COSMETICS: tabs --> spaces, some prettyprinting

Originally committed as revision 4764 to svn://svn.ffmpeg.org/ffmpeg/trunk

1 files changed, 450 insertions, 450 deletions

diff --git a/libavcodec/i386/mpegvideo_mmx.c b/libavcodec/i386/mpegvideo_mmx.c
index af799b6b00..6899c3938c 100644
--- a/libavcodec/i386/mpegvideo_mmx.c
+++ b/libavcodec/i386/mpegvideo_mmx.c
@@ -57,52 +57,52 @@ static void dct_unquantize_h263_intra_mmx(MpegEncContext *s,
         nCoeffs= s->inter_scantable.raster_end[ s->block_last_index[n] ];
 //printf("%d %d  ", qmul, qadd);
 asm volatile(
-		"movd %1, %%mm6			\n\t" //qmul
-		"packssdw %%mm6, %%mm6		\n\t"
-		"packssdw %%mm6, %%mm6		\n\t"
-		"movd %2, %%mm5			\n\t" //qadd
-		"pxor %%mm7, %%mm7		\n\t"
-		"packssdw %%mm5, %%mm5		\n\t"
-		"packssdw %%mm5, %%mm5		\n\t"
-		"psubw %%mm5, %%mm7		\n\t"
-		"pxor %%mm4, %%mm4		\n\t"
-		".balign 16\n\t"
-		"1:				\n\t"
-		"movq (%0, %3), %%mm0		\n\t"
-		"movq 8(%0, %3), %%mm1		\n\t"
-
-		"pmullw %%mm6, %%mm0		\n\t"
-		"pmullw %%mm6, %%mm1		\n\t"
-
-		"movq (%0, %3), %%mm2		\n\t"
-		"movq 8(%0, %3), %%mm3		\n\t"
-
-		"pcmpgtw %%mm4, %%mm2		\n\t" // block[i] < 0 ? -1 : 0
-		"pcmpgtw %%mm4, %%mm3		\n\t" // block[i] < 0 ? -1 : 0
-
-		"pxor %%mm2, %%mm0		\n\t"
-		"pxor %%mm3, %%mm1		\n\t"
-
-		"paddw %%mm7, %%mm0		\n\t"
-		"paddw %%mm7, %%mm1		\n\t"
-
-		"pxor %%mm0, %%mm2		\n\t"
-		"pxor %%mm1, %%mm3		\n\t"
-
-		"pcmpeqw %%mm7, %%mm0		\n\t" // block[i] == 0 ? -1 : 0
-		"pcmpeqw %%mm7, %%mm1		\n\t" // block[i] == 0 ? -1 : 0
-
-		"pandn %%mm2, %%mm0		\n\t"
-		"pandn %%mm3, %%mm1		\n\t"
-
-		"movq %%mm0, (%0, %3)		\n\t"
-		"movq %%mm1, 8(%0, %3)		\n\t"
-
-		"add $16, %3			\n\t"
-		"jng 1b				\n\t"
-		::"r" (block+nCoeffs), "g"(qmul), "g" (qadd), "r" (2*(-nCoeffs))
-		: "memory"
-	);
+                "movd %1, %%mm6                 \n\t" //qmul
+                "packssdw %%mm6, %%mm6          \n\t"
+                "packssdw %%mm6, %%mm6          \n\t"
+                "movd %2, %%mm5                 \n\t" //qadd
+                "pxor %%mm7, %%mm7              \n\t"
+                "packssdw %%mm5, %%mm5          \n\t"
+                "packssdw %%mm5, %%mm5          \n\t"
+                "psubw %%mm5, %%mm7             \n\t"
+                "pxor %%mm4, %%mm4              \n\t"
+                ".balign 16                     \n\t"
+                "1:                             \n\t"
+                "movq (%0, %3), %%mm0           \n\t"
+                "movq 8(%0, %3), %%mm1          \n\t"
+
+                "pmullw %%mm6, %%mm0            \n\t"
+                "pmullw %%mm6, %%mm1            \n\t"
+
+                "movq (%0, %3), %%mm2           \n\t"
+                "movq 8(%0, %3), %%mm3          \n\t"
+
+                "pcmpgtw %%mm4, %%mm2           \n\t" // block[i] < 0 ? -1 : 0
+                "pcmpgtw %%mm4, %%mm3           \n\t" // block[i] < 0 ? -1 : 0
+
+                "pxor %%mm2, %%mm0              \n\t"
+                "pxor %%mm3, %%mm1              \n\t"
+
+                "paddw %%mm7, %%mm0             \n\t"
+                "paddw %%mm7, %%mm1             \n\t"
+
+                "pxor %%mm0, %%mm2              \n\t"
+                "pxor %%mm1, %%mm3              \n\t"
+
+                "pcmpeqw %%mm7, %%mm0           \n\t" // block[i] == 0 ? -1 : 0
+                "pcmpeqw %%mm7, %%mm1           \n\t" // block[i] == 0 ? -1 : 0
+
+                "pandn %%mm2, %%mm0             \n\t"
+                "pandn %%mm3, %%mm1             \n\t"
+
+                "movq %%mm0, (%0, %3)           \n\t"
+                "movq %%mm1, 8(%0, %3)          \n\t"
+
+                "add $16, %3                    \n\t"
+                "jng 1b                         \n\t"
+                ::"r" (block+nCoeffs), "g"(qmul), "g" (qadd), "r" (2*(-nCoeffs))
+                : "memory"
+        );
         block[0]= level;
 }
 
@@ -120,52 +120,52 @@ static void dct_unquantize_h263_inter_mmx(MpegEncContext *s,
     nCoeffs= s->inter_scantable.raster_end[ s->block_last_index[n] ];
 //printf("%d %d  ", qmul, qadd);
 asm volatile(
-		"movd %1, %%mm6			\n\t" //qmul
-		"packssdw %%mm6, %%mm6		\n\t"
-		"packssdw %%mm6, %%mm6		\n\t"
-		"movd %2, %%mm5			\n\t" //qadd
-		"pxor %%mm7, %%mm7		\n\t"
-		"packssdw %%mm5, %%mm5		\n\t"
-		"packssdw %%mm5, %%mm5		\n\t"
-		"psubw %%mm5, %%mm7		\n\t"
-		"pxor %%mm4, %%mm4		\n\t"
-		".balign 16\n\t"
-		"1:				\n\t"
-		"movq (%0, %3), %%mm0		\n\t"
-		"movq 8(%0, %3), %%mm1		\n\t"
-
-		"pmullw %%mm6, %%mm0		\n\t"
-		"pmullw %%mm6, %%mm1		\n\t"
-
-		"movq (%0, %3), %%mm2		\n\t"
-		"movq 8(%0, %3), %%mm3		\n\t"
-
-		"pcmpgtw %%mm4, %%mm2		\n\t" // block[i] < 0 ? -1 : 0
-		"pcmpgtw %%mm4, %%mm3		\n\t" // block[i] < 0 ? -1 : 0
-
-		"pxor %%mm2, %%mm0		\n\t"
-		"pxor %%mm3, %%mm1		\n\t"
-
-		"paddw %%mm7, %%mm0		\n\t"
-		"paddw %%mm7, %%mm1		\n\t"
-
-		"pxor %%mm0, %%mm2		\n\t"
-		"pxor %%mm1, %%mm3		\n\t"
-
-		"pcmpeqw %%mm7, %%mm0		\n\t" // block[i] == 0 ? -1 : 0
-		"pcmpeqw %%mm7, %%mm1		\n\t" // block[i] == 0 ? -1 : 0
-
-		"pandn %%mm2, %%mm0		\n\t"
-		"pandn %%mm3, %%mm1		\n\t"
-
-		"movq %%mm0, (%0, %3)		\n\t"
-		"movq %%mm1, 8(%0, %3)		\n\t"
-
-		"add $16, %3			\n\t"
-		"jng 1b				\n\t"
-		::"r" (block+nCoeffs), "g"(qmul), "g" (qadd), "r" (2*(-nCoeffs))
-		: "memory"
-	);
+                "movd %1, %%mm6                 \n\t" //qmul
+                "packssdw %%mm6, %%mm6          \n\t"
+                "packssdw %%mm6, %%mm6          \n\t"
+                "movd %2, %%mm5                 \n\t" //qadd
+                "pxor %%mm7, %%mm7              \n\t"
+                "packssdw %%mm5, %%mm5          \n\t"
+                "packssdw %%mm5, %%mm5          \n\t"
+                "psubw %%mm5, %%mm7             \n\t"
+                "pxor %%mm4, %%mm4              \n\t"
+                ".balign 16                     \n\t"
+                "1:                             \n\t"
+                "movq (%0, %3), %%mm0           \n\t"
+                "movq 8(%0, %3), %%mm1          \n\t"
+
+                "pmullw %%mm6, %%mm0            \n\t"
+                "pmullw %%mm6, %%mm1            \n\t"
+
+                "movq (%0, %3), %%mm2           \n\t"
+                "movq 8(%0, %3), %%mm3          \n\t"
+
+                "pcmpgtw %%mm4, %%mm2           \n\t" // block[i] < 0 ? -1 : 0
+                "pcmpgtw %%mm4, %%mm3           \n\t" // block[i] < 0 ? -1 : 0
+
+                "pxor %%mm2, %%mm0              \n\t"
+                "pxor %%mm3, %%mm1              \n\t"
+
+                "paddw %%mm7, %%mm0             \n\t"
+                "paddw %%mm7, %%mm1             \n\t"
+
+                "pxor %%mm0, %%mm2              \n\t"
+                "pxor %%mm1, %%mm3              \n\t"
+
+                "pcmpeqw %%mm7, %%mm0           \n\t" // block[i] == 0 ? -1 : 0
+                "pcmpeqw %%mm7, %%mm1           \n\t" // block[i] == 0 ? -1 : 0
+
+                "pandn %%mm2, %%mm0             \n\t"
+                "pandn %%mm3, %%mm1             \n\t"
+
+                "movq %%mm0, (%0, %3)           \n\t"
+                "movq %%mm1, 8(%0, %3)          \n\t"
+
+                "add $16, %3                    \n\t"
+                "jng 1b                         \n\t"
+                ::"r" (block+nCoeffs), "g"(qmul), "g" (qadd), "r" (2*(-nCoeffs))
+                : "memory"
+        );
 }
 
 
@@ -216,54 +216,54 @@ static void dct_unquantize_mpeg1_intra_mmx(MpegEncContext *s,
     /* XXX: only mpeg1 */
     quant_matrix = s->intra_matrix;
 asm volatile(
-		"pcmpeqw %%mm7, %%mm7		\n\t"
-		"psrlw $15, %%mm7		\n\t"
-		"movd %2, %%mm6			\n\t"
-		"packssdw %%mm6, %%mm6		\n\t"
-		"packssdw %%mm6, %%mm6		\n\t"
-		"mov %3, %%"REG_a"		\n\t"
-		".balign 16\n\t"
-		"1:				\n\t"
-		"movq (%0, %%"REG_a"), %%mm0	\n\t"
-		"movq 8(%0, %%"REG_a"), %%mm1	\n\t"
-		"movq (%1, %%"REG_a"), %%mm4	\n\t"
-		"movq 8(%1, %%"REG_a"), %%mm5	\n\t"
-		"pmullw %%mm6, %%mm4		\n\t" // q=qscale*quant_matrix[i]
-		"pmullw %%mm6, %%mm5		\n\t" // q=qscale*quant_matrix[i]
-		"pxor %%mm2, %%mm2		\n\t"
-		"pxor %%mm3, %%mm3		\n\t"
-		"pcmpgtw %%mm0, %%mm2		\n\t" // block[i] < 0 ? -1 : 0
-		"pcmpgtw %%mm1, %%mm3		\n\t" // block[i] < 0 ? -1 : 0
-		"pxor %%mm2, %%mm0		\n\t"
-		"pxor %%mm3, %%mm1		\n\t"
-		"psubw %%mm2, %%mm0		\n\t" // abs(block[i])
-		"psubw %%mm3, %%mm1		\n\t" // abs(block[i])
-		"pmullw %%mm4, %%mm0		\n\t" // abs(block[i])*q
-		"pmullw %%mm5, %%mm1		\n\t" // abs(block[i])*q
-		"pxor %%mm4, %%mm4		\n\t"
-		"pxor %%mm5, %%mm5		\n\t" // FIXME slow
-		"pcmpeqw (%0, %%"REG_a"), %%mm4	\n\t" // block[i] == 0 ? -1 : 0
-		"pcmpeqw 8(%0, %%"REG_a"), %%mm5\n\t" // block[i] == 0 ? -1 : 0
-		"psraw $3, %%mm0		\n\t"
-		"psraw $3, %%mm1		\n\t"
-		"psubw %%mm7, %%mm0		\n\t"
-		"psubw %%mm7, %%mm1		\n\t"
-		"por %%mm7, %%mm0		\n\t"
-		"por %%mm7, %%mm1		\n\t"
-		"pxor %%mm2, %%mm0		\n\t"
-		"pxor %%mm3, %%mm1		\n\t"
-		"psubw %%mm2, %%mm0		\n\t"
-		"psubw %%mm3, %%mm1		\n\t"
-		"pandn %%mm0, %%mm4		\n\t"
-		"pandn %%mm1, %%mm5		\n\t"
-		"movq %%mm4, (%0, %%"REG_a")	\n\t"
-		"movq %%mm5, 8(%0, %%"REG_a")	\n\t"
-
-		"add $16, %%"REG_a"		\n\t"
-		"js 1b				\n\t"
-		::"r" (block+nCoeffs), "r"(quant_matrix+nCoeffs), "g" (qscale), "g" (-2*nCoeffs)
-		: "%"REG_a, "memory"
-	);
+                "pcmpeqw %%mm7, %%mm7           \n\t"
+                "psrlw $15, %%mm7               \n\t"
+                "movd %2, %%mm6                 \n\t"
+                "packssdw %%mm6, %%mm6          \n\t"
+                "packssdw %%mm6, %%mm6          \n\t"
+                "mov %3, %%"REG_a"              \n\t"
+                ".balign 16                     \n\t"
+                "1:                             \n\t"
+                "movq (%0, %%"REG_a"), %%mm0    \n\t"
+                "movq 8(%0, %%"REG_a"), %%mm1   \n\t"
+                "movq (%1, %%"REG_a"), %%mm4    \n\t"
+                "movq 8(%1, %%"REG_a"), %%mm5   \n\t"
+                "pmullw %%mm6, %%mm4            \n\t" // q=qscale*quant_matrix[i]
+                "pmullw %%mm6, %%mm5            \n\t" // q=qscale*quant_matrix[i]
+                "pxor %%mm2, %%mm2              \n\t"
+                "pxor %%mm3, %%mm3              \n\t"
+                "pcmpgtw %%mm0, %%mm2           \n\t" // block[i] < 0 ? -1 : 0
+                "pcmpgtw %%mm1, %%mm3           \n\t" // block[i] < 0 ? -1 : 0
+                "pxor %%mm2, %%mm0              \n\t"
+                "pxor %%mm3, %%mm1              \n\t"
+                "psubw %%mm2, %%mm0             \n\t" // abs(block[i])
+                "psubw %%mm3, %%mm1             \n\t" // abs(block[i])
+                "pmullw %%mm4, %%mm0            \n\t" // abs(block[i])*q
+                "pmullw %%mm5, %%mm1            \n\t" // abs(block[i])*q
+                "pxor %%mm4, %%mm4              \n\t"
+                "pxor %%mm5, %%mm5              \n\t" // FIXME slow
+                "pcmpeqw (%0, %%"REG_a"), %%mm4 \n\t" // block[i] == 0 ? -1 : 0
+                "pcmpeqw 8(%0, %%"REG_a"), %%mm5\n\t" // block[i] == 0 ? -1 : 0
+                "psraw $3, %%mm0                \n\t"
+                "psraw $3, %%mm1                \n\t"
+                "psubw %%mm7, %%mm0             \n\t"
+                "psubw %%mm7, %%mm1             \n\t"
+                "por %%mm7, %%mm0               \n\t"
+                "por %%mm7, %%mm1               \n\t"
+                "pxor %%mm2, %%mm0              \n\t"
+                "pxor %%mm3, %%mm1              \n\t"
+                "psubw %%mm2, %%mm0             \n\t"
+                "psubw %%mm3, %%mm1             \n\t"
+                "pandn %%mm0, %%mm4             \n\t"
+                "pandn %%mm1, %%mm5             \n\t"
+                "movq %%mm4, (%0, %%"REG_a")    \n\t"
+                "movq %%mm5, 8(%0, %%"REG_a")   \n\t"
+
+                "add $16, %%"REG_a"             \n\t"
+                "js 1b                          \n\t"
+                ::"r" (block+nCoeffs), "r"(quant_matrix+nCoeffs), "g" (qscale), "g" (-2*nCoeffs)
+                : "%"REG_a, "memory"
+        );
     block[0]= block0;
 }
 
@@ -279,58 +279,58 @@ static void dct_unquantize_mpeg1_inter_mmx(MpegEncContext *s,
 
         quant_matrix = s->inter_matrix;
 asm volatile(
-		"pcmpeqw %%mm7, %%mm7		\n\t"
-		"psrlw $15, %%mm7		\n\t"
-		"movd %2, %%mm6			\n\t"
-		"packssdw %%mm6, %%mm6		\n\t"
-		"packssdw %%mm6, %%mm6		\n\t"
-		"mov %3, %%"REG_a"		\n\t"
-		".balign 16\n\t"
-		"1:				\n\t"
-		"movq (%0, %%"REG_a"), %%mm0	\n\t"
-		"movq 8(%0, %%"REG_a"), %%mm1	\n\t"
-		"movq (%1, %%"REG_a"), %%mm4	\n\t"
-		"movq 8(%1, %%"REG_a"), %%mm5	\n\t"
-		"pmullw %%mm6, %%mm4		\n\t" // q=qscale*quant_matrix[i]
-		"pmullw %%mm6, %%mm5		\n\t" // q=qscale*quant_matrix[i]
-		"pxor %%mm2, %%mm2		\n\t"
-		"pxor %%mm3, %%mm3		\n\t"
-		"pcmpgtw %%mm0, %%mm2		\n\t" // block[i] < 0 ? -1 : 0
-		"pcmpgtw %%mm1, %%mm3		\n\t" // block[i] < 0 ? -1 : 0
-		"pxor %%mm2, %%mm0		\n\t"
-		"pxor %%mm3, %%mm1		\n\t"
-		"psubw %%mm2, %%mm0		\n\t" // abs(block[i])
-		"psubw %%mm3, %%mm1		\n\t" // abs(block[i])
-		"paddw %%mm0, %%mm0		\n\t" // abs(block[i])*2
-		"paddw %%mm1, %%mm1		\n\t" // abs(block[i])*2
-		"paddw %%mm7, %%mm0		\n\t" // abs(block[i])*2 + 1
-		"paddw %%mm7, %%mm1		\n\t" // abs(block[i])*2 + 1
-		"pmullw %%mm4, %%mm0		\n\t" // (abs(block[i])*2 + 1)*q
-		"pmullw %%mm5, %%mm1		\n\t" // (abs(block[i])*2 + 1)*q
-		"pxor %%mm4, %%mm4		\n\t"
-		"pxor %%mm5, %%mm5		\n\t" // FIXME slow
-		"pcmpeqw (%0, %%"REG_a"), %%mm4	\n\t" // block[i] == 0 ? -1 : 0
-		"pcmpeqw 8(%0, %%"REG_a"), %%mm5\n\t" // block[i] == 0 ? -1 : 0
-		"psraw $4, %%mm0		\n\t"
-		"psraw $4, %%mm1		\n\t"
-		"psubw %%mm7, %%mm0		\n\t"
-		"psubw %%mm7, %%mm1		\n\t"
-		"por %%mm7, %%mm0		\n\t"
-		"por %%mm7, %%mm1		\n\t"
-		"pxor %%mm2, %%mm0		\n\t"
-		"pxor %%mm3, %%mm1		\n\t"
-		"psubw %%mm2, %%mm0		\n\t"
-		"psubw %%mm3, %%mm1		\n\t"
-		"pandn %%mm0, %%mm4		\n\t"
-		"pandn %%mm1, %%mm5		\n\t"
-		"movq %%mm4, (%0, %%"REG_a")	\n\t"
-		"movq %%mm5, 8(%0, %%"REG_a")	\n\t"
-
-		"add $16, %%"REG_a"		\n\t"
-		"js 1b				\n\t"
-		::"r" (block+nCoeffs), "r"(quant_matrix+nCoeffs), "g" (qscale), "g" (-2*nCoeffs)
-		: "%"REG_a, "memory"
-	);
+                "pcmpeqw %%mm7, %%mm7           \n\t"
+                "psrlw $15, %%mm7               \n\t"
+                "movd %2, %%mm6                 \n\t"
+                "packssdw %%mm6, %%mm6          \n\t"
+                "packssdw %%mm6, %%mm6          \n\t"
+                "mov %3, %%"REG_a"              \n\t"
+                ".balign 16                     \n\t"
+                "1:                             \n\t"
+                "movq (%0, %%"REG_a"), %%mm0    \n\t"
+                "movq 8(%0, %%"REG_a"), %%mm1   \n\t"
+                "movq (%1, %%"REG_a"), %%mm4    \n\t"
+                "movq 8(%1, %%"REG_a"), %%mm5   \n\t"
+                "pmullw %%mm6, %%mm4            \n\t" // q=qscale*quant_matrix[i]
+                "pmullw %%mm6, %%mm5            \n\t" // q=qscale*quant_matrix[i]
+                "pxor %%mm2, %%mm2              \n\t"
+                "pxor %%mm3, %%mm3              \n\t"
+                "pcmpgtw %%mm0, %%mm2           \n\t" // block[i] < 0 ? -1 : 0
+                "pcmpgtw %%mm1, %%mm3           \n\t" // block[i] < 0 ? -1 : 0
+                "pxor %%mm2, %%mm0              \n\t"
+                "pxor %%mm3, %%mm1              \n\t"
+                "psubw %%mm2, %%mm0             \n\t" // abs(block[i])
+                "psubw %%mm3, %%mm1             \n\t" // abs(block[i])
+                "paddw %%mm0, %%mm0             \n\t" // abs(block[i])*2
+                "paddw %%mm1, %%mm1             \n\t" // abs(block[i])*2
+                "paddw %%mm7, %%mm0             \n\t" // abs(block[i])*2 + 1
+                "paddw %%mm7, %%mm1             \n\t" // abs(block[i])*2 + 1
+                "pmullw %%mm4, %%mm0            \n\t" // (abs(block[i])*2 + 1)*q
+                "pmullw %%mm5, %%mm1            \n\t" // (abs(block[i])*2 + 1)*q
+                "pxor %%mm4, %%mm4              \n\t"
+                "pxor %%mm5, %%mm5              \n\t" // FIXME slow
+                "pcmpeqw (%0, %%"REG_a"), %%mm4 \n\t" // block[i] == 0 ? -1 : 0
+                "pcmpeqw 8(%0, %%"REG_a"), %%mm5\n\t" // block[i] == 0 ? -1 : 0
+                "psraw $4, %%mm0                \n\t"
+                "psraw $4, %%mm1                \n\t"
+                "psubw %%mm7, %%mm0             \n\t"
+                "psubw %%mm7, %%mm1             \n\t"
+                "por %%mm7, %%mm0               \n\t"
+                "por %%mm7, %%mm1               \n\t"
+                "pxor %%mm2, %%mm0              \n\t"
+                "pxor %%mm3, %%mm1              \n\t"
+                "psubw %%mm2, %%mm0             \n\t"
+                "psubw %%mm3, %%mm1             \n\t"
+                "pandn %%mm0, %%mm4             \n\t"
+                "pandn %%mm1, %%mm5             \n\t"
+                "movq %%mm4, (%0, %%"REG_a")    \n\t"
+                "movq %%mm5, 8(%0, %%"REG_a")   \n\t"
+
+                "add $16, %%"REG_a"             \n\t"
+                "js 1b                          \n\t"
+                ::"r" (block+nCoeffs), "r"(quant_matrix+nCoeffs), "g" (qscale), "g" (-2*nCoeffs)
+                : "%"REG_a, "memory"
+        );
 }
 
 static void dct_unquantize_mpeg2_intra_mmx(MpegEncContext *s,
@@ -351,50 +351,50 @@ static void dct_unquantize_mpeg2_intra_mmx(MpegEncContext *s,
         block0 = block[0] * s->c_dc_scale;
     quant_matrix = s->intra_matrix;
 asm volatile(
-		"pcmpeqw %%mm7, %%mm7		\n\t"
-		"psrlw $15, %%mm7		\n\t"
-		"movd %2, %%mm6			\n\t"
-		"packssdw %%mm6, %%mm6		\n\t"
-		"packssdw %%mm6, %%mm6		\n\t"
-		"mov %3, %%"REG_a"		\n\t"
-		".balign 16\n\t"
-		"1:				\n\t"
-		"movq (%0, %%"REG_a"), %%mm0	\n\t"
-		"movq 8(%0, %%"REG_a"), %%mm1	\n\t"
-		"movq (%1, %%"REG_a"), %%mm4	\n\t"
-		"movq 8(%1, %%"REG_a"), %%mm5	\n\t"
-		"pmullw %%mm6, %%mm4		\n\t" // q=qscale*quant_matrix[i]
-		"pmullw %%mm6, %%mm5		\n\t" // q=qscale*quant_matrix[i]
-		"pxor %%mm2, %%mm2		\n\t"
-		"pxor %%mm3, %%mm3		\n\t"
-		"pcmpgtw %%mm0, %%mm2		\n\t" // block[i] < 0 ? -1 : 0
-		"pcmpgtw %%mm1, %%mm3		\n\t" // block[i] < 0 ? -1 : 0
-		"pxor %%mm2, %%mm0		\n\t"
-		"pxor %%mm3, %%mm1		\n\t"
-		"psubw %%mm2, %%mm0		\n\t" // abs(block[i])
-		"psubw %%mm3, %%mm1		\n\t" // abs(block[i])
-		"pmullw %%mm4, %%mm0		\n\t" // abs(block[i])*q
-		"pmullw %%mm5, %%mm1		\n\t" // abs(block[i])*q
-		"pxor %%mm4, %%mm4		\n\t"
-		"pxor %%mm5, %%mm5		\n\t" // FIXME slow
-		"pcmpeqw (%0, %%"REG_a"), %%mm4	\n\t" // block[i] == 0 ? -1 : 0
-		"pcmpeqw 8(%0, %%"REG_a"), %%mm5\n\t" // block[i] == 0 ? -1 : 0
-		"psraw $3, %%mm0		\n\t"
-		"psraw $3, %%mm1		\n\t"
-		"pxor %%mm2, %%mm0		\n\t"
-		"pxor %%mm3, %%mm1		\n\t"
-		"psubw %%mm2, %%mm0		\n\t"
-		"psubw %%mm3, %%mm1		\n\t"
-		"pandn %%mm0, %%mm4		\n\t"
-		"pandn %%mm1, %%mm5		\n\t"
-		"movq %%mm4, (%0, %%"REG_a")	\n\t"
-		"movq %%mm5, 8(%0, %%"REG_a")	\n\t"
-
-		"add $16, %%"REG_a"		\n\t"
-		"jng 1b				\n\t"
-		::"r" (block+nCoeffs), "r"(quant_matrix+nCoeffs), "g" (qscale), "g" (-2*nCoeffs)
-		: "%"REG_a, "memory"
-	);
+                "pcmpeqw %%mm7, %%mm7           \n\t"
+                "psrlw $15, %%mm7               \n\t"
+                "movd %2, %%mm6                 \n\t"
+                "packssdw %%mm6, %%mm6          \n\t"
+                "packssdw %%mm6, %%mm6          \n\t"
+                "mov %3, %%"REG_a"              \n\t"
+                ".balign 16                     \n\t"
+                "1:                             \n\t"
+                "movq (%0, %%"REG_a"), %%mm0    \n\t"
+                "movq 8(%0, %%"REG_a"), %%mm1   \n\t"
+                "movq (%1, %%"REG_a"), %%mm4    \n\t"
+                "movq 8(%1, %%"REG_a"), %%mm5   \n\t"
+                "pmullw %%mm6, %%mm4            \n\t" // q=qscale*quant_matrix[i]
+                "pmullw %%mm6, %%mm5            \n\t" // q=qscale*quant_matrix[i]
+                "pxor %%mm2, %%mm2              \n\t"
+                "pxor %%mm3, %%mm3              \n\t"
+                "pcmpgtw %%mm0, %%mm2           \n\t" // block[i] < 0 ? -1 : 0
+                "pcmpgtw %%mm1, %%mm3           \n\t" // block[i] < 0 ? -1 : 0
+                "pxor %%mm2, %%mm0              \n\t"
+                "pxor %%mm3, %%mm1              \n\t"
+                "psubw %%mm2, %%mm0             \n\t" // abs(block[i])
+                "psubw %%mm3, %%mm1             \n\t" // abs(block[i])
+                "pmullw %%mm4, %%mm0            \n\t" // abs(block[i])*q
+                "pmullw %%mm5, %%mm1            \n\t" // abs(block[i])*q
+                "pxor %%mm4, %%mm4              \n\t"
+                "pxor %%mm5, %%mm5              \n\t" // FIXME slow
+                "pcmpeqw (%0, %%"REG_a"), %%mm4 \n\t" // block[i] == 0 ? -1 : 0
+                "pcmpeqw 8(%0, %%"REG_a"), %%mm5\n\t" // block[i] == 0 ? -1 : 0
+                "psraw $3, %%mm0                \n\t"
+                "psraw $3, %%mm1                \n\t"
+                "pxor %%mm2, %%mm0              \n\t"
+                "pxor %%mm3, %%mm1              \n\t"
+                "psubw %%mm2, %%mm0             \n\t"
+                "psubw %%mm3, %%mm1             \n\t"
+                "pandn %%mm0, %%mm4             \n\t"
+                "pandn %%mm1, %%mm5             \n\t"
+                "movq %%mm4, (%0, %%"REG_a")    \n\t"
+                "movq %%mm5, 8(%0, %%"REG_a")   \n\t"
+
+                "add $16, %%"REG_a"             \n\t"
+                "jng 1b                         \n\t"
+                ::"r" (block+nCoeffs), "r"(quant_matrix+nCoeffs), "g" (qscale), "g" (-2*nCoeffs)
+                : "%"REG_a, "memory"
+        );
     block[0]= block0;
         //Note, we dont do mismatch control for intra as errors cannot accumulate
 }
@@ -412,68 +412,68 @@ static void dct_unquantize_mpeg2_inter_mmx(MpegEncContext *s,
 
         quant_matrix = s->inter_matrix;
 asm volatile(
-		"pcmpeqw %%mm7, %%mm7		\n\t"
-                "psrlq $48, %%mm7		\n\t"
-		"movd %2, %%mm6			\n\t"
-		"packssdw %%mm6, %%mm6		\n\t"
-		"packssdw %%mm6, %%mm6		\n\t"
-		"mov %3, %%"REG_a"		\n\t"
-		".balign 16\n\t"
-		"1:				\n\t"
-		"movq (%0, %%"REG_a"), %%mm0	\n\t"
-		"movq 8(%0, %%"REG_a"), %%mm1	\n\t"
-		"movq (%1, %%"REG_a"), %%mm4	\n\t"
-		"movq 8(%1, %%"REG_a"), %%mm5	\n\t"
-		"pmullw %%mm6, %%mm4		\n\t" // q=qscale*quant_matrix[i]
-		"pmullw %%mm6, %%mm5		\n\t" // q=qscale*quant_matrix[i]
-		"pxor %%mm2, %%mm2		\n\t"
-		"pxor %%mm3, %%mm3		\n\t"
-		"pcmpgtw %%mm0, %%mm2		\n\t" // block[i] < 0 ? -1 : 0
-		"pcmpgtw %%mm1, %%mm3		\n\t" // block[i] < 0 ? -1 : 0
-		"pxor %%mm2, %%mm0		\n\t"
-		"pxor %%mm3, %%mm1		\n\t"
-		"psubw %%mm2, %%mm0		\n\t" // abs(block[i])
-		"psubw %%mm3, %%mm1		\n\t" // abs(block[i])
-		"paddw %%mm0, %%mm0		\n\t" // abs(block[i])*2
-		"paddw %%mm1, %%mm1		\n\t" // abs(block[i])*2
-		"pmullw %%mm4, %%mm0		\n\t" // abs(block[i])*2*q
-		"pmullw %%mm5, %%mm1		\n\t" // abs(block[i])*2*q
-		"paddw %%mm4, %%mm0		\n\t" // (abs(block[i])*2 + 1)*q
-		"paddw %%mm5, %%mm1		\n\t" // (abs(block[i])*2 + 1)*q
-		"pxor %%mm4, %%mm4		\n\t"
-		"pxor %%mm5, %%mm5		\n\t" // FIXME slow
-		"pcmpeqw (%0, %%"REG_a"), %%mm4	\n\t" // block[i] == 0 ? -1 : 0
-		"pcmpeqw 8(%0, %%"REG_a"), %%mm5\n\t" // block[i] == 0 ? -1 : 0
-		"psrlw $4, %%mm0		\n\t"
-		"psrlw $4, %%mm1		\n\t"
-		"pxor %%mm2, %%mm0		\n\t"
-		"pxor %%mm3, %%mm1		\n\t"
-		"psubw %%mm2, %%mm0		\n\t"
-		"psubw %%mm3, %%mm1		\n\t"
-		"pandn %%mm0, %%mm4		\n\t"
-		"pandn %%mm1, %%mm5		\n\t"
-                "pxor %%mm4, %%mm7		\n\t"
-                "pxor %%mm5, %%mm7		\n\t"
-		"movq %%mm4, (%0, %%"REG_a")	\n\t"
-		"movq %%mm5, 8(%0, %%"REG_a")	\n\t"
-
-		"add $16, %%"REG_a"		\n\t"
-		"jng 1b				\n\t"
-                "movd 124(%0, %3), %%mm0	\n\t"
-                "movq %%mm7, %%mm6		\n\t"
-                "psrlq $32, %%mm7		\n\t"
-                "pxor %%mm6, %%mm7		\n\t"
-                "movq %%mm7, %%mm6		\n\t"
-                "psrlq $16, %%mm7		\n\t"
-                "pxor %%mm6, %%mm7		\n\t"
-                "pslld $31, %%mm7		\n\t"
-                "psrlq $15, %%mm7		\n\t"
-                "pxor %%mm7, %%mm0		\n\t"
-                "movd %%mm0, 124(%0, %3)	\n\t"
-
-		::"r" (block+nCoeffs), "r"(quant_matrix+nCoeffs), "g" (qscale), "r" (-2*nCoeffs)
-		: "%"REG_a, "memory"
-	);
+                "pcmpeqw %%mm7, %%mm7           \n\t"
+                "psrlq $48, %%mm7               \n\t"
+                "movd %2, %%mm6                 \n\t"
+                "packssdw %%mm6, %%mm6          \n\t"
+                "packssdw %%mm6, %%mm6          \n\t"
+                "mov %3, %%"REG_a"              \n\t"
+                ".balign 16                     \n\t"
+                "1:                             \n\t"
+                "movq (%0, %%"REG_a"), %%mm0    \n\t"
+                "movq 8(%0, %%"REG_a"), %%mm1   \n\t"
+                "movq (%1, %%"REG_a"), %%mm4    \n\t"
+                "movq 8(%1, %%"REG_a"), %%mm5   \n\t"
+                "pmullw %%mm6, %%mm4            \n\t" // q=qscale*quant_matrix[i]
+                "pmullw %%mm6, %%mm5            \n\t" // q=qscale*quant_matrix[i]
+                "pxor %%mm2, %%mm2              \n\t"
+                "pxor %%mm3, %%mm3              \n\t"
+                "pcmpgtw %%mm0, %%mm2           \n\t" // block[i] < 0 ? -1 : 0
+                "pcmpgtw %%mm1, %%mm3           \n\t" // block[i] < 0 ? -1 : 0
+                "pxor %%mm2, %%mm0              \n\t"
+                "pxor %%mm3, %%mm1              \n\t"
+                "psubw %%mm2, %%mm0             \n\t" // abs(block[i])
+                "psubw %%mm3, %%mm1             \n\t" // abs(block[i])
+                "paddw %%mm0, %%mm0             \n\t" // abs(block[i])*2
+                "paddw %%mm1, %%mm1             \n\t" // abs(block[i])*2
+                "pmullw %%mm4, %%mm0            \n\t" // abs(block[i])*2*q
+                "pmullw %%mm5, %%mm1            \n\t" // abs(block[i])*2*q
+                "paddw %%mm4, %%mm0             \n\t" // (abs(block[i])*2 + 1)*q
+                "paddw %%mm5, %%mm1             \n\t" // (abs(block[i])*2 + 1)*q
+                "pxor %%mm4, %%mm4              \n\t"
+                "pxor %%mm5, %%mm5              \n\t" // FIXME slow
+                "pcmpeqw (%0, %%"REG_a"), %%mm4 \n\t" // block[i] == 0 ? -1 : 0
+                "pcmpeqw 8(%0, %%"REG_a"), %%mm5\n\t" // block[i] == 0 ? -1 : 0
+                "psrlw $4, %%mm0                \n\t"
+                "psrlw $4, %%mm1                \n\t"
+                "pxor %%mm2, %%mm0              \n\t"
+                "pxor %%mm3, %%mm1              \n\t"
+                "psubw %%mm2, %%mm0             \n\t"
+                "psubw %%mm3, %%mm1             \n\t"
+                "pandn %%mm0, %%mm4             \n\t"
+                "pandn %%mm1, %%mm5             \n\t"
+                "pxor %%mm4, %%mm7              \n\t"
+                "pxor %%mm5, %%mm7              \n\t"
+                "movq %%mm4, (%0, %%"REG_a")    \n\t"
+                "movq %%mm5, 8(%0, %%"REG_a")   \n\t"
+
+                "add $16, %%"REG_a"             \n\t"
+                "jng 1b                         \n\t"
+                "movd 124(%0, %3), %%mm0        \n\t"
+                "movq %%mm7, %%mm6              \n\t"
+                "psrlq $32, %%mm7               \n\t"
+                "pxor %%mm6, %%mm7              \n\t"
+                "movq %%mm7, %%mm6              \n\t"
+                "psrlq $16, %%mm7               \n\t"
+                "pxor %%mm6, %%mm7              \n\t"
+                "pslld $31, %%mm7               \n\t"
+                "psrlq $15, %%mm7               \n\t"
+                "pxor %%mm7, %%mm0              \n\t"
+                "movd %%mm0, 124(%0, %3)        \n\t"
+
+                ::"r" (block+nCoeffs), "r"(quant_matrix+nCoeffs), "g" (qscale), "r" (-2*nCoeffs)
+                : "%"REG_a, "memory"
+        );
 }
 
 /* draw the edges of width 'w' of an image of size width, height
@@ -488,79 +488,79 @@ static void draw_edges_mmx(uint8_t *buf, int wrap, int width, int height, int w)
     ptr = buf;
     if(w==8)
     {
-	asm volatile(
-		"1:				\n\t"
-		"movd (%0), %%mm0		\n\t"
-		"punpcklbw %%mm0, %%mm0		\n\t"
-		"punpcklwd %%mm0, %%mm0		\n\t"
-		"punpckldq %%mm0, %%mm0		\n\t"
-		"movq %%mm0, -8(%0)		\n\t"
-		"movq -8(%0, %2), %%mm1		\n\t"
-		"punpckhbw %%mm1, %%mm1		\n\t"
-		"punpckhwd %%mm1, %%mm1		\n\t"
-		"punpckhdq %%mm1, %%mm1		\n\t"
-		"movq %%mm1, (%0, %2)		\n\t"
-		"add %1, %0			\n\t"
-		"cmp %3, %0			\n\t"
-		" jb 1b				\n\t"
-		: "+r" (ptr)
-		: "r" ((long)wrap), "r" ((long)width), "r" (ptr + wrap*height)
-	);
+        asm volatile(
+                "1:                             \n\t"
+                "movd (%0), %%mm0               \n\t"
+                "punpcklbw %%mm0, %%mm0         \n\t"
+                "punpcklwd %%mm0, %%mm0         \n\t"
+                "punpckldq %%mm0, %%mm0         \n\t"
+                "movq %%mm0, -8(%0)             \n\t"
+                "movq -8(%0, %2), %%mm1         \n\t"
+                "punpckhbw %%mm1, %%mm1         \n\t"
+                "punpckhwd %%mm1, %%mm1         \n\t"
+                "punpckhdq %%mm1, %%mm1         \n\t"
+                "movq %%mm1, (%0, %2)           \n\t"
+                "add %1, %0                     \n\t"
+                "cmp %3, %0                     \n\t"
+                " jb 1b                         \n\t"
+                : "+r" (ptr)
+                : "r" ((long)wrap), "r" ((long)width), "r" (ptr + wrap*height)
+        );
     }
     else
     {
-	asm volatile(
-		"1:				\n\t"
-		"movd (%0), %%mm0		\n\t"
-		"punpcklbw %%mm0, %%mm0		\n\t"
-		"punpcklwd %%mm0, %%mm0		\n\t"
-		"punpckldq %%mm0, %%mm0		\n\t"
-		"movq %%mm0, -8(%0)		\n\t"
-		"movq %%mm0, -16(%0)		\n\t"
-		"movq -8(%0, %2), %%mm1		\n\t"
-		"punpckhbw %%mm1, %%mm1		\n\t"
-		"punpckhwd %%mm1, %%mm1		\n\t"
-		"punpckhdq %%mm1, %%mm1		\n\t"
-		"movq %%mm1, (%0, %2)		\n\t"
-		"movq %%mm1, 8(%0, %2)		\n\t"
-		"add %1, %0			\n\t"
-		"cmp %3, %0			\n\t"
-		" jb 1b				\n\t"
-		: "+r" (ptr)
-		: "r" ((long)wrap), "r" ((long)width), "r" (ptr + wrap*height)
-	);
+        asm volatile(
+                "1:                             \n\t"
+                "movd (%0), %%mm0               \n\t"
+                "punpcklbw %%mm0, %%mm0         \n\t"
+                "punpcklwd %%mm0, %%mm0         \n\t"
+                "punpckldq %%mm0, %%mm0         \n\t"
+                "movq %%mm0, -8(%0)             \n\t"
+                "movq %%mm0, -16(%0)            \n\t"
+                "movq -8(%0, %2), %%mm1         \n\t"
+                "punpckhbw %%mm1, %%mm1         \n\t"
+                "punpckhwd %%mm1, %%mm1         \n\t"
+                "punpckhdq %%mm1, %%mm1         \n\t"
+                "movq %%mm1, (%0, %2)           \n\t"
+                "movq %%mm1, 8(%0, %2)          \n\t"
+                "add %1, %0                     \n\t"
+                "cmp %3, %0                     \n\t"
+                " jb 1b                         \n\t"
+                : "+r" (ptr)
+                : "r" ((long)wrap), "r" ((long)width), "r" (ptr + wrap*height)
+        );
     }
 
     for(i=0;i<w;i+=4) {
         /* top and bottom (and hopefully also the corners) */
-	ptr= buf - (i + 1) * wrap - w;
-	asm volatile(
-		"1:				\n\t"
-		"movq (%1, %0), %%mm0		\n\t"
-		"movq %%mm0, (%0)		\n\t"
-		"movq %%mm0, (%0, %2)		\n\t"
-		"movq %%mm0, (%0, %2, 2)	\n\t"
-		"movq %%mm0, (%0, %3)		\n\t"
-		"add $8, %0			\n\t"
-		"cmp %4, %0			\n\t"
-		" jb 1b				\n\t"
-		: "+r" (ptr)
-		: "r" ((long)buf - (long)ptr - w), "r" ((long)-wrap), "r" ((long)-wrap*3), "r" (ptr+width+2*w)
-	);
-	ptr= last_line + (i + 1) * wrap - w;
-	asm volatile(
-		"1:				\n\t"
-		"movq (%1, %0), %%mm0		\n\t"
-		"movq %%mm0, (%0)		\n\t"
-		"movq %%mm0, (%0, %2)		\n\t"
-		"movq %%mm0, (%0, %2, 2)	\n\t"
-		"movq %%mm0, (%0, %3)		\n\t"
-		"add $8, %0			\n\t"
-		"cmp %4, %0			\n\t"
-		" jb 1b				\n\t"
-		: "+r" (ptr)
-		: "r" ((long)last_line - (long)ptr - w), "r" ((long)wrap), "r" ((long)wrap*3), "r" (ptr+width+2*w)
-	);
+        ptr= buf - (i + 1) * wrap - w;
+        asm volatile(
+                "1:                             \n\t"
+                "movq (%1, %0), %%mm0           \n\t"
+                "movq %%mm0, (%0)               \n\t"
+                "movq %%mm0, (%0, %2)           \n\t"
+                "movq %%mm0, (%0, %2, 2)        \n\t"
+                "movq %%mm0, (%0, %3)           \n\t"
+                "add $8, %0                     \n\t"
+                "cmp %4, %0                     \n\t"
+                " jb 1b                         \n\t"
+                : "+r" (ptr)
+                : "r" ((long)buf - (long)ptr - w), "r" ((long)-wrap), "r" ((long)-wrap*3), "r" (ptr+width+2*w)
+        );
+        ptr= last_line + (i + 1) * wrap - w;
+        asm volatile(
+                "1:                             \n\t"
+                "movq (%1, %0), %%mm0           \n\t"
+                "movq %%mm0, (%0)               \n\t"
+                "movq %%mm0, (%0, %2)           \n\t"
+                "movq %%mm0, (%0, %2, 2)        \n\t"
+                "movq %%mm0, (%0, %3)           \n\t"
+                "add $8, %0                     \n\t"
+                "cmp %4, %0                     \n\t"
+                " jb 1b                         \n\t"
+                : "+r" (ptr)
+                : "r" ((long)last_line - (long)ptr - w), "r" ((long)wrap), "r" ((long)wrap*3), "r" (ptr+width+2*w)
+        );
     }
 }
 
@@ -572,47 +572,47 @@ static void  denoise_dct_mmx(MpegEncContext *s, DCTELEM *block){
     s->dct_count[intra]++;
 
     asm volatile(
-        "pxor %%mm7, %%mm7		\n\t"
-        "1:				\n\t"
-        "pxor %%mm0, %%mm0		\n\t"
-        "pxor %%mm1, %%mm1		\n\t"
-        "movq (%0), %%mm2		\n\t"
-        "movq 8(%0), %%mm3		\n\t"
-        "pcmpgtw %%mm2, %%mm0		\n\t"
-        "pcmpgtw %%mm3, %%mm1		\n\t"
-        "pxor %%mm0, %%mm2		\n\t"
-        "pxor %%mm1, %%mm3		\n\t"
-        "psubw %%mm0, %%mm2		\n\t"
-        "psubw %%mm1, %%mm3		\n\t"
-        "movq %%mm2, %%mm4		\n\t"
-        "movq %%mm3, %%mm5		\n\t"
-        "psubusw (%2), %%mm2		\n\t"
-        "psubusw 8(%2), %%mm3		\n\t"
-        "pxor %%mm0, %%mm2		\n\t"
-        "pxor %%mm1, %%mm3		\n\t"
-        "psubw %%mm0, %%mm2		\n\t"
-        "psubw %%mm1, %%mm3		\n\t"
-        "movq %%mm2, (%0)		\n\t"
-        "movq %%mm3, 8(%0)		\n\t"
-        "movq %%mm4, %%mm2		\n\t"
-        "movq %%mm5, %%mm3		\n\t"
-        "punpcklwd %%mm7, %%mm4		\n\t"
-        "punpckhwd %%mm7, %%mm2		\n\t"
-        "punpcklwd %%mm7, %%mm5		\n\t"
-        "punpckhwd %%mm7, %%mm3		\n\t"
-        "paddd (%1), %%mm4		\n\t"
-        "paddd 8(%1), %%mm2		\n\t"
-        "paddd 16(%1), %%mm5		\n\t"
-        "paddd 24(%1), %%mm3		\n\t"
-        "movq %%mm4, (%1)		\n\t"
-        "movq %%mm2, 8(%1)		\n\t"
-        "movq %%mm5, 16(%1)		\n\t"
-        "movq %%mm3, 24(%1)		\n\t"
-        "add $16, %0			\n\t"
-        "add $32, %1			\n\t"
-        "add $16, %2			\n\t"
-        "cmp %3, %0			\n\t"
-            " jb 1b			\n\t"
+        "pxor %%mm7, %%mm7                      \n\t"
+        "1:                                     \n\t"
+        "pxor %%mm0, %%mm0                      \n\t"
+        "pxor %%mm1, %%mm1                      \n\t"
+        "movq (%0), %%mm2                       \n\t"
+        "movq 8(%0), %%mm3                      \n\t"
+        "pcmpgtw %%mm2, %%mm0                   \n\t"
+        "pcmpgtw %%mm3, %%mm1                   \n\t"
+        "pxor %%mm0, %%mm2                      \n\t"
+        "pxor %%mm1, %%mm3                      \n\t"
+        "psubw %%mm0, %%mm2                     \n\t"
+        "psubw %%mm1, %%mm3                     \n\t"
+        "movq %%mm2, %%mm4                      \n\t"
+        "movq %%mm3, %%mm5                      \n\t"
+        "psubusw (%2), %%mm2                    \n\t"
+        "psubusw 8(%2), %%mm3                   \n\t"
+        "pxor %%mm0, %%mm2                      \n\t"
+        "pxor %%mm1, %%mm3                      \n\t"
+        "psubw %%mm0, %%mm2                     \n\t"
+        "psubw %%mm1, %%mm3                     \n\t"
+        "movq %%mm2, (%0)                       \n\t"
+        "movq %%mm3, 8(%0)                      \n\t"
+        "movq %%mm4, %%mm2                      \n\t"
+        "movq %%mm5, %%mm3                      \n\t"
+        "punpcklwd %%mm7, %%mm4                 \n\t"
+        "punpckhwd %%mm7, %%mm2                 \n\t"
+        "punpcklwd %%mm7, %%mm5                 \n\t"
+        "punpckhwd %%mm7, %%mm3                 \n\t"
+        "paddd (%1), %%mm4                      \n\t"
+        "paddd 8(%1), %%mm2                     \n\t"
+        "paddd 16(%1), %%mm5                    \n\t"
+        "paddd 24(%1), %%mm3                    \n\t"
+        "movq %%mm4, (%1)                       \n\t"
+        "movq %%mm2, 8(%1)                      \n\t"
+        "movq %%mm5, 16(%1)                     \n\t"
+        "movq %%mm3, 24(%1)                     \n\t"
+        "add $16, %0                            \n\t"
+        "add $32, %1                            \n\t"
+        "add $16, %2                            \n\t"
+        "cmp %3, %0                             \n\t"
+            " jb 1b                             \n\t"
         : "+r" (block), "+r" (sum), "+r" (offset)
         : "r"(block+64)
     );
@@ -626,47 +626,47 @@ static void  denoise_dct_sse2(MpegEncContext *s, DCTELEM *block){
     s->dct_count[intra]++;
 
     asm volatile(
-        "pxor %%xmm7, %%xmm7		\n\t"
-        "1:				\n\t"
-        "pxor %%xmm0, %%xmm0		\n\t"
-        "pxor %%xmm1, %%xmm1		\n\t"
-        "movdqa (%0), %%xmm2		\n\t"
-        "movdqa 16(%0), %%xmm3		\n\t"
-        "pcmpgtw %%xmm2, %%xmm0		\n\t"
-        "pcmpgtw %%xmm3, %%xmm1		\n\t"
-        "pxor %%xmm0, %%xmm2		\n\t"
-        "pxor %%xmm1, %%xmm3		\n\t"
-        "psubw %%xmm0, %%xmm2		\n\t"
-        "psubw %%xmm1, %%xmm3		\n\t"
-        "movdqa %%xmm2, %%xmm4		\n\t"
-        "movdqa %%xmm3, %%xmm5		\n\t"
-        "psubusw (%2), %%xmm2		\n\t"
-        "psubusw 16(%2), %%xmm3		\n\t"
-        "pxor %%xmm0, %%xmm2		\n\t"
-        "pxor %%xmm1, %%xmm3		\n\t"
-        "psubw %%xmm0, %%xmm2		\n\t"
-        "psubw %%xmm1, %%xmm3		\n\t"
-        "movdqa %%xmm2, (%0)		\n\t"
-        "movdqa %%xmm3, 16(%0)		\n\t"
-        "movdqa %%xmm4, %%xmm6		\n\t"
-        "movdqa %%xmm5, %%xmm0		\n\t"
-        "punpcklwd %%xmm7, %%xmm4	\n\t"
-        "punpckhwd %%xmm7, %%xmm6	\n\t"
-        "punpcklwd %%xmm7, %%xmm5	\n\t"
-        "punpckhwd %%xmm7, %%xmm0	\n\t"
-        "paddd (%1), %%xmm4		\n\t"
-        "paddd 16(%1), %%xmm6		\n\t"
-        "paddd 32(%1), %%xmm5		\n\t"
-        "paddd 48(%1), %%xmm0		\n\t"
-        "movdqa %%xmm4, (%1)		\n\t"
-        "movdqa %%xmm6, 16(%1)		\n\t"
-        "movdqa %%xmm5, 32(%1)		\n\t"
-        "movdqa %%xmm0, 48(%1)		\n\t"
-        "add $32, %0			\n\t"
-        "add $64, %1			\n\t"
-        "add $32, %2			\n\t"
-        "cmp %3, %0			\n\t"
-            " jb 1b			\n\t"
+        "pxor %%xmm7, %%xmm7                    \n\t"
+        "1:                                     \n\t"
+        "pxor %%xmm0, %%xmm0                    \n\t"
+        "pxor %%xmm1, %%xmm1                    \n\t"
+        "movdqa (%0), %%xmm2                    \n\t"
+        "movdqa 16(%0), %%xmm3                  \n\t"
+        "pcmpgtw %%xmm2, %%xmm0                 \n\t"
+        "pcmpgtw %%xmm3, %%xmm1                 \n\t"
+        "pxor %%xmm0, %%xmm2                    \n\t"
+        "pxor %%xmm1, %%xmm3                    \n\t"
+        "psubw %%xmm0, %%xmm2                   \n\t"
+        "psubw %%xmm1, %%xmm3                   \n\t"
+        "movdqa %%xmm2, %%xmm4                  \n\t"
+        "movdqa %%xmm3, %%xmm5                  \n\t"
+        "psubusw (%2), %%xmm2                   \n\t"
+        "psubusw 16(%2), %%xmm3                 \n\t"
+        "pxor %%xmm0, %%xmm2                    \n\t"
+        "pxor %%xmm1, %%xmm3                    \n\t"
+        "psubw %%xmm0, %%xmm2                   \n\t"
+        "psubw %%xmm1, %%xmm3                   \n\t"
+        "movdqa %%xmm2, (%0)                    \n\t"
+        "movdqa %%xmm3, 16(%0)                  \n\t"
+        "movdqa %%xmm4, %%xmm6                  \n\t"
+        "movdqa %%xmm5, %%xmm0                  \n\t"
+        "punpcklwd %%xmm7, %%xmm4               \n\t"
+        "punpckhwd %%xmm7, %%xmm6               \n\t"
+        "punpcklwd %%xmm7, %%xmm5               \n\t"
+        "punpckhwd %%xmm7, %%xmm0               \n\t"
+        "paddd (%1), %%xmm4                     \n\t"
+        "paddd 16(%1), %%xmm6                   \n\t"
+        "paddd 32(%1), %%xmm5                   \n\t"
+        "paddd 48(%1), %%xmm0                   \n\t"
+        "movdqa %%xmm4, (%1)                    \n\t"
+        "movdqa %%xmm6, 16(%1)                  \n\t"
+        "movdqa %%xmm5, 32(%1)                  \n\t"
+        "movdqa %%xmm0, 48(%1)                  \n\t"
+        "add $32, %0                            \n\t"
+        "add $64, %1                            \n\t"
+        "add $32, %2                            \n\t"
+        "cmp %3, %0                             \n\t"
+            " jb 1b                             \n\t"
         : "+r" (block), "+r" (sum), "+r" (offset)
         : "r"(block+64)
     );
@@ -705,10 +705,10 @@ void MPV_common_init_mmx(MpegEncContext *s)
         draw_edges = draw_edges_mmx;
 
         if (mm_flags & MM_SSE2) {
-	    s->denoise_dct= denoise_dct_sse2;
-	} else {
-    	    s->denoise_dct= denoise_dct_mmx;
-	}
+            s->denoise_dct= denoise_dct_sse2;
+        } else {
+                s->denoise_dct= denoise_dct_mmx;
+        }
 
         if(dct_algo==FF_DCT_AUTO || dct_algo==FF_DCT_MMX){
             if(mm_flags & MM_SSE2){