aboutsummaryrefslogtreecommitdiffstats
path: root/libavcodec/x86/h264_idct.asm
diff options
context:
space:
mode:
authorDaniel Kang <daniel.d.kang@gmail.com>2011-05-24 15:15:08 -0400
committerRonald S. Bultje <rbultje@google.com>2011-05-31 15:02:32 -0700
commit348493db60de19d1997fd2861e130720218b9fcf (patch)
treedc9c8b9489d6a452bf63a07ed77bcf57d99269ca /libavcodec/x86/h264_idct.asm
parent836f47d34b49e8ba9883e738a42f154130421caa (diff)
downloadffmpeg-348493db60de19d1997fd2861e130720218b9fcf.tar.gz
Update 8-bit H.264 IDCT function names to reflect bit-depth.
Signed-off-by: Ronald S. Bultje <rbultje@google.com>
Diffstat (limited to 'libavcodec/x86/h264_idct.asm')
-rw-r--r--libavcodec/x86/h264_idct.asm38
1 files changed, 19 insertions, 19 deletions
diff --git a/libavcodec/x86/h264_idct.asm b/libavcodec/x86/h264_idct.asm
index ae70a3049b..f90f41c4bc 100644
--- a/libavcodec/x86/h264_idct.asm
+++ b/libavcodec/x86/h264_idct.asm
@@ -73,7 +73,7 @@ SECTION .text
INIT_MMX
; ff_h264_idct_add_mmx(uint8_t *dst, int16_t *block, int stride)
-cglobal h264_idct_add_mmx, 3, 3, 0
+cglobal h264_idct_add_8_mmx, 3, 3, 0
IDCT4_ADD r0, r1, r2
RET
@@ -125,7 +125,7 @@ cglobal h264_idct_add_mmx, 3, 3, 0
SUMSUB_BA w, 0, 4
SUMSUB_BA w, 3, 2
SUMSUB_BA w, 1, 5
- SWAP 7, 6, 4, 5, 2, 3, 1, 0 ; 70315246 -> 01234567
+ SWAP 7, 6, 4, 5, 2, 3, 1, 0 ; 70315246 -> 01234567
%endmacro
%macro IDCT8_1D_FULL 1
@@ -177,7 +177,7 @@ cglobal h264_idct_add_mmx, 3, 3, 0
INIT_MMX
; ff_h264_idct8_add_mmx(uint8_t *dst, int16_t *block, int stride)
-cglobal h264_idct8_add_mmx, 3, 4, 0
+cglobal h264_idct8_add_8_mmx, 3, 4, 0
%assign pad 128+4-(stack_offset&7)
SUB rsp, pad
@@ -237,7 +237,7 @@ cglobal h264_idct8_add_mmx, 3, 4, 0
INIT_XMM
; ff_h264_idct8_add_sse2(uint8_t *dst, int16_t *block, int stride)
-cglobal h264_idct8_add_sse2, 3, 4, 10
+cglobal h264_idct8_add_8_sse2, 3, 4, 10
IDCT8_ADD_SSE r0, r1, r2, r3
RET
@@ -261,7 +261,7 @@ cglobal h264_idct8_add_sse2, 3, 4, 10
packuswb m1, m1
%endmacro
-%macro DC_ADD_MMX2_OP 3-4
+%macro DC_ADD_MMX2_OP 4
%1 m2, [%2 ]
%1 m3, [%2+%3 ]
%1 m4, [%2+%3*2]
@@ -282,13 +282,13 @@ cglobal h264_idct8_add_sse2, 3, 4, 10
INIT_MMX
; ff_h264_idct_dc_add_mmx2(uint8_t *dst, int16_t *block, int stride)
-cglobal h264_idct_dc_add_mmx2, 3, 3, 0
+cglobal h264_idct_dc_add_8_mmx2, 3, 3, 0
DC_ADD_MMX2_INIT r1, r2
DC_ADD_MMX2_OP movh, r0, r2, r1
RET
; ff_h264_idct8_dc_add_mmx2(uint8_t *dst, int16_t *block, int stride)
-cglobal h264_idct8_dc_add_mmx2, 3, 3, 0
+cglobal h264_idct8_dc_add_8_mmx2, 3, 3, 0
DC_ADD_MMX2_INIT r1, r2
DC_ADD_MMX2_OP mova, r0, r2, r1
lea r0, [r0+r2*4]
@@ -297,7 +297,7 @@ cglobal h264_idct8_dc_add_mmx2, 3, 3, 0
; ff_h264_idct_add16_mmx(uint8_t *dst, const int *block_offset,
; DCTELEM *block, int stride, const uint8_t nnzc[6*8])
-cglobal h264_idct_add16_mmx, 5, 7, 0
+cglobal h264_idct_add16_8_mmx, 5, 7, 0
xor r5, r5
%ifdef PIC
lea r11, [scan8_mem]
@@ -319,7 +319,7 @@ cglobal h264_idct_add16_mmx, 5, 7, 0
; ff_h264_idct8_add4_mmx(uint8_t *dst, const int *block_offset,
; DCTELEM *block, int stride, const uint8_t nnzc[6*8])
-cglobal h264_idct8_add4_mmx, 5, 7, 0
+cglobal h264_idct8_add4_8_mmx, 5, 7, 0
%assign pad 128+4-(stack_offset&7)
SUB rsp, pad
@@ -351,7 +351,7 @@ cglobal h264_idct8_add4_mmx, 5, 7, 0
; ff_h264_idct_add16_mmx2(uint8_t *dst, const int *block_offset,
; DCTELEM *block, int stride, const uint8_t nnzc[6*8])
-cglobal h264_idct_add16_mmx2, 5, 7, 0
+cglobal h264_idct_add16_8_mmx2, 5, 7, 0
xor r5, r5
%ifdef PIC
lea r11, [scan8_mem]
@@ -398,7 +398,7 @@ cglobal h264_idct_add16_mmx2, 5, 7, 0
; ff_h264_idct_add16intra_mmx(uint8_t *dst, const int *block_offset,
; DCTELEM *block, int stride, const uint8_t nnzc[6*8])
-cglobal h264_idct_add16intra_mmx, 5, 7, 0
+cglobal h264_idct_add16intra_8_mmx, 5, 7, 0
xor r5, r5
%ifdef PIC
lea r11, [scan8_mem]
@@ -421,7 +421,7 @@ cglobal h264_idct_add16intra_mmx, 5, 7, 0
; ff_h264_idct_add16intra_mmx2(uint8_t *dst, const int *block_offset,
; DCTELEM *block, int stride, const uint8_t nnzc[6*8])
-cglobal h264_idct_add16intra_mmx2, 5, 7, 0
+cglobal h264_idct_add16intra_8_mmx2, 5, 7, 0
xor r5, r5
%ifdef PIC
lea r11, [scan8_mem]
@@ -466,7 +466,7 @@ cglobal h264_idct_add16intra_mmx2, 5, 7, 0
; ff_h264_idct8_add4_mmx2(uint8_t *dst, const int *block_offset,
; DCTELEM *block, int stride, const uint8_t nnzc[6*8])
-cglobal h264_idct8_add4_mmx2, 5, 7, 0
+cglobal h264_idct8_add4_8_mmx2, 5, 7, 0
%assign pad 128+4-(stack_offset&7)
SUB rsp, pad
@@ -529,7 +529,7 @@ cglobal h264_idct8_add4_mmx2, 5, 7, 0
INIT_XMM
; ff_h264_idct8_add4_sse2(uint8_t *dst, const int *block_offset,
; DCTELEM *block, int stride, const uint8_t nnzc[6*8])
-cglobal h264_idct8_add4_sse2, 5, 7, 10
+cglobal h264_idct8_add4_8_sse2, 5, 7, 10
xor r5, r5
%ifdef PIC
lea r11, [scan8_mem]
@@ -607,7 +607,7 @@ h264_idct_add8_mmx_plane:
; ff_h264_idct_add8_mmx(uint8_t **dest, const int *block_offset,
; DCTELEM *block, int stride, const uint8_t nnzc[6*8])
-cglobal h264_idct_add8_mmx, 5, 7, 0
+cglobal h264_idct_add8_8_mmx, 5, 7, 0
mov r5, 16
add r2, 512
%ifdef PIC
@@ -668,7 +668,7 @@ h264_idct_add8_mmx2_plane
; ff_h264_idct_add8_mmx2(uint8_t **dest, const int *block_offset,
; DCTELEM *block, int stride, const uint8_t nnzc[6*8])
-cglobal h264_idct_add8_mmx2, 5, 7, 0
+cglobal h264_idct_add8_8_mmx2, 5, 7, 0
mov r5, 16
add r2, 512
%ifdef ARCH_X86_64
@@ -744,7 +744,7 @@ x264_add8x4_idct_sse2:
; ff_h264_idct_add16_sse2(uint8_t *dst, const int *block_offset,
; DCTELEM *block, int stride, const uint8_t nnzc[6*8])
-cglobal h264_idct_add16_sse2, 5, 5, 8
+cglobal h264_idct_add16_8_sse2, 5, 5, 8
%ifdef ARCH_X86_64
mov r10, r0
%endif
@@ -791,7 +791,7 @@ cglobal h264_idct_add16_sse2, 5, 5, 8
; ff_h264_idct_add16intra_sse2(uint8_t *dst, const int *block_offset,
; DCTELEM *block, int stride, const uint8_t nnzc[6*8])
-cglobal h264_idct_add16intra_sse2, 5, 7, 8
+cglobal h264_idct_add16intra_8_sse2, 5, 7, 8
%ifdef ARCH_X86_64
mov r10, r0
%endif
@@ -840,7 +840,7 @@ cglobal h264_idct_add16intra_sse2, 5, 7, 8
; ff_h264_idct_add8_sse2(uint8_t **dest, const int *block_offset,
; DCTELEM *block, int stride, const uint8_t nnzc[6*8])
-cglobal h264_idct_add8_sse2, 5, 7, 8
+cglobal h264_idct_add8_8_sse2, 5, 7, 8
add r2, 512
%ifdef ARCH_X86_64
mov r10, r0