X-Git-Url: https://git.saurik.com/wxWidgets.git/blobdiff_plain/c6b71bffdf1c57371b048e2b0be04bf88b9e4b3e..c5288c5cfebea56239369dddcce8ac3ef6f4a8dd:/src/png/pnggccrd.c?ds=sidebyside diff --git a/src/png/pnggccrd.c b/src/png/pnggccrd.c index 2d1d1d3b36..27c716a2c0 100644 --- a/src/png/pnggccrd.c +++ b/src/png/pnggccrd.c @@ -6,9 +6,9 @@ * and http://www.intel.com/drg/pentiumII/appnotes/923/923.htm * for Intel's performance analysis of the MMX vs. non-MMX code. * - * libpng version 1.2.4 - July 8, 2002 + * libpng version 1.2.7 - September 12, 2004 * For conditions of distribution and use, see copyright notice in png.h - * Copyright (c) 1998-2002 Glenn Randers-Pehrson + * Copyright (c) 1998-2004 Glenn Randers-Pehrson * Copyright (c) 1998, Intel Corporation * * Based on MSVC code contributed by Nirav Chhatrapati, Intel Corp., 1998. @@ -223,6 +223,10 @@ * 20020304: * - eliminated incorrect use of width_mmx in pixel_bytes == 8 case * + * 20040724: + * - more tinkering with clobber list at lines 4529 and 5033, to get + * it to compile on gcc-3.4. + * * STILL TO DO: * - test png_do_read_interlace() 64-bit case (pixel_bytes == 8) * - write MMX code for 48-bit case (pixel_bytes == 6) @@ -327,18 +331,18 @@ static unsigned long long _mask48_1 = 0x2020202040404040LL; static unsigned long long _mask48_0 = 0x4040808080808080LL; static unsigned long long _const4 = 0x0000000000FFFFFFLL; -//static unsigned long long _const5 = 0x000000FFFFFF0000LL; // NOT USED +/* static unsigned long long _const5 = 0x000000FFFFFF0000LL; */ /* NOT USED */ static unsigned long long _const6 = 0x00000000000000FFLL; -// These are used in the row-filter routines and should/would be local -// variables if not for gcc addressing limitations. -// WARNING: Their presence probably defeats the thread safety of libpng. +/* These are used in the row-filter routines and should/would be local */ +/* variables if not for gcc addressing limitations. */ +/* WARNING: Their presence probably defeats the thread safety of libpng. */ #ifdef PNG_THREAD_UNSAFE_OK static png_uint_32 _FullLength; static png_uint_32 _MMXLength; static int _dif; -static int _patemp; // temp variables for Paeth routine +static int _patemp; /* temp variables for Paeth routine */ static int _pbtemp; static int _pctemp; #endif @@ -412,8 +416,10 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask) #if defined(PNG_ASSEMBLER_CODE_SUPPORTED) if (_mmx_supported == 2) { +#if !defined(PNG_1_0_X) /* this should have happened in png_init_mmx_flags() already */ png_warning(png_ptr, "asm_flags may not have been initialized"); +#endif png_mmx_support(); } #endif @@ -422,7 +428,7 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask) { png_debug(2,"mask == 0xff: doing single png_memcpy()\n"); png_memcpy(row, png_ptr->row_buf + 1, - (png_size_t)((png_ptr->width * png_ptr->row_info.pixel_depth + 7) >> 3)); + (png_size_t)PNG_ROWBYTES(png_ptr->row_info.pixel_depth,png_ptr->width)); } else /* (png_combine_row() is never called with mask == 0) */ { @@ -609,58 +615,58 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask) { png_uint_32 len; int diff; - int dummy_value_a; // fix 'forbidden register spilled' error + int dummy_value_a; /* fix 'forbidden register spilled' error */ int dummy_value_d; int dummy_value_c; int dummy_value_S; int dummy_value_D; - _unmask = ~mask; // global variable for -fPIC version + _unmask = ~mask; /* global variable for -fPIC version */ srcptr = png_ptr->row_buf + 1; dstptr = row; - len = png_ptr->width &~7; // reduce to multiple of 8 - diff = (int) (png_ptr->width & 7); // amount lost + len = png_ptr->width &~7; /* reduce to multiple of 8 */ + diff = (int) (png_ptr->width & 7); /* amount lost */ __asm__ __volatile__ ( - "movd _unmask, %%mm7 \n\t" // load bit pattern - "psubb %%mm6, %%mm6 \n\t" // zero mm6 + "movd _unmask, %%mm7 \n\t" /* load bit pattern */ + "psubb %%mm6, %%mm6 \n\t" /* zero mm6 */ "punpcklbw %%mm7, %%mm7 \n\t" "punpcklwd %%mm7, %%mm7 \n\t" - "punpckldq %%mm7, %%mm7 \n\t" // fill reg with 8 masks + "punpckldq %%mm7, %%mm7 \n\t" /* fill reg with 8 masks */ "movq _mask8_0, %%mm0 \n\t" - "pand %%mm7, %%mm0 \n\t" // nonzero if keep byte - "pcmpeqb %%mm6, %%mm0 \n\t" // zeros->1s, v versa + "pand %%mm7, %%mm0 \n\t" /* nonzero if keep byte */ + "pcmpeqb %%mm6, %%mm0 \n\t" /* zeros->1s, v versa */ -// preload "movl len, %%ecx \n\t" // load length of line -// preload "movl srcptr, %%esi \n\t" // load source -// preload "movl dstptr, %%edi \n\t" // load dest +/* preload "movl len, %%ecx \n\t" // load length of line */ +/* preload "movl srcptr, %%esi \n\t" // load source */ +/* preload "movl dstptr, %%edi \n\t" // load dest */ - "cmpl $0, %%ecx \n\t" // len == 0 ? + "cmpl $0, %%ecx \n\t" /* len == 0 ? */ "je mainloop8end \n\t" "mainloop8: \n\t" - "movq (%%esi), %%mm4 \n\t" // *srcptr + "movq (%%esi), %%mm4 \n\t" /* *srcptr */ "pand %%mm0, %%mm4 \n\t" "movq %%mm0, %%mm6 \n\t" - "pandn (%%edi), %%mm6 \n\t" // *dstptr + "pandn (%%edi), %%mm6 \n\t" /* *dstptr */ "por %%mm6, %%mm4 \n\t" "movq %%mm4, (%%edi) \n\t" - "addl $8, %%esi \n\t" // inc by 8 bytes processed + "addl $8, %%esi \n\t" /* inc by 8 bytes processed */ "addl $8, %%edi \n\t" - "subl $8, %%ecx \n\t" // dec by 8 pixels processed + "subl $8, %%ecx \n\t" /* dec by 8 pixels processed */ "ja mainloop8 \n\t" "mainloop8end: \n\t" -// preload "movl diff, %%ecx \n\t" // (diff is in eax) +/* preload "movl diff, %%ecx \n\t" // (diff is in eax) */ "movl %%eax, %%ecx \n\t" "cmpl $0, %%ecx \n\t" "jz end8 \n\t" -// preload "movl mask, %%edx \n\t" - "sall $24, %%edx \n\t" // make low byte, high byte +/* preload "movl mask, %%edx \n\t" */ + "sall $24, %%edx \n\t" /* make low byte, high byte */ "secondloop8: \n\t" - "sall %%edx \n\t" // move high bit to CF - "jnc skip8 \n\t" // if CF = 0 + "sall %%edx \n\t" /* move high bit to CF */ + "jnc skip8 \n\t" /* if CF = 0 */ "movb (%%esi), %%al \n\t" "movb %%al, (%%edi) \n\t" @@ -671,23 +677,23 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask) "jnz secondloop8 \n\t" "end8: \n\t" - "EMMS \n\t" // DONE + "EMMS \n\t" /* DONE */ - : "=a" (dummy_value_a), // output regs (dummy) + : "=a" (dummy_value_a), /* output regs (dummy) */ "=d" (dummy_value_d), "=c" (dummy_value_c), "=S" (dummy_value_S), "=D" (dummy_value_D) - : "3" (srcptr), // esi // input regs - "4" (dstptr), // edi - "0" (diff), // eax -// was (unmask) "b" RESERVED // ebx // Global Offset Table idx - "2" (len), // ecx - "1" (mask) // edx + : "3" (srcptr), /* esi // input regs */ + "4" (dstptr), /* edi */ + "0" (diff), /* eax */ +/* was (unmask) "b" RESERVED // ebx // Global Offset Table idx */ + "2" (len), /* ecx */ + "1" (mask) /* edx */ #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ - : "%mm0", "%mm4", "%mm6", "%mm7" // clobber list + : "%mm0", "%mm4", "%mm6", "%mm7" /* clobber list */ #endif ); } @@ -747,23 +753,23 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask) { png_uint_32 len; int diff; - int dummy_value_a; // fix 'forbidden register spilled' error + int dummy_value_a; /* fix 'forbidden register spilled' error */ int dummy_value_d; int dummy_value_c; int dummy_value_S; int dummy_value_D; - _unmask = ~mask; // global variable for -fPIC version + _unmask = ~mask; /* global variable for -fPIC version */ srcptr = png_ptr->row_buf + 1; dstptr = row; - len = png_ptr->width &~7; // reduce to multiple of 8 - diff = (int) (png_ptr->width & 7); // amount lost // + len = png_ptr->width &~7; /* reduce to multiple of 8 */ + diff = (int) (png_ptr->width & 7); /* amount lost // */ __asm__ __volatile__ ( - "movd _unmask, %%mm7 \n\t" // load bit pattern - "psubb %%mm6, %%mm6 \n\t" // zero mm6 + "movd _unmask, %%mm7 \n\t" /* load bit pattern */ + "psubb %%mm6, %%mm6 \n\t" /* zero mm6 */ "punpcklbw %%mm7, %%mm7 \n\t" "punpcklwd %%mm7, %%mm7 \n\t" - "punpckldq %%mm7, %%mm7 \n\t" // fill reg with 8 masks + "punpckldq %%mm7, %%mm7 \n\t" /* fill reg with 8 masks */ "movq _mask16_0, %%mm0 \n\t" "movq _mask16_1, %%mm1 \n\t" @@ -774,9 +780,9 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask) "pcmpeqb %%mm6, %%mm0 \n\t" "pcmpeqb %%mm6, %%mm1 \n\t" -// preload "movl len, %%ecx \n\t" // load length of line -// preload "movl srcptr, %%esi \n\t" // load source -// preload "movl dstptr, %%edi \n\t" // load dest +/* preload "movl len, %%ecx \n\t" // load length of line */ +/* preload "movl srcptr, %%esi \n\t" // load source */ +/* preload "movl dstptr, %%edi \n\t" // load dest */ "cmpl $0, %%ecx \n\t" "jz mainloop16end \n\t" @@ -798,22 +804,22 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask) "por %%mm7, %%mm5 \n\t" "movq %%mm5, 8(%%edi) \n\t" - "addl $16, %%esi \n\t" // inc by 16 bytes processed + "addl $16, %%esi \n\t" /* inc by 16 bytes processed */ "addl $16, %%edi \n\t" - "subl $8, %%ecx \n\t" // dec by 8 pixels processed + "subl $8, %%ecx \n\t" /* dec by 8 pixels processed */ "ja mainloop16 \n\t" "mainloop16end: \n\t" -// preload "movl diff, %%ecx \n\t" // (diff is in eax) +/* preload "movl diff, %%ecx \n\t" // (diff is in eax) */ "movl %%eax, %%ecx \n\t" "cmpl $0, %%ecx \n\t" "jz end16 \n\t" -// preload "movl mask, %%edx \n\t" - "sall $24, %%edx \n\t" // make low byte, high byte +/* preload "movl mask, %%edx \n\t" */ + "sall $24, %%edx \n\t" /* make low byte, high byte */ "secondloop16: \n\t" - "sall %%edx \n\t" // move high bit to CF - "jnc skip16 \n\t" // if CF = 0 + "sall %%edx \n\t" /* move high bit to CF */ + "jnc skip16 \n\t" /* if CF = 0 */ "movw (%%esi), %%ax \n\t" "movw %%ax, (%%edi) \n\t" @@ -824,23 +830,23 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask) "jnz secondloop16 \n\t" "end16: \n\t" - "EMMS \n\t" // DONE + "EMMS \n\t" /* DONE */ - : "=a" (dummy_value_a), // output regs (dummy) + : "=a" (dummy_value_a), /* output regs (dummy) */ "=c" (dummy_value_c), "=d" (dummy_value_d), "=S" (dummy_value_S), "=D" (dummy_value_D) - : "0" (diff), // eax // input regs -// was (unmask) " " RESERVED // ebx // Global Offset Table idx - "1" (len), // ecx - "2" (mask), // edx - "3" (srcptr), // esi - "4" (dstptr) // edi + : "0" (diff), /* eax // input regs */ +/* was (unmask) " " RESERVED // ebx // Global Offset Table idx */ + "1" (len), /* ecx */ + "2" (mask), /* edx */ + "3" (srcptr), /* esi */ + "4" (dstptr) /* edi */ #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ - : "%mm0", "%mm1", "%mm4" // clobber list + : "%mm0", "%mm1", "%mm4" /* clobber list */ , "%mm5", "%mm6", "%mm7" #endif ); @@ -900,23 +906,23 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask) { png_uint_32 len; int diff; - int dummy_value_a; // fix 'forbidden register spilled' error + int dummy_value_a; /* fix 'forbidden register spilled' error */ int dummy_value_d; int dummy_value_c; int dummy_value_S; int dummy_value_D; - _unmask = ~mask; // global variable for -fPIC version + _unmask = ~mask; /* global variable for -fPIC version */ srcptr = png_ptr->row_buf + 1; dstptr = row; - len = png_ptr->width &~7; // reduce to multiple of 8 - diff = (int) (png_ptr->width & 7); // amount lost // + len = png_ptr->width &~7; /* reduce to multiple of 8 */ + diff = (int) (png_ptr->width & 7); /* amount lost // */ __asm__ __volatile__ ( - "movd _unmask, %%mm7 \n\t" // load bit pattern - "psubb %%mm6, %%mm6 \n\t" // zero mm6 + "movd _unmask, %%mm7 \n\t" /* load bit pattern */ + "psubb %%mm6, %%mm6 \n\t" /* zero mm6 */ "punpcklbw %%mm7, %%mm7 \n\t" "punpcklwd %%mm7, %%mm7 \n\t" - "punpckldq %%mm7, %%mm7 \n\t" // fill reg with 8 masks + "punpckldq %%mm7, %%mm7 \n\t" /* fill reg with 8 masks */ "movq _mask24_0, %%mm0 \n\t" "movq _mask24_1, %%mm1 \n\t" @@ -930,9 +936,9 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask) "pcmpeqb %%mm6, %%mm1 \n\t" "pcmpeqb %%mm6, %%mm2 \n\t" -// preload "movl len, %%ecx \n\t" // load length of line -// preload "movl srcptr, %%esi \n\t" // load source -// preload "movl dstptr, %%edi \n\t" // load dest +/* preload "movl len, %%ecx \n\t" // load length of line */ +/* preload "movl srcptr, %%esi \n\t" // load source */ +/* preload "movl dstptr, %%edi \n\t" // load dest */ "cmpl $0, %%ecx \n\t" "jz mainloop24end \n\t" @@ -962,23 +968,23 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask) "por %%mm4, %%mm6 \n\t" "movq %%mm6, 16(%%edi) \n\t" - "addl $24, %%esi \n\t" // inc by 24 bytes processed + "addl $24, %%esi \n\t" /* inc by 24 bytes processed */ "addl $24, %%edi \n\t" - "subl $8, %%ecx \n\t" // dec by 8 pixels processed + "subl $8, %%ecx \n\t" /* dec by 8 pixels processed */ "ja mainloop24 \n\t" "mainloop24end: \n\t" -// preload "movl diff, %%ecx \n\t" // (diff is in eax) +/* preload "movl diff, %%ecx \n\t" // (diff is in eax) */ "movl %%eax, %%ecx \n\t" "cmpl $0, %%ecx \n\t" "jz end24 \n\t" -// preload "movl mask, %%edx \n\t" - "sall $24, %%edx \n\t" // make low byte, high byte +/* preload "movl mask, %%edx \n\t" */ + "sall $24, %%edx \n\t" /* make low byte, high byte */ "secondloop24: \n\t" - "sall %%edx \n\t" // move high bit to CF - "jnc skip24 \n\t" // if CF = 0 + "sall %%edx \n\t" /* move high bit to CF */ + "jnc skip24 \n\t" /* if CF = 0 */ "movw (%%esi), %%ax \n\t" "movw %%ax, (%%edi) \n\t" "xorl %%eax, %%eax \n\t" @@ -992,23 +998,23 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask) "jnz secondloop24 \n\t" "end24: \n\t" - "EMMS \n\t" // DONE + "EMMS \n\t" /* DONE */ - : "=a" (dummy_value_a), // output regs (dummy) + : "=a" (dummy_value_a), /* output regs (dummy) */ "=d" (dummy_value_d), "=c" (dummy_value_c), "=S" (dummy_value_S), "=D" (dummy_value_D) - : "3" (srcptr), // esi // input regs - "4" (dstptr), // edi - "0" (diff), // eax -// was (unmask) "b" RESERVED // ebx // Global Offset Table idx - "2" (len), // ecx - "1" (mask) // edx + : "3" (srcptr), /* esi // input regs */ + "4" (dstptr), /* edi */ + "0" (diff), /* eax */ +/* was (unmask) "b" RESERVED // ebx // Global Offset Table idx */ + "2" (len), /* ecx */ + "1" (mask) /* edx */ #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ - : "%mm0", "%mm1", "%mm2" // clobber list + : "%mm0", "%mm1", "%mm2" /* clobber list */ , "%mm4", "%mm5", "%mm6", "%mm7" #endif ); @@ -1068,23 +1074,23 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask) { png_uint_32 len; int diff; - int dummy_value_a; // fix 'forbidden register spilled' error + int dummy_value_a; /* fix 'forbidden register spilled' error */ int dummy_value_d; int dummy_value_c; int dummy_value_S; int dummy_value_D; - _unmask = ~mask; // global variable for -fPIC version + _unmask = ~mask; /* global variable for -fPIC version */ srcptr = png_ptr->row_buf + 1; dstptr = row; - len = png_ptr->width &~7; // reduce to multiple of 8 - diff = (int) (png_ptr->width & 7); // amount lost // + len = png_ptr->width &~7; /* reduce to multiple of 8 */ + diff = (int) (png_ptr->width & 7); /* amount lost // */ __asm__ __volatile__ ( - "movd _unmask, %%mm7 \n\t" // load bit pattern - "psubb %%mm6, %%mm6 \n\t" // zero mm6 + "movd _unmask, %%mm7 \n\t" /* load bit pattern */ + "psubb %%mm6, %%mm6 \n\t" /* zero mm6 */ "punpcklbw %%mm7, %%mm7 \n\t" "punpcklwd %%mm7, %%mm7 \n\t" - "punpckldq %%mm7, %%mm7 \n\t" // fill reg with 8 masks + "punpckldq %%mm7, %%mm7 \n\t" /* fill reg with 8 masks */ "movq _mask32_0, %%mm0 \n\t" "movq _mask32_1, %%mm1 \n\t" @@ -1101,11 +1107,11 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask) "pcmpeqb %%mm6, %%mm2 \n\t" "pcmpeqb %%mm6, %%mm3 \n\t" -// preload "movl len, %%ecx \n\t" // load length of line -// preload "movl srcptr, %%esi \n\t" // load source -// preload "movl dstptr, %%edi \n\t" // load dest +/* preload "movl len, %%ecx \n\t" // load length of line */ +/* preload "movl srcptr, %%esi \n\t" // load source */ +/* preload "movl dstptr, %%edi \n\t" // load dest */ - "cmpl $0, %%ecx \n\t" // lcr + "cmpl $0, %%ecx \n\t" /* lcr */ "jz mainloop32end \n\t" "mainloop32: \n\t" @@ -1141,22 +1147,22 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask) "por %%mm5, %%mm7 \n\t" "movq %%mm7, 24(%%edi) \n\t" - "addl $32, %%esi \n\t" // inc by 32 bytes processed + "addl $32, %%esi \n\t" /* inc by 32 bytes processed */ "addl $32, %%edi \n\t" - "subl $8, %%ecx \n\t" // dec by 8 pixels processed + "subl $8, %%ecx \n\t" /* dec by 8 pixels processed */ "ja mainloop32 \n\t" "mainloop32end: \n\t" -// preload "movl diff, %%ecx \n\t" // (diff is in eax) +/* preload "movl diff, %%ecx \n\t" // (diff is in eax) */ "movl %%eax, %%ecx \n\t" "cmpl $0, %%ecx \n\t" "jz end32 \n\t" -// preload "movl mask, %%edx \n\t" - "sall $24, %%edx \n\t" // low byte => high byte +/* preload "movl mask, %%edx \n\t" */ + "sall $24, %%edx \n\t" /* low byte => high byte */ "secondloop32: \n\t" - "sall %%edx \n\t" // move high bit to CF - "jnc skip32 \n\t" // if CF = 0 + "sall %%edx \n\t" /* move high bit to CF */ + "jnc skip32 \n\t" /* if CF = 0 */ "movl (%%esi), %%eax \n\t" "movl %%eax, (%%edi) \n\t" @@ -1167,23 +1173,23 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask) "jnz secondloop32 \n\t" "end32: \n\t" - "EMMS \n\t" // DONE + "EMMS \n\t" /* DONE */ - : "=a" (dummy_value_a), // output regs (dummy) + : "=a" (dummy_value_a), /* output regs (dummy) */ "=d" (dummy_value_d), "=c" (dummy_value_c), "=S" (dummy_value_S), "=D" (dummy_value_D) - : "3" (srcptr), // esi // input regs - "4" (dstptr), // edi - "0" (diff), // eax -// was (unmask) "b" RESERVED // ebx // Global Offset Table idx - "2" (len), // ecx - "1" (mask) // edx + : "3" (srcptr), /* esi // input regs */ + "4" (dstptr), /* edi */ + "0" (diff), /* eax */ +/* was (unmask) "b" RESERVED // ebx // Global Offset Table idx */ + "2" (len), /* ecx */ + "1" (mask) /* edx */ #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ - : "%mm0", "%mm1", "%mm2", "%mm3" // clobber list + : "%mm0", "%mm1", "%mm2", "%mm3" /* clobber list */ , "%mm4", "%mm5", "%mm6", "%mm7" #endif ); @@ -1243,23 +1249,23 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask) { png_uint_32 len; int diff; - int dummy_value_a; // fix 'forbidden register spilled' error + int dummy_value_a; /* fix 'forbidden register spilled' error */ int dummy_value_d; int dummy_value_c; int dummy_value_S; int dummy_value_D; - _unmask = ~mask; // global variable for -fPIC version + _unmask = ~mask; /* global variable for -fPIC version */ srcptr = png_ptr->row_buf + 1; dstptr = row; - len = png_ptr->width &~7; // reduce to multiple of 8 - diff = (int) (png_ptr->width & 7); // amount lost // + len = png_ptr->width &~7; /* reduce to multiple of 8 */ + diff = (int) (png_ptr->width & 7); /* amount lost // */ __asm__ __volatile__ ( - "movd _unmask, %%mm7 \n\t" // load bit pattern - "psubb %%mm6, %%mm6 \n\t" // zero mm6 + "movd _unmask, %%mm7 \n\t" /* load bit pattern */ + "psubb %%mm6, %%mm6 \n\t" /* zero mm6 */ "punpcklbw %%mm7, %%mm7 \n\t" "punpcklwd %%mm7, %%mm7 \n\t" - "punpckldq %%mm7, %%mm7 \n\t" // fill reg with 8 masks + "punpckldq %%mm7, %%mm7 \n\t" /* fill reg with 8 masks */ "movq _mask48_0, %%mm0 \n\t" "movq _mask48_1, %%mm1 \n\t" @@ -1282,9 +1288,9 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask) "pcmpeqb %%mm6, %%mm4 \n\t" "pcmpeqb %%mm6, %%mm5 \n\t" -// preload "movl len, %%ecx \n\t" // load length of line -// preload "movl srcptr, %%esi \n\t" // load source -// preload "movl dstptr, %%edi \n\t" // load dest +/* preload "movl len, %%ecx \n\t" // load length of line */ +/* preload "movl srcptr, %%esi \n\t" // load source */ +/* preload "movl dstptr, %%edi \n\t" // load dest */ "cmpl $0, %%ecx \n\t" "jz mainloop48end \n\t" @@ -1332,23 +1338,23 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask) "por %%mm6, %%mm7 \n\t" "movq %%mm7, 40(%%edi) \n\t" - "addl $48, %%esi \n\t" // inc by 48 bytes processed + "addl $48, %%esi \n\t" /* inc by 48 bytes processed */ "addl $48, %%edi \n\t" - "subl $8, %%ecx \n\t" // dec by 8 pixels processed + "subl $8, %%ecx \n\t" /* dec by 8 pixels processed */ "ja mainloop48 \n\t" "mainloop48end: \n\t" -// preload "movl diff, %%ecx \n\t" // (diff is in eax) +/* preload "movl diff, %%ecx \n\t" // (diff is in eax) */ "movl %%eax, %%ecx \n\t" "cmpl $0, %%ecx \n\t" "jz end48 \n\t" -// preload "movl mask, %%edx \n\t" - "sall $24, %%edx \n\t" // make low byte, high byte +/* preload "movl mask, %%edx \n\t" */ + "sall $24, %%edx \n\t" /* make low byte, high byte */ "secondloop48: \n\t" - "sall %%edx \n\t" // move high bit to CF - "jnc skip48 \n\t" // if CF = 0 + "sall %%edx \n\t" /* move high bit to CF */ + "jnc skip48 \n\t" /* if CF = 0 */ "movl (%%esi), %%eax \n\t" "movl %%eax, (%%edi) \n\t" @@ -1359,23 +1365,23 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask) "jnz secondloop48 \n\t" "end48: \n\t" - "EMMS \n\t" // DONE + "EMMS \n\t" /* DONE */ - : "=a" (dummy_value_a), // output regs (dummy) + : "=a" (dummy_value_a), /* output regs (dummy) */ "=d" (dummy_value_d), "=c" (dummy_value_c), "=S" (dummy_value_S), "=D" (dummy_value_D) - : "3" (srcptr), // esi // input regs - "4" (dstptr), // edi - "0" (diff), // eax -// was (unmask) "b" RESERVED // ebx // Global Offset Table idx - "2" (len), // ecx - "1" (mask) // edx + : "3" (srcptr), /* esi // input regs */ + "4" (dstptr), /* edi */ + "0" (diff), /* eax */ +/* was (unmask) "b" RESERVED // ebx // Global Offset Table idx */ + "2" (len), /* ecx */ + "1" (mask) /* edx */ #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ - : "%mm0", "%mm1", "%mm2", "%mm3" // clobber list + : "%mm0", "%mm1", "%mm2", "%mm3" /* clobber list */ , "%mm4", "%mm5", "%mm6", "%mm7" #endif ); @@ -1695,10 +1701,10 @@ png_do_read_interlace(png_structp png_ptr) default: /* 8-bit or larger (this is where the routine is modified) */ { #if 0 -// static unsigned long long _const4 = 0x0000000000FFFFFFLL; no good -// static unsigned long long const4 = 0x0000000000FFFFFFLL; no good -// unsigned long long _const4 = 0x0000000000FFFFFFLL; no good -// unsigned long long const4 = 0x0000000000FFFFFFLL; no good +/* static unsigned long long _const4 = 0x0000000000FFFFFFLL; no good */ +/* static unsigned long long const4 = 0x0000000000FFFFFFLL; no good */ +/* unsigned long long _const4 = 0x0000000000FFFFFFLL; no good */ +/* unsigned long long const4 = 0x0000000000FFFFFFLL; no good */ #endif png_bytep sptr, dp; png_uint_32 i; @@ -1728,147 +1734,150 @@ png_do_read_interlace(png_structp png_ptr) { if (((pass == 0) || (pass == 1)) && width) { - int dummy_value_c; // fix 'forbidden register spilled' + int dummy_value_c; /* fix 'forbidden register spilled' */ int dummy_value_S; int dummy_value_D; __asm__ __volatile__ ( "subl $21, %%edi \n\t" - // (png_pass_inc[pass] - 1)*pixel_bytes + /* (png_pass_inc[pass] - 1)*pixel_bytes */ ".loop3_pass0: \n\t" - "movd (%%esi), %%mm0 \n\t" // x x x x x 2 1 0 - "pand _const4, %%mm0 \n\t" // z z z z z 2 1 0 - "movq %%mm0, %%mm1 \n\t" // z z z z z 2 1 0 - "psllq $16, %%mm0 \n\t" // z z z 2 1 0 z z - "movq %%mm0, %%mm2 \n\t" // z z z 2 1 0 z z - "psllq $24, %%mm0 \n\t" // 2 1 0 z z z z z - "psrlq $8, %%mm1 \n\t" // z z z z z z 2 1 - "por %%mm2, %%mm0 \n\t" // 2 1 0 2 1 0 z z - "por %%mm1, %%mm0 \n\t" // 2 1 0 2 1 0 2 1 - "movq %%mm0, %%mm3 \n\t" // 2 1 0 2 1 0 2 1 - "psllq $16, %%mm0 \n\t" // 0 2 1 0 2 1 z z - "movq %%mm3, %%mm4 \n\t" // 2 1 0 2 1 0 2 1 - "punpckhdq %%mm0, %%mm3 \n\t" // 0 2 1 0 2 1 0 2 + "movd (%%esi), %%mm0 \n\t" /* x x x x x 2 1 0 */ + "pand _const4, %%mm0 \n\t" /* z z z z z 2 1 0 */ + "movq %%mm0, %%mm1 \n\t" /* z z z z z 2 1 0 */ + "psllq $16, %%mm0 \n\t" /* z z z 2 1 0 z z */ + "movq %%mm0, %%mm2 \n\t" /* z z z 2 1 0 z z */ + "psllq $24, %%mm0 \n\t" /* 2 1 0 z z z z z */ + "psrlq $8, %%mm1 \n\t" /* z z z z z z 2 1 */ + "por %%mm2, %%mm0 \n\t" /* 2 1 0 2 1 0 z z */ + "por %%mm1, %%mm0 \n\t" /* 2 1 0 2 1 0 2 1 */ + "movq %%mm0, %%mm3 \n\t" /* 2 1 0 2 1 0 2 1 */ + "psllq $16, %%mm0 \n\t" /* 0 2 1 0 2 1 z z */ + "movq %%mm3, %%mm4 \n\t" /* 2 1 0 2 1 0 2 1 */ + "punpckhdq %%mm0, %%mm3 \n\t" /* 0 2 1 0 2 1 0 2 */ "movq %%mm4, 16(%%edi) \n\t" - "psrlq $32, %%mm0 \n\t" // z z z z 0 2 1 0 + "psrlq $32, %%mm0 \n\t" /* z z z z 0 2 1 0 */ "movq %%mm3, 8(%%edi) \n\t" - "punpckldq %%mm4, %%mm0 \n\t" // 1 0 2 1 0 2 1 0 + "punpckldq %%mm4, %%mm0 \n\t" /* 1 0 2 1 0 2 1 0 */ "subl $3, %%esi \n\t" "movq %%mm0, (%%edi) \n\t" "subl $24, %%edi \n\t" "decl %%ecx \n\t" "jnz .loop3_pass0 \n\t" - "EMMS \n\t" // DONE + "EMMS \n\t" /* DONE */ - : "=c" (dummy_value_c), // output regs (dummy) + : "=c" (dummy_value_c), /* output regs (dummy) */ "=S" (dummy_value_S), "=D" (dummy_value_D) : "1" (sptr), // esi // input regs "2" (dp), // edi - "0" (width) // ecx -// doesn't work "i" (0x0000000000FFFFFFLL) // %1 (a.k.a. _const4) + "0" (width), // ecx + "rim" (_const4) // %1(?) (0x0000000000FFFFFFLL) #if 0 /* %mm0, ..., %mm4 not supported by gcc 2.7.2.3 or egcs 1.1 */ - : "%mm0", "%mm1", "%mm2" // clobber list + : "%mm0", "%mm1", "%mm2" /* clobber list */ , "%mm3", "%mm4" #endif ); } else if (((pass == 2) || (pass == 3)) && width) { - int dummy_value_c; // fix 'forbidden register spilled' + int dummy_value_c; /* fix 'forbidden register spilled' */ int dummy_value_S; int dummy_value_D; __asm__ __volatile__ ( "subl $9, %%edi \n\t" - // (png_pass_inc[pass] - 1)*pixel_bytes + /* (png_pass_inc[pass] - 1)*pixel_bytes */ ".loop3_pass2: \n\t" - "movd (%%esi), %%mm0 \n\t" // x x x x x 2 1 0 - "pand _const4, %%mm0 \n\t" // z z z z z 2 1 0 - "movq %%mm0, %%mm1 \n\t" // z z z z z 2 1 0 - "psllq $16, %%mm0 \n\t" // z z z 2 1 0 z z - "movq %%mm0, %%mm2 \n\t" // z z z 2 1 0 z z - "psllq $24, %%mm0 \n\t" // 2 1 0 z z z z z - "psrlq $8, %%mm1 \n\t" // z z z z z z 2 1 - "por %%mm2, %%mm0 \n\t" // 2 1 0 2 1 0 z z - "por %%mm1, %%mm0 \n\t" // 2 1 0 2 1 0 2 1 + "movd (%%esi), %%mm0 \n\t" /* x x x x x 2 1 0 */ + "pand _const4, %%mm0 \n\t" /* z z z z z 2 1 0 */ + "movq %%mm0, %%mm1 \n\t" /* z z z z z 2 1 0 */ + "psllq $16, %%mm0 \n\t" /* z z z 2 1 0 z z */ + "movq %%mm0, %%mm2 \n\t" /* z z z 2 1 0 z z */ + "psllq $24, %%mm0 \n\t" /* 2 1 0 z z z z z */ + "psrlq $8, %%mm1 \n\t" /* z z z z z z 2 1 */ + "por %%mm2, %%mm0 \n\t" /* 2 1 0 2 1 0 z z */ + "por %%mm1, %%mm0 \n\t" /* 2 1 0 2 1 0 2 1 */ "movq %%mm0, 4(%%edi) \n\t" - "psrlq $16, %%mm0 \n\t" // z z 2 1 0 2 1 0 + "psrlq $16, %%mm0 \n\t" /* z z 2 1 0 2 1 0 */ "subl $3, %%esi \n\t" "movd %%mm0, (%%edi) \n\t" "subl $12, %%edi \n\t" "decl %%ecx \n\t" "jnz .loop3_pass2 \n\t" - "EMMS \n\t" // DONE + "EMMS \n\t" /* DONE */ - : "=c" (dummy_value_c), // output regs (dummy) + : "=c" (dummy_value_c), /* output regs (dummy) */ "=S" (dummy_value_S), "=D" (dummy_value_D) : "1" (sptr), // esi // input regs "2" (dp), // edi - "0" (width) // ecx + "0" (width), // ecx + "rim" (_const4) // (0x0000000000FFFFFFLL) #if 0 /* %mm0, ..., %mm2 not supported by gcc 2.7.2.3 or egcs 1.1 */ - : "%mm0", "%mm1", "%mm2" // clobber list + : "%mm0", "%mm1", "%mm2" /* clobber list */ #endif ); } else if (width) /* && ((pass == 4) || (pass == 5)) */ { - int width_mmx = ((width >> 1) << 1) - 8; // GRR: huh? + int width_mmx = ((width >> 1) << 1) - 8; /* GRR: huh? */ if (width_mmx < 0) width_mmx = 0; - width -= width_mmx; // 8 or 9 pix, 24 or 27 bytes + width -= width_mmx; /* 8 or 9 pix, 24 or 27 bytes */ if (width_mmx) { - // png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1}; - // sptr points at last pixel in pre-expanded row - // dp points at last pixel position in expanded row - int dummy_value_c; // fix 'forbidden register spilled' + /* png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1}; */ + /* sptr points at last pixel in pre-expanded row */ + /* dp points at last pixel position in expanded row */ + int dummy_value_c; /* fix 'forbidden register spilled' */ int dummy_value_S; int dummy_value_D; __asm__ __volatile__ ( "subl $3, %%esi \n\t" "subl $9, %%edi \n\t" - // (png_pass_inc[pass] + 1)*pixel_bytes + /* (png_pass_inc[pass] + 1)*pixel_bytes */ ".loop3_pass4: \n\t" - "movq (%%esi), %%mm0 \n\t" // x x 5 4 3 2 1 0 - "movq %%mm0, %%mm1 \n\t" // x x 5 4 3 2 1 0 - "movq %%mm0, %%mm2 \n\t" // x x 5 4 3 2 1 0 - "psllq $24, %%mm0 \n\t" // 4 3 2 1 0 z z z - "pand _const4, %%mm1 \n\t" // z z z z z 2 1 0 - "psrlq $24, %%mm2 \n\t" // z z z x x 5 4 3 - "por %%mm1, %%mm0 \n\t" // 4 3 2 1 0 2 1 0 - "movq %%mm2, %%mm3 \n\t" // z z z x x 5 4 3 - "psllq $8, %%mm2 \n\t" // z z x x 5 4 3 z + "movq (%%esi), %%mm0 \n\t" /* x x 5 4 3 2 1 0 */ + "movq %%mm0, %%mm1 \n\t" /* x x 5 4 3 2 1 0 */ + "movq %%mm0, %%mm2 \n\t" /* x x 5 4 3 2 1 0 */ + "psllq $24, %%mm0 \n\t" /* 4 3 2 1 0 z z z */ + "pand _const4, %%mm1 \n\t" /* z z z z z 2 1 0 */ + "psrlq $24, %%mm2 \n\t" /* z z z x x 5 4 3 */ + "por %%mm1, %%mm0 \n\t" /* 4 3 2 1 0 2 1 0 */ + "movq %%mm2, %%mm3 \n\t" /* z z z x x 5 4 3 */ + "psllq $8, %%mm2 \n\t" /* z z x x 5 4 3 z */ "movq %%mm0, (%%edi) \n\t" - "psrlq $16, %%mm3 \n\t" // z z z z z x x 5 - "pand _const6, %%mm3 \n\t" // z z z z z z z 5 - "por %%mm3, %%mm2 \n\t" // z z x x 5 4 3 5 + "psrlq $16, %%mm3 \n\t" /* z z z z z x x 5 */ + "pand _const6, %%mm3 \n\t" /* z z z z z z z 5 */ + "por %%mm3, %%mm2 \n\t" /* z z x x 5 4 3 5 */ "subl $6, %%esi \n\t" "movd %%mm2, 8(%%edi) \n\t" "subl $12, %%edi \n\t" "subl $2, %%ecx \n\t" "jnz .loop3_pass4 \n\t" - "EMMS \n\t" // DONE + "EMMS \n\t" /* DONE */ - : "=c" (dummy_value_c), // output regs (dummy) + : "=c" (dummy_value_c), /* output regs (dummy) */ "=S" (dummy_value_S), "=D" (dummy_value_D) : "1" (sptr), // esi // input regs "2" (dp), // edi - "0" (width_mmx) // ecx + "0" (width_mmx), // ecx + "rim" (_const4), // 0x0000000000FFFFFFLL + "rim" (_const6) // 0x00000000000000FFLL #if 0 /* %mm0, ..., %mm3 not supported by gcc 2.7.2.3 or egcs 1.1 */ - : "%mm0", "%mm1" // clobber list + : "%mm0", "%mm1" /* clobber list */ , "%mm2", "%mm3" #endif ); @@ -1898,10 +1907,10 @@ png_do_read_interlace(png_structp png_ptr) if (((pass == 0) || (pass == 1)) && width) { int width_mmx = ((width >> 2) << 2); - width -= width_mmx; // 0-3 pixels => 0-3 bytes + width -= width_mmx; /* 0-3 pixels => 0-3 bytes */ if (width_mmx) { - int dummy_value_c; // fix 'forbidden register spilled' + int dummy_value_c; /* fix 'forbidden register spilled' */ int dummy_value_S; int dummy_value_D; @@ -1910,38 +1919,38 @@ png_do_read_interlace(png_structp png_ptr) "subl $31, %%edi \n\t" ".loop1_pass0: \n\t" - "movd (%%esi), %%mm0 \n\t" // x x x x 3 2 1 0 - "movq %%mm0, %%mm1 \n\t" // x x x x 3 2 1 0 - "punpcklbw %%mm0, %%mm0 \n\t" // 3 3 2 2 1 1 0 0 - "movq %%mm0, %%mm2 \n\t" // 3 3 2 2 1 1 0 0 - "punpcklwd %%mm0, %%mm0 \n\t" // 1 1 1 1 0 0 0 0 - "movq %%mm0, %%mm3 \n\t" // 1 1 1 1 0 0 0 0 - "punpckldq %%mm0, %%mm0 \n\t" // 0 0 0 0 0 0 0 0 - "punpckhdq %%mm3, %%mm3 \n\t" // 1 1 1 1 1 1 1 1 + "movd (%%esi), %%mm0 \n\t" /* x x x x 3 2 1 0 */ + "movq %%mm0, %%mm1 \n\t" /* x x x x 3 2 1 0 */ + "punpcklbw %%mm0, %%mm0 \n\t" /* 3 3 2 2 1 1 0 0 */ + "movq %%mm0, %%mm2 \n\t" /* 3 3 2 2 1 1 0 0 */ + "punpcklwd %%mm0, %%mm0 \n\t" /* 1 1 1 1 0 0 0 0 */ + "movq %%mm0, %%mm3 \n\t" /* 1 1 1 1 0 0 0 0 */ + "punpckldq %%mm0, %%mm0 \n\t" /* 0 0 0 0 0 0 0 0 */ + "punpckhdq %%mm3, %%mm3 \n\t" /* 1 1 1 1 1 1 1 1 */ "movq %%mm0, (%%edi) \n\t" - "punpckhwd %%mm2, %%mm2 \n\t" // 3 3 3 3 2 2 2 2 + "punpckhwd %%mm2, %%mm2 \n\t" /* 3 3 3 3 2 2 2 2 */ "movq %%mm3, 8(%%edi) \n\t" - "movq %%mm2, %%mm4 \n\t" // 3 3 3 3 2 2 2 2 - "punpckldq %%mm2, %%mm2 \n\t" // 2 2 2 2 2 2 2 2 - "punpckhdq %%mm4, %%mm4 \n\t" // 3 3 3 3 3 3 3 3 + "movq %%mm2, %%mm4 \n\t" /* 3 3 3 3 2 2 2 2 */ + "punpckldq %%mm2, %%mm2 \n\t" /* 2 2 2 2 2 2 2 2 */ + "punpckhdq %%mm4, %%mm4 \n\t" /* 3 3 3 3 3 3 3 3 */ "movq %%mm2, 16(%%edi) \n\t" "subl $4, %%esi \n\t" "movq %%mm4, 24(%%edi) \n\t" "subl $32, %%edi \n\t" "subl $4, %%ecx \n\t" "jnz .loop1_pass0 \n\t" - "EMMS \n\t" // DONE + "EMMS \n\t" /* DONE */ - : "=c" (dummy_value_c), // output regs (dummy) + : "=c" (dummy_value_c), /* output regs (dummy) */ "=S" (dummy_value_S), "=D" (dummy_value_D) - : "1" (sptr), // esi // input regs - "2" (dp), // edi - "0" (width_mmx) // ecx + : "1" (sptr), /* esi // input regs */ + "2" (dp), /* edi */ + "0" (width_mmx) /* ecx */ #if 0 /* %mm0, ..., %mm4 not supported by gcc 2.7.2.3 or egcs 1.1 */ - : "%mm0", "%mm1", "%mm2" // clobber list + : "%mm0", "%mm1", "%mm2" /* clobber list */ , "%mm3", "%mm4" #endif ); @@ -1981,10 +1990,10 @@ png_do_read_interlace(png_structp png_ptr) else if (((pass == 2) || (pass == 3)) && width) { int width_mmx = ((width >> 2) << 2); - width -= width_mmx; // 0-3 pixels => 0-3 bytes + width -= width_mmx; /* 0-3 pixels => 0-3 bytes */ if (width_mmx) { - int dummy_value_c; // fix 'forbidden register spilled' + int dummy_value_c; /* fix 'forbidden register spilled' */ int dummy_value_S; int dummy_value_D; @@ -1993,29 +2002,29 @@ png_do_read_interlace(png_structp png_ptr) "subl $15, %%edi \n\t" ".loop1_pass2: \n\t" - "movd (%%esi), %%mm0 \n\t" // x x x x 3 2 1 0 - "punpcklbw %%mm0, %%mm0 \n\t" // 3 3 2 2 1 1 0 0 - "movq %%mm0, %%mm1 \n\t" // 3 3 2 2 1 1 0 0 - "punpcklwd %%mm0, %%mm0 \n\t" // 1 1 1 1 0 0 0 0 - "punpckhwd %%mm1, %%mm1 \n\t" // 3 3 3 3 2 2 2 2 + "movd (%%esi), %%mm0 \n\t" /* x x x x 3 2 1 0 */ + "punpcklbw %%mm0, %%mm0 \n\t" /* 3 3 2 2 1 1 0 0 */ + "movq %%mm0, %%mm1 \n\t" /* 3 3 2 2 1 1 0 0 */ + "punpcklwd %%mm0, %%mm0 \n\t" /* 1 1 1 1 0 0 0 0 */ + "punpckhwd %%mm1, %%mm1 \n\t" /* 3 3 3 3 2 2 2 2 */ "movq %%mm0, (%%edi) \n\t" "subl $4, %%esi \n\t" "movq %%mm1, 8(%%edi) \n\t" "subl $16, %%edi \n\t" "subl $4, %%ecx \n\t" "jnz .loop1_pass2 \n\t" - "EMMS \n\t" // DONE + "EMMS \n\t" /* DONE */ - : "=c" (dummy_value_c), // output regs (dummy) + : "=c" (dummy_value_c), /* output regs (dummy) */ "=S" (dummy_value_S), "=D" (dummy_value_D) - : "1" (sptr), // esi // input regs - "2" (dp), // edi - "0" (width_mmx) // ecx + : "1" (sptr), /* esi // input regs */ + "2" (dp), /* edi */ + "0" (width_mmx) /* ecx */ #if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */ - : "%mm0", "%mm1" // clobber list + : "%mm0", "%mm1" /* clobber list */ #endif ); } @@ -2036,10 +2045,10 @@ png_do_read_interlace(png_structp png_ptr) else if (width) /* && ((pass == 4) || (pass == 5)) */ { int width_mmx = ((width >> 3) << 3); - width -= width_mmx; // 0-3 pixels => 0-3 bytes + width -= width_mmx; /* 0-3 pixels => 0-3 bytes */ if (width_mmx) { - int dummy_value_c; // fix 'forbidden register spilled' + int dummy_value_c; /* fix 'forbidden register spilled' */ int dummy_value_S; int dummy_value_D; @@ -2048,28 +2057,28 @@ png_do_read_interlace(png_structp png_ptr) "subl $15, %%edi \n\t" ".loop1_pass4: \n\t" - "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0 - "movq %%mm0, %%mm1 \n\t" // 7 6 5 4 3 2 1 0 - "punpcklbw %%mm0, %%mm0 \n\t" // 3 3 2 2 1 1 0 0 - "punpckhbw %%mm1, %%mm1 \n\t" // 7 7 6 6 5 5 4 4 + "movq (%%esi), %%mm0 \n\t" /* 7 6 5 4 3 2 1 0 */ + "movq %%mm0, %%mm1 \n\t" /* 7 6 5 4 3 2 1 0 */ + "punpcklbw %%mm0, %%mm0 \n\t" /* 3 3 2 2 1 1 0 0 */ + "punpckhbw %%mm1, %%mm1 \n\t" /* 7 7 6 6 5 5 4 4 */ "movq %%mm1, 8(%%edi) \n\t" "subl $8, %%esi \n\t" "movq %%mm0, (%%edi) \n\t" "subl $16, %%edi \n\t" "subl $8, %%ecx \n\t" "jnz .loop1_pass4 \n\t" - "EMMS \n\t" // DONE + "EMMS \n\t" /* DONE */ - : "=c" (dummy_value_c), // output regs (none) + : "=c" (dummy_value_c), /* output regs (none) */ "=S" (dummy_value_S), "=D" (dummy_value_D) - : "1" (sptr), // esi // input regs - "2" (dp), // edi - "0" (width_mmx) // ecx + : "1" (sptr), /* esi // input regs */ + "2" (dp), /* edi */ + "0" (width_mmx) /* ecx */ #if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */ - : "%mm0", "%mm1" // clobber list + : "%mm0", "%mm1" /* clobber list */ #endif ); } @@ -2095,10 +2104,10 @@ png_do_read_interlace(png_structp png_ptr) if (((pass == 0) || (pass == 1)) && width) { int width_mmx = ((width >> 1) << 1); - width -= width_mmx; // 0,1 pixels => 0,2 bytes + width -= width_mmx; /* 0,1 pixels => 0,2 bytes */ if (width_mmx) { - int dummy_value_c; // fix 'forbidden register spilled' + int dummy_value_c; /* fix 'forbidden register spilled' */ int dummy_value_S; int dummy_value_D; @@ -2107,11 +2116,11 @@ png_do_read_interlace(png_structp png_ptr) "subl $30, %%edi \n\t" ".loop2_pass0: \n\t" - "movd (%%esi), %%mm0 \n\t" // x x x x 3 2 1 0 - "punpcklwd %%mm0, %%mm0 \n\t" // 3 2 3 2 1 0 1 0 - "movq %%mm0, %%mm1 \n\t" // 3 2 3 2 1 0 1 0 - "punpckldq %%mm0, %%mm0 \n\t" // 1 0 1 0 1 0 1 0 - "punpckhdq %%mm1, %%mm1 \n\t" // 3 2 3 2 3 2 3 2 + "movd (%%esi), %%mm0 \n\t" /* x x x x 3 2 1 0 */ + "punpcklwd %%mm0, %%mm0 \n\t" /* 3 2 3 2 1 0 1 0 */ + "movq %%mm0, %%mm1 \n\t" /* 3 2 3 2 1 0 1 0 */ + "punpckldq %%mm0, %%mm0 \n\t" /* 1 0 1 0 1 0 1 0 */ + "punpckhdq %%mm1, %%mm1 \n\t" /* 3 2 3 2 3 2 3 2 */ "movq %%mm0, (%%edi) \n\t" "movq %%mm0, 8(%%edi) \n\t" "movq %%mm1, 16(%%edi) \n\t" @@ -2120,24 +2129,24 @@ png_do_read_interlace(png_structp png_ptr) "subl $32, %%edi \n\t" "subl $2, %%ecx \n\t" "jnz .loop2_pass0 \n\t" - "EMMS \n\t" // DONE + "EMMS \n\t" /* DONE */ - : "=c" (dummy_value_c), // output regs (dummy) + : "=c" (dummy_value_c), /* output regs (dummy) */ "=S" (dummy_value_S), "=D" (dummy_value_D) - : "1" (sptr), // esi // input regs - "2" (dp), // edi - "0" (width_mmx) // ecx + : "1" (sptr), /* esi // input regs */ + "2" (dp), /* edi */ + "0" (width_mmx) /* ecx */ #if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */ - : "%mm0", "%mm1" // clobber list + : "%mm0", "%mm1" /* clobber list */ #endif ); } - sptr -= (width_mmx*2 - 2); // sign fixed - dp -= (width_mmx*16 - 2); // sign fixed + sptr -= (width_mmx*2 - 2); /* sign fixed */ + dp -= (width_mmx*16 - 2); /* sign fixed */ for (i = width; i; i--) { png_byte v[8]; @@ -2154,10 +2163,10 @@ png_do_read_interlace(png_structp png_ptr) else if (((pass == 2) || (pass == 3)) && width) { int width_mmx = ((width >> 1) << 1) ; - width -= width_mmx; // 0,1 pixels => 0,2 bytes + width -= width_mmx; /* 0,1 pixels => 0,2 bytes */ if (width_mmx) { - int dummy_value_c; // fix 'forbidden register spilled' + int dummy_value_c; /* fix 'forbidden register spilled' */ int dummy_value_S; int dummy_value_D; @@ -2166,35 +2175,35 @@ png_do_read_interlace(png_structp png_ptr) "subl $14, %%edi \n\t" ".loop2_pass2: \n\t" - "movd (%%esi), %%mm0 \n\t" // x x x x 3 2 1 0 - "punpcklwd %%mm0, %%mm0 \n\t" // 3 2 3 2 1 0 1 0 - "movq %%mm0, %%mm1 \n\t" // 3 2 3 2 1 0 1 0 - "punpckldq %%mm0, %%mm0 \n\t" // 1 0 1 0 1 0 1 0 - "punpckhdq %%mm1, %%mm1 \n\t" // 3 2 3 2 3 2 3 2 + "movd (%%esi), %%mm0 \n\t" /* x x x x 3 2 1 0 */ + "punpcklwd %%mm0, %%mm0 \n\t" /* 3 2 3 2 1 0 1 0 */ + "movq %%mm0, %%mm1 \n\t" /* 3 2 3 2 1 0 1 0 */ + "punpckldq %%mm0, %%mm0 \n\t" /* 1 0 1 0 1 0 1 0 */ + "punpckhdq %%mm1, %%mm1 \n\t" /* 3 2 3 2 3 2 3 2 */ "movq %%mm0, (%%edi) \n\t" "subl $4, %%esi \n\t" "movq %%mm1, 8(%%edi) \n\t" "subl $16, %%edi \n\t" "subl $2, %%ecx \n\t" "jnz .loop2_pass2 \n\t" - "EMMS \n\t" // DONE + "EMMS \n\t" /* DONE */ - : "=c" (dummy_value_c), // output regs (dummy) + : "=c" (dummy_value_c), /* output regs (dummy) */ "=S" (dummy_value_S), "=D" (dummy_value_D) - : "1" (sptr), // esi // input regs - "2" (dp), // edi - "0" (width_mmx) // ecx + : "1" (sptr), /* esi // input regs */ + "2" (dp), /* edi */ + "0" (width_mmx) /* ecx */ #if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */ - : "%mm0", "%mm1" // clobber list + : "%mm0", "%mm1" /* clobber list */ #endif ); } - sptr -= (width_mmx*2 - 2); // sign fixed - dp -= (width_mmx*8 - 2); // sign fixed + sptr -= (width_mmx*2 - 2); /* sign fixed */ + dp -= (width_mmx*8 - 2); /* sign fixed */ for (i = width; i; i--) { png_byte v[8]; @@ -2208,13 +2217,13 @@ png_do_read_interlace(png_structp png_ptr) } } } - else if (width) // pass == 4 or 5 + else if (width) /* pass == 4 or 5 */ { int width_mmx = ((width >> 1) << 1) ; - width -= width_mmx; // 0,1 pixels => 0,2 bytes + width -= width_mmx; /* 0,1 pixels => 0,2 bytes */ if (width_mmx) { - int dummy_value_c; // fix 'forbidden register spilled' + int dummy_value_c; /* fix 'forbidden register spilled' */ int dummy_value_S; int dummy_value_D; @@ -2223,31 +2232,31 @@ png_do_read_interlace(png_structp png_ptr) "subl $6, %%edi \n\t" ".loop2_pass4: \n\t" - "movd (%%esi), %%mm0 \n\t" // x x x x 3 2 1 0 - "punpcklwd %%mm0, %%mm0 \n\t" // 3 2 3 2 1 0 1 0 + "movd (%%esi), %%mm0 \n\t" /* x x x x 3 2 1 0 */ + "punpcklwd %%mm0, %%mm0 \n\t" /* 3 2 3 2 1 0 1 0 */ "subl $4, %%esi \n\t" "movq %%mm0, (%%edi) \n\t" "subl $8, %%edi \n\t" "subl $2, %%ecx \n\t" "jnz .loop2_pass4 \n\t" - "EMMS \n\t" // DONE + "EMMS \n\t" /* DONE */ - : "=c" (dummy_value_c), // output regs (dummy) + : "=c" (dummy_value_c), /* output regs (dummy) */ "=S" (dummy_value_S), "=D" (dummy_value_D) - : "1" (sptr), // esi // input regs - "2" (dp), // edi - "0" (width_mmx) // ecx + : "1" (sptr), /* esi // input regs */ + "2" (dp), /* edi */ + "0" (width_mmx) /* ecx */ #if 0 /* %mm0 not supported by gcc 2.7.2.3 or egcs 1.1 */ - : "%mm0" // clobber list + : "%mm0" /* clobber list */ #endif ); } - sptr -= (width_mmx*2 - 2); // sign fixed - dp -= (width_mmx*4 - 2); // sign fixed + sptr -= (width_mmx*2 - 2); /* sign fixed */ + dp -= (width_mmx*4 - 2); /* sign fixed */ for (i = width; i; i--) { png_byte v[8]; @@ -2269,10 +2278,10 @@ png_do_read_interlace(png_structp png_ptr) if (((pass == 0) || (pass == 1)) && width) { int width_mmx = ((width >> 1) << 1); - width -= width_mmx; // 0,1 pixels => 0,4 bytes + width -= width_mmx; /* 0,1 pixels => 0,4 bytes */ if (width_mmx) { - int dummy_value_c; // fix 'forbidden register spilled' + int dummy_value_c; /* fix 'forbidden register spilled' */ int dummy_value_S; int dummy_value_D; @@ -2281,10 +2290,10 @@ png_do_read_interlace(png_structp png_ptr) "subl $60, %%edi \n\t" ".loop4_pass0: \n\t" - "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0 - "movq %%mm0, %%mm1 \n\t" // 7 6 5 4 3 2 1 0 - "punpckldq %%mm0, %%mm0 \n\t" // 3 2 1 0 3 2 1 0 - "punpckhdq %%mm1, %%mm1 \n\t" // 7 6 5 4 7 6 5 4 + "movq (%%esi), %%mm0 \n\t" /* 7 6 5 4 3 2 1 0 */ + "movq %%mm0, %%mm1 \n\t" /* 7 6 5 4 3 2 1 0 */ + "punpckldq %%mm0, %%mm0 \n\t" /* 3 2 1 0 3 2 1 0 */ + "punpckhdq %%mm1, %%mm1 \n\t" /* 7 6 5 4 7 6 5 4 */ "movq %%mm0, (%%edi) \n\t" "movq %%mm0, 8(%%edi) \n\t" "movq %%mm0, 16(%%edi) \n\t" @@ -2297,24 +2306,24 @@ png_do_read_interlace(png_structp png_ptr) "subl $64, %%edi \n\t" "subl $2, %%ecx \n\t" "jnz .loop4_pass0 \n\t" - "EMMS \n\t" // DONE + "EMMS \n\t" /* DONE */ - : "=c" (dummy_value_c), // output regs (dummy) + : "=c" (dummy_value_c), /* output regs (dummy) */ "=S" (dummy_value_S), "=D" (dummy_value_D) - : "1" (sptr), // esi // input regs - "2" (dp), // edi - "0" (width_mmx) // ecx + : "1" (sptr), /* esi // input regs */ + "2" (dp), /* edi */ + "0" (width_mmx) /* ecx */ #if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */ - : "%mm0", "%mm1" // clobber list + : "%mm0", "%mm1" /* clobber list */ #endif ); } - sptr -= (width_mmx*4 - 4); // sign fixed - dp -= (width_mmx*32 - 4); // sign fixed + sptr -= (width_mmx*4 - 4); /* sign fixed */ + dp -= (width_mmx*32 - 4); /* sign fixed */ for (i = width; i; i--) { png_byte v[8]; @@ -2331,10 +2340,10 @@ png_do_read_interlace(png_structp png_ptr) else if (((pass == 2) || (pass == 3)) && width) { int width_mmx = ((width >> 1) << 1); - width -= width_mmx; // 0,1 pixels => 0,4 bytes + width -= width_mmx; /* 0,1 pixels => 0,4 bytes */ if (width_mmx) { - int dummy_value_c; // fix 'forbidden register spilled' + int dummy_value_c; /* fix 'forbidden register spilled' */ int dummy_value_S; int dummy_value_D; @@ -2343,10 +2352,10 @@ png_do_read_interlace(png_structp png_ptr) "subl $28, %%edi \n\t" ".loop4_pass2: \n\t" - "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0 - "movq %%mm0, %%mm1 \n\t" // 7 6 5 4 3 2 1 0 - "punpckldq %%mm0, %%mm0 \n\t" // 3 2 1 0 3 2 1 0 - "punpckhdq %%mm1, %%mm1 \n\t" // 7 6 5 4 7 6 5 4 + "movq (%%esi), %%mm0 \n\t" /* 7 6 5 4 3 2 1 0 */ + "movq %%mm0, %%mm1 \n\t" /* 7 6 5 4 3 2 1 0 */ + "punpckldq %%mm0, %%mm0 \n\t" /* 3 2 1 0 3 2 1 0 */ + "punpckhdq %%mm1, %%mm1 \n\t" /* 7 6 5 4 7 6 5 4 */ "movq %%mm0, (%%edi) \n\t" "movq %%mm0, 8(%%edi) \n\t" "movq %%mm1, 16(%%edi) \n\t" @@ -2355,24 +2364,24 @@ png_do_read_interlace(png_structp png_ptr) "subl $32, %%edi \n\t" "subl $2, %%ecx \n\t" "jnz .loop4_pass2 \n\t" - "EMMS \n\t" // DONE + "EMMS \n\t" /* DONE */ - : "=c" (dummy_value_c), // output regs (dummy) + : "=c" (dummy_value_c), /* output regs (dummy) */ "=S" (dummy_value_S), "=D" (dummy_value_D) - : "1" (sptr), // esi // input regs - "2" (dp), // edi - "0" (width_mmx) // ecx + : "1" (sptr), /* esi // input regs */ + "2" (dp), /* edi */ + "0" (width_mmx) /* ecx */ #if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */ - : "%mm0", "%mm1" // clobber list + : "%mm0", "%mm1" /* clobber list */ #endif ); } - sptr -= (width_mmx*4 - 4); // sign fixed - dp -= (width_mmx*16 - 4); // sign fixed + sptr -= (width_mmx*4 - 4); /* sign fixed */ + dp -= (width_mmx*16 - 4); /* sign fixed */ for (i = width; i; i--) { png_byte v[8]; @@ -2386,13 +2395,13 @@ png_do_read_interlace(png_structp png_ptr) } } } - else if (width) // pass == 4 or 5 + else if (width) /* pass == 4 or 5 */ { int width_mmx = ((width >> 1) << 1) ; - width -= width_mmx; // 0,1 pixels => 0,4 bytes + width -= width_mmx; /* 0,1 pixels => 0,4 bytes */ if (width_mmx) { - int dummy_value_c; // fix 'forbidden register spilled' + int dummy_value_c; /* fix 'forbidden register spilled' */ int dummy_value_S; int dummy_value_D; @@ -2401,34 +2410,34 @@ png_do_read_interlace(png_structp png_ptr) "subl $12, %%edi \n\t" ".loop4_pass4: \n\t" - "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0 - "movq %%mm0, %%mm1 \n\t" // 7 6 5 4 3 2 1 0 - "punpckldq %%mm0, %%mm0 \n\t" // 3 2 1 0 3 2 1 0 - "punpckhdq %%mm1, %%mm1 \n\t" // 7 6 5 4 7 6 5 4 + "movq (%%esi), %%mm0 \n\t" /* 7 6 5 4 3 2 1 0 */ + "movq %%mm0, %%mm1 \n\t" /* 7 6 5 4 3 2 1 0 */ + "punpckldq %%mm0, %%mm0 \n\t" /* 3 2 1 0 3 2 1 0 */ + "punpckhdq %%mm1, %%mm1 \n\t" /* 7 6 5 4 7 6 5 4 */ "movq %%mm0, (%%edi) \n\t" "subl $8, %%esi \n\t" "movq %%mm1, 8(%%edi) \n\t" "subl $16, %%edi \n\t" "subl $2, %%ecx \n\t" "jnz .loop4_pass4 \n\t" - "EMMS \n\t" // DONE + "EMMS \n\t" /* DONE */ - : "=c" (dummy_value_c), // output regs (dummy) + : "=c" (dummy_value_c), /* output regs (dummy) */ "=S" (dummy_value_S), "=D" (dummy_value_D) - : "1" (sptr), // esi // input regs - "2" (dp), // edi - "0" (width_mmx) // ecx + : "1" (sptr), /* esi // input regs */ + "2" (dp), /* edi */ + "0" (width_mmx) /* ecx */ #if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */ - : "%mm0", "%mm1" // clobber list + : "%mm0", "%mm1" /* clobber list */ #endif ); } - sptr -= (width_mmx*4 - 4); // sign fixed - dp -= (width_mmx*8 - 4); // sign fixed + sptr -= (width_mmx*4 - 4); /* sign fixed */ + dp -= (width_mmx*8 - 4); /* sign fixed */ for (i = width; i; i--) { png_byte v[8]; @@ -2447,21 +2456,21 @@ png_do_read_interlace(png_structp png_ptr) //-------------------------------------------------------------- else if (pixel_bytes == 8) { -// GRR TEST: should work, but needs testing (special 64-bit version of rpng2?) - // GRR NOTE: no need to combine passes here! +/* GRR TEST: should work, but needs testing (special 64-bit version of rpng2?) */ + /* GRR NOTE: no need to combine passes here! */ if (((pass == 0) || (pass == 1)) && width) { - int dummy_value_c; // fix 'forbidden register spilled' + int dummy_value_c; /* fix 'forbidden register spilled' */ int dummy_value_S; int dummy_value_D; - // source is 8-byte RRGGBBAA - // dest is 64-byte RRGGBBAA RRGGBBAA RRGGBBAA RRGGBBAA ... + /* source is 8-byte RRGGBBAA */ + /* dest is 64-byte RRGGBBAA RRGGBBAA RRGGBBAA RRGGBBAA ... */ __asm__ __volatile__ ( - "subl $56, %%edi \n\t" // start of last block + "subl $56, %%edi \n\t" /* start of last block */ ".loop8_pass0: \n\t" - "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0 + "movq (%%esi), %%mm0 \n\t" /* 7 6 5 4 3 2 1 0 */ "movq %%mm0, (%%edi) \n\t" "movq %%mm0, 8(%%edi) \n\t" "movq %%mm0, 16(%%edi) \n\t" @@ -2474,37 +2483,37 @@ png_do_read_interlace(png_structp png_ptr) "subl $64, %%edi \n\t" "decl %%ecx \n\t" "jnz .loop8_pass0 \n\t" - "EMMS \n\t" // DONE + "EMMS \n\t" /* DONE */ - : "=c" (dummy_value_c), // output regs (dummy) + : "=c" (dummy_value_c), /* output regs (dummy) */ "=S" (dummy_value_S), "=D" (dummy_value_D) - : "1" (sptr), // esi // input regs - "2" (dp), // edi - "0" (width) // ecx + : "1" (sptr), /* esi // input regs */ + "2" (dp), /* edi */ + "0" (width) /* ecx */ #if 0 /* %mm0 not supported by gcc 2.7.2.3 or egcs 1.1 */ - : "%mm0" // clobber list + : "%mm0" /* clobber list */ #endif ); } else if (((pass == 2) || (pass == 3)) && width) { - // source is 8-byte RRGGBBAA - // dest is 32-byte RRGGBBAA RRGGBBAA RRGGBBAA RRGGBBAA - // (recall that expansion is _in place_: sptr and dp - // both point at locations within same row buffer) + /* source is 8-byte RRGGBBAA */ + /* dest is 32-byte RRGGBBAA RRGGBBAA RRGGBBAA RRGGBBAA */ + /* (recall that expansion is _in place_: sptr and dp */ + /* both point at locations within same row buffer) */ { - int dummy_value_c; // fix 'forbidden register spilled' + int dummy_value_c; /* fix 'forbidden register spilled' */ int dummy_value_S; int dummy_value_D; __asm__ __volatile__ ( - "subl $24, %%edi \n\t" // start of last block + "subl $24, %%edi \n\t" /* start of last block */ ".loop8_pass2: \n\t" - "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0 + "movq (%%esi), %%mm0 \n\t" /* 7 6 5 4 3 2 1 0 */ "movq %%mm0, (%%edi) \n\t" "movq %%mm0, 8(%%edi) \n\t" "movq %%mm0, 16(%%edi) \n\t" @@ -2513,54 +2522,54 @@ png_do_read_interlace(png_structp png_ptr) "subl $32, %%edi \n\t" "decl %%ecx \n\t" "jnz .loop8_pass2 \n\t" - "EMMS \n\t" // DONE + "EMMS \n\t" /* DONE */ - : "=c" (dummy_value_c), // output regs (dummy) + : "=c" (dummy_value_c), /* output regs (dummy) */ "=S" (dummy_value_S), "=D" (dummy_value_D) - : "1" (sptr), // esi // input regs - "2" (dp), // edi - "0" (width) // ecx + : "1" (sptr), /* esi // input regs */ + "2" (dp), /* edi */ + "0" (width) /* ecx */ #if 0 /* %mm0 not supported by gcc 2.7.2.3 or egcs 1.1 */ - : "%mm0" // clobber list + : "%mm0" /* clobber list */ #endif ); } } - else if (width) // pass == 4 or 5 + else if (width) /* pass == 4 or 5 */ { - // source is 8-byte RRGGBBAA - // dest is 16-byte RRGGBBAA RRGGBBAA + /* source is 8-byte RRGGBBAA */ + /* dest is 16-byte RRGGBBAA RRGGBBAA */ { - int dummy_value_c; // fix 'forbidden register spilled' + int dummy_value_c; /* fix 'forbidden register spilled' */ int dummy_value_S; int dummy_value_D; __asm__ __volatile__ ( - "subl $8, %%edi \n\t" // start of last block + "subl $8, %%edi \n\t" /* start of last block */ ".loop8_pass4: \n\t" - "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0 + "movq (%%esi), %%mm0 \n\t" /* 7 6 5 4 3 2 1 0 */ "movq %%mm0, (%%edi) \n\t" "subl $8, %%esi \n\t" "movq %%mm0, 8(%%edi) \n\t" "subl $16, %%edi \n\t" "decl %%ecx \n\t" "jnz .loop8_pass4 \n\t" - "EMMS \n\t" // DONE + "EMMS \n\t" /* DONE */ - : "=c" (dummy_value_c), // output regs (dummy) + : "=c" (dummy_value_c), /* output regs (dummy) */ "=S" (dummy_value_S), "=D" (dummy_value_D) - : "1" (sptr), // esi // input regs - "2" (dp), // edi - "0" (width) // ecx + : "1" (sptr), /* esi // input regs */ + "2" (dp), /* edi */ + "0" (width) /* ecx */ #if 0 /* %mm0 not supported by gcc 2.7.2.3 or egcs 1.1 */ - : "%mm0" // clobber list + : "%mm0" /* clobber list */ #endif ); } @@ -2601,7 +2610,7 @@ png_do_read_interlace(png_structp png_ptr) sptr-= pixel_bytes; } } - } // end of _mmx_supported ======================================== + } /* end of _mmx_supported ======================================== */ else /* MMX not supported: use modified C code - takes advantage * of inlining of png_memcpy for a constant */ @@ -2727,8 +2736,8 @@ png_do_read_interlace(png_structp png_ptr) } /* end switch (row_info->pixel_depth) */ row_info->width = final_width; - row_info->rowbytes = ((final_width * - (png_uint_32)row_info->pixel_depth + 7) >> 3); + + row_info->rowbytes = PNG_ROWBYTES(row_info->pixel_depth,final_width); } } /* end png_do_read_interlace() */ @@ -2741,8 +2750,8 @@ png_do_read_interlace(png_structp png_ptr) #if defined(PNG_HAVE_ASSEMBLER_READ_FILTER_ROW) #if defined(PNG_ASSEMBLER_CODE_SUPPORTED) -// These variables are utilized in the functions below. They are declared -// globally here to ensure alignment on 8-byte boundaries. +/* These variables are utilized in the functions below. They are declared */ +/* globally here to ensure alignment on 8-byte boundaries. */ union uAll { long long use; @@ -2752,565 +2761,565 @@ union uAll { _ActiveMask, _ActiveMask2, _ActiveMaskEnd, _ShiftBpp, _ShiftRem; #ifdef PNG_THREAD_UNSAFE_OK -//===========================================================================// -// // -// P N G _ R E A D _ F I L T E R _ R O W _ M M X _ A V G // -// // -//===========================================================================// +/*===========================================================================*/ +/* */ +/* P N G _ R E A D _ F I L T E R _ R O W _ M M X _ A V G */ +/* */ +/*===========================================================================*/ -// Optimized code for PNG Average filter decoder +/* Optimized code for PNG Average filter decoder */ static void /* PRIVATE */ png_read_filter_row_mmx_avg(png_row_infop row_info, png_bytep row, png_bytep prev_row) { int bpp; - int dummy_value_c; // fix 'forbidden register 2 (cx) was spilled' error + int dummy_value_c; /* fix 'forbidden register 2 (cx) was spilled' error */ int dummy_value_S; int dummy_value_D; - bpp = (row_info->pixel_depth + 7) >> 3; // get # bytes per pixel - _FullLength = row_info->rowbytes; // # of bytes to filter + bpp = (row_info->pixel_depth + 7) >> 3; /* get # bytes per pixel */ + _FullLength = row_info->rowbytes; /* # of bytes to filter */ __asm__ __volatile__ ( - // initialize address pointers and offset + /* initialize address pointers and offset */ #ifdef __PIC__ - "pushl %%ebx \n\t" // save index to Global Offset Table + "pushl %%ebx \n\t" /* save index to Global Offset Table */ #endif -//pre "movl row, %%edi \n\t" // edi: Avg(x) - "xorl %%ebx, %%ebx \n\t" // ebx: x +/*pre "movl row, %%edi \n\t" */ /* edi: Avg(x) */ + "xorl %%ebx, %%ebx \n\t" /* ebx: x */ "movl %%edi, %%edx \n\t" -//pre "movl prev_row, %%esi \n\t" // esi: Prior(x) -//pre "subl bpp, %%edx \n\t" // (bpp is preloaded into ecx) - "subl %%ecx, %%edx \n\t" // edx: Raw(x-bpp) +/*pre "movl prev_row, %%esi \n\t" */ /* esi: Prior(x) */ +/*pre "subl bpp, %%edx \n\t" */ /* (bpp is preloaded into ecx) */ + "subl %%ecx, %%edx \n\t" /* edx: Raw(x-bpp) */ "xorl %%eax,%%eax \n\t" - // Compute the Raw value for the first bpp bytes - // Raw(x) = Avg(x) + (Prior(x)/2) + /* Compute the Raw value for the first bpp bytes */ + /* Raw(x) = Avg(x) + (Prior(x)/2) */ "avg_rlp: \n\t" - "movb (%%esi,%%ebx,),%%al \n\t" // load al with Prior(x) + "movb (%%esi,%%ebx,),%%al \n\t" /* load al with Prior(x) */ "incl %%ebx \n\t" - "shrb %%al \n\t" // divide by 2 - "addb -1(%%edi,%%ebx,),%%al \n\t" // add Avg(x); -1 to offset inc ebx -//pre "cmpl bpp, %%ebx \n\t" // (bpp is preloaded into ecx) + "shrb %%al \n\t" /* divide by 2 */ + "addb -1(%%edi,%%ebx,),%%al \n\t" /* add Avg(x); -1 to offset inc ebx */ +/* pre "cmpl bpp, %%ebx \n\t" */ /* (bpp is preloaded into ecx) */ "cmpl %%ecx, %%ebx \n\t" - "movb %%al,-1(%%edi,%%ebx,) \n\t" // write Raw(x); -1 to offset inc ebx - "jb avg_rlp \n\t" // mov does not affect flags - - // get # of bytes to alignment - "movl %%edi, _dif \n\t" // take start of row - "addl %%ebx, _dif \n\t" // add bpp - "addl $0xf, _dif \n\t" // add 7+8 to incr past alignment bdry - "andl $0xfffffff8, _dif \n\t" // mask to alignment boundary - "subl %%edi, _dif \n\t" // subtract from start => value ebx at - "jz avg_go \n\t" // alignment - - // fix alignment - // Compute the Raw value for the bytes up to the alignment boundary - // Raw(x) = Avg(x) + ((Raw(x-bpp) + Prior(x))/2) + "movb %%al,-1(%%edi,%%ebx,) \n\t" /* write Raw(x); -1 to offset inc ebx */ + "jb avg_rlp \n\t" /* mov does not affect flags */ + + /* get # of bytes to alignment */ + "movl %%edi, _dif \n\t" /* take start of row */ + "addl %%ebx, _dif \n\t" /* add bpp */ + "addl $0xf, _dif \n\t" /* add 7+8 to incr past alignment bdry */ + "andl $0xfffffff8, _dif \n\t" /* mask to alignment boundary */ + "subl %%edi, _dif \n\t" /* subtract from start => value ebx at */ + "jz avg_go \n\t" /* alignment */ + + /* fix alignment */ + /* Compute the Raw value for the bytes up to the alignment boundary */ + /* Raw(x) = Avg(x) + ((Raw(x-bpp) + Prior(x))/2) */ "xorl %%ecx, %%ecx \n\t" "avg_lp1: \n\t" "xorl %%eax, %%eax \n\t" - "movb (%%esi,%%ebx,), %%cl \n\t" // load cl with Prior(x) - "movb (%%edx,%%ebx,), %%al \n\t" // load al with Raw(x-bpp) + "movb (%%esi,%%ebx,), %%cl \n\t" /* load cl with Prior(x) */ + "movb (%%edx,%%ebx,), %%al \n\t" /* load al with Raw(x-bpp) */ "addw %%cx, %%ax \n\t" "incl %%ebx \n\t" - "shrw %%ax \n\t" // divide by 2 - "addb -1(%%edi,%%ebx,), %%al \n\t" // add Avg(x); -1 to offset inc ebx - "cmpl _dif, %%ebx \n\t" // check if at alignment boundary - "movb %%al, -1(%%edi,%%ebx,) \n\t" // write Raw(x); -1 to offset inc ebx - "jb avg_lp1 \n\t" // repeat until at alignment boundary + "shrw %%ax \n\t" /* divide by 2 */ + "addb -1(%%edi,%%ebx,), %%al \n\t" /* add Avg(x); -1 to offset inc ebx */ + "cmpl _dif, %%ebx \n\t" /* check if at alignment boundary */ + "movb %%al, -1(%%edi,%%ebx,) \n\t" /* write Raw(x); -1 to offset inc ebx */ + "jb avg_lp1 \n\t" /* repeat until at alignment boundary */ "avg_go: \n\t" "movl _FullLength, %%eax \n\t" "movl %%eax, %%ecx \n\t" - "subl %%ebx, %%eax \n\t" // subtract alignment fix - "andl $0x00000007, %%eax \n\t" // calc bytes over mult of 8 - "subl %%eax, %%ecx \n\t" // drop over bytes from original length + "subl %%ebx, %%eax \n\t" /* subtract alignment fix */ + "andl $0x00000007, %%eax \n\t" /* calc bytes over mult of 8 */ + "subl %%eax, %%ecx \n\t" /* drop over bytes from original length */ "movl %%ecx, _MMXLength \n\t" #ifdef __PIC__ - "popl %%ebx \n\t" // restore index to Global Offset Table + "popl %%ebx \n\t" /* restore index to Global Offset Table */ #endif - : "=c" (dummy_value_c), // output regs (dummy) + : "=c" (dummy_value_c), /* output regs (dummy) */ "=S" (dummy_value_S), "=D" (dummy_value_D) - : "0" (bpp), // ecx // input regs - "1" (prev_row), // esi - "2" (row) // edi + : "0" (bpp), /* ecx // input regs */ + "1" (prev_row), /* esi */ + "2" (row) /* edi */ - : "%eax", "%edx" // clobber list + : "%eax", "%edx" /* clobber list */ #ifndef __PIC__ , "%ebx" #endif - // GRR: INCLUDE "memory" as clobbered? (_dif, _MMXLength) - // (seems to work fine without...) + /* GRR: INCLUDE "memory" as clobbered? (_dif, _MMXLength) */ + /* (seems to work fine without...) */ ); - // now do the math for the rest of the row + /* now do the math for the rest of the row */ switch (bpp) { case 3: { _ActiveMask.use = 0x0000000000ffffffLL; - _ShiftBpp.use = 24; // == 3 * 8 - _ShiftRem.use = 40; // == 64 - 24 + _ShiftBpp.use = 24; /* == 3 * 8 */ + _ShiftRem.use = 40; /* == 64 - 24 */ __asm__ __volatile__ ( - // re-init address pointers and offset + /* re-init address pointers and offset */ "movq _ActiveMask, %%mm7 \n\t" - "movl _dif, %%ecx \n\t" // ecx: x = offset to - "movq _LBCarryMask, %%mm5 \n\t" // alignment boundary -// preload "movl row, %%edi \n\t" // edi: Avg(x) + "movl _dif, %%ecx \n\t" /* ecx: x = offset to */ + "movq _LBCarryMask, %%mm5 \n\t" /* alignment boundary */ +/* preload "movl row, %%edi \n\t" // edi: Avg(x) */ "movq _HBClearMask, %%mm4 \n\t" -// preload "movl prev_row, %%esi \n\t" // esi: Prior(x) +/* preload "movl prev_row, %%esi \n\t" // esi: Prior(x) */ - // prime the pump: load the first Raw(x-bpp) data set - "movq -8(%%edi,%%ecx,), %%mm2 \n\t" // load previous aligned 8 bytes - // (correct pos. in loop below) + /* prime the pump: load the first Raw(x-bpp) data set */ + "movq -8(%%edi,%%ecx,), %%mm2 \n\t" /* load previous aligned 8 bytes */ + /* (correct pos. in loop below) */ "avg_3lp: \n\t" - "movq (%%edi,%%ecx,), %%mm0 \n\t" // load mm0 with Avg(x) + "movq (%%edi,%%ecx,), %%mm0 \n\t" /* load mm0 with Avg(x) */ "movq %%mm5, %%mm3 \n\t" - "psrlq _ShiftRem, %%mm2 \n\t" // correct position Raw(x-bpp) - // data - "movq (%%esi,%%ecx,), %%mm1 \n\t" // load mm1 with Prior(x) + "psrlq _ShiftRem, %%mm2 \n\t" /* correct position Raw(x-bpp) */ + /* data */ + "movq (%%esi,%%ecx,), %%mm1 \n\t" /* load mm1 with Prior(x) */ "movq %%mm7, %%mm6 \n\t" - "pand %%mm1, %%mm3 \n\t" // get lsb for each prev_row byte - "psrlq $1, %%mm1 \n\t" // divide prev_row bytes by 2 - "pand %%mm4, %%mm1 \n\t" // clear invalid bit 7 of each - // byte - "paddb %%mm1, %%mm0 \n\t" // add (Prev_row/2) to Avg for - // each byte - // add 1st active group (Raw(x-bpp)/2) to average with LBCarry - "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting - // LBCarrys - "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte - // where both - // lsb's were == 1 (only valid for active group) - "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 - "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each - // byte - "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2) - // for each byte - "pand %%mm6, %%mm2 \n\t" // leave only Active Group 1 - // bytes to add to Avg - "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to - // Avg for each Active - // byte - // add 2nd active group (Raw(x-bpp)/2) to average with _LBCarry - "psllq _ShiftBpp, %%mm6 \n\t" // shift the mm6 mask to cover - // bytes 3-5 - "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2 - "psllq _ShiftBpp, %%mm2 \n\t" // shift data to pos. correctly - "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting - // LBCarrys - "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte - // where both - // lsb's were == 1 (only valid for active group) - "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 - "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each - // byte - "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2) - // for each byte - "pand %%mm6, %%mm2 \n\t" // leave only Active Group 2 - // bytes to add to Avg - "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to - // Avg for each Active - // byte - - // add 3rd active group (Raw(x-bpp)/2) to average with _LBCarry - "psllq _ShiftBpp, %%mm6 \n\t" // shift mm6 mask to cover last - // two - // bytes - "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2 - "psllq _ShiftBpp, %%mm2 \n\t" // shift data to pos. correctly - // Data only needs to be shifted once here to - // get the correct x-bpp offset. - "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting - // LBCarrys - "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte - // where both - // lsb's were == 1 (only valid for active group) - "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 - "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each - // byte - "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2) - // for each byte - "pand %%mm6, %%mm2 \n\t" // leave only Active Group 2 - // bytes to add to Avg + "pand %%mm1, %%mm3 \n\t" /* get lsb for each prev_row byte */ + "psrlq $1, %%mm1 \n\t" /* divide prev_row bytes by 2 */ + "pand %%mm4, %%mm1 \n\t" /* clear invalid bit 7 of each */ + /* byte */ + "paddb %%mm1, %%mm0 \n\t" /* add (Prev_row/2) to Avg for */ + /* each byte */ + /* add 1st active group (Raw(x-bpp)/2) to average with LBCarry */ + "movq %%mm3, %%mm1 \n\t" /* now use mm1 for getting */ + /* LBCarrys */ + "pand %%mm2, %%mm1 \n\t" /* get LBCarrys for each byte */ + /* where both */ + /* lsb's were == 1 (only valid for active group) */ + "psrlq $1, %%mm2 \n\t" /* divide raw bytes by 2 */ + "pand %%mm4, %%mm2 \n\t" /* clear invalid bit 7 of each */ + /* byte */ + "paddb %%mm1, %%mm2 \n\t" /* add LBCarrys to (Raw(x-bpp)/2) */ + /* for each byte */ + "pand %%mm6, %%mm2 \n\t" /* leave only Active Group 1 */ + /* bytes to add to Avg */ + "paddb %%mm2, %%mm0 \n\t" /* add (Raw/2) + LBCarrys to */ + /* Avg for each Active */ + /* byte */ + /* add 2nd active group (Raw(x-bpp)/2) to average with _LBCarry */ + "psllq _ShiftBpp, %%mm6 \n\t" /* shift the mm6 mask to cover */ + /* bytes 3-5 */ + "movq %%mm0, %%mm2 \n\t" /* mov updated Raws to mm2 */ + "psllq _ShiftBpp, %%mm2 \n\t" /* shift data to pos. correctly */ + "movq %%mm3, %%mm1 \n\t" /* now use mm1 for getting */ + /* LBCarrys */ + "pand %%mm2, %%mm1 \n\t" /* get LBCarrys for each byte */ + /* where both */ + /* lsb's were == 1 (only valid for active group) */ + "psrlq $1, %%mm2 \n\t" /* divide raw bytes by 2 */ + "pand %%mm4, %%mm2 \n\t" /* clear invalid bit 7 of each */ + /* byte */ + "paddb %%mm1, %%mm2 \n\t" /* add LBCarrys to (Raw(x-bpp)/2) */ + /* for each byte */ + "pand %%mm6, %%mm2 \n\t" /* leave only Active Group 2 */ + /* bytes to add to Avg */ + "paddb %%mm2, %%mm0 \n\t" /* add (Raw/2) + LBCarrys to */ + /* Avg for each Active */ + /* byte */ + + /* add 3rd active group (Raw(x-bpp)/2) to average with _LBCarry */ + "psllq _ShiftBpp, %%mm6 \n\t" /* shift mm6 mask to cover last */ + /* two */ + /* bytes */ + "movq %%mm0, %%mm2 \n\t" /* mov updated Raws to mm2 */ + "psllq _ShiftBpp, %%mm2 \n\t" /* shift data to pos. correctly */ + /* Data only needs to be shifted once here to */ + /* get the correct x-bpp offset. */ + "movq %%mm3, %%mm1 \n\t" /* now use mm1 for getting */ + /* LBCarrys */ + "pand %%mm2, %%mm1 \n\t" /* get LBCarrys for each byte */ + /* where both */ + /* lsb's were == 1 (only valid for active group) */ + "psrlq $1, %%mm2 \n\t" /* divide raw bytes by 2 */ + "pand %%mm4, %%mm2 \n\t" /* clear invalid bit 7 of each */ + /* byte */ + "paddb %%mm1, %%mm2 \n\t" /* add LBCarrys to (Raw(x-bpp)/2) */ + /* for each byte */ + "pand %%mm6, %%mm2 \n\t" /* leave only Active Group 2 */ + /* bytes to add to Avg */ "addl $8, %%ecx \n\t" - "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to - // Avg for each Active - // byte - // now ready to write back to memory + "paddb %%mm2, %%mm0 \n\t" /* add (Raw/2) + LBCarrys to */ + /* Avg for each Active */ + /* byte */ + /* now ready to write back to memory */ "movq %%mm0, -8(%%edi,%%ecx,) \n\t" - // move updated Raw(x) to use as Raw(x-bpp) for next loop + /* move updated Raw(x) to use as Raw(x-bpp) for next loop */ "cmpl _MMXLength, %%ecx \n\t" - "movq %%mm0, %%mm2 \n\t" // mov updated Raw(x) to mm2 + "movq %%mm0, %%mm2 \n\t" /* mov updated Raw(x) to mm2 */ "jb avg_3lp \n\t" - : "=S" (dummy_value_S), // output regs (dummy) + : "=S" (dummy_value_S), /* output regs (dummy) */ "=D" (dummy_value_D) - : "0" (prev_row), // esi // input regs - "1" (row) // edi + : "0" (prev_row), /* esi // input regs */ + "1" (row) /* edi */ - : "%ecx" // clobber list + : "%ecx" /* clobber list */ #if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */ , "%mm0", "%mm1", "%mm2", "%mm3" , "%mm4", "%mm5", "%mm6", "%mm7" #endif ); } - break; // end 3 bpp + break; /* end 3 bpp */ case 6: case 4: - //case 7: // who wrote this? PNG doesn't support 5 or 7 bytes/pixel - //case 5: // GRR BOGUS + //case 7: /* who wrote this? PNG doesn't support 5 or 7 bytes/pixel */ + //case 5: /* GRR BOGUS */ { - _ActiveMask.use = 0xffffffffffffffffLL; // use shift below to clear - // appropriate inactive bytes + _ActiveMask.use = 0xffffffffffffffffLL; /* use shift below to clear */ + /* appropriate inactive bytes */ _ShiftBpp.use = bpp << 3; _ShiftRem.use = 64 - _ShiftBpp.use; __asm__ __volatile__ ( "movq _HBClearMask, %%mm4 \n\t" - // re-init address pointers and offset - "movl _dif, %%ecx \n\t" // ecx: x = offset to - // alignment boundary + /* re-init address pointers and offset */ + "movl _dif, %%ecx \n\t" /* ecx: x = offset to */ + /* alignment boundary */ - // load _ActiveMask and clear all bytes except for 1st active group + /* load _ActiveMask and clear all bytes except for 1st active group */ "movq _ActiveMask, %%mm7 \n\t" -// preload "movl row, %%edi \n\t" // edi: Avg(x) +/* preload "movl row, %%edi \n\t" // edi: Avg(x) */ "psrlq _ShiftRem, %%mm7 \n\t" -// preload "movl prev_row, %%esi \n\t" // esi: Prior(x) +/* preload "movl prev_row, %%esi \n\t" // esi: Prior(x) */ "movq %%mm7, %%mm6 \n\t" "movq _LBCarryMask, %%mm5 \n\t" - "psllq _ShiftBpp, %%mm6 \n\t" // create mask for 2nd active - // group + "psllq _ShiftBpp, %%mm6 \n\t" /* create mask for 2nd active */ + /* group */ - // prime the pump: load the first Raw(x-bpp) data set - "movq -8(%%edi,%%ecx,), %%mm2 \n\t" // load previous aligned 8 bytes - // (we correct pos. in loop below) + /* prime the pump: load the first Raw(x-bpp) data set */ + "movq -8(%%edi,%%ecx,), %%mm2 \n\t" /* load previous aligned 8 bytes */ + /* (we correct pos. in loop below) */ "avg_4lp: \n\t" "movq (%%edi,%%ecx,), %%mm0 \n\t" - "psrlq _ShiftRem, %%mm2 \n\t" // shift data to pos. correctly + "psrlq _ShiftRem, %%mm2 \n\t" /* shift data to pos. correctly */ "movq (%%esi,%%ecx,), %%mm1 \n\t" - // add (Prev_row/2) to average + /* add (Prev_row/2) to average */ "movq %%mm5, %%mm3 \n\t" - "pand %%mm1, %%mm3 \n\t" // get lsb for each prev_row byte - "psrlq $1, %%mm1 \n\t" // divide prev_row bytes by 2 - "pand %%mm4, %%mm1 \n\t" // clear invalid bit 7 of each - // byte - "paddb %%mm1, %%mm0 \n\t" // add (Prev_row/2) to Avg for - // each byte - // add 1st active group (Raw(x-bpp)/2) to average with _LBCarry - "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting - // LBCarrys - "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte - // where both - // lsb's were == 1 (only valid for active group) - "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 - "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each - // byte - "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2) - // for each byte - "pand %%mm7, %%mm2 \n\t" // leave only Active Group 1 - // bytes to add to Avg - "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to Avg - // for each Active - // byte - // add 2nd active group (Raw(x-bpp)/2) to average with _LBCarry - "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2 - "psllq _ShiftBpp, %%mm2 \n\t" // shift data to pos. correctly + "pand %%mm1, %%mm3 \n\t" /* get lsb for each prev_row byte */ + "psrlq $1, %%mm1 \n\t" /* divide prev_row bytes by 2 */ + "pand %%mm4, %%mm1 \n\t" /* clear invalid bit 7 of each */ + /* byte */ + "paddb %%mm1, %%mm0 \n\t" /* add (Prev_row/2) to Avg for */ + /* each byte */ + /* add 1st active group (Raw(x-bpp)/2) to average with _LBCarry */ + "movq %%mm3, %%mm1 \n\t" /* now use mm1 for getting */ + /* LBCarrys */ + "pand %%mm2, %%mm1 \n\t" /* get LBCarrys for each byte */ + /* where both */ + /* lsb's were == 1 (only valid for active group) */ + "psrlq $1, %%mm2 \n\t" /* divide raw bytes by 2 */ + "pand %%mm4, %%mm2 \n\t" /* clear invalid bit 7 of each */ + /* byte */ + "paddb %%mm1, %%mm2 \n\t" /* add LBCarrys to (Raw(x-bpp)/2) */ + /* for each byte */ + "pand %%mm7, %%mm2 \n\t" /* leave only Active Group 1 */ + /* bytes to add to Avg */ + "paddb %%mm2, %%mm0 \n\t" /* add (Raw/2) + LBCarrys to Avg */ + /* for each Active */ + /* byte */ + /* add 2nd active group (Raw(x-bpp)/2) to average with _LBCarry */ + "movq %%mm0, %%mm2 \n\t" /* mov updated Raws to mm2 */ + "psllq _ShiftBpp, %%mm2 \n\t" /* shift data to pos. correctly */ "addl $8, %%ecx \n\t" - "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting - // LBCarrys - "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte - // where both - // lsb's were == 1 (only valid for active group) - "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 - "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each - // byte - "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2) - // for each byte - "pand %%mm6, %%mm2 \n\t" // leave only Active Group 2 - // bytes to add to Avg - "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to - // Avg for each Active - // byte + "movq %%mm3, %%mm1 \n\t" /* now use mm1 for getting */ + /* LBCarrys */ + "pand %%mm2, %%mm1 \n\t" /* get LBCarrys for each byte */ + /* where both */ + /* lsb's were == 1 (only valid for active group) */ + "psrlq $1, %%mm2 \n\t" /* divide raw bytes by 2 */ + "pand %%mm4, %%mm2 \n\t" /* clear invalid bit 7 of each */ + /* byte */ + "paddb %%mm1, %%mm2 \n\t" /* add LBCarrys to (Raw(x-bpp)/2) */ + /* for each byte */ + "pand %%mm6, %%mm2 \n\t" /* leave only Active Group 2 */ + /* bytes to add to Avg */ + "paddb %%mm2, %%mm0 \n\t" /* add (Raw/2) + LBCarrys to */ + /* Avg for each Active */ + /* byte */ "cmpl _MMXLength, %%ecx \n\t" - // now ready to write back to memory + /* now ready to write back to memory */ "movq %%mm0, -8(%%edi,%%ecx,) \n\t" - // prep Raw(x-bpp) for next loop - "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2 + /* prep Raw(x-bpp) for next loop */ + "movq %%mm0, %%mm2 \n\t" /* mov updated Raws to mm2 */ "jb avg_4lp \n\t" - : "=S" (dummy_value_S), // output regs (dummy) + : "=S" (dummy_value_S), /* output regs (dummy) */ "=D" (dummy_value_D) - : "0" (prev_row), // esi // input regs - "1" (row) // edi + : "0" (prev_row), /* esi // input regs */ + "1" (row) /* edi */ - : "%ecx" // clobber list + : "%ecx" /* clobber list */ #if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */ , "%mm0", "%mm1", "%mm2", "%mm3" , "%mm4", "%mm5", "%mm6", "%mm7" #endif ); } - break; // end 4,6 bpp + break; /* end 4,6 bpp */ case 2: { _ActiveMask.use = 0x000000000000ffffLL; - _ShiftBpp.use = 16; // == 2 * 8 - _ShiftRem.use = 48; // == 64 - 16 + _ShiftBpp.use = 16; /* == 2 * 8 */ + _ShiftRem.use = 48; /* == 64 - 16 */ __asm__ __volatile__ ( - // load _ActiveMask + /* load _ActiveMask */ "movq _ActiveMask, %%mm7 \n\t" - // re-init address pointers and offset - "movl _dif, %%ecx \n\t" // ecx: x = offset to alignment - // boundary + /* re-init address pointers and offset */ + "movl _dif, %%ecx \n\t" /* ecx: x = offset to alignment */ + /* boundary */ "movq _LBCarryMask, %%mm5 \n\t" -// preload "movl row, %%edi \n\t" // edi: Avg(x) +/* preload "movl row, %%edi \n\t" // edi: Avg(x) */ "movq _HBClearMask, %%mm4 \n\t" -// preload "movl prev_row, %%esi \n\t" // esi: Prior(x) +/* preload "movl prev_row, %%esi \n\t" // esi: Prior(x) */ - // prime the pump: load the first Raw(x-bpp) data set - "movq -8(%%edi,%%ecx,), %%mm2 \n\t" // load previous aligned 8 bytes - // (we correct pos. in loop below) + /* prime the pump: load the first Raw(x-bpp) data set */ + "movq -8(%%edi,%%ecx,), %%mm2 \n\t" /* load previous aligned 8 bytes */ + /* (we correct pos. in loop below) */ "avg_2lp: \n\t" "movq (%%edi,%%ecx,), %%mm0 \n\t" - "psrlq _ShiftRem, %%mm2 \n\t" // shift data to pos. correctly - "movq (%%esi,%%ecx,), %%mm1 \n\t" // (GRR BUGFIX: was psllq) - // add (Prev_row/2) to average + "psrlq _ShiftRem, %%mm2 \n\t" /* shift data to pos. correctly */ + "movq (%%esi,%%ecx,), %%mm1 \n\t" /* (GRR BUGFIX: was psllq) */ + /* add (Prev_row/2) to average */ "movq %%mm5, %%mm3 \n\t" - "pand %%mm1, %%mm3 \n\t" // get lsb for each prev_row byte - "psrlq $1, %%mm1 \n\t" // divide prev_row bytes by 2 - "pand %%mm4, %%mm1 \n\t" // clear invalid bit 7 of each - // byte + "pand %%mm1, %%mm3 \n\t" /* get lsb for each prev_row byte */ + "psrlq $1, %%mm1 \n\t" /* divide prev_row bytes by 2 */ + "pand %%mm4, %%mm1 \n\t" /* clear invalid bit 7 of each */ + /* byte */ "movq %%mm7, %%mm6 \n\t" - "paddb %%mm1, %%mm0 \n\t" // add (Prev_row/2) to Avg for - // each byte - - // add 1st active group (Raw(x-bpp)/2) to average with _LBCarry - "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting - // LBCarrys - "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte - // where both - // lsb's were == 1 (only valid - // for active group) - "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 - "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each - // byte - "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2) - // for each byte - "pand %%mm6, %%mm2 \n\t" // leave only Active Group 1 - // bytes to add to Avg - "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to Avg - // for each Active byte - - // add 2nd active group (Raw(x-bpp)/2) to average with _LBCarry - "psllq _ShiftBpp, %%mm6 \n\t" // shift the mm6 mask to cover - // bytes 2 & 3 - "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2 - "psllq _ShiftBpp, %%mm2 \n\t" // shift data to pos. correctly - "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting - // LBCarrys - "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte - // where both - // lsb's were == 1 (only valid - // for active group) - "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 - "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each - // byte - "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2) - // for each byte - "pand %%mm6, %%mm2 \n\t" // leave only Active Group 2 - // bytes to add to Avg - "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to - // Avg for each Active byte - - // add 3rd active group (Raw(x-bpp)/2) to average with _LBCarry - "psllq _ShiftBpp, %%mm6 \n\t" // shift the mm6 mask to cover - // bytes 4 & 5 - "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2 - "psllq _ShiftBpp, %%mm2 \n\t" // shift data to pos. correctly - "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting - // LBCarrys - "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte - // where both lsb's were == 1 - // (only valid for active group) - "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 - "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each - // byte - "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2) - // for each byte - "pand %%mm6, %%mm2 \n\t" // leave only Active Group 2 - // bytes to add to Avg - "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to - // Avg for each Active byte - - // add 4th active group (Raw(x-bpp)/2) to average with _LBCarry - "psllq _ShiftBpp, %%mm6 \n\t" // shift the mm6 mask to cover - // bytes 6 & 7 - "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2 - "psllq _ShiftBpp, %%mm2 \n\t" // shift data to pos. correctly + "paddb %%mm1, %%mm0 \n\t" /* add (Prev_row/2) to Avg for */ + /* each byte */ + + /* add 1st active group (Raw(x-bpp)/2) to average with _LBCarry */ + "movq %%mm3, %%mm1 \n\t" /* now use mm1 for getting */ + /* LBCarrys */ + "pand %%mm2, %%mm1 \n\t" /* get LBCarrys for each byte */ + /* where both */ + /* lsb's were == 1 (only valid */ + /* for active group) */ + "psrlq $1, %%mm2 \n\t" /* divide raw bytes by 2 */ + "pand %%mm4, %%mm2 \n\t" /* clear invalid bit 7 of each */ + /* byte */ + "paddb %%mm1, %%mm2 \n\t" /* add LBCarrys to (Raw(x-bpp)/2) */ + /* for each byte */ + "pand %%mm6, %%mm2 \n\t" /* leave only Active Group 1 */ + /* bytes to add to Avg */ + "paddb %%mm2, %%mm0 \n\t" /* add (Raw/2) + LBCarrys to Avg */ + /* for each Active byte */ + + /* add 2nd active group (Raw(x-bpp)/2) to average with _LBCarry */ + "psllq _ShiftBpp, %%mm6 \n\t" /* shift the mm6 mask to cover */ + /* bytes 2 & 3 */ + "movq %%mm0, %%mm2 \n\t" /* mov updated Raws to mm2 */ + "psllq _ShiftBpp, %%mm2 \n\t" /* shift data to pos. correctly */ + "movq %%mm3, %%mm1 \n\t" /* now use mm1 for getting */ + /* LBCarrys */ + "pand %%mm2, %%mm1 \n\t" /* get LBCarrys for each byte */ + /* where both */ + /* lsb's were == 1 (only valid */ + /* for active group) */ + "psrlq $1, %%mm2 \n\t" /* divide raw bytes by 2 */ + "pand %%mm4, %%mm2 \n\t" /* clear invalid bit 7 of each */ + /* byte */ + "paddb %%mm1, %%mm2 \n\t" /* add LBCarrys to (Raw(x-bpp)/2) */ + /* for each byte */ + "pand %%mm6, %%mm2 \n\t" /* leave only Active Group 2 */ + /* bytes to add to Avg */ + "paddb %%mm2, %%mm0 \n\t" /* add (Raw/2) + LBCarrys to */ + /* Avg for each Active byte */ + + /* add 3rd active group (Raw(x-bpp)/2) to average with _LBCarry */ + "psllq _ShiftBpp, %%mm6 \n\t" /* shift the mm6 mask to cover */ + /* bytes 4 & 5 */ + "movq %%mm0, %%mm2 \n\t" /* mov updated Raws to mm2 */ + "psllq _ShiftBpp, %%mm2 \n\t" /* shift data to pos. correctly */ + "movq %%mm3, %%mm1 \n\t" /* now use mm1 for getting */ + /* LBCarrys */ + "pand %%mm2, %%mm1 \n\t" /* get LBCarrys for each byte */ + /* where both lsb's were == 1 */ + /* (only valid for active group) */ + "psrlq $1, %%mm2 \n\t" /* divide raw bytes by 2 */ + "pand %%mm4, %%mm2 \n\t" /* clear invalid bit 7 of each */ + /* byte */ + "paddb %%mm1, %%mm2 \n\t" /* add LBCarrys to (Raw(x-bpp)/2) */ + /* for each byte */ + "pand %%mm6, %%mm2 \n\t" /* leave only Active Group 2 */ + /* bytes to add to Avg */ + "paddb %%mm2, %%mm0 \n\t" /* add (Raw/2) + LBCarrys to */ + /* Avg for each Active byte */ + + /* add 4th active group (Raw(x-bpp)/2) to average with _LBCarry */ + "psllq _ShiftBpp, %%mm6 \n\t" /* shift the mm6 mask to cover */ + /* bytes 6 & 7 */ + "movq %%mm0, %%mm2 \n\t" /* mov updated Raws to mm2 */ + "psllq _ShiftBpp, %%mm2 \n\t" /* shift data to pos. correctly */ "addl $8, %%ecx \n\t" - "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting - // LBCarrys - "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte - // where both - // lsb's were == 1 (only valid - // for active group) - "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 - "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each - // byte - "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2) - // for each byte - "pand %%mm6, %%mm2 \n\t" // leave only Active Group 2 - // bytes to add to Avg - "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to - // Avg for each Active byte + "movq %%mm3, %%mm1 \n\t" /* now use mm1 for getting */ + /* LBCarrys */ + "pand %%mm2, %%mm1 \n\t" /* get LBCarrys for each byte */ + /* where both */ + /* lsb's were == 1 (only valid */ + /* for active group) */ + "psrlq $1, %%mm2 \n\t" /* divide raw bytes by 2 */ + "pand %%mm4, %%mm2 \n\t" /* clear invalid bit 7 of each */ + /* byte */ + "paddb %%mm1, %%mm2 \n\t" /* add LBCarrys to (Raw(x-bpp)/2) */ + /* for each byte */ + "pand %%mm6, %%mm2 \n\t" /* leave only Active Group 2 */ + /* bytes to add to Avg */ + "paddb %%mm2, %%mm0 \n\t" /* add (Raw/2) + LBCarrys to */ + /* Avg for each Active byte */ "cmpl _MMXLength, %%ecx \n\t" - // now ready to write back to memory + /* now ready to write back to memory */ "movq %%mm0, -8(%%edi,%%ecx,) \n\t" - // prep Raw(x-bpp) for next loop - "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2 + /* prep Raw(x-bpp) for next loop */ + "movq %%mm0, %%mm2 \n\t" /* mov updated Raws to mm2 */ "jb avg_2lp \n\t" - : "=S" (dummy_value_S), // output regs (dummy) + : "=S" (dummy_value_S), /* output regs (dummy) */ "=D" (dummy_value_D) - : "0" (prev_row), // esi // input regs - "1" (row) // edi + : "0" (prev_row), /* esi // input regs */ + "1" (row) /* edi */ - : "%ecx" // clobber list + : "%ecx" /* clobber list */ #if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */ , "%mm0", "%mm1", "%mm2", "%mm3" , "%mm4", "%mm5", "%mm6", "%mm7" #endif ); } - break; // end 2 bpp + break; /* end 2 bpp */ case 1: { __asm__ __volatile__ ( - // re-init address pointers and offset + /* re-init address pointers and offset */ #ifdef __PIC__ - "pushl %%ebx \n\t" // save Global Offset Table index + "pushl %%ebx \n\t" /* save Global Offset Table index */ #endif - "movl _dif, %%ebx \n\t" // ebx: x = offset to alignment - // boundary -// preload "movl row, %%edi \n\t" // edi: Avg(x) - "cmpl _FullLength, %%ebx \n\t" // test if offset at end of array + "movl _dif, %%ebx \n\t" /* ebx: x = offset to alignment */ + /* boundary */ +/* preload "movl row, %%edi \n\t" // edi: Avg(x) */ + "cmpl _FullLength, %%ebx \n\t" /* test if offset at end of array */ "jnb avg_1end \n\t" - // do Paeth decode for remaining bytes -// preload "movl prev_row, %%esi \n\t" // esi: Prior(x) + /* do Paeth decode for remaining bytes */ +/* preload "movl prev_row, %%esi \n\t" // esi: Prior(x) */ "movl %%edi, %%edx \n\t" -// preload "subl bpp, %%edx \n\t" // (bpp is preloaded into ecx) - "subl %%ecx, %%edx \n\t" // edx: Raw(x-bpp) - "xorl %%ecx, %%ecx \n\t" // zero ecx before using cl & cx - // in loop below +/* preload "subl bpp, %%edx \n\t" // (bpp is preloaded into ecx) */ + "subl %%ecx, %%edx \n\t" /* edx: Raw(x-bpp) */ + "xorl %%ecx, %%ecx \n\t" /* zero ecx before using cl & cx */ + /* in loop below */ "avg_1lp: \n\t" - // Raw(x) = Avg(x) + ((Raw(x-bpp) + Prior(x))/2) + /* Raw(x) = Avg(x) + ((Raw(x-bpp) + Prior(x))/2) */ "xorl %%eax, %%eax \n\t" - "movb (%%esi,%%ebx,), %%cl \n\t" // load cl with Prior(x) - "movb (%%edx,%%ebx,), %%al \n\t" // load al with Raw(x-bpp) + "movb (%%esi,%%ebx,), %%cl \n\t" /* load cl with Prior(x) */ + "movb (%%edx,%%ebx,), %%al \n\t" /* load al with Raw(x-bpp) */ "addw %%cx, %%ax \n\t" "incl %%ebx \n\t" - "shrw %%ax \n\t" // divide by 2 - "addb -1(%%edi,%%ebx,), %%al \n\t" // add Avg(x); -1 to offset - // inc ebx - "cmpl _FullLength, %%ebx \n\t" // check if at end of array - "movb %%al, -1(%%edi,%%ebx,) \n\t" // write back Raw(x); - // mov does not affect flags; -1 to offset inc ebx + "shrw %%ax \n\t" /* divide by 2 */ + "addb -1(%%edi,%%ebx,), %%al \n\t" /* add Avg(x); -1 to offset */ + /* inc ebx */ + "cmpl _FullLength, %%ebx \n\t" /* check if at end of array */ + "movb %%al, -1(%%edi,%%ebx,) \n\t" /* write back Raw(x); */ + /* mov does not affect flags; -1 to offset inc ebx */ "jb avg_1lp \n\t" "avg_1end: \n\t" #ifdef __PIC__ - "popl %%ebx \n\t" // Global Offset Table index + "popl %%ebx \n\t" /* Global Offset Table index */ #endif - : "=c" (dummy_value_c), // output regs (dummy) + : "=c" (dummy_value_c), /* output regs (dummy) */ "=S" (dummy_value_S), "=D" (dummy_value_D) - : "0" (bpp), // ecx // input regs - "1" (prev_row), // esi - "2" (row) // edi + : "0" (bpp), /* ecx // input regs */ + "1" (prev_row), /* esi */ + "2" (row) /* edi */ - : "%eax", "%edx" // clobber list + : "%eax", "%edx" /* clobber list */ #ifndef __PIC__ , "%ebx" #endif ); } - return; // end 1 bpp + return; /* end 1 bpp */ case 8: { __asm__ __volatile__ ( - // re-init address pointers and offset - "movl _dif, %%ecx \n\t" // ecx: x == offset to alignment - "movq _LBCarryMask, %%mm5 \n\t" // boundary -// preload "movl row, %%edi \n\t" // edi: Avg(x) + /* re-init address pointers and offset */ + "movl _dif, %%ecx \n\t" /* ecx: x == offset to alignment */ + "movq _LBCarryMask, %%mm5 \n\t" /* boundary */ +/* preload "movl row, %%edi \n\t" // edi: Avg(x) */ "movq _HBClearMask, %%mm4 \n\t" -// preload "movl prev_row, %%esi \n\t" // esi: Prior(x) +/* preload "movl prev_row, %%esi \n\t" // esi: Prior(x) */ - // prime the pump: load the first Raw(x-bpp) data set - "movq -8(%%edi,%%ecx,), %%mm2 \n\t" // load previous aligned 8 bytes - // (NO NEED to correct pos. in loop below) + /* prime the pump: load the first Raw(x-bpp) data set */ + "movq -8(%%edi,%%ecx,), %%mm2 \n\t" /* load previous aligned 8 bytes */ + /* (NO NEED to correct pos. in loop below) */ "avg_8lp: \n\t" "movq (%%edi,%%ecx,), %%mm0 \n\t" "movq %%mm5, %%mm3 \n\t" "movq (%%esi,%%ecx,), %%mm1 \n\t" "addl $8, %%ecx \n\t" - "pand %%mm1, %%mm3 \n\t" // get lsb for each prev_row byte - "psrlq $1, %%mm1 \n\t" // divide prev_row bytes by 2 - "pand %%mm2, %%mm3 \n\t" // get LBCarrys for each byte - // where both lsb's were == 1 - "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 - "pand %%mm4, %%mm1 \n\t" // clear invalid bit 7, each byte - "paddb %%mm3, %%mm0 \n\t" // add LBCarrys to Avg, each byte - "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7, each byte - "paddb %%mm1, %%mm0 \n\t" // add (Prev_row/2) to Avg, each - "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) to Avg for each + "pand %%mm1, %%mm3 \n\t" /* get lsb for each prev_row byte */ + "psrlq $1, %%mm1 \n\t" /* divide prev_row bytes by 2 */ + "pand %%mm2, %%mm3 \n\t" /* get LBCarrys for each byte */ + /* where both lsb's were == 1 */ + "psrlq $1, %%mm2 \n\t" /* divide raw bytes by 2 */ + "pand %%mm4, %%mm1 \n\t" /* clear invalid bit 7, each byte */ + "paddb %%mm3, %%mm0 \n\t" /* add LBCarrys to Avg, each byte */ + "pand %%mm4, %%mm2 \n\t" /* clear invalid bit 7, each byte */ + "paddb %%mm1, %%mm0 \n\t" /* add (Prev_row/2) to Avg, each */ + "paddb %%mm2, %%mm0 \n\t" /* add (Raw/2) to Avg for each */ "cmpl _MMXLength, %%ecx \n\t" "movq %%mm0, -8(%%edi,%%ecx,) \n\t" - "movq %%mm0, %%mm2 \n\t" // reuse as Raw(x-bpp) + "movq %%mm0, %%mm2 \n\t" /* reuse as Raw(x-bpp) */ "jb avg_8lp \n\t" - : "=S" (dummy_value_S), // output regs (dummy) + : "=S" (dummy_value_S), /* output regs (dummy) */ "=D" (dummy_value_D) - : "0" (prev_row), // esi // input regs - "1" (row) // edi + : "0" (prev_row), /* esi // input regs */ + "1" (row) /* edi */ - : "%ecx" // clobber list + : "%ecx" /* clobber list */ #if 0 /* %mm0, ..., %mm5 not supported by gcc 2.7.2.3 or egcs 1.1 */ , "%mm0", "%mm1", "%mm2" , "%mm3", "%mm4", "%mm5" #endif ); } - break; // end 8 bpp + break; /* end 8 bpp */ - default: // bpp greater than 8 (!= 1,2,3,4,[5],6,[7],8) + default: /* bpp greater than 8 (!= 1,2,3,4,[5],6,[7],8) */ { #ifdef PNG_DEBUG - // GRR: PRINT ERROR HERE: SHOULD NEVER BE REACHED + /* GRR: PRINT ERROR HERE: SHOULD NEVER BE REACHED */ png_debug(1, "Internal logic error in pnggccrd (png_read_filter_row_mmx_avg())\n"); #endif @@ -3318,97 +3327,97 @@ png_read_filter_row_mmx_avg(png_row_infop row_info, png_bytep row, #if 0 __asm__ __volatile__ ( "movq _LBCarryMask, %%mm5 \n\t" - // re-init address pointers and offset - "movl _dif, %%ebx \n\t" // ebx: x = offset to - // alignment boundary - "movl row, %%edi \n\t" // edi: Avg(x) + /* re-init address pointers and offset */ + "movl _dif, %%ebx \n\t" /* ebx: x = offset to */ + /* alignment boundary */ + "movl row, %%edi \n\t" /* edi: Avg(x) */ "movq _HBClearMask, %%mm4 \n\t" "movl %%edi, %%edx \n\t" - "movl prev_row, %%esi \n\t" // esi: Prior(x) - "subl bpp, %%edx \n\t" // edx: Raw(x-bpp) + "movl prev_row, %%esi \n\t" /* esi: Prior(x) */ + "subl bpp, %%edx \n\t" /* edx: Raw(x-bpp) */ "avg_Alp: \n\t" "movq (%%edi,%%ebx,), %%mm0 \n\t" "movq %%mm5, %%mm3 \n\t" "movq (%%esi,%%ebx,), %%mm1 \n\t" - "pand %%mm1, %%mm3 \n\t" // get lsb for each prev_row byte + "pand %%mm1, %%mm3 \n\t" /* get lsb for each prev_row byte */ "movq (%%edx,%%ebx,), %%mm2 \n\t" - "psrlq $1, %%mm1 \n\t" // divide prev_row bytes by 2 - "pand %%mm2, %%mm3 \n\t" // get LBCarrys for each byte - // where both lsb's were == 1 - "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2 - "pand %%mm4, %%mm1 \n\t" // clear invalid bit 7 of each - // byte - "paddb %%mm3, %%mm0 \n\t" // add LBCarrys to Avg for each - // byte - "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each - // byte - "paddb %%mm1, %%mm0 \n\t" // add (Prev_row/2) to Avg for - // each byte + "psrlq $1, %%mm1 \n\t" /* divide prev_row bytes by 2 */ + "pand %%mm2, %%mm3 \n\t" /* get LBCarrys for each byte */ + /* where both lsb's were == 1 */ + "psrlq $1, %%mm2 \n\t" /* divide raw bytes by 2 */ + "pand %%mm4, %%mm1 \n\t" /* clear invalid bit 7 of each */ + /* byte */ + "paddb %%mm3, %%mm0 \n\t" /* add LBCarrys to Avg for each */ + /* byte */ + "pand %%mm4, %%mm2 \n\t" /* clear invalid bit 7 of each */ + /* byte */ + "paddb %%mm1, %%mm0 \n\t" /* add (Prev_row/2) to Avg for */ + /* each byte */ "addl $8, %%ebx \n\t" - "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) to Avg for each - // byte + "paddb %%mm2, %%mm0 \n\t" /* add (Raw/2) to Avg for each */ + /* byte */ "cmpl _MMXLength, %%ebx \n\t" "movq %%mm0, -8(%%edi,%%ebx,) \n\t" "jb avg_Alp \n\t" - : // FIXASM: output regs/vars go here, e.g.: "=m" (memory_var) + : /* FIXASM: output regs/vars go here, e.g.: "=m" (memory_var) */ - : // FIXASM: input regs, e.g.: "c" (count), "S" (src), "D" (dest) + : /* FIXASM: input regs, e.g.: "c" (count), "S" (src), "D" (dest) */ - : "%ebx", "%edx", "%edi", "%esi" // CHECKASM: clobber list + : "%ebx", "%edx", "%edi", "%esi" /* CHECKASM: clobber list */ ); #endif /* 0 - NEVER REACHED */ } break; - } // end switch (bpp) + } /* end switch (bpp) */ __asm__ __volatile__ ( - // MMX acceleration complete; now do clean-up - // check if any remaining bytes left to decode + /* MMX acceleration complete; now do clean-up */ + /* check if any remaining bytes left to decode */ #ifdef __PIC__ - "pushl %%ebx \n\t" // save index to Global Offset Table + "pushl %%ebx \n\t" /* save index to Global Offset Table */ #endif - "movl _MMXLength, %%ebx \n\t" // ebx: x == offset bytes after MMX -//pre "movl row, %%edi \n\t" // edi: Avg(x) - "cmpl _FullLength, %%ebx \n\t" // test if offset at end of array + "movl _MMXLength, %%ebx \n\t" /* ebx: x == offset bytes after MMX */ +/* pre "movl row, %%edi \n\t" */ /* edi: Avg(x) */ + "cmpl _FullLength, %%ebx \n\t" /* test if offset at end of array */ "jnb avg_end \n\t" - // do Avg decode for remaining bytes -//pre "movl prev_row, %%esi \n\t" // esi: Prior(x) + /* do Avg decode for remaining bytes */ +/*pre "movl prev_row, %%esi \n\t" */ /* esi: Prior(x) */ "movl %%edi, %%edx \n\t" -//pre "subl bpp, %%edx \n\t" // (bpp is preloaded into ecx) - "subl %%ecx, %%edx \n\t" // edx: Raw(x-bpp) - "xorl %%ecx, %%ecx \n\t" // zero ecx before using cl & cx below +/*pre "subl bpp, %%edx \n\t" */ /* (bpp is preloaded into ecx) */ + "subl %%ecx, %%edx \n\t" /* edx: Raw(x-bpp) */ + "xorl %%ecx, %%ecx \n\t" /* zero ecx before using cl & cx below */ "avg_lp2: \n\t" - // Raw(x) = Avg(x) + ((Raw(x-bpp) + Prior(x))/2) + /* Raw(x) = Avg(x) + ((Raw(x-bpp) + Prior(x))/2) */ "xorl %%eax, %%eax \n\t" - "movb (%%esi,%%ebx,), %%cl \n\t" // load cl with Prior(x) - "movb (%%edx,%%ebx,), %%al \n\t" // load al with Raw(x-bpp) + "movb (%%esi,%%ebx,), %%cl \n\t" /* load cl with Prior(x) */ + "movb (%%edx,%%ebx,), %%al \n\t" /* load al with Raw(x-bpp) */ "addw %%cx, %%ax \n\t" "incl %%ebx \n\t" - "shrw %%ax \n\t" // divide by 2 - "addb -1(%%edi,%%ebx,), %%al \n\t" // add Avg(x); -1 to offset inc ebx - "cmpl _FullLength, %%ebx \n\t" // check if at end of array - "movb %%al, -1(%%edi,%%ebx,) \n\t" // write back Raw(x) [mov does not - "jb avg_lp2 \n\t" // affect flags; -1 to offset inc ebx] + "shrw %%ax \n\t" /* divide by 2 */ + "addb -1(%%edi,%%ebx,), %%al \n\t" /* add Avg(x); -1 to offset inc ebx */ + "cmpl _FullLength, %%ebx \n\t" /* check if at end of array */ + "movb %%al, -1(%%edi,%%ebx,) \n\t" /* write back Raw(x) [mov does not */ + "jb avg_lp2 \n\t" /* affect flags; -1 to offset inc ebx] */ "avg_end: \n\t" - "EMMS \n\t" // end MMX; prep for poss. FP instrs. + "EMMS \n\t" /* end MMX; prep for poss. FP instrs. */ #ifdef __PIC__ - "popl %%ebx \n\t" // restore index to Global Offset Table + "popl %%ebx \n\t" /* restore index to Global Offset Table */ #endif - : "=c" (dummy_value_c), // output regs (dummy) + : "=c" (dummy_value_c), /* output regs (dummy) */ "=S" (dummy_value_S), "=D" (dummy_value_D) - : "0" (bpp), // ecx // input regs - "1" (prev_row), // esi - "2" (row) // edi + : "0" (bpp), /* ecx // input regs */ + "1" (prev_row), /* esi */ + "2" (row) /* edi */ - : "%eax", "%edx" // clobber list + : "%eax", "%edx" /* clobber list */ #ifndef __PIC__ , "%ebx" #endif @@ -3420,126 +3429,126 @@ png_read_filter_row_mmx_avg(png_row_infop row_info, png_bytep row, #ifdef PNG_THREAD_UNSAFE_OK -//===========================================================================// -// // -// P N G _ R E A D _ F I L T E R _ R O W _ M M X _ P A E T H // -// // -//===========================================================================// +/*===========================================================================*/ +/* */ +/* P N G _ R E A D _ F I L T E R _ R O W _ M M X _ P A E T H */ +/* */ +/*===========================================================================*/ -// Optimized code for PNG Paeth filter decoder +/* Optimized code for PNG Paeth filter decoder */ static void /* PRIVATE */ png_read_filter_row_mmx_paeth(png_row_infop row_info, png_bytep row, png_bytep prev_row) { int bpp; - int dummy_value_c; // fix 'forbidden register 2 (cx) was spilled' error + int dummy_value_c; /* fix 'forbidden register 2 (cx) was spilled' error */ int dummy_value_S; int dummy_value_D; - bpp = (row_info->pixel_depth + 7) >> 3; // Get # bytes per pixel - _FullLength = row_info->rowbytes; // # of bytes to filter + bpp = (row_info->pixel_depth + 7) >> 3; /* Get # bytes per pixel */ + _FullLength = row_info->rowbytes; /* # of bytes to filter */ __asm__ __volatile__ ( #ifdef __PIC__ - "pushl %%ebx \n\t" // save index to Global Offset Table + "pushl %%ebx \n\t" /* save index to Global Offset Table */ #endif - "xorl %%ebx, %%ebx \n\t" // ebx: x offset -//pre "movl row, %%edi \n\t" - "xorl %%edx, %%edx \n\t" // edx: x-bpp offset -//pre "movl prev_row, %%esi \n\t" + "xorl %%ebx, %%ebx \n\t" /* ebx: x offset */ +/*pre "movl row, %%edi \n\t" */ + "xorl %%edx, %%edx \n\t" /* edx: x-bpp offset */ +/*pre "movl prev_row, %%esi \n\t" */ "xorl %%eax, %%eax \n\t" - // Compute the Raw value for the first bpp bytes - // Note: the formula works out to be always - // Paeth(x) = Raw(x) + Prior(x) where x < bpp + /* Compute the Raw value for the first bpp bytes */ + /* Note: the formula works out to be always */ + /* Paeth(x) = Raw(x) + Prior(x) where x < bpp */ "paeth_rlp: \n\t" "movb (%%edi,%%ebx,), %%al \n\t" "addb (%%esi,%%ebx,), %%al \n\t" "incl %%ebx \n\t" -//pre "cmpl bpp, %%ebx \n\t" (bpp is preloaded into ecx) +/*pre "cmpl bpp, %%ebx \n\t" (bpp is preloaded into ecx) */ "cmpl %%ecx, %%ebx \n\t" "movb %%al, -1(%%edi,%%ebx,) \n\t" "jb paeth_rlp \n\t" - // get # of bytes to alignment - "movl %%edi, _dif \n\t" // take start of row - "addl %%ebx, _dif \n\t" // add bpp + /* get # of bytes to alignment */ + "movl %%edi, _dif \n\t" /* take start of row */ + "addl %%ebx, _dif \n\t" /* add bpp */ "xorl %%ecx, %%ecx \n\t" - "addl $0xf, _dif \n\t" // add 7 + 8 to incr past alignment - // boundary - "andl $0xfffffff8, _dif \n\t" // mask to alignment boundary - "subl %%edi, _dif \n\t" // subtract from start ==> value ebx - // at alignment + "addl $0xf, _dif \n\t" /* add 7 + 8 to incr past alignment */ + /* boundary */ + "andl $0xfffffff8, _dif \n\t" /* mask to alignment boundary */ + "subl %%edi, _dif \n\t" /* subtract from start ==> value ebx */ + /* at alignment */ "jz paeth_go \n\t" - // fix alignment + /* fix alignment */ "paeth_lp1: \n\t" "xorl %%eax, %%eax \n\t" - // pav = p - a = (a + b - c) - a = b - c - "movb (%%esi,%%ebx,), %%al \n\t" // load Prior(x) into al - "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl - "subl %%ecx, %%eax \n\t" // subtract Prior(x-bpp) - "movl %%eax, _patemp \n\t" // Save pav for later use + /* pav = p - a = (a + b - c) - a = b - c */ + "movb (%%esi,%%ebx,), %%al \n\t" /* load Prior(x) into al */ + "movb (%%esi,%%edx,), %%cl \n\t" /* load Prior(x-bpp) into cl */ + "subl %%ecx, %%eax \n\t" /* subtract Prior(x-bpp) */ + "movl %%eax, _patemp \n\t" /* Save pav for later use */ "xorl %%eax, %%eax \n\t" - // pbv = p - b = (a + b - c) - b = a - c - "movb (%%edi,%%edx,), %%al \n\t" // load Raw(x-bpp) into al - "subl %%ecx, %%eax \n\t" // subtract Prior(x-bpp) + /* pbv = p - b = (a + b - c) - b = a - c */ + "movb (%%edi,%%edx,), %%al \n\t" /* load Raw(x-bpp) into al */ + "subl %%ecx, %%eax \n\t" /* subtract Prior(x-bpp) */ "movl %%eax, %%ecx \n\t" - // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv - "addl _patemp, %%eax \n\t" // pcv = pav + pbv - // pc = abs(pcv) + /* pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv */ + "addl _patemp, %%eax \n\t" /* pcv = pav + pbv */ + /* pc = abs(pcv) */ "testl $0x80000000, %%eax \n\t" "jz paeth_pca \n\t" - "negl %%eax \n\t" // reverse sign of neg values + "negl %%eax \n\t" /* reverse sign of neg values */ "paeth_pca: \n\t" - "movl %%eax, _pctemp \n\t" // save pc for later use - // pb = abs(pbv) + "movl %%eax, _pctemp \n\t" /* save pc for later use */ + /* pb = abs(pbv) */ "testl $0x80000000, %%ecx \n\t" "jz paeth_pba \n\t" - "negl %%ecx \n\t" // reverse sign of neg values + "negl %%ecx \n\t" /* reverse sign of neg values */ "paeth_pba: \n\t" - "movl %%ecx, _pbtemp \n\t" // save pb for later use - // pa = abs(pav) + "movl %%ecx, _pbtemp \n\t" /* save pb for later use */ + /* pa = abs(pav) */ "movl _patemp, %%eax \n\t" "testl $0x80000000, %%eax \n\t" "jz paeth_paa \n\t" - "negl %%eax \n\t" // reverse sign of neg values + "negl %%eax \n\t" /* reverse sign of neg values */ "paeth_paa: \n\t" - "movl %%eax, _patemp \n\t" // save pa for later use - // test if pa <= pb + "movl %%eax, _patemp \n\t" /* save pa for later use */ + /* test if pa <= pb */ "cmpl %%ecx, %%eax \n\t" "jna paeth_abb \n\t" - // pa > pb; now test if pb <= pc + /* pa > pb; now test if pb <= pc */ "cmpl _pctemp, %%ecx \n\t" "jna paeth_bbc \n\t" - // pb > pc; Raw(x) = Paeth(x) + Prior(x-bpp) - "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl + /* pb > pc; Raw(x) = Paeth(x) + Prior(x-bpp) */ + "movb (%%esi,%%edx,), %%cl \n\t" /* load Prior(x-bpp) into cl */ "jmp paeth_paeth \n\t" "paeth_bbc: \n\t" - // pb <= pc; Raw(x) = Paeth(x) + Prior(x) - "movb (%%esi,%%ebx,), %%cl \n\t" // load Prior(x) into cl + /* pb <= pc; Raw(x) = Paeth(x) + Prior(x) */ + "movb (%%esi,%%ebx,), %%cl \n\t" /* load Prior(x) into cl */ "jmp paeth_paeth \n\t" "paeth_abb: \n\t" - // pa <= pb; now test if pa <= pc + /* pa <= pb; now test if pa <= pc */ "cmpl _pctemp, %%eax \n\t" "jna paeth_abc \n\t" - // pa > pc; Raw(x) = Paeth(x) + Prior(x-bpp) - "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl + /* pa > pc; Raw(x) = Paeth(x) + Prior(x-bpp) */ + "movb (%%esi,%%edx,), %%cl \n\t" /* load Prior(x-bpp) into cl */ "jmp paeth_paeth \n\t" "paeth_abc: \n\t" - // pa <= pc; Raw(x) = Paeth(x) + Raw(x-bpp) - "movb (%%edi,%%edx,), %%cl \n\t" // load Raw(x-bpp) into cl + /* pa <= pc; Raw(x) = Paeth(x) + Raw(x-bpp) */ + "movb (%%edi,%%edx,), %%cl \n\t" /* load Raw(x-bpp) into cl */ "paeth_paeth: \n\t" "incl %%ebx \n\t" "incl %%edx \n\t" - // Raw(x) = (Paeth(x) + Paeth_Predictor( a, b, c )) mod 256 + /* Raw(x) = (Paeth(x) + Paeth_Predictor( a, b, c )) mod 256 */ "addb %%cl, -1(%%edi,%%ebx,) \n\t" "cmpl _dif, %%ebx \n\t" "jb paeth_lp1 \n\t" @@ -3547,413 +3556,413 @@ png_read_filter_row_mmx_paeth(png_row_infop row_info, png_bytep row, "paeth_go: \n\t" "movl _FullLength, %%ecx \n\t" "movl %%ecx, %%eax \n\t" - "subl %%ebx, %%eax \n\t" // subtract alignment fix - "andl $0x00000007, %%eax \n\t" // calc bytes over mult of 8 - "subl %%eax, %%ecx \n\t" // drop over bytes from original length + "subl %%ebx, %%eax \n\t" /* subtract alignment fix */ + "andl $0x00000007, %%eax \n\t" /* calc bytes over mult of 8 */ + "subl %%eax, %%ecx \n\t" /* drop over bytes from original length */ "movl %%ecx, _MMXLength \n\t" #ifdef __PIC__ - "popl %%ebx \n\t" // restore index to Global Offset Table + "popl %%ebx \n\t" /* restore index to Global Offset Table */ #endif - : "=c" (dummy_value_c), // output regs (dummy) + : "=c" (dummy_value_c), /* output regs (dummy) */ "=S" (dummy_value_S), "=D" (dummy_value_D) - : "0" (bpp), // ecx // input regs - "1" (prev_row), // esi - "2" (row) // edi + : "0" (bpp), /* ecx // input regs */ + "1" (prev_row), /* esi */ + "2" (row) /* edi */ - : "%eax", "%edx" // clobber list + : "%eax", "%edx" /* clobber list */ #ifndef __PIC__ , "%ebx" #endif ); - // now do the math for the rest of the row + /* now do the math for the rest of the row */ switch (bpp) { case 3: { _ActiveMask.use = 0x0000000000ffffffLL; _ActiveMaskEnd.use = 0xffff000000000000LL; - _ShiftBpp.use = 24; // == bpp(3) * 8 - _ShiftRem.use = 40; // == 64 - 24 + _ShiftBpp.use = 24; /* == bpp(3) * 8 */ + _ShiftRem.use = 40; /* == 64 - 24 */ __asm__ __volatile__ ( "movl _dif, %%ecx \n\t" -// preload "movl row, %%edi \n\t" -// preload "movl prev_row, %%esi \n\t" +/* preload "movl row, %%edi \n\t" */ +/* preload "movl prev_row, %%esi \n\t" */ "pxor %%mm0, %%mm0 \n\t" - // prime the pump: load the first Raw(x-bpp) data set + /* prime the pump: load the first Raw(x-bpp) data set */ "movq -8(%%edi,%%ecx,), %%mm1 \n\t" "paeth_3lp: \n\t" - "psrlq _ShiftRem, %%mm1 \n\t" // shift last 3 bytes to 1st - // 3 bytes - "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x) - "punpcklbw %%mm0, %%mm1 \n\t" // unpack High bytes of a - "movq -8(%%esi,%%ecx,), %%mm3 \n\t" // prep c=Prior(x-bpp) bytes - "punpcklbw %%mm0, %%mm2 \n\t" // unpack High bytes of b - "psrlq _ShiftRem, %%mm3 \n\t" // shift last 3 bytes to 1st - // 3 bytes - // pav = p - a = (a + b - c) - a = b - c + "psrlq _ShiftRem, %%mm1 \n\t" /* shift last 3 bytes to 1st */ + /* 3 bytes */ + "movq (%%esi,%%ecx,), %%mm2 \n\t" /* load b=Prior(x) */ + "punpcklbw %%mm0, %%mm1 \n\t" /* unpack High bytes of a */ + "movq -8(%%esi,%%ecx,), %%mm3 \n\t" /* prep c=Prior(x-bpp) bytes */ + "punpcklbw %%mm0, %%mm2 \n\t" /* unpack High bytes of b */ + "psrlq _ShiftRem, %%mm3 \n\t" /* shift last 3 bytes to 1st */ + /* 3 bytes */ + /* pav = p - a = (a + b - c) - a = b - c */ "movq %%mm2, %%mm4 \n\t" - "punpcklbw %%mm0, %%mm3 \n\t" // unpack High bytes of c - // pbv = p - b = (a + b - c) - b = a - c + "punpcklbw %%mm0, %%mm3 \n\t" /* unpack High bytes of c */ + /* pbv = p - b = (a + b - c) - b = a - c */ "movq %%mm1, %%mm5 \n\t" "psubw %%mm3, %%mm4 \n\t" "pxor %%mm7, %%mm7 \n\t" - // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv + /* pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv */ "movq %%mm4, %%mm6 \n\t" "psubw %%mm3, %%mm5 \n\t" - // pa = abs(p-a) = abs(pav) - // pb = abs(p-b) = abs(pbv) - // pc = abs(p-c) = abs(pcv) - "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0 + /* pa = abs(p-a) = abs(pav) */ + /* pb = abs(p-b) = abs(pbv) */ + /* pc = abs(p-c) = abs(pcv) */ + "pcmpgtw %%mm4, %%mm0 \n\t" /* create mask pav bytes < 0 */ "paddw %%mm5, %%mm6 \n\t" - "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7 - "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0 + "pand %%mm4, %%mm0 \n\t" /* only pav bytes < 0 in mm7 */ + "pcmpgtw %%mm5, %%mm7 \n\t" /* create mask pbv bytes < 0 */ "psubw %%mm0, %%mm4 \n\t" - "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0 + "pand %%mm5, %%mm7 \n\t" /* only pbv bytes < 0 in mm0 */ "psubw %%mm0, %%mm4 \n\t" "psubw %%mm7, %%mm5 \n\t" "pxor %%mm0, %%mm0 \n\t" - "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0 - "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7 + "pcmpgtw %%mm6, %%mm0 \n\t" /* create mask pcv bytes < 0 */ + "pand %%mm6, %%mm0 \n\t" /* only pav bytes < 0 in mm7 */ "psubw %%mm7, %%mm5 \n\t" "psubw %%mm0, %%mm6 \n\t" - // test pa <= pb + /* test pa <= pb */ "movq %%mm4, %%mm7 \n\t" "psubw %%mm0, %%mm6 \n\t" - "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb? + "pcmpgtw %%mm5, %%mm7 \n\t" /* pa > pb? */ "movq %%mm7, %%mm0 \n\t" - // use mm7 mask to merge pa & pb + /* use mm7 mask to merge pa & pb */ "pand %%mm7, %%mm5 \n\t" - // use mm0 mask copy to merge a & b + /* use mm0 mask copy to merge a & b */ "pand %%mm0, %%mm2 \n\t" "pandn %%mm4, %%mm7 \n\t" "pandn %%mm1, %%mm0 \n\t" "paddw %%mm5, %%mm7 \n\t" "paddw %%mm2, %%mm0 \n\t" - // test ((pa <= pb)? pa:pb) <= pc - "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc? + /* test ((pa <= pb)? pa:pb) <= pc */ + "pcmpgtw %%mm6, %%mm7 \n\t" /* pab > pc? */ "pxor %%mm1, %%mm1 \n\t" "pand %%mm7, %%mm3 \n\t" "pandn %%mm0, %%mm7 \n\t" "paddw %%mm3, %%mm7 \n\t" "pxor %%mm0, %%mm0 \n\t" "packuswb %%mm1, %%mm7 \n\t" - "movq (%%esi,%%ecx,), %%mm3 \n\t" // load c=Prior(x-bpp) + "movq (%%esi,%%ecx,), %%mm3 \n\t" /* load c=Prior(x-bpp) */ "pand _ActiveMask, %%mm7 \n\t" - "movq %%mm3, %%mm2 \n\t" // load b=Prior(x) step 1 - "paddb (%%edi,%%ecx,), %%mm7 \n\t" // add Paeth predictor with Raw(x) - "punpcklbw %%mm0, %%mm3 \n\t" // unpack High bytes of c - "movq %%mm7, (%%edi,%%ecx,) \n\t" // write back updated value - "movq %%mm7, %%mm1 \n\t" // now mm1 will be used as - // Raw(x-bpp) - // now do Paeth for 2nd set of bytes (3-5) - "psrlq _ShiftBpp, %%mm2 \n\t" // load b=Prior(x) step 2 - "punpcklbw %%mm0, %%mm1 \n\t" // unpack High bytes of a + "movq %%mm3, %%mm2 \n\t" /* load b=Prior(x) step 1 */ + "paddb (%%edi,%%ecx,), %%mm7 \n\t" /* add Paeth predictor with Raw(x) */ + "punpcklbw %%mm0, %%mm3 \n\t" /* unpack High bytes of c */ + "movq %%mm7, (%%edi,%%ecx,) \n\t" /* write back updated value */ + "movq %%mm7, %%mm1 \n\t" /* now mm1 will be used as */ + /* Raw(x-bpp) */ + /* now do Paeth for 2nd set of bytes (3-5) */ + "psrlq _ShiftBpp, %%mm2 \n\t" /* load b=Prior(x) step 2 */ + "punpcklbw %%mm0, %%mm1 \n\t" /* unpack High bytes of a */ "pxor %%mm7, %%mm7 \n\t" - "punpcklbw %%mm0, %%mm2 \n\t" // unpack High bytes of b - // pbv = p - b = (a + b - c) - b = a - c + "punpcklbw %%mm0, %%mm2 \n\t" /* unpack High bytes of b */ + /* pbv = p - b = (a + b - c) - b = a - c */ "movq %%mm1, %%mm5 \n\t" - // pav = p - a = (a + b - c) - a = b - c + /* pav = p - a = (a + b - c) - a = b - c */ "movq %%mm2, %%mm4 \n\t" "psubw %%mm3, %%mm5 \n\t" "psubw %%mm3, %%mm4 \n\t" - // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = - // pav + pbv = pbv + pav + /* pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = */ + /* pav + pbv = pbv + pav */ "movq %%mm5, %%mm6 \n\t" "paddw %%mm4, %%mm6 \n\t" - // pa = abs(p-a) = abs(pav) - // pb = abs(p-b) = abs(pbv) - // pc = abs(p-c) = abs(pcv) - "pcmpgtw %%mm5, %%mm0 \n\t" // create mask pbv bytes < 0 - "pcmpgtw %%mm4, %%mm7 \n\t" // create mask pav bytes < 0 - "pand %%mm5, %%mm0 \n\t" // only pbv bytes < 0 in mm0 - "pand %%mm4, %%mm7 \n\t" // only pav bytes < 0 in mm7 + /* pa = abs(p-a) = abs(pav) */ + /* pb = abs(p-b) = abs(pbv) */ + /* pc = abs(p-c) = abs(pcv) */ + "pcmpgtw %%mm5, %%mm0 \n\t" /* create mask pbv bytes < 0 */ + "pcmpgtw %%mm4, %%mm7 \n\t" /* create mask pav bytes < 0 */ + "pand %%mm5, %%mm0 \n\t" /* only pbv bytes < 0 in mm0 */ + "pand %%mm4, %%mm7 \n\t" /* only pav bytes < 0 in mm7 */ "psubw %%mm0, %%mm5 \n\t" "psubw %%mm7, %%mm4 \n\t" "psubw %%mm0, %%mm5 \n\t" "psubw %%mm7, %%mm4 \n\t" "pxor %%mm0, %%mm0 \n\t" - "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0 - "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7 + "pcmpgtw %%mm6, %%mm0 \n\t" /* create mask pcv bytes < 0 */ + "pand %%mm6, %%mm0 \n\t" /* only pav bytes < 0 in mm7 */ "psubw %%mm0, %%mm6 \n\t" - // test pa <= pb + /* test pa <= pb */ "movq %%mm4, %%mm7 \n\t" "psubw %%mm0, %%mm6 \n\t" - "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb? + "pcmpgtw %%mm5, %%mm7 \n\t" /* pa > pb? */ "movq %%mm7, %%mm0 \n\t" - // use mm7 mask to merge pa & pb + /* use mm7 mask to merge pa & pb */ "pand %%mm7, %%mm5 \n\t" - // use mm0 mask copy to merge a & b + /* use mm0 mask copy to merge a & b */ "pand %%mm0, %%mm2 \n\t" "pandn %%mm4, %%mm7 \n\t" "pandn %%mm1, %%mm0 \n\t" "paddw %%mm5, %%mm7 \n\t" "paddw %%mm2, %%mm0 \n\t" - // test ((pa <= pb)? pa:pb) <= pc - "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc? - "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x) + /* test ((pa <= pb)? pa:pb) <= pc */ + "pcmpgtw %%mm6, %%mm7 \n\t" /* pab > pc? */ + "movq (%%esi,%%ecx,), %%mm2 \n\t" /* load b=Prior(x) */ "pand %%mm7, %%mm3 \n\t" "pandn %%mm0, %%mm7 \n\t" "pxor %%mm1, %%mm1 \n\t" "paddw %%mm3, %%mm7 \n\t" "pxor %%mm0, %%mm0 \n\t" "packuswb %%mm1, %%mm7 \n\t" - "movq %%mm2, %%mm3 \n\t" // load c=Prior(x-bpp) step 1 + "movq %%mm2, %%mm3 \n\t" /* load c=Prior(x-bpp) step 1 */ "pand _ActiveMask, %%mm7 \n\t" - "punpckhbw %%mm0, %%mm2 \n\t" // unpack High bytes of b - "psllq _ShiftBpp, %%mm7 \n\t" // shift bytes to 2nd group of - // 3 bytes - // pav = p - a = (a + b - c) - a = b - c + "punpckhbw %%mm0, %%mm2 \n\t" /* unpack High bytes of b */ + "psllq _ShiftBpp, %%mm7 \n\t" /* shift bytes to 2nd group of */ + /* 3 bytes */ + /* pav = p - a = (a + b - c) - a = b - c */ "movq %%mm2, %%mm4 \n\t" - "paddb (%%edi,%%ecx,), %%mm7 \n\t" // add Paeth predictor with Raw(x) - "psllq _ShiftBpp, %%mm3 \n\t" // load c=Prior(x-bpp) step 2 - "movq %%mm7, (%%edi,%%ecx,) \n\t" // write back updated value + "paddb (%%edi,%%ecx,), %%mm7 \n\t" /* add Paeth predictor with Raw(x) */ + "psllq _ShiftBpp, %%mm3 \n\t" /* load c=Prior(x-bpp) step 2 */ + "movq %%mm7, (%%edi,%%ecx,) \n\t" /* write back updated value */ "movq %%mm7, %%mm1 \n\t" - "punpckhbw %%mm0, %%mm3 \n\t" // unpack High bytes of c - "psllq _ShiftBpp, %%mm1 \n\t" // shift bytes - // now mm1 will be used as Raw(x-bpp) - // now do Paeth for 3rd, and final, set of bytes (6-7) + "punpckhbw %%mm0, %%mm3 \n\t" /* unpack High bytes of c */ + "psllq _ShiftBpp, %%mm1 \n\t" /* shift bytes */ + /* now mm1 will be used as Raw(x-bpp) */ + /* now do Paeth for 3rd, and final, set of bytes (6-7) */ "pxor %%mm7, %%mm7 \n\t" - "punpckhbw %%mm0, %%mm1 \n\t" // unpack High bytes of a + "punpckhbw %%mm0, %%mm1 \n\t" /* unpack High bytes of a */ "psubw %%mm3, %%mm4 \n\t" - // pbv = p - b = (a + b - c) - b = a - c + /* pbv = p - b = (a + b - c) - b = a - c */ "movq %%mm1, %%mm5 \n\t" - // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv + /* pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv */ "movq %%mm4, %%mm6 \n\t" "psubw %%mm3, %%mm5 \n\t" "pxor %%mm0, %%mm0 \n\t" "paddw %%mm5, %%mm6 \n\t" - // pa = abs(p-a) = abs(pav) - // pb = abs(p-b) = abs(pbv) - // pc = abs(p-c) = abs(pcv) - "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0 - "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0 - "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7 - "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0 + /* pa = abs(p-a) = abs(pav) */ + /* pb = abs(p-b) = abs(pbv) */ + /* pc = abs(p-c) = abs(pcv) */ + "pcmpgtw %%mm4, %%mm0 \n\t" /* create mask pav bytes < 0 */ + "pcmpgtw %%mm5, %%mm7 \n\t" /* create mask pbv bytes < 0 */ + "pand %%mm4, %%mm0 \n\t" /* only pav bytes < 0 in mm7 */ + "pand %%mm5, %%mm7 \n\t" /* only pbv bytes < 0 in mm0 */ "psubw %%mm0, %%mm4 \n\t" "psubw %%mm7, %%mm5 \n\t" "psubw %%mm0, %%mm4 \n\t" "psubw %%mm7, %%mm5 \n\t" "pxor %%mm0, %%mm0 \n\t" - "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0 - "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7 + "pcmpgtw %%mm6, %%mm0 \n\t" /* create mask pcv bytes < 0 */ + "pand %%mm6, %%mm0 \n\t" /* only pav bytes < 0 in mm7 */ "psubw %%mm0, %%mm6 \n\t" - // test pa <= pb + /* test pa <= pb */ "movq %%mm4, %%mm7 \n\t" "psubw %%mm0, %%mm6 \n\t" - "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb? + "pcmpgtw %%mm5, %%mm7 \n\t" /* pa > pb? */ "movq %%mm7, %%mm0 \n\t" - // use mm0 mask copy to merge a & b + /* use mm0 mask copy to merge a & b */ "pand %%mm0, %%mm2 \n\t" - // use mm7 mask to merge pa & pb + /* use mm7 mask to merge pa & pb */ "pand %%mm7, %%mm5 \n\t" "pandn %%mm1, %%mm0 \n\t" "pandn %%mm4, %%mm7 \n\t" "paddw %%mm2, %%mm0 \n\t" "paddw %%mm5, %%mm7 \n\t" - // test ((pa <= pb)? pa:pb) <= pc - "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc? + /* test ((pa <= pb)? pa:pb) <= pc */ + "pcmpgtw %%mm6, %%mm7 \n\t" /* pab > pc? */ "pand %%mm7, %%mm3 \n\t" "pandn %%mm0, %%mm7 \n\t" "paddw %%mm3, %%mm7 \n\t" "pxor %%mm1, %%mm1 \n\t" "packuswb %%mm7, %%mm1 \n\t" - // step ecx to next set of 8 bytes and repeat loop til done + /* step ecx to next set of 8 bytes and repeat loop til done */ "addl $8, %%ecx \n\t" "pand _ActiveMaskEnd, %%mm1 \n\t" - "paddb -8(%%edi,%%ecx,), %%mm1 \n\t" // add Paeth predictor with - // Raw(x) + "paddb -8(%%edi,%%ecx,), %%mm1 \n\t" /* add Paeth predictor with */ + /* Raw(x) */ "cmpl _MMXLength, %%ecx \n\t" - "pxor %%mm0, %%mm0 \n\t" // pxor does not affect flags - "movq %%mm1, -8(%%edi,%%ecx,) \n\t" // write back updated value - // mm1 will be used as Raw(x-bpp) next loop - // mm3 ready to be used as Prior(x-bpp) next loop + "pxor %%mm0, %%mm0 \n\t" /* pxor does not affect flags */ + "movq %%mm1, -8(%%edi,%%ecx,) \n\t" /* write back updated value */ + /* mm1 will be used as Raw(x-bpp) next loop */ + /* mm3 ready to be used as Prior(x-bpp) next loop */ "jb paeth_3lp \n\t" - : "=S" (dummy_value_S), // output regs (dummy) + : "=S" (dummy_value_S), /* output regs (dummy) */ "=D" (dummy_value_D) - : "0" (prev_row), // esi // input regs - "1" (row) // edi + : "0" (prev_row), /* esi // input regs */ + "1" (row) /* edi */ - : "%ecx" // clobber list + : "%ecx" /* clobber list */ #if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */ , "%mm0", "%mm1", "%mm2", "%mm3" , "%mm4", "%mm5", "%mm6", "%mm7" #endif ); } - break; // end 3 bpp + break; /* end 3 bpp */ case 6: - //case 7: // GRR BOGUS - //case 5: // GRR BOGUS + //case 7: /* GRR BOGUS */ + //case 5: /* GRR BOGUS */ { _ActiveMask.use = 0x00000000ffffffffLL; _ActiveMask2.use = 0xffffffff00000000LL; - _ShiftBpp.use = bpp << 3; // == bpp * 8 + _ShiftBpp.use = bpp << 3; /* == bpp * 8 */ _ShiftRem.use = 64 - _ShiftBpp.use; __asm__ __volatile__ ( "movl _dif, %%ecx \n\t" -// preload "movl row, %%edi \n\t" -// preload "movl prev_row, %%esi \n\t" - // prime the pump: load the first Raw(x-bpp) data set +/* preload "movl row, %%edi \n\t" */ +/* preload "movl prev_row, %%esi \n\t" */ + /* prime the pump: load the first Raw(x-bpp) data set */ "movq -8(%%edi,%%ecx,), %%mm1 \n\t" "pxor %%mm0, %%mm0 \n\t" "paeth_6lp: \n\t" - // must shift to position Raw(x-bpp) data + /* must shift to position Raw(x-bpp) data */ "psrlq _ShiftRem, %%mm1 \n\t" - // do first set of 4 bytes - "movq -8(%%esi,%%ecx,), %%mm3 \n\t" // read c=Prior(x-bpp) bytes - "punpcklbw %%mm0, %%mm1 \n\t" // unpack Low bytes of a - "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x) - "punpcklbw %%mm0, %%mm2 \n\t" // unpack Low bytes of b - // must shift to position Prior(x-bpp) data + /* do first set of 4 bytes */ + "movq -8(%%esi,%%ecx,), %%mm3 \n\t" /* read c=Prior(x-bpp) bytes */ + "punpcklbw %%mm0, %%mm1 \n\t" /* unpack Low bytes of a */ + "movq (%%esi,%%ecx,), %%mm2 \n\t" /* load b=Prior(x) */ + "punpcklbw %%mm0, %%mm2 \n\t" /* unpack Low bytes of b */ + /* must shift to position Prior(x-bpp) data */ "psrlq _ShiftRem, %%mm3 \n\t" - // pav = p - a = (a + b - c) - a = b - c + /* pav = p - a = (a + b - c) - a = b - c */ "movq %%mm2, %%mm4 \n\t" - "punpcklbw %%mm0, %%mm3 \n\t" // unpack Low bytes of c - // pbv = p - b = (a + b - c) - b = a - c + "punpcklbw %%mm0, %%mm3 \n\t" /* unpack Low bytes of c */ + /* pbv = p - b = (a + b - c) - b = a - c */ "movq %%mm1, %%mm5 \n\t" "psubw %%mm3, %%mm4 \n\t" "pxor %%mm7, %%mm7 \n\t" - // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv + /* pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv */ "movq %%mm4, %%mm6 \n\t" "psubw %%mm3, %%mm5 \n\t" - // pa = abs(p-a) = abs(pav) - // pb = abs(p-b) = abs(pbv) - // pc = abs(p-c) = abs(pcv) - "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0 + /* pa = abs(p-a) = abs(pav) */ + /* pb = abs(p-b) = abs(pbv) */ + /* pc = abs(p-c) = abs(pcv) */ + "pcmpgtw %%mm4, %%mm0 \n\t" /* create mask pav bytes < 0 */ "paddw %%mm5, %%mm6 \n\t" - "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7 - "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0 + "pand %%mm4, %%mm0 \n\t" /* only pav bytes < 0 in mm7 */ + "pcmpgtw %%mm5, %%mm7 \n\t" /* create mask pbv bytes < 0 */ "psubw %%mm0, %%mm4 \n\t" - "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0 + "pand %%mm5, %%mm7 \n\t" /* only pbv bytes < 0 in mm0 */ "psubw %%mm0, %%mm4 \n\t" "psubw %%mm7, %%mm5 \n\t" "pxor %%mm0, %%mm0 \n\t" - "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0 - "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7 + "pcmpgtw %%mm6, %%mm0 \n\t" /* create mask pcv bytes < 0 */ + "pand %%mm6, %%mm0 \n\t" /* only pav bytes < 0 in mm7 */ "psubw %%mm7, %%mm5 \n\t" "psubw %%mm0, %%mm6 \n\t" - // test pa <= pb + /* test pa <= pb */ "movq %%mm4, %%mm7 \n\t" "psubw %%mm0, %%mm6 \n\t" - "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb? + "pcmpgtw %%mm5, %%mm7 \n\t" /* pa > pb? */ "movq %%mm7, %%mm0 \n\t" - // use mm7 mask to merge pa & pb + /* use mm7 mask to merge pa & pb */ "pand %%mm7, %%mm5 \n\t" - // use mm0 mask copy to merge a & b + /* use mm0 mask copy to merge a & b */ "pand %%mm0, %%mm2 \n\t" "pandn %%mm4, %%mm7 \n\t" "pandn %%mm1, %%mm0 \n\t" "paddw %%mm5, %%mm7 \n\t" "paddw %%mm2, %%mm0 \n\t" - // test ((pa <= pb)? pa:pb) <= pc - "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc? + /* test ((pa <= pb)? pa:pb) <= pc */ + "pcmpgtw %%mm6, %%mm7 \n\t" /* pab > pc? */ "pxor %%mm1, %%mm1 \n\t" "pand %%mm7, %%mm3 \n\t" "pandn %%mm0, %%mm7 \n\t" "paddw %%mm3, %%mm7 \n\t" "pxor %%mm0, %%mm0 \n\t" "packuswb %%mm1, %%mm7 \n\t" - "movq -8(%%esi,%%ecx,), %%mm3 \n\t" // load c=Prior(x-bpp) + "movq -8(%%esi,%%ecx,), %%mm3 \n\t" /* load c=Prior(x-bpp) */ "pand _ActiveMask, %%mm7 \n\t" "psrlq _ShiftRem, %%mm3 \n\t" - "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x) step 1 - "paddb (%%edi,%%ecx,), %%mm7 \n\t" // add Paeth predictor and Raw(x) + "movq (%%esi,%%ecx,), %%mm2 \n\t" /* load b=Prior(x) step 1 */ + "paddb (%%edi,%%ecx,), %%mm7 \n\t" /* add Paeth predictor and Raw(x) */ "movq %%mm2, %%mm6 \n\t" - "movq %%mm7, (%%edi,%%ecx,) \n\t" // write back updated value + "movq %%mm7, (%%edi,%%ecx,) \n\t" /* write back updated value */ "movq -8(%%edi,%%ecx,), %%mm1 \n\t" "psllq _ShiftBpp, %%mm6 \n\t" "movq %%mm7, %%mm5 \n\t" "psrlq _ShiftRem, %%mm1 \n\t" "por %%mm6, %%mm3 \n\t" "psllq _ShiftBpp, %%mm5 \n\t" - "punpckhbw %%mm0, %%mm3 \n\t" // unpack High bytes of c + "punpckhbw %%mm0, %%mm3 \n\t" /* unpack High bytes of c */ "por %%mm5, %%mm1 \n\t" - // do second set of 4 bytes - "punpckhbw %%mm0, %%mm2 \n\t" // unpack High bytes of b - "punpckhbw %%mm0, %%mm1 \n\t" // unpack High bytes of a - // pav = p - a = (a + b - c) - a = b - c + /* do second set of 4 bytes */ + "punpckhbw %%mm0, %%mm2 \n\t" /* unpack High bytes of b */ + "punpckhbw %%mm0, %%mm1 \n\t" /* unpack High bytes of a */ + /* pav = p - a = (a + b - c) - a = b - c */ "movq %%mm2, %%mm4 \n\t" - // pbv = p - b = (a + b - c) - b = a - c + /* pbv = p - b = (a + b - c) - b = a - c */ "movq %%mm1, %%mm5 \n\t" "psubw %%mm3, %%mm4 \n\t" "pxor %%mm7, %%mm7 \n\t" - // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv + /* pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv */ "movq %%mm4, %%mm6 \n\t" "psubw %%mm3, %%mm5 \n\t" - // pa = abs(p-a) = abs(pav) - // pb = abs(p-b) = abs(pbv) - // pc = abs(p-c) = abs(pcv) - "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0 + /* pa = abs(p-a) = abs(pav) */ + /* pb = abs(p-b) = abs(pbv) */ + /* pc = abs(p-c) = abs(pcv) */ + "pcmpgtw %%mm4, %%mm0 \n\t" /* create mask pav bytes < 0 */ "paddw %%mm5, %%mm6 \n\t" - "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7 - "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0 + "pand %%mm4, %%mm0 \n\t" /* only pav bytes < 0 in mm7 */ + "pcmpgtw %%mm5, %%mm7 \n\t" /* create mask pbv bytes < 0 */ "psubw %%mm0, %%mm4 \n\t" - "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0 + "pand %%mm5, %%mm7 \n\t" /* only pbv bytes < 0 in mm0 */ "psubw %%mm0, %%mm4 \n\t" "psubw %%mm7, %%mm5 \n\t" "pxor %%mm0, %%mm0 \n\t" - "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0 - "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7 + "pcmpgtw %%mm6, %%mm0 \n\t" /* create mask pcv bytes < 0 */ + "pand %%mm6, %%mm0 \n\t" /* only pav bytes < 0 in mm7 */ "psubw %%mm7, %%mm5 \n\t" "psubw %%mm0, %%mm6 \n\t" - // test pa <= pb + /* test pa <= pb */ "movq %%mm4, %%mm7 \n\t" "psubw %%mm0, %%mm6 \n\t" - "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb? + "pcmpgtw %%mm5, %%mm7 \n\t" /* pa > pb? */ "movq %%mm7, %%mm0 \n\t" - // use mm7 mask to merge pa & pb + /* use mm7 mask to merge pa & pb */ "pand %%mm7, %%mm5 \n\t" - // use mm0 mask copy to merge a & b + /* use mm0 mask copy to merge a & b */ "pand %%mm0, %%mm2 \n\t" "pandn %%mm4, %%mm7 \n\t" "pandn %%mm1, %%mm0 \n\t" "paddw %%mm5, %%mm7 \n\t" "paddw %%mm2, %%mm0 \n\t" - // test ((pa <= pb)? pa:pb) <= pc - "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc? + /* test ((pa <= pb)? pa:pb) <= pc */ + "pcmpgtw %%mm6, %%mm7 \n\t" /* pab > pc? */ "pxor %%mm1, %%mm1 \n\t" "pand %%mm7, %%mm3 \n\t" "pandn %%mm0, %%mm7 \n\t" "pxor %%mm1, %%mm1 \n\t" "paddw %%mm3, %%mm7 \n\t" "pxor %%mm0, %%mm0 \n\t" - // step ecx to next set of 8 bytes and repeat loop til done + /* step ecx to next set of 8 bytes and repeat loop til done */ "addl $8, %%ecx \n\t" "packuswb %%mm7, %%mm1 \n\t" - "paddb -8(%%edi,%%ecx,), %%mm1 \n\t" // add Paeth predictor with Raw(x) + "paddb -8(%%edi,%%ecx,), %%mm1 \n\t" /* add Paeth predictor with Raw(x) */ "cmpl _MMXLength, %%ecx \n\t" - "movq %%mm1, -8(%%edi,%%ecx,) \n\t" // write back updated value - // mm1 will be used as Raw(x-bpp) next loop + "movq %%mm1, -8(%%edi,%%ecx,) \n\t" /* write back updated value */ + /* mm1 will be used as Raw(x-bpp) next loop */ "jb paeth_6lp \n\t" - : "=S" (dummy_value_S), // output regs (dummy) + : "=S" (dummy_value_S), /* output regs (dummy) */ "=D" (dummy_value_D) - : "0" (prev_row), // esi // input regs - "1" (row) // edi + : "0" (prev_row), /* esi // input regs */ + "1" (row) /* edi */ - : "%ecx" // clobber list + : "%ecx" /* clobber list */ #if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */ , "%mm0", "%mm1", "%mm2", "%mm3" , "%mm4", "%mm5", "%mm6", "%mm7" #endif ); } - break; // end 6 bpp + break; /* end 6 bpp */ case 4: { @@ -3961,508 +3970,508 @@ png_read_filter_row_mmx_paeth(png_row_infop row_info, png_bytep row, __asm__ __volatile__ ( "movl _dif, %%ecx \n\t" -// preload "movl row, %%edi \n\t" -// preload "movl prev_row, %%esi \n\t" +/* preload "movl row, %%edi \n\t" */ +/* preload "movl prev_row, %%esi \n\t" */ "pxor %%mm0, %%mm0 \n\t" - // prime the pump: load the first Raw(x-bpp) data set - "movq -8(%%edi,%%ecx,), %%mm1 \n\t" // only time should need to read - // a=Raw(x-bpp) bytes + /* prime the pump: load the first Raw(x-bpp) data set */ + "movq -8(%%edi,%%ecx,), %%mm1 \n\t" /* only time should need to read */ + /* a=Raw(x-bpp) bytes */ "paeth_4lp: \n\t" - // do first set of 4 bytes - "movq -8(%%esi,%%ecx,), %%mm3 \n\t" // read c=Prior(x-bpp) bytes - "punpckhbw %%mm0, %%mm1 \n\t" // unpack Low bytes of a - "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x) - "punpcklbw %%mm0, %%mm2 \n\t" // unpack High bytes of b - // pav = p - a = (a + b - c) - a = b - c + /* do first set of 4 bytes */ + "movq -8(%%esi,%%ecx,), %%mm3 \n\t" /* read c=Prior(x-bpp) bytes */ + "punpckhbw %%mm0, %%mm1 \n\t" /* unpack Low bytes of a */ + "movq (%%esi,%%ecx,), %%mm2 \n\t" /* load b=Prior(x) */ + "punpcklbw %%mm0, %%mm2 \n\t" /* unpack High bytes of b */ + /* pav = p - a = (a + b - c) - a = b - c */ "movq %%mm2, %%mm4 \n\t" - "punpckhbw %%mm0, %%mm3 \n\t" // unpack High bytes of c - // pbv = p - b = (a + b - c) - b = a - c + "punpckhbw %%mm0, %%mm3 \n\t" /* unpack High bytes of c */ + /* pbv = p - b = (a + b - c) - b = a - c */ "movq %%mm1, %%mm5 \n\t" "psubw %%mm3, %%mm4 \n\t" "pxor %%mm7, %%mm7 \n\t" - // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv + /* pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv */ "movq %%mm4, %%mm6 \n\t" "psubw %%mm3, %%mm5 \n\t" - // pa = abs(p-a) = abs(pav) - // pb = abs(p-b) = abs(pbv) - // pc = abs(p-c) = abs(pcv) - "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0 + /* pa = abs(p-a) = abs(pav) */ + /* pb = abs(p-b) = abs(pbv) */ + /* pc = abs(p-c) = abs(pcv) */ + "pcmpgtw %%mm4, %%mm0 \n\t" /* create mask pav bytes < 0 */ "paddw %%mm5, %%mm6 \n\t" - "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7 - "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0 + "pand %%mm4, %%mm0 \n\t" /* only pav bytes < 0 in mm7 */ + "pcmpgtw %%mm5, %%mm7 \n\t" /* create mask pbv bytes < 0 */ "psubw %%mm0, %%mm4 \n\t" - "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0 + "pand %%mm5, %%mm7 \n\t" /* only pbv bytes < 0 in mm0 */ "psubw %%mm0, %%mm4 \n\t" "psubw %%mm7, %%mm5 \n\t" "pxor %%mm0, %%mm0 \n\t" - "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0 - "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7 + "pcmpgtw %%mm6, %%mm0 \n\t" /* create mask pcv bytes < 0 */ + "pand %%mm6, %%mm0 \n\t" /* only pav bytes < 0 in mm7 */ "psubw %%mm7, %%mm5 \n\t" "psubw %%mm0, %%mm6 \n\t" - // test pa <= pb + /* test pa <= pb */ "movq %%mm4, %%mm7 \n\t" "psubw %%mm0, %%mm6 \n\t" - "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb? + "pcmpgtw %%mm5, %%mm7 \n\t" /* pa > pb? */ "movq %%mm7, %%mm0 \n\t" - // use mm7 mask to merge pa & pb + /* use mm7 mask to merge pa & pb */ "pand %%mm7, %%mm5 \n\t" - // use mm0 mask copy to merge a & b + /* use mm0 mask copy to merge a & b */ "pand %%mm0, %%mm2 \n\t" "pandn %%mm4, %%mm7 \n\t" "pandn %%mm1, %%mm0 \n\t" "paddw %%mm5, %%mm7 \n\t" "paddw %%mm2, %%mm0 \n\t" - // test ((pa <= pb)? pa:pb) <= pc - "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc? + /* test ((pa <= pb)? pa:pb) <= pc */ + "pcmpgtw %%mm6, %%mm7 \n\t" /* pab > pc? */ "pxor %%mm1, %%mm1 \n\t" "pand %%mm7, %%mm3 \n\t" "pandn %%mm0, %%mm7 \n\t" "paddw %%mm3, %%mm7 \n\t" "pxor %%mm0, %%mm0 \n\t" "packuswb %%mm1, %%mm7 \n\t" - "movq (%%esi,%%ecx,), %%mm3 \n\t" // load c=Prior(x-bpp) + "movq (%%esi,%%ecx,), %%mm3 \n\t" /* load c=Prior(x-bpp) */ "pand _ActiveMask, %%mm7 \n\t" - "movq %%mm3, %%mm2 \n\t" // load b=Prior(x) step 1 - "paddb (%%edi,%%ecx,), %%mm7 \n\t" // add Paeth predictor with Raw(x) - "punpcklbw %%mm0, %%mm3 \n\t" // unpack High bytes of c - "movq %%mm7, (%%edi,%%ecx,) \n\t" // write back updated value - "movq %%mm7, %%mm1 \n\t" // now mm1 will be used as Raw(x-bpp) - // do second set of 4 bytes - "punpckhbw %%mm0, %%mm2 \n\t" // unpack Low bytes of b - "punpcklbw %%mm0, %%mm1 \n\t" // unpack Low bytes of a - // pav = p - a = (a + b - c) - a = b - c + "movq %%mm3, %%mm2 \n\t" /* load b=Prior(x) step 1 */ + "paddb (%%edi,%%ecx,), %%mm7 \n\t" /* add Paeth predictor with Raw(x) */ + "punpcklbw %%mm0, %%mm3 \n\t" /* unpack High bytes of c */ + "movq %%mm7, (%%edi,%%ecx,) \n\t" /* write back updated value */ + "movq %%mm7, %%mm1 \n\t" /* now mm1 will be used as Raw(x-bpp) */ + /* do second set of 4 bytes */ + "punpckhbw %%mm0, %%mm2 \n\t" /* unpack Low bytes of b */ + "punpcklbw %%mm0, %%mm1 \n\t" /* unpack Low bytes of a */ + /* pav = p - a = (a + b - c) - a = b - c */ "movq %%mm2, %%mm4 \n\t" - // pbv = p - b = (a + b - c) - b = a - c + /* pbv = p - b = (a + b - c) - b = a - c */ "movq %%mm1, %%mm5 \n\t" "psubw %%mm3, %%mm4 \n\t" "pxor %%mm7, %%mm7 \n\t" - // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv + /* pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv */ "movq %%mm4, %%mm6 \n\t" "psubw %%mm3, %%mm5 \n\t" - // pa = abs(p-a) = abs(pav) - // pb = abs(p-b) = abs(pbv) - // pc = abs(p-c) = abs(pcv) - "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0 + /* pa = abs(p-a) = abs(pav) */ + /* pb = abs(p-b) = abs(pbv) */ + /* pc = abs(p-c) = abs(pcv) */ + "pcmpgtw %%mm4, %%mm0 \n\t" /* create mask pav bytes < 0 */ "paddw %%mm5, %%mm6 \n\t" - "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7 - "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0 + "pand %%mm4, %%mm0 \n\t" /* only pav bytes < 0 in mm7 */ + "pcmpgtw %%mm5, %%mm7 \n\t" /* create mask pbv bytes < 0 */ "psubw %%mm0, %%mm4 \n\t" - "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0 + "pand %%mm5, %%mm7 \n\t" /* only pbv bytes < 0 in mm0 */ "psubw %%mm0, %%mm4 \n\t" "psubw %%mm7, %%mm5 \n\t" "pxor %%mm0, %%mm0 \n\t" - "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0 - "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7 + "pcmpgtw %%mm6, %%mm0 \n\t" /* create mask pcv bytes < 0 */ + "pand %%mm6, %%mm0 \n\t" /* only pav bytes < 0 in mm7 */ "psubw %%mm7, %%mm5 \n\t" "psubw %%mm0, %%mm6 \n\t" - // test pa <= pb + /* test pa <= pb */ "movq %%mm4, %%mm7 \n\t" "psubw %%mm0, %%mm6 \n\t" - "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb? + "pcmpgtw %%mm5, %%mm7 \n\t" /* pa > pb? */ "movq %%mm7, %%mm0 \n\t" - // use mm7 mask to merge pa & pb + /* use mm7 mask to merge pa & pb */ "pand %%mm7, %%mm5 \n\t" - // use mm0 mask copy to merge a & b + /* use mm0 mask copy to merge a & b */ "pand %%mm0, %%mm2 \n\t" "pandn %%mm4, %%mm7 \n\t" "pandn %%mm1, %%mm0 \n\t" "paddw %%mm5, %%mm7 \n\t" "paddw %%mm2, %%mm0 \n\t" - // test ((pa <= pb)? pa:pb) <= pc - "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc? + /* test ((pa <= pb)? pa:pb) <= pc */ + "pcmpgtw %%mm6, %%mm7 \n\t" /* pab > pc? */ "pxor %%mm1, %%mm1 \n\t" "pand %%mm7, %%mm3 \n\t" "pandn %%mm0, %%mm7 \n\t" "pxor %%mm1, %%mm1 \n\t" "paddw %%mm3, %%mm7 \n\t" "pxor %%mm0, %%mm0 \n\t" - // step ecx to next set of 8 bytes and repeat loop til done + /* step ecx to next set of 8 bytes and repeat loop til done */ "addl $8, %%ecx \n\t" "packuswb %%mm7, %%mm1 \n\t" - "paddb -8(%%edi,%%ecx,), %%mm1 \n\t" // add predictor with Raw(x) + "paddb -8(%%edi,%%ecx,), %%mm1 \n\t" /* add predictor with Raw(x) */ "cmpl _MMXLength, %%ecx \n\t" - "movq %%mm1, -8(%%edi,%%ecx,) \n\t" // write back updated value - // mm1 will be used as Raw(x-bpp) next loop + "movq %%mm1, -8(%%edi,%%ecx,) \n\t" /* write back updated value */ + /* mm1 will be used as Raw(x-bpp) next loop */ "jb paeth_4lp \n\t" - : "=S" (dummy_value_S), // output regs (dummy) + : "=S" (dummy_value_S), /* output regs (dummy) */ "=D" (dummy_value_D) - : "0" (prev_row), // esi // input regs - "1" (row) // edi + : "0" (prev_row), /* esi // input regs */ + "1" (row) /* edi */ - : "%ecx" // clobber list + : "%ecx" /* clobber list */ #if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */ , "%mm0", "%mm1", "%mm2", "%mm3" , "%mm4", "%mm5", "%mm6", "%mm7" #endif ); } - break; // end 4 bpp + break; /* end 4 bpp */ - case 8: // bpp == 8 + case 8: /* bpp == 8 */ { _ActiveMask.use = 0x00000000ffffffffLL; __asm__ __volatile__ ( "movl _dif, %%ecx \n\t" -// preload "movl row, %%edi \n\t" -// preload "movl prev_row, %%esi \n\t" +/* preload "movl row, %%edi \n\t" */ +/* preload "movl prev_row, %%esi \n\t" */ "pxor %%mm0, %%mm0 \n\t" - // prime the pump: load the first Raw(x-bpp) data set - "movq -8(%%edi,%%ecx,), %%mm1 \n\t" // only time should need to read - // a=Raw(x-bpp) bytes + /* prime the pump: load the first Raw(x-bpp) data set */ + "movq -8(%%edi,%%ecx,), %%mm1 \n\t" /* only time should need to read */ + /* a=Raw(x-bpp) bytes */ "paeth_8lp: \n\t" - // do first set of 4 bytes - "movq -8(%%esi,%%ecx,), %%mm3 \n\t" // read c=Prior(x-bpp) bytes - "punpcklbw %%mm0, %%mm1 \n\t" // unpack Low bytes of a - "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x) - "punpcklbw %%mm0, %%mm2 \n\t" // unpack Low bytes of b - // pav = p - a = (a + b - c) - a = b - c + /* do first set of 4 bytes */ + "movq -8(%%esi,%%ecx,), %%mm3 \n\t" /* read c=Prior(x-bpp) bytes */ + "punpcklbw %%mm0, %%mm1 \n\t" /* unpack Low bytes of a */ + "movq (%%esi,%%ecx,), %%mm2 \n\t" /* load b=Prior(x) */ + "punpcklbw %%mm0, %%mm2 \n\t" /* unpack Low bytes of b */ + /* pav = p - a = (a + b - c) - a = b - c */ "movq %%mm2, %%mm4 \n\t" - "punpcklbw %%mm0, %%mm3 \n\t" // unpack Low bytes of c - // pbv = p - b = (a + b - c) - b = a - c + "punpcklbw %%mm0, %%mm3 \n\t" /* unpack Low bytes of c */ + /* pbv = p - b = (a + b - c) - b = a - c */ "movq %%mm1, %%mm5 \n\t" "psubw %%mm3, %%mm4 \n\t" "pxor %%mm7, %%mm7 \n\t" - // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv + /* pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv */ "movq %%mm4, %%mm6 \n\t" "psubw %%mm3, %%mm5 \n\t" - // pa = abs(p-a) = abs(pav) - // pb = abs(p-b) = abs(pbv) - // pc = abs(p-c) = abs(pcv) - "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0 + /* pa = abs(p-a) = abs(pav) */ + /* pb = abs(p-b) = abs(pbv) */ + /* pc = abs(p-c) = abs(pcv) */ + "pcmpgtw %%mm4, %%mm0 \n\t" /* create mask pav bytes < 0 */ "paddw %%mm5, %%mm6 \n\t" - "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7 - "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0 + "pand %%mm4, %%mm0 \n\t" /* only pav bytes < 0 in mm7 */ + "pcmpgtw %%mm5, %%mm7 \n\t" /* create mask pbv bytes < 0 */ "psubw %%mm0, %%mm4 \n\t" - "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0 + "pand %%mm5, %%mm7 \n\t" /* only pbv bytes < 0 in mm0 */ "psubw %%mm0, %%mm4 \n\t" "psubw %%mm7, %%mm5 \n\t" "pxor %%mm0, %%mm0 \n\t" - "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0 - "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7 + "pcmpgtw %%mm6, %%mm0 \n\t" /* create mask pcv bytes < 0 */ + "pand %%mm6, %%mm0 \n\t" /* only pav bytes < 0 in mm7 */ "psubw %%mm7, %%mm5 \n\t" "psubw %%mm0, %%mm6 \n\t" - // test pa <= pb + /* test pa <= pb */ "movq %%mm4, %%mm7 \n\t" "psubw %%mm0, %%mm6 \n\t" - "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb? + "pcmpgtw %%mm5, %%mm7 \n\t" /* pa > pb? */ "movq %%mm7, %%mm0 \n\t" - // use mm7 mask to merge pa & pb + /* use mm7 mask to merge pa & pb */ "pand %%mm7, %%mm5 \n\t" - // use mm0 mask copy to merge a & b + /* use mm0 mask copy to merge a & b */ "pand %%mm0, %%mm2 \n\t" "pandn %%mm4, %%mm7 \n\t" "pandn %%mm1, %%mm0 \n\t" "paddw %%mm5, %%mm7 \n\t" "paddw %%mm2, %%mm0 \n\t" - // test ((pa <= pb)? pa:pb) <= pc - "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc? + /* test ((pa <= pb)? pa:pb) <= pc */ + "pcmpgtw %%mm6, %%mm7 \n\t" /* pab > pc? */ "pxor %%mm1, %%mm1 \n\t" "pand %%mm7, %%mm3 \n\t" "pandn %%mm0, %%mm7 \n\t" "paddw %%mm3, %%mm7 \n\t" "pxor %%mm0, %%mm0 \n\t" "packuswb %%mm1, %%mm7 \n\t" - "movq -8(%%esi,%%ecx,), %%mm3 \n\t" // read c=Prior(x-bpp) bytes + "movq -8(%%esi,%%ecx,), %%mm3 \n\t" /* read c=Prior(x-bpp) bytes */ "pand _ActiveMask, %%mm7 \n\t" - "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x) - "paddb (%%edi,%%ecx,), %%mm7 \n\t" // add Paeth predictor with Raw(x) - "punpckhbw %%mm0, %%mm3 \n\t" // unpack High bytes of c - "movq %%mm7, (%%edi,%%ecx,) \n\t" // write back updated value - "movq -8(%%edi,%%ecx,), %%mm1 \n\t" // read a=Raw(x-bpp) bytes - - // do second set of 4 bytes - "punpckhbw %%mm0, %%mm2 \n\t" // unpack High bytes of b - "punpckhbw %%mm0, %%mm1 \n\t" // unpack High bytes of a - // pav = p - a = (a + b - c) - a = b - c + "movq (%%esi,%%ecx,), %%mm2 \n\t" /* load b=Prior(x) */ + "paddb (%%edi,%%ecx,), %%mm7 \n\t" /* add Paeth predictor with Raw(x) */ + "punpckhbw %%mm0, %%mm3 \n\t" /* unpack High bytes of c */ + "movq %%mm7, (%%edi,%%ecx,) \n\t" /* write back updated value */ + "movq -8(%%edi,%%ecx,), %%mm1 \n\t" /* read a=Raw(x-bpp) bytes */ + + /* do second set of 4 bytes */ + "punpckhbw %%mm0, %%mm2 \n\t" /* unpack High bytes of b */ + "punpckhbw %%mm0, %%mm1 \n\t" /* unpack High bytes of a */ + /* pav = p - a = (a + b - c) - a = b - c */ "movq %%mm2, %%mm4 \n\t" - // pbv = p - b = (a + b - c) - b = a - c + /* pbv = p - b = (a + b - c) - b = a - c */ "movq %%mm1, %%mm5 \n\t" "psubw %%mm3, %%mm4 \n\t" "pxor %%mm7, %%mm7 \n\t" - // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv + /* pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv */ "movq %%mm4, %%mm6 \n\t" "psubw %%mm3, %%mm5 \n\t" - // pa = abs(p-a) = abs(pav) - // pb = abs(p-b) = abs(pbv) - // pc = abs(p-c) = abs(pcv) - "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0 + /* pa = abs(p-a) = abs(pav) */ + /* pb = abs(p-b) = abs(pbv) */ + /* pc = abs(p-c) = abs(pcv) */ + "pcmpgtw %%mm4, %%mm0 \n\t" /* create mask pav bytes < 0 */ "paddw %%mm5, %%mm6 \n\t" - "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7 - "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0 + "pand %%mm4, %%mm0 \n\t" /* only pav bytes < 0 in mm7 */ + "pcmpgtw %%mm5, %%mm7 \n\t" /* create mask pbv bytes < 0 */ "psubw %%mm0, %%mm4 \n\t" - "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0 + "pand %%mm5, %%mm7 \n\t" /* only pbv bytes < 0 in mm0 */ "psubw %%mm0, %%mm4 \n\t" "psubw %%mm7, %%mm5 \n\t" "pxor %%mm0, %%mm0 \n\t" - "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0 - "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7 + "pcmpgtw %%mm6, %%mm0 \n\t" /* create mask pcv bytes < 0 */ + "pand %%mm6, %%mm0 \n\t" /* only pav bytes < 0 in mm7 */ "psubw %%mm7, %%mm5 \n\t" "psubw %%mm0, %%mm6 \n\t" - // test pa <= pb + /* test pa <= pb */ "movq %%mm4, %%mm7 \n\t" "psubw %%mm0, %%mm6 \n\t" - "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb? + "pcmpgtw %%mm5, %%mm7 \n\t" /* pa > pb? */ "movq %%mm7, %%mm0 \n\t" - // use mm7 mask to merge pa & pb + /* use mm7 mask to merge pa & pb */ "pand %%mm7, %%mm5 \n\t" - // use mm0 mask copy to merge a & b + /* use mm0 mask copy to merge a & b */ "pand %%mm0, %%mm2 \n\t" "pandn %%mm4, %%mm7 \n\t" "pandn %%mm1, %%mm0 \n\t" "paddw %%mm5, %%mm7 \n\t" "paddw %%mm2, %%mm0 \n\t" - // test ((pa <= pb)? pa:pb) <= pc - "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc? + /* test ((pa <= pb)? pa:pb) <= pc */ + "pcmpgtw %%mm6, %%mm7 \n\t" /* pab > pc? */ "pxor %%mm1, %%mm1 \n\t" "pand %%mm7, %%mm3 \n\t" "pandn %%mm0, %%mm7 \n\t" "pxor %%mm1, %%mm1 \n\t" "paddw %%mm3, %%mm7 \n\t" "pxor %%mm0, %%mm0 \n\t" - // step ecx to next set of 8 bytes and repeat loop til done + /* step ecx to next set of 8 bytes and repeat loop til done */ "addl $8, %%ecx \n\t" "packuswb %%mm7, %%mm1 \n\t" - "paddb -8(%%edi,%%ecx,), %%mm1 \n\t" // add Paeth predictor with Raw(x) + "paddb -8(%%edi,%%ecx,), %%mm1 \n\t" /* add Paeth predictor with Raw(x) */ "cmpl _MMXLength, %%ecx \n\t" - "movq %%mm1, -8(%%edi,%%ecx,) \n\t" // write back updated value - // mm1 will be used as Raw(x-bpp) next loop + "movq %%mm1, -8(%%edi,%%ecx,) \n\t" /* write back updated value */ + /* mm1 will be used as Raw(x-bpp) next loop */ "jb paeth_8lp \n\t" - : "=S" (dummy_value_S), // output regs (dummy) + : "=S" (dummy_value_S), /* output regs (dummy) */ "=D" (dummy_value_D) - : "0" (prev_row), // esi // input regs - "1" (row) // edi + : "0" (prev_row), /* esi // input regs */ + "1" (row) /* edi */ - : "%ecx" // clobber list + : "%ecx" /* clobber list */ #if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */ , "%mm0", "%mm1", "%mm2", "%mm3" , "%mm4", "%mm5", "%mm6", "%mm7" #endif ); } - break; // end 8 bpp + break; /* end 8 bpp */ - case 1: // bpp = 1 - case 2: // bpp = 2 - default: // bpp > 8 + case 1: /* bpp = 1 */ + case 2: /* bpp = 2 */ + default: /* bpp > 8 */ { __asm__ __volatile__ ( #ifdef __PIC__ - "pushl %%ebx \n\t" // save Global Offset Table index + "pushl %%ebx \n\t" /* save Global Offset Table index */ #endif "movl _dif, %%ebx \n\t" "cmpl _FullLength, %%ebx \n\t" "jnb paeth_dend \n\t" -// preload "movl row, %%edi \n\t" -// preload "movl prev_row, %%esi \n\t" - // do Paeth decode for remaining bytes +/* preload "movl row, %%edi \n\t" */ +/* preload "movl prev_row, %%esi \n\t" */ + /* do Paeth decode for remaining bytes */ "movl %%ebx, %%edx \n\t" -// preload "subl bpp, %%edx \n\t" // (bpp is preloaded into ecx) - "subl %%ecx, %%edx \n\t" // edx = ebx - bpp - "xorl %%ecx, %%ecx \n\t" // zero ecx before using cl & cx +/* preload "subl bpp, %%edx \n\t" // (bpp is preloaded into ecx) */ + "subl %%ecx, %%edx \n\t" /* edx = ebx - bpp */ + "xorl %%ecx, %%ecx \n\t" /* zero ecx before using cl & cx */ "paeth_dlp: \n\t" "xorl %%eax, %%eax \n\t" - // pav = p - a = (a + b - c) - a = b - c - "movb (%%esi,%%ebx,), %%al \n\t" // load Prior(x) into al - "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl - "subl %%ecx, %%eax \n\t" // subtract Prior(x-bpp) - "movl %%eax, _patemp \n\t" // Save pav for later use + /* pav = p - a = (a + b - c) - a = b - c */ + "movb (%%esi,%%ebx,), %%al \n\t" /* load Prior(x) into al */ + "movb (%%esi,%%edx,), %%cl \n\t" /* load Prior(x-bpp) into cl */ + "subl %%ecx, %%eax \n\t" /* subtract Prior(x-bpp) */ + "movl %%eax, _patemp \n\t" /* Save pav for later use */ "xorl %%eax, %%eax \n\t" - // pbv = p - b = (a + b - c) - b = a - c - "movb (%%edi,%%edx,), %%al \n\t" // load Raw(x-bpp) into al - "subl %%ecx, %%eax \n\t" // subtract Prior(x-bpp) + /* pbv = p - b = (a + b - c) - b = a - c */ + "movb (%%edi,%%edx,), %%al \n\t" /* load Raw(x-bpp) into al */ + "subl %%ecx, %%eax \n\t" /* subtract Prior(x-bpp) */ "movl %%eax, %%ecx \n\t" - // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv - "addl _patemp, %%eax \n\t" // pcv = pav + pbv - // pc = abs(pcv) + /* pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv */ + "addl _patemp, %%eax \n\t" /* pcv = pav + pbv */ + /* pc = abs(pcv) */ "testl $0x80000000, %%eax \n\t" "jz paeth_dpca \n\t" - "negl %%eax \n\t" // reverse sign of neg values + "negl %%eax \n\t" /* reverse sign of neg values */ "paeth_dpca: \n\t" - "movl %%eax, _pctemp \n\t" // save pc for later use - // pb = abs(pbv) + "movl %%eax, _pctemp \n\t" /* save pc for later use */ + /* pb = abs(pbv) */ "testl $0x80000000, %%ecx \n\t" "jz paeth_dpba \n\t" - "negl %%ecx \n\t" // reverse sign of neg values + "negl %%ecx \n\t" /* reverse sign of neg values */ "paeth_dpba: \n\t" - "movl %%ecx, _pbtemp \n\t" // save pb for later use - // pa = abs(pav) + "movl %%ecx, _pbtemp \n\t" /* save pb for later use */ + /* pa = abs(pav) */ "movl _patemp, %%eax \n\t" "testl $0x80000000, %%eax \n\t" "jz paeth_dpaa \n\t" - "negl %%eax \n\t" // reverse sign of neg values + "negl %%eax \n\t" /* reverse sign of neg values */ "paeth_dpaa: \n\t" - "movl %%eax, _patemp \n\t" // save pa for later use - // test if pa <= pb + "movl %%eax, _patemp \n\t" /* save pa for later use */ + /* test if pa <= pb */ "cmpl %%ecx, %%eax \n\t" "jna paeth_dabb \n\t" - // pa > pb; now test if pb <= pc + /* pa > pb; now test if pb <= pc */ "cmpl _pctemp, %%ecx \n\t" "jna paeth_dbbc \n\t" - // pb > pc; Raw(x) = Paeth(x) + Prior(x-bpp) - "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl + /* pb > pc; Raw(x) = Paeth(x) + Prior(x-bpp) */ + "movb (%%esi,%%edx,), %%cl \n\t" /* load Prior(x-bpp) into cl */ "jmp paeth_dpaeth \n\t" "paeth_dbbc: \n\t" - // pb <= pc; Raw(x) = Paeth(x) + Prior(x) - "movb (%%esi,%%ebx,), %%cl \n\t" // load Prior(x) into cl + /* pb <= pc; Raw(x) = Paeth(x) + Prior(x) */ + "movb (%%esi,%%ebx,), %%cl \n\t" /* load Prior(x) into cl */ "jmp paeth_dpaeth \n\t" "paeth_dabb: \n\t" - // pa <= pb; now test if pa <= pc + /* pa <= pb; now test if pa <= pc */ "cmpl _pctemp, %%eax \n\t" "jna paeth_dabc \n\t" - // pa > pc; Raw(x) = Paeth(x) + Prior(x-bpp) - "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl + /* pa > pc; Raw(x) = Paeth(x) + Prior(x-bpp) */ + "movb (%%esi,%%edx,), %%cl \n\t" /* load Prior(x-bpp) into cl */ "jmp paeth_dpaeth \n\t" "paeth_dabc: \n\t" - // pa <= pc; Raw(x) = Paeth(x) + Raw(x-bpp) - "movb (%%edi,%%edx,), %%cl \n\t" // load Raw(x-bpp) into cl + /* pa <= pc; Raw(x) = Paeth(x) + Raw(x-bpp) */ + "movb (%%edi,%%edx,), %%cl \n\t" /* load Raw(x-bpp) into cl */ "paeth_dpaeth: \n\t" "incl %%ebx \n\t" "incl %%edx \n\t" - // Raw(x) = (Paeth(x) + Paeth_Predictor( a, b, c )) mod 256 + /* Raw(x) = (Paeth(x) + Paeth_Predictor( a, b, c )) mod 256 */ "addb %%cl, -1(%%edi,%%ebx,) \n\t" "cmpl _FullLength, %%ebx \n\t" "jb paeth_dlp \n\t" "paeth_dend: \n\t" #ifdef __PIC__ - "popl %%ebx \n\t" // index to Global Offset Table + "popl %%ebx \n\t" /* index to Global Offset Table */ #endif - : "=c" (dummy_value_c), // output regs (dummy) + : "=c" (dummy_value_c), /* output regs (dummy) */ "=S" (dummy_value_S), "=D" (dummy_value_D) - : "0" (bpp), // ecx // input regs - "1" (prev_row), // esi - "2" (row) // edi + : "0" (bpp), /* ecx // input regs */ + "1" (prev_row), /* esi */ + "2" (row) /* edi */ - : "%eax", "%edx" // clobber list + : "%eax", "%edx" /* clobber list */ #ifndef __PIC__ , "%ebx" #endif ); } - return; // No need to go further with this one + return; /* No need to go further with this one */ - } // end switch (bpp) + } /* end switch (bpp) */ __asm__ __volatile__ ( - // MMX acceleration complete; now do clean-up - // check if any remaining bytes left to decode + /* MMX acceleration complete; now do clean-up */ + /* check if any remaining bytes left to decode */ #ifdef __PIC__ - "pushl %%ebx \n\t" // save index to Global Offset Table + "pushl %%ebx \n\t" /* save index to Global Offset Table */ #endif "movl _MMXLength, %%ebx \n\t" "cmpl _FullLength, %%ebx \n\t" "jnb paeth_end \n\t" -//pre "movl row, %%edi \n\t" -//pre "movl prev_row, %%esi \n\t" - // do Paeth decode for remaining bytes +/*pre "movl row, %%edi \n\t" */ +/*pre "movl prev_row, %%esi \n\t" */ + /* do Paeth decode for remaining bytes */ "movl %%ebx, %%edx \n\t" -//pre "subl bpp, %%edx \n\t" // (bpp is preloaded into ecx) - "subl %%ecx, %%edx \n\t" // edx = ebx - bpp - "xorl %%ecx, %%ecx \n\t" // zero ecx before using cl & cx below +/*pre "subl bpp, %%edx \n\t" */ /* (bpp is preloaded into ecx) */ + "subl %%ecx, %%edx \n\t" /* edx = ebx - bpp */ + "xorl %%ecx, %%ecx \n\t" /* zero ecx before using cl & cx below */ "paeth_lp2: \n\t" "xorl %%eax, %%eax \n\t" - // pav = p - a = (a + b - c) - a = b - c - "movb (%%esi,%%ebx,), %%al \n\t" // load Prior(x) into al - "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl - "subl %%ecx, %%eax \n\t" // subtract Prior(x-bpp) - "movl %%eax, _patemp \n\t" // Save pav for later use + /* pav = p - a = (a + b - c) - a = b - c */ + "movb (%%esi,%%ebx,), %%al \n\t" /* load Prior(x) into al */ + "movb (%%esi,%%edx,), %%cl \n\t" /* load Prior(x-bpp) into cl */ + "subl %%ecx, %%eax \n\t" /* subtract Prior(x-bpp) */ + "movl %%eax, _patemp \n\t" /* Save pav for later use */ "xorl %%eax, %%eax \n\t" - // pbv = p - b = (a + b - c) - b = a - c - "movb (%%edi,%%edx,), %%al \n\t" // load Raw(x-bpp) into al - "subl %%ecx, %%eax \n\t" // subtract Prior(x-bpp) + /* pbv = p - b = (a + b - c) - b = a - c */ + "movb (%%edi,%%edx,), %%al \n\t" /* load Raw(x-bpp) into al */ + "subl %%ecx, %%eax \n\t" /* subtract Prior(x-bpp) */ "movl %%eax, %%ecx \n\t" - // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv - "addl _patemp, %%eax \n\t" // pcv = pav + pbv - // pc = abs(pcv) + /* pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv */ + "addl _patemp, %%eax \n\t" /* pcv = pav + pbv */ + /* pc = abs(pcv) */ "testl $0x80000000, %%eax \n\t" "jz paeth_pca2 \n\t" - "negl %%eax \n\t" // reverse sign of neg values + "negl %%eax \n\t" /* reverse sign of neg values */ "paeth_pca2: \n\t" - "movl %%eax, _pctemp \n\t" // save pc for later use - // pb = abs(pbv) + "movl %%eax, _pctemp \n\t" /* save pc for later use */ + /* pb = abs(pbv) */ "testl $0x80000000, %%ecx \n\t" "jz paeth_pba2 \n\t" - "negl %%ecx \n\t" // reverse sign of neg values + "negl %%ecx \n\t" /* reverse sign of neg values */ "paeth_pba2: \n\t" - "movl %%ecx, _pbtemp \n\t" // save pb for later use - // pa = abs(pav) + "movl %%ecx, _pbtemp \n\t" /* save pb for later use */ + /* pa = abs(pav) */ "movl _patemp, %%eax \n\t" "testl $0x80000000, %%eax \n\t" "jz paeth_paa2 \n\t" - "negl %%eax \n\t" // reverse sign of neg values + "negl %%eax \n\t" /* reverse sign of neg values */ "paeth_paa2: \n\t" - "movl %%eax, _patemp \n\t" // save pa for later use - // test if pa <= pb + "movl %%eax, _patemp \n\t" /* save pa for later use */ + /* test if pa <= pb */ "cmpl %%ecx, %%eax \n\t" "jna paeth_abb2 \n\t" - // pa > pb; now test if pb <= pc + /* pa > pb; now test if pb <= pc */ "cmpl _pctemp, %%ecx \n\t" "jna paeth_bbc2 \n\t" - // pb > pc; Raw(x) = Paeth(x) + Prior(x-bpp) - "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl + /* pb > pc; Raw(x) = Paeth(x) + Prior(x-bpp) */ + "movb (%%esi,%%edx,), %%cl \n\t" /* load Prior(x-bpp) into cl */ "jmp paeth_paeth2 \n\t" "paeth_bbc2: \n\t" - // pb <= pc; Raw(x) = Paeth(x) + Prior(x) - "movb (%%esi,%%ebx,), %%cl \n\t" // load Prior(x) into cl + /* pb <= pc; Raw(x) = Paeth(x) + Prior(x) */ + "movb (%%esi,%%ebx,), %%cl \n\t" /* load Prior(x) into cl */ "jmp paeth_paeth2 \n\t" "paeth_abb2: \n\t" - // pa <= pb; now test if pa <= pc + /* pa <= pb; now test if pa <= pc */ "cmpl _pctemp, %%eax \n\t" "jna paeth_abc2 \n\t" - // pa > pc; Raw(x) = Paeth(x) + Prior(x-bpp) - "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl + /* pa > pc; Raw(x) = Paeth(x) + Prior(x-bpp) */ + "movb (%%esi,%%edx,), %%cl \n\t" /* load Prior(x-bpp) into cl */ "jmp paeth_paeth2 \n\t" "paeth_abc2: \n\t" - // pa <= pc; Raw(x) = Paeth(x) + Raw(x-bpp) - "movb (%%edi,%%edx,), %%cl \n\t" // load Raw(x-bpp) into cl + /* pa <= pc; Raw(x) = Paeth(x) + Raw(x-bpp) */ + "movb (%%edi,%%edx,), %%cl \n\t" /* load Raw(x-bpp) into cl */ "paeth_paeth2: \n\t" "incl %%ebx \n\t" "incl %%edx \n\t" - // Raw(x) = (Paeth(x) + Paeth_Predictor( a, b, c )) mod 256 + /* Raw(x) = (Paeth(x) + Paeth_Predictor( a, b, c )) mod 256 */ "addb %%cl, -1(%%edi,%%ebx,) \n\t" "cmpl _FullLength, %%ebx \n\t" "jb paeth_lp2 \n\t" "paeth_end: \n\t" - "EMMS \n\t" // end MMX; prep for poss. FP instrs. + "EMMS \n\t" /* end MMX; prep for poss. FP instrs. */ #ifdef __PIC__ - "popl %%ebx \n\t" // restore index to Global Offset Table + "popl %%ebx \n\t" /* restore index to Global Offset Table */ #endif - : "=c" (dummy_value_c), // output regs (dummy) + : "=c" (dummy_value_c), /* output regs (dummy) */ "=S" (dummy_value_S), "=D" (dummy_value_D) - : "0" (bpp), // ecx // input regs - "1" (prev_row), // esi - "2" (row) // edi + : "0" (bpp), /* ecx // input regs */ + "1" (prev_row), /* esi */ + "2" (row) /* edi */ - : "%eax", "%edx" // clobber list (no input regs!) + : "%eax", "%edx" /* clobber list (no input regs!) */ #ifndef __PIC__ , "%ebx" #endif @@ -4475,13 +4484,13 @@ png_read_filter_row_mmx_paeth(png_row_infop row_info, png_bytep row, #ifdef PNG_THREAD_UNSAFE_OK -//===========================================================================// -// // -// P N G _ R E A D _ F I L T E R _ R O W _ M M X _ S U B // -// // -//===========================================================================// +/*===========================================================================*/ +/* */ +/* P N G _ R E A D _ F I L T E R _ R O W _ M M X _ S U B */ +/* */ +/*===========================================================================*/ -// Optimized code for PNG Sub filter decoder +/* Optimized code for PNG Sub filter decoder */ static void /* PRIVATE */ png_read_filter_row_mmx_sub(png_row_infop row_info, png_bytep row) @@ -4490,25 +4499,25 @@ png_read_filter_row_mmx_sub(png_row_infop row_info, png_bytep row) int dummy_value_a; int dummy_value_D; - bpp = (row_info->pixel_depth + 7) >> 3; // calc number of bytes per pixel - _FullLength = row_info->rowbytes - bpp; // number of bytes to filter + bpp = (row_info->pixel_depth + 7) >> 3; /* calc number of bytes per pixel */ + _FullLength = row_info->rowbytes - bpp; /* number of bytes to filter */ __asm__ __volatile__ ( -//pre "movl row, %%edi \n\t" - "movl %%edi, %%esi \n\t" // lp = row -//pre "movl bpp, %%eax \n\t" - "addl %%eax, %%edi \n\t" // rp = row + bpp -//irr "xorl %%eax, %%eax \n\t" - // get # of bytes to alignment - "movl %%edi, _dif \n\t" // take start of row - "addl $0xf, _dif \n\t" // add 7 + 8 to incr past - // alignment boundary +/*pre "movl row, %%edi \n\t" */ + "movl %%edi, %%esi \n\t" /* lp = row */ +/*pre "movl bpp, %%eax \n\t" */ + "addl %%eax, %%edi \n\t" /* rp = row + bpp */ +/*irr "xorl %%eax, %%eax \n\t" */ + /* get # of bytes to alignment */ + "movl %%edi, _dif \n\t" /* take start of row */ + "addl $0xf, _dif \n\t" /* add 7 + 8 to incr past */ + /* alignment boundary */ "xorl %%ecx, %%ecx \n\t" - "andl $0xfffffff8, _dif \n\t" // mask to alignment boundary - "subl %%edi, _dif \n\t" // subtract from start ==> value - "jz sub_go \n\t" // ecx at alignment + "andl $0xfffffff8, _dif \n\t" /* mask to alignment boundary */ + "subl %%edi, _dif \n\t" /* subtract from start ==> value */ + "jz sub_go \n\t" /* ecx at alignment */ - "sub_lp1: \n\t" // fix alignment + "sub_lp1: \n\t" /* fix alignment */ "movb (%%esi,%%ecx,), %%al \n\t" "addb %%al, (%%edi,%%ecx,) \n\t" "incl %%ecx \n\t" @@ -4518,19 +4527,18 @@ png_read_filter_row_mmx_sub(png_row_infop row_info, png_bytep row) "sub_go: \n\t" "movl _FullLength, %%eax \n\t" "movl %%eax, %%edx \n\t" - "subl %%ecx, %%edx \n\t" // subtract alignment fix - "andl $0x00000007, %%edx \n\t" // calc bytes over mult of 8 - "subl %%edx, %%eax \n\t" // drop over bytes from length + "subl %%ecx, %%edx \n\t" /* subtract alignment fix */ + "andl $0x00000007, %%edx \n\t" /* calc bytes over mult of 8 */ + "subl %%edx, %%eax \n\t" /* drop over bytes from length */ "movl %%eax, _MMXLength \n\t" - : "=a" (dummy_value_a), // 0 // output regs (dummy) - "=D" (dummy_value_D) // 1 + : "=a" (dummy_value_a), /* 0 // output regs (dummy) */ + "=D" (dummy_value_D) /* 1 */ - : "0" (bpp), // eax // input regs - "1" (row) // edi + : "0" (bpp), /* eax // input regs */ + "1" (row) /* edi */ - : "%ebx", "%ecx", "%edx" // clobber list - , "%esi" + : "%esi", "%ecx", "%edx" // clobber list #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ , "%mm0", "%mm1", "%mm2", "%mm3" @@ -4538,61 +4546,61 @@ png_read_filter_row_mmx_sub(png_row_infop row_info, png_bytep row) #endif ); - // now do the math for the rest of the row + /* now do the math for the rest of the row */ switch (bpp) { case 3: { _ActiveMask.use = 0x0000ffffff000000LL; - _ShiftBpp.use = 24; // == 3 * 8 - _ShiftRem.use = 40; // == 64 - 24 + _ShiftBpp.use = 24; /* == 3 * 8 */ + _ShiftRem.use = 40; /* == 64 - 24 */ __asm__ __volatile__ ( -// preload "movl row, %%edi \n\t" - "movq _ActiveMask, %%mm7 \n\t" // load _ActiveMask for 2nd - // active byte group - "movl %%edi, %%esi \n\t" // lp = row -// preload "movl bpp, %%eax \n\t" - "addl %%eax, %%edi \n\t" // rp = row + bpp +/* preload "movl row, %%edi \n\t" */ + "movq _ActiveMask, %%mm7 \n\t" /* load _ActiveMask for 2nd */ + /* active byte group */ + "movl %%edi, %%esi \n\t" /* lp = row */ +/* preload "movl bpp, %%eax \n\t" */ + "addl %%eax, %%edi \n\t" /* rp = row + bpp */ "movq %%mm7, %%mm6 \n\t" "movl _dif, %%edx \n\t" - "psllq _ShiftBpp, %%mm6 \n\t" // move mask in mm6 to cover - // 3rd active byte group - // prime the pump: load the first Raw(x-bpp) data set + "psllq _ShiftBpp, %%mm6 \n\t" /* move mask in mm6 to cover */ + /* 3rd active byte group */ + /* prime the pump: load the first Raw(x-bpp) data set */ "movq -8(%%edi,%%edx,), %%mm1 \n\t" - "sub_3lp: \n\t" // shift data for adding first - "psrlq _ShiftRem, %%mm1 \n\t" // bpp bytes (no need for mask; - // shift clears inactive bytes) - // add 1st active group + "sub_3lp: \n\t" /* shift data for adding first */ + "psrlq _ShiftRem, %%mm1 \n\t" /* bpp bytes (no need for mask; */ + /* shift clears inactive bytes) */ + /* add 1st active group */ "movq (%%edi,%%edx,), %%mm0 \n\t" "paddb %%mm1, %%mm0 \n\t" - // add 2nd active group - "movq %%mm0, %%mm1 \n\t" // mov updated Raws to mm1 - "psllq _ShiftBpp, %%mm1 \n\t" // shift data to pos. correctly - "pand %%mm7, %%mm1 \n\t" // mask to use 2nd active group + /* add 2nd active group */ + "movq %%mm0, %%mm1 \n\t" /* mov updated Raws to mm1 */ + "psllq _ShiftBpp, %%mm1 \n\t" /* shift data to pos. correctly */ + "pand %%mm7, %%mm1 \n\t" /* mask to use 2nd active group */ "paddb %%mm1, %%mm0 \n\t" - // add 3rd active group - "movq %%mm0, %%mm1 \n\t" // mov updated Raws to mm1 - "psllq _ShiftBpp, %%mm1 \n\t" // shift data to pos. correctly - "pand %%mm6, %%mm1 \n\t" // mask to use 3rd active group + /* add 3rd active group */ + "movq %%mm0, %%mm1 \n\t" /* mov updated Raws to mm1 */ + "psllq _ShiftBpp, %%mm1 \n\t" /* shift data to pos. correctly */ + "pand %%mm6, %%mm1 \n\t" /* mask to use 3rd active group */ "addl $8, %%edx \n\t" "paddb %%mm1, %%mm0 \n\t" "cmpl _MMXLength, %%edx \n\t" - "movq %%mm0, -8(%%edi,%%edx,) \n\t" // write updated Raws to array - "movq %%mm0, %%mm1 \n\t" // prep 1st add at top of loop + "movq %%mm0, -8(%%edi,%%edx,) \n\t" /* write updated Raws to array */ + "movq %%mm0, %%mm1 \n\t" /* prep 1st add at top of loop */ "jb sub_3lp \n\t" - : "=a" (dummy_value_a), // 0 // output regs (dummy) - "=D" (dummy_value_D) // 1 + : "=a" (dummy_value_a), /* 0 // output regs (dummy) */ + "=D" (dummy_value_D) /* 1 */ - : "0" (bpp), // eax // input regs - "1" (row) // edi + : "0" (bpp), /* eax // input regs */ + "1" (row) /* edi */ - : "%edx", "%esi" // clobber list + : "%edx", "%esi" /* clobber list */ #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ , "%mm0", "%mm1", "%mm6", "%mm7" #endif @@ -4604,13 +4612,13 @@ png_read_filter_row_mmx_sub(png_row_infop row_info, png_bytep row) { __asm__ __volatile__ ( "movl _dif, %%edx \n\t" -// preload "movl row, %%edi \n\t" +/* preload "movl row, %%edi \n\t" */ "cmpl _FullLength, %%edx \n\t" "jnb sub_1end \n\t" - "movl %%edi, %%esi \n\t" // lp = row + "movl %%edi, %%esi \n\t" /* lp = row */ "xorl %%eax, %%eax \n\t" -// preload "movl bpp, %%eax \n\t" - "addl %%eax, %%edi \n\t" // rp = row + bpp +/* preload "movl bpp, %%eax \n\t" */ + "addl %%eax, %%edi \n\t" /* rp = row + bpp */ "sub_1lp: \n\t" "movb (%%esi,%%edx,), %%al \n\t" @@ -4621,59 +4629,59 @@ png_read_filter_row_mmx_sub(png_row_infop row_info, png_bytep row) "sub_1end: \n\t" - : "=a" (dummy_value_a), // 0 // output regs (dummy) - "=D" (dummy_value_D) // 1 + : "=a" (dummy_value_a), /* 0 // output regs (dummy) */ + "=D" (dummy_value_D) /* 1 */ - : "0" (bpp), // eax // input regs - "1" (row) // edi + : "0" (bpp), /* eax // input regs */ + "1" (row) /* edi */ - : "%edx", "%esi" // clobber list + : "%edx", "%esi" /* clobber list */ ); } return; case 6: case 4: - //case 7: // GRR BOGUS - //case 5: // GRR BOGUS + //case 7: /* GRR BOGUS */ + //case 5: /* GRR BOGUS */ { _ShiftBpp.use = bpp << 3; _ShiftRem.use = 64 - _ShiftBpp.use; __asm__ __volatile__ ( -// preload "movl row, %%edi \n\t" +/* preload "movl row, %%edi \n\t" */ "movl _dif, %%edx \n\t" - "movl %%edi, %%esi \n\t" // lp = row -// preload "movl bpp, %%eax \n\t" - "addl %%eax, %%edi \n\t" // rp = row + bpp + "movl %%edi, %%esi \n\t" /* lp = row */ +/* preload "movl bpp, %%eax \n\t" */ + "addl %%eax, %%edi \n\t" /* rp = row + bpp */ - // prime the pump: load the first Raw(x-bpp) data set + /* prime the pump: load the first Raw(x-bpp) data set */ "movq -8(%%edi,%%edx,), %%mm1 \n\t" - "sub_4lp: \n\t" // shift data for adding first - "psrlq _ShiftRem, %%mm1 \n\t" // bpp bytes (no need for mask; - // shift clears inactive bytes) + "sub_4lp: \n\t" /* shift data for adding first */ + "psrlq _ShiftRem, %%mm1 \n\t" /* bpp bytes (no need for mask; */ + /* shift clears inactive bytes) */ "movq (%%edi,%%edx,), %%mm0 \n\t" "paddb %%mm1, %%mm0 \n\t" - // add 2nd active group - "movq %%mm0, %%mm1 \n\t" // mov updated Raws to mm1 - "psllq _ShiftBpp, %%mm1 \n\t" // shift data to pos. correctly + /* add 2nd active group */ + "movq %%mm0, %%mm1 \n\t" /* mov updated Raws to mm1 */ + "psllq _ShiftBpp, %%mm1 \n\t" /* shift data to pos. correctly */ "addl $8, %%edx \n\t" "paddb %%mm1, %%mm0 \n\t" "cmpl _MMXLength, %%edx \n\t" "movq %%mm0, -8(%%edi,%%edx,) \n\t" - "movq %%mm0, %%mm1 \n\t" // prep 1st add at top of loop + "movq %%mm0, %%mm1 \n\t" /* prep 1st add at top of loop */ "jb sub_4lp \n\t" - : "=a" (dummy_value_a), // 0 // output regs (dummy) - "=D" (dummy_value_D) // 1 + : "=a" (dummy_value_a), /* 0 // output regs (dummy) */ + "=D" (dummy_value_D) /* 1 */ - : "0" (bpp), // eax // input regs - "1" (row) // edi + : "0" (bpp), /* eax // input regs */ + "1" (row) /* edi */ - : "%edx", "%esi" // clobber list + : "%edx", "%esi" /* clobber list */ #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ , "%mm0", "%mm1" #endif @@ -4684,63 +4692,63 @@ png_read_filter_row_mmx_sub(png_row_infop row_info, png_bytep row) case 2: { _ActiveMask.use = 0x00000000ffff0000LL; - _ShiftBpp.use = 16; // == 2 * 8 - _ShiftRem.use = 48; // == 64 - 16 + _ShiftBpp.use = 16; /* == 2 * 8 */ + _ShiftRem.use = 48; /* == 64 - 16 */ __asm__ __volatile__ ( - "movq _ActiveMask, %%mm7 \n\t" // load _ActiveMask for 2nd - // active byte group + "movq _ActiveMask, %%mm7 \n\t" /* load _ActiveMask for 2nd */ + /* active byte group */ "movl _dif, %%edx \n\t" "movq %%mm7, %%mm6 \n\t" -// preload "movl row, %%edi \n\t" - "psllq _ShiftBpp, %%mm6 \n\t" // move mask in mm6 to cover - // 3rd active byte group - "movl %%edi, %%esi \n\t" // lp = row +/* preload "movl row, %%edi \n\t" */ + "psllq _ShiftBpp, %%mm6 \n\t" /* move mask in mm6 to cover */ + /* 3rd active byte group */ + "movl %%edi, %%esi \n\t" /* lp = row */ "movq %%mm6, %%mm5 \n\t" -// preload "movl bpp, %%eax \n\t" - "addl %%eax, %%edi \n\t" // rp = row + bpp - "psllq _ShiftBpp, %%mm5 \n\t" // move mask in mm5 to cover - // 4th active byte group - // prime the pump: load the first Raw(x-bpp) data set +/* preload "movl bpp, %%eax \n\t" */ + "addl %%eax, %%edi \n\t" /* rp = row + bpp */ + "psllq _ShiftBpp, %%mm5 \n\t" /* move mask in mm5 to cover */ + /* 4th active byte group */ + /* prime the pump: load the first Raw(x-bpp) data set */ "movq -8(%%edi,%%edx,), %%mm1 \n\t" - "sub_2lp: \n\t" // shift data for adding first - "psrlq _ShiftRem, %%mm1 \n\t" // bpp bytes (no need for mask; - // shift clears inactive bytes) - // add 1st active group + "sub_2lp: \n\t" /* shift data for adding first */ + "psrlq _ShiftRem, %%mm1 \n\t" /* bpp bytes (no need for mask; */ + /* shift clears inactive bytes) */ + /* add 1st active group */ "movq (%%edi,%%edx,), %%mm0 \n\t" "paddb %%mm1, %%mm0 \n\t" - // add 2nd active group - "movq %%mm0, %%mm1 \n\t" // mov updated Raws to mm1 - "psllq _ShiftBpp, %%mm1 \n\t" // shift data to pos. correctly - "pand %%mm7, %%mm1 \n\t" // mask to use 2nd active group + /* add 2nd active group */ + "movq %%mm0, %%mm1 \n\t" /* mov updated Raws to mm1 */ + "psllq _ShiftBpp, %%mm1 \n\t" /* shift data to pos. correctly */ + "pand %%mm7, %%mm1 \n\t" /* mask to use 2nd active group */ "paddb %%mm1, %%mm0 \n\t" - // add 3rd active group - "movq %%mm0, %%mm1 \n\t" // mov updated Raws to mm1 - "psllq _ShiftBpp, %%mm1 \n\t" // shift data to pos. correctly - "pand %%mm6, %%mm1 \n\t" // mask to use 3rd active group + /* add 3rd active group */ + "movq %%mm0, %%mm1 \n\t" /* mov updated Raws to mm1 */ + "psllq _ShiftBpp, %%mm1 \n\t" /* shift data to pos. correctly */ + "pand %%mm6, %%mm1 \n\t" /* mask to use 3rd active group */ "paddb %%mm1, %%mm0 \n\t" - // add 4th active group - "movq %%mm0, %%mm1 \n\t" // mov updated Raws to mm1 - "psllq _ShiftBpp, %%mm1 \n\t" // shift data to pos. correctly - "pand %%mm5, %%mm1 \n\t" // mask to use 4th active group + /* add 4th active group */ + "movq %%mm0, %%mm1 \n\t" /* mov updated Raws to mm1 */ + "psllq _ShiftBpp, %%mm1 \n\t" /* shift data to pos. correctly */ + "pand %%mm5, %%mm1 \n\t" /* mask to use 4th active group */ "addl $8, %%edx \n\t" "paddb %%mm1, %%mm0 \n\t" "cmpl _MMXLength, %%edx \n\t" - "movq %%mm0, -8(%%edi,%%edx,) \n\t" // write updated Raws to array - "movq %%mm0, %%mm1 \n\t" // prep 1st add at top of loop + "movq %%mm0, -8(%%edi,%%edx,) \n\t" /* write updated Raws to array */ + "movq %%mm0, %%mm1 \n\t" /* prep 1st add at top of loop */ "jb sub_2lp \n\t" - : "=a" (dummy_value_a), // 0 // output regs (dummy) - "=D" (dummy_value_D) // 1 + : "=a" (dummy_value_a), /* 0 // output regs (dummy) */ + "=D" (dummy_value_D) /* 1 */ - : "0" (bpp), // eax // input regs - "1" (row) // edi + : "0" (bpp), /* eax // input regs */ + "1" (row) /* edi */ - : "%edx", "%esi" // clobber list + : "%edx", "%esi" /* clobber list */ #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ , "%mm0", "%mm1", "%mm5", "%mm6", "%mm7" #endif @@ -4751,50 +4759,50 @@ png_read_filter_row_mmx_sub(png_row_infop row_info, png_bytep row) case 8: { __asm__ __volatile__ ( -// preload "movl row, %%edi \n\t" +/* preload "movl row, %%edi \n\t" */ "movl _dif, %%edx \n\t" - "movl %%edi, %%esi \n\t" // lp = row -// preload "movl bpp, %%eax \n\t" - "addl %%eax, %%edi \n\t" // rp = row + bpp + "movl %%edi, %%esi \n\t" /* lp = row */ +/* preload "movl bpp, %%eax \n\t" */ + "addl %%eax, %%edi \n\t" /* rp = row + bpp */ "movl _MMXLength, %%ecx \n\t" - // prime the pump: load the first Raw(x-bpp) data set + /* prime the pump: load the first Raw(x-bpp) data set */ "movq -8(%%edi,%%edx,), %%mm7 \n\t" - "andl $0x0000003f, %%ecx \n\t" // calc bytes over mult of 64 + "andl $0x0000003f, %%ecx \n\t" /* calc bytes over mult of 64 */ "sub_8lp: \n\t" - "movq (%%edi,%%edx,), %%mm0 \n\t" // load Sub(x) for 1st 8 bytes + "movq (%%edi,%%edx,), %%mm0 \n\t" /* load Sub(x) for 1st 8 bytes */ "paddb %%mm7, %%mm0 \n\t" - "movq 8(%%edi,%%edx,), %%mm1 \n\t" // load Sub(x) for 2nd 8 bytes - "movq %%mm0, (%%edi,%%edx,) \n\t" // write Raw(x) for 1st 8 bytes + "movq 8(%%edi,%%edx,), %%mm1 \n\t" /* load Sub(x) for 2nd 8 bytes */ + "movq %%mm0, (%%edi,%%edx,) \n\t" /* write Raw(x) for 1st 8 bytes */ - // Now mm0 will be used as Raw(x-bpp) for the 2nd group of 8 bytes. - // This will be repeated for each group of 8 bytes with the 8th - // group being used as the Raw(x-bpp) for the 1st group of the - // next loop. + /* Now mm0 will be used as Raw(x-bpp) for the 2nd group of 8 bytes. */ + /* This will be repeated for each group of 8 bytes with the 8th */ + /* group being used as the Raw(x-bpp) for the 1st group of the */ + /* next loop. */ "paddb %%mm0, %%mm1 \n\t" - "movq 16(%%edi,%%edx,), %%mm2 \n\t" // load Sub(x) for 3rd 8 bytes - "movq %%mm1, 8(%%edi,%%edx,) \n\t" // write Raw(x) for 2nd 8 bytes + "movq 16(%%edi,%%edx,), %%mm2 \n\t" /* load Sub(x) for 3rd 8 bytes */ + "movq %%mm1, 8(%%edi,%%edx,) \n\t" /* write Raw(x) for 2nd 8 bytes */ "paddb %%mm1, %%mm2 \n\t" - "movq 24(%%edi,%%edx,), %%mm3 \n\t" // load Sub(x) for 4th 8 bytes - "movq %%mm2, 16(%%edi,%%edx,) \n\t" // write Raw(x) for 3rd 8 bytes + "movq 24(%%edi,%%edx,), %%mm3 \n\t" /* load Sub(x) for 4th 8 bytes */ + "movq %%mm2, 16(%%edi,%%edx,) \n\t" /* write Raw(x) for 3rd 8 bytes */ "paddb %%mm2, %%mm3 \n\t" - "movq 32(%%edi,%%edx,), %%mm4 \n\t" // load Sub(x) for 5th 8 bytes - "movq %%mm3, 24(%%edi,%%edx,) \n\t" // write Raw(x) for 4th 8 bytes + "movq 32(%%edi,%%edx,), %%mm4 \n\t" /* load Sub(x) for 5th 8 bytes */ + "movq %%mm3, 24(%%edi,%%edx,) \n\t" /* write Raw(x) for 4th 8 bytes */ "paddb %%mm3, %%mm4 \n\t" - "movq 40(%%edi,%%edx,), %%mm5 \n\t" // load Sub(x) for 6th 8 bytes - "movq %%mm4, 32(%%edi,%%edx,) \n\t" // write Raw(x) for 5th 8 bytes + "movq 40(%%edi,%%edx,), %%mm5 \n\t" /* load Sub(x) for 6th 8 bytes */ + "movq %%mm4, 32(%%edi,%%edx,) \n\t" /* write Raw(x) for 5th 8 bytes */ "paddb %%mm4, %%mm5 \n\t" - "movq 48(%%edi,%%edx,), %%mm6 \n\t" // load Sub(x) for 7th 8 bytes - "movq %%mm5, 40(%%edi,%%edx,) \n\t" // write Raw(x) for 6th 8 bytes + "movq 48(%%edi,%%edx,), %%mm6 \n\t" /* load Sub(x) for 7th 8 bytes */ + "movq %%mm5, 40(%%edi,%%edx,) \n\t" /* write Raw(x) for 6th 8 bytes */ "paddb %%mm5, %%mm6 \n\t" - "movq 56(%%edi,%%edx,), %%mm7 \n\t" // load Sub(x) for 8th 8 bytes - "movq %%mm6, 48(%%edi,%%edx,) \n\t" // write Raw(x) for 7th 8 bytes + "movq 56(%%edi,%%edx,), %%mm7 \n\t" /* load Sub(x) for 8th 8 bytes */ + "movq %%mm6, 48(%%edi,%%edx,) \n\t" /* write Raw(x) for 7th 8 bytes */ "addl $64, %%edx \n\t" "paddb %%mm6, %%mm7 \n\t" "cmpl %%ecx, %%edx \n\t" - "movq %%mm7, -8(%%edi,%%edx,) \n\t" // write Raw(x) for 8th 8 bytes + "movq %%mm7, -8(%%edi,%%edx,) \n\t" /* write Raw(x) for 8th 8 bytes */ "jb sub_8lp \n\t" "cmpl _MMXLength, %%edx \n\t" @@ -4805,21 +4813,21 @@ png_read_filter_row_mmx_sub(png_row_infop row_info, png_bytep row) "addl $8, %%edx \n\t" "paddb %%mm7, %%mm0 \n\t" "cmpl _MMXLength, %%edx \n\t" - "movq %%mm0, -8(%%edi,%%edx,) \n\t" // -8 to offset early addl edx - "movq %%mm0, %%mm7 \n\t" // move calculated Raw(x) data - // to mm1 to be new Raw(x-bpp) - // for next loop + "movq %%mm0, -8(%%edi,%%edx,) \n\t" /* -8 to offset early addl edx */ + "movq %%mm0, %%mm7 \n\t" /* move calculated Raw(x) data */ + /* to mm1 to be new Raw(x-bpp) */ + /* for next loop */ "jb sub_8lpA \n\t" "sub_8lt8: \n\t" - : "=a" (dummy_value_a), // 0 // output regs (dummy) - "=D" (dummy_value_D) // 1 + : "=a" (dummy_value_a), /* 0 // output regs (dummy) */ + "=D" (dummy_value_D) /* 1 */ - : "0" (bpp), // eax // input regs - "1" (row) // edi + : "0" (bpp), /* eax // input regs */ + "1" (row) /* edi */ - : "%ecx", "%edx", "%esi" // clobber list + : "%ecx", "%edx", "%esi" /* clobber list */ #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ , "%mm0", "%mm1", "%mm2", "%mm3", "%mm4", "%mm5", "%mm6", "%mm7" #endif @@ -4827,14 +4835,14 @@ png_read_filter_row_mmx_sub(png_row_infop row_info, png_bytep row) } break; - default: // bpp greater than 8 bytes GRR BOGUS + default: /* bpp greater than 8 bytes GRR BOGUS */ { __asm__ __volatile__ ( "movl _dif, %%edx \n\t" -// preload "movl row, %%edi \n\t" - "movl %%edi, %%esi \n\t" // lp = row -// preload "movl bpp, %%eax \n\t" - "addl %%eax, %%edi \n\t" // rp = row + bpp +/* preload "movl row, %%edi \n\t" */ + "movl %%edi, %%esi \n\t" /* lp = row */ +/* preload "movl bpp, %%eax \n\t" */ + "addl %%eax, %%edi \n\t" /* rp = row + bpp */ "sub_Alp: \n\t" "movq (%%edi,%%edx,), %%mm0 \n\t" @@ -4842,17 +4850,17 @@ png_read_filter_row_mmx_sub(png_row_infop row_info, png_bytep row) "addl $8, %%edx \n\t" "paddb %%mm1, %%mm0 \n\t" "cmpl _MMXLength, %%edx \n\t" - "movq %%mm0, -8(%%edi,%%edx,) \n\t" // mov does not affect flags; - // -8 to offset addl edx + "movq %%mm0, -8(%%edi,%%edx,) \n\t" /* mov does not affect flags; */ + /* -8 to offset addl edx */ "jb sub_Alp \n\t" - : "=a" (dummy_value_a), // 0 // output regs (dummy) - "=D" (dummy_value_D) // 1 + : "=a" (dummy_value_a), /* 0 // output regs (dummy) */ + "=D" (dummy_value_D) /* 1 */ - : "0" (bpp), // eax // input regs - "1" (row) // edi + : "0" (bpp), /* eax // input regs */ + "1" (row) /* edi */ - : "%edx", "%esi" // clobber list + : "%edx", "%esi" /* clobber list */ #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ , "%mm0", "%mm1" #endif @@ -4860,17 +4868,17 @@ png_read_filter_row_mmx_sub(png_row_infop row_info, png_bytep row) } break; - } // end switch (bpp) + } /* end switch (bpp) */ __asm__ __volatile__ ( "movl _MMXLength, %%edx \n\t" -//pre "movl row, %%edi \n\t" +/* pre "movl row, %%edi \n\t" */ "cmpl _FullLength, %%edx \n\t" "jnb sub_end \n\t" - "movl %%edi, %%esi \n\t" // lp = row -//pre "movl bpp, %%eax \n\t" - "addl %%eax, %%edi \n\t" // rp = row + bpp + "movl %%edi, %%esi \n\t" /* lp = row */ +/* pre "movl bpp, %%eax \n\t" */ + "addl %%eax, %%edi \n\t" /* rp = row + bpp */ "xorl %%eax, %%eax \n\t" "sub_lp2: \n\t" @@ -4881,45 +4889,45 @@ png_read_filter_row_mmx_sub(png_row_infop row_info, png_bytep row) "jb sub_lp2 \n\t" "sub_end: \n\t" - "EMMS \n\t" // end MMX instructions + "EMMS \n\t" /* end MMX instructions */ - : "=a" (dummy_value_a), // 0 // output regs (dummy) - "=D" (dummy_value_D) // 1 + : "=a" (dummy_value_a), /* 0 // output regs (dummy) */ + "=D" (dummy_value_D) /* 1 */ - : "0" (bpp), // eax // input regs - "1" (row) // edi + : "0" (bpp), /* eax // input regs */ + "1" (row) /* edi */ - : "%edx", "%esi" // clobber list + : "%edx", "%esi" /* clobber list */ ); -} // end of png_read_filter_row_mmx_sub() +} /* end of png_read_filter_row_mmx_sub() */ #endif -//===========================================================================// -// // -// P N G _ R E A D _ F I L T E R _ R O W _ M M X _ U P // -// // -//===========================================================================// +/*===========================================================================*/ +/* */ +/* P N G _ R E A D _ F I L T E R _ R O W _ M M X _ U P */ +/* */ +/*===========================================================================*/ -// Optimized code for PNG Up filter decoder +/* Optimized code for PNG Up filter decoder */ static void /* PRIVATE */ png_read_filter_row_mmx_up(png_row_infop row_info, png_bytep row, png_bytep prev_row) { png_uint_32 len; - int dummy_value_d; // fix 'forbidden register 3 (dx) was spilled' error + int dummy_value_d; /* fix 'forbidden register 3 (dx) was spilled' error */ int dummy_value_S; int dummy_value_D; - len = row_info->rowbytes; // number of bytes to filter + len = row_info->rowbytes; /* number of bytes to filter */ __asm__ __volatile__ ( -//pre "movl row, %%edi \n\t" - // get # of bytes to alignment +/* pre "movl row, %%edi \n\t" */ + /* get # of bytes to alignment */ #ifdef __PIC__ "pushl %%ebx \n\t" #endif @@ -4928,27 +4936,27 @@ png_read_filter_row_mmx_up(png_row_infop row_info, png_bytep row, "addl $0x7, %%ecx \n\t" "xorl %%eax, %%eax \n\t" "andl $0xfffffff8, %%ecx \n\t" -//pre "movl prev_row, %%esi \n\t" +/* pre "movl prev_row, %%esi \n\t" */ "subl %%edi, %%ecx \n\t" "jz up_go \n\t" - "up_lp1: \n\t" // fix alignment + "up_lp1: \n\t" /* fix alignment */ "movb (%%edi,%%ebx,), %%al \n\t" "addb (%%esi,%%ebx,), %%al \n\t" "incl %%ebx \n\t" "cmpl %%ecx, %%ebx \n\t" - "movb %%al, -1(%%edi,%%ebx,) \n\t" // mov does not affect flags; -1 to - "jb up_lp1 \n\t" // offset incl ebx + "movb %%al, -1(%%edi,%%ebx,) \n\t" /* mov does not affect flags; -1 to */ + "jb up_lp1 \n\t" /* offset incl ebx */ "up_go: \n\t" -//pre "movl len, %%edx \n\t" +/* pre "movl len, %%edx \n\t" */ "movl %%edx, %%ecx \n\t" - "subl %%ebx, %%edx \n\t" // subtract alignment fix - "andl $0x0000003f, %%edx \n\t" // calc bytes over mult of 64 - "subl %%edx, %%ecx \n\t" // drop over bytes from length + "subl %%ebx, %%edx \n\t" /* subtract alignment fix */ + "andl $0x0000003f, %%edx \n\t" /* calc bytes over mult of 64 */ + "subl %%edx, %%ecx \n\t" /* drop over bytes from length */ - // unrolled loop - use all MMX registers and interleave to reduce - // number of branch instructions (loops) and reduce partial stalls + /* unrolled loop - use all MMX registers and interleave to reduce */ + /* number of branch instructions (loops) and reduce partial stalls */ "up_loop: \n\t" "movq (%%esi,%%ebx,), %%mm1 \n\t" "movq (%%edi,%%ebx,), %%mm0 \n\t" @@ -4983,58 +4991,61 @@ png_read_filter_row_mmx_up(png_row_infop row_info, png_bytep row, "addl $64, %%ebx \n\t" "paddb %%mm7, %%mm6 \n\t" "cmpl %%ecx, %%ebx \n\t" - "movq %%mm6, -8(%%edi,%%ebx,) \n\t" // (+56)movq does not affect flags; - "jb up_loop \n\t" // -8 to offset addl ebx + "movq %%mm6, -8(%%edi,%%ebx,) \n\t" /* (+56)movq does not affect flags; */ + "jb up_loop \n\t" /* -8 to offset addl ebx */ - "cmpl $0, %%edx \n\t" // test for bytes over mult of 64 + "cmpl $0, %%edx \n\t" /* test for bytes over mult of 64 */ "jz up_end \n\t" - "cmpl $8, %%edx \n\t" // test for less than 8 bytes - "jb up_lt8 \n\t" // [added by lcreeve@netins.net] + "cmpl $8, %%edx \n\t" /* test for less than 8 bytes */ + "jb up_lt8 \n\t" /* [added by lcreeve@netins.net] */ "addl %%edx, %%ecx \n\t" - "andl $0x00000007, %%edx \n\t" // calc bytes over mult of 8 - "subl %%edx, %%ecx \n\t" // drop over bytes from length + "andl $0x00000007, %%edx \n\t" /* calc bytes over mult of 8 */ + "subl %%edx, %%ecx \n\t" /* drop over bytes from length */ "jz up_lt8 \n\t" - "up_lpA: \n\t" // use MMX regs to update 8 bytes sim. + "up_lpA: \n\t" /* use MMX regs to update 8 bytes sim. */ "movq (%%esi,%%ebx,), %%mm1 \n\t" "movq (%%edi,%%ebx,), %%mm0 \n\t" "addl $8, %%ebx \n\t" "paddb %%mm1, %%mm0 \n\t" "cmpl %%ecx, %%ebx \n\t" - "movq %%mm0, -8(%%edi,%%ebx,) \n\t" // movq does not affect flags; -8 to - "jb up_lpA \n\t" // offset add ebx - "cmpl $0, %%edx \n\t" // test for bytes over mult of 8 + "movq %%mm0, -8(%%edi,%%ebx,) \n\t" /* movq does not affect flags; -8 to */ + "jb up_lpA \n\t" /* offset add ebx */ + "cmpl $0, %%edx \n\t" /* test for bytes over mult of 8 */ "jz up_end \n\t" "up_lt8: \n\t" "xorl %%eax, %%eax \n\t" - "addl %%edx, %%ecx \n\t" // move over byte count into counter + "addl %%edx, %%ecx \n\t" /* move over byte count into counter */ - "up_lp2: \n\t" // use x86 regs for remaining bytes + "up_lp2: \n\t" /* use x86 regs for remaining bytes */ "movb (%%edi,%%ebx,), %%al \n\t" "addb (%%esi,%%ebx,), %%al \n\t" "incl %%ebx \n\t" "cmpl %%ecx, %%ebx \n\t" - "movb %%al, -1(%%edi,%%ebx,) \n\t" // mov does not affect flags; -1 to - "jb up_lp2 \n\t" // offset inc ebx + "movb %%al, -1(%%edi,%%ebx,) \n\t" /* mov does not affect flags; -1 to */ + "jb up_lp2 \n\t" /* offset inc ebx */ "up_end: \n\t" - "EMMS \n\t" // conversion of filtered row complete + "EMMS \n\t" /* conversion of filtered row complete */ #ifdef __PIC__ "popl %%ebx \n\t" #endif - : "=d" (dummy_value_d), // 0 // output regs (dummy) - "=S" (dummy_value_S), // 1 - "=D" (dummy_value_D) // 2 + : "=d" (dummy_value_d), /* 0 // output regs (dummy) */ + "=S" (dummy_value_S), /* 1 */ + "=D" (dummy_value_D) /* 2 */ - : "0" (len), // edx // input regs - "1" (prev_row), // esi - "2" (row) // edi + : "0" (len), /* edx // input regs */ + "1" (prev_row), /* esi */ + "2" (row) /* edi */ - : "%eax", "%ebx", "%ecx" // clobber list (no input regs!) + : "%eax", "%ecx" // clobber list (no input regs!) +#ifndef __PIC__ + , "%ebx" +#endif #if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */ , "%mm0", "%mm1", "%mm2", "%mm3" @@ -5042,7 +5053,7 @@ png_read_filter_row_mmx_up(png_row_infop row_info, png_bytep row, #endif ); -} // end of png_read_filter_row_mmx_up() +} /* end of png_read_filter_row_mmx_up() */ #endif /* PNG_ASSEMBLER_CODE_SUPPORTED */ @@ -5068,14 +5079,16 @@ png_read_filter_row(png_structp png_ptr, png_row_infop row_info, png_bytep #if defined(PNG_ASSEMBLER_CODE_SUPPORTED) /* GRR: these are superseded by png_ptr->asm_flags: */ -#define UseMMX_sub 1 // GRR: converted 20000730 -#define UseMMX_up 1 // GRR: converted 20000729 -#define UseMMX_avg 1 // GRR: converted 20000828 (+ 16-bit bugfix 20000916) -#define UseMMX_paeth 1 // GRR: converted 20000828 +#define UseMMX_sub 1 /* GRR: converted 20000730 */ +#define UseMMX_up 1 /* GRR: converted 20000729 */ +#define UseMMX_avg 1 /* GRR: converted 20000828 (+ 16-bit bugfix 20000916) */ +#define UseMMX_paeth 1 /* GRR: converted 20000828 */ if (_mmx_supported == 2) { /* this should have happened in png_init_mmx_flags() already */ +#if !defined(PNG_1_0_X) png_warning(png_ptr, "asm_flags may not have been initialized"); +#endif png_mmx_support(); } #endif /* PNG_ASSEMBLER_CODE_SUPPORTED */ @@ -5345,13 +5358,13 @@ png_mmx_support(void) "pushl %%ecx \n\t" // save original Eflag to stack "popfl \n\t" // restore original Eflag "xorl %%ecx, %%eax \n\t" // compare new Eflag with original Eflag - "jz .NOT_SUPPORTED \n\t" // if same, CPUID instr. is not supported + "jz 0f \n\t" // if same, CPUID instr. is not supported "xorl %%eax, %%eax \n\t" // set eax to zero // ".byte 0x0f, 0xa2 \n\t" // CPUID instruction (two-byte opcode) "cpuid \n\t" // get the CPU identification info "cmpl $1, %%eax \n\t" // make sure eax return non-zero value - "jl .NOT_SUPPORTED \n\t" // if eax is zero, MMX is not supported + "jl 0f \n\t" // if eax is zero, MMX is not supported "xorl %%eax, %%eax \n\t" // set eax to zero and... "incl %%eax \n\t" // ...increment eax to 1. This pair is @@ -5359,14 +5372,14 @@ png_mmx_support(void) "cpuid \n\t" // get the CPU identification info again "andl $0x800000, %%edx \n\t" // mask out all bits but MMX bit (23) "cmpl $0, %%edx \n\t" // 0 = MMX not supported - "jz .NOT_SUPPORTED \n\t" // non-zero = yes, MMX IS supported + "jz 0f \n\t" // non-zero = yes, MMX IS supported "movl $1, %%eax \n\t" // set return value to 1 - "jmp .RETURN \n\t" // DONE: have MMX support + "jmp 1f \n\t" // DONE: have MMX support - ".NOT_SUPPORTED: \n\t" // target label for jump instructions + "0: \n\t" // .NOT_SUPPORTED: target label for jump instructions "movl $0, %%eax \n\t" // set return value to 0 - ".RETURN: \n\t" // target label for jump instructions + "1: \n\t" // .RETURN: target label for jump instructions "movl %%eax, _mmx_supported \n\t" // save in global static variable, too "popl %%edx \n\t" // restore edx "popl %%ecx \n\t" // restore ecx