMI_SDC1(%[ftmp3], %[block], 0x08) + MMI_ULDC1($f5, %[pixels], 0x00) + MMI_ULDC1($f7, %[pixels], 0x08) PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" - PTR_ADDU "%[block], %[block], %[line_size] \n\t" PTR_ADDI "%[h], %[h], -0x04 \n\t" + + MMI_SDC1($f0, %[block], 0x00) + MMI_SDC1($f2, %[block], 0x08) + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + MMI_SDC1($f1, %[block], 0x00) + MMI_SDC1($f3, %[block], 0x08) + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + MMI_SDC1($f4, %[block], 0x00) + MMI_SDC1($f6, %[block], 0x08) + PTR_ADDU "%[block], %[block], %[line_size] \n\t" + MMI_SDC1($f5, %[block], 0x00) + MMI_SDC1($f7, %[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]), - RESTRICT_ASM_ALL64 + : RESTRICT_ASM_ALL64 [block]"+&r"(block), [pixels]"+&r"(pixels), [h]"+&r"(h) : [line_size]"r"((mips_reg)line_size) diff --git a/libavcodec/mips/idctdsp_mmi.c b/libavcodec/mips/idctdsp_mmi.c index b797965..93d5fc6 100644 --- a/libavcodec/mips/idctdsp_mmi.c +++ b/libavcodec/mips/idctdsp_mmi.c @@ -174,50 +174,35 @@ void ff_put_signed_pixels_clamped_mmi(const int16_t *block, void ff_add_pixels_clamped_mmi(const int16_t *block, uint8_t *av_restrict pixels, ptrdiff_t line_size) { - double ftmp[8]; - uint64_t tmp[1]; - mips_reg addr[1]; - DECLARE_VAR_ALL64; - DECLARE_VAR_ADDRT; - __asm__ volatile ( - "li %[tmp0], 0x04 \n\t" - "xor %[ftmp0], %[ftmp0], %[ftmp0] \n\t" - "1: \n\t" - MMI_LDC1(%[ftmp1], %[block], 0x00) - MMI_LDC1(%[ftmp2], %[block], 0x08) - MMI_LDC1(%[ftmp3], %[block], 0x10) - MMI_LDC1(%[ftmp4], %[block], 0x18) - MMI_LDC1(%[ftmp5], %[pixels], 0x00) - MMI_LDXC1(%[ftmp6], %[pixels], %[line_size], 0x00) - "mov.d %[ftmp7], %[ftmp5] \n\t" - "punpcklbh %[ftmp5], %[ftmp5], %[ftmp0] \n\t" - "punpckhbh %[ftmp7], %[ftmp7], %[ftmp0] \n\t" - "paddh %[ftmp1], %[ftmp1], %[ftmp5] \n\t" - "paddh %[ftmp2], %[ftmp2], %[ftmp7] \n\t" - "mov.d %[ftmp7], %[ftmp6] \n\t" - "punpcklbh %[ftmp6], %[ftmp6], %[ftmp0] \n\t" - "punpckhbh %[ftmp7], %[ftmp7], %[ftmp0] \n\t" - "paddh %[ftmp3], %[ftmp3], %[ftmp6] \n\t" - "paddh %[ftmp4], %[ftmp4], %[ftmp7] \n\t" - "packushb %[ftmp1], %[ftmp1], %[ftmp2] \n\t" - "packushb %[ftmp3], %[ftmp3], %[ftmp4] \n\t" - MMI_SDC1(%[ftmp1], %[pixels], 0x00) - MMI_SDXC1(%[ftmp3], %[pixels], %[line_size], 0x00) - "addi %[tmp0], %[tmp0], -0x01 \n\t" - PTR_ADDIU "%[block], %[block], 0x20 \n\t" - PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" - PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" - "bnez %[tmp0], 1b" - : [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]), - [tmp0]"=&r"(tmp[0]), - RESTRICT_ASM_ALL64 - RESTRICT_ASM_ADDRT - [addr0]"=&r"(addr[0]), - [pixels]"+&r"(pixels), [block]"+&r"(block) + "li $10, 0x04 \n\t" + "xor $f0, $f0, $f0 \n\t" + "1: \n\t" + + "gslqc1 $f2, $f1, 0x00(%[block]) \n\t" + "gslqc1 $f4, $f3, 0x10(%[block]) \n\t" + PTR_ADDIU "%[block], %[block], 0x20 \n\t" + MMI_LDC1($f5, %[pixels], 0x00) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + MMI_LDC1($f6, %[pixels], 0x00) + PTR_SUBU "%[pixels], %[pixels], %[line_size] \n\t" + "punpckhbh $f7, $f5, $f0 \n\t" + "punpcklbh $f5, $f5, $f0 \n\t" + "punpckhbh $f8, $f6, $f0 \n\t" + "punpcklbh $f6, $f6, $f0 \n\t" + "paddh $f1, $f1, $f5 \n\t" + "paddh $f2, $f2, $f7 \n\t" + "paddh $f3, $f3, $f6 \n\t" + "paddh $f4, $f4, $f8 \n\t" + "packushb $f1, $f1, $f2 \n\t" + "packushb $f3, $f3, $f4 \n\t" + MMI_SDC1($f1, %[pixels], 0x00) + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + MMI_SDC1($f3, %[pixels], 0x00) + "addi $10, $10, -0x01 \n\t" + PTR_ADDU "%[pixels], %[pixels], %[line_size] \n\t" + "bnez $10, 1b \n\t" + : [pixels]"+&r"(pixels), [block]"+&r"(block) : [line_size]"r"((mips_reg)line_size) : "memory" );