diff options
Diffstat (limited to 'libavcodec/mips/hpeldsp_mmi.c')
| -rw-r--r-- | libavcodec/mips/hpeldsp_mmi.c | 181 |
1 files changed, 87 insertions, 94 deletions
diff --git a/libavcodec/mips/hpeldsp_mmi.c b/libavcodec/mips/hpeldsp_mmi.c index 2dbef22ccd..db2fa10fba 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) |