aboutsummaryrefslogtreecommitdiffstats
path: root/libavcodec/x86/vp56dsp.asm
diff options
context:
space:
mode:
authorMichael Niedermayer <michaelni@gmx.at>2012-07-29 01:56:31 +0200
committerMichael Niedermayer <michaelni@gmx.at>2012-07-29 02:16:26 +0200
commit706bd8ea19a6f723795547885714033ac68a4d74 (patch)
tree39f7933c9432b35801c81903fa7dc352de92fe95 /libavcodec/x86/vp56dsp.asm
parent0f8f9248471bbee5649c8efdc52d02c1cf93bba1 (diff)
parentc83f44dba11930744e167856b48fbc24a8ff0e63 (diff)
downloadffmpeg-706bd8ea19a6f723795547885714033ac68a4d74.tar.gz
Merge remote-tracking branch 'qatar/master'
* qatar/master: (35 commits) h264_idct_10bit: port x86 assembly to cpuflags. x86inc: clip num_args to 7 on x86-32. x86inc: sync to latest version from x264. fft: rename "z" to "zc" to prevent name collision. wv: return meaningful error codes. wv: return AVERROR_EOF on EOF, not EIO. mp3dec: forward errors for av_get_packet(). mp3dec: remove a pointless local variable. mp3dec: remove commented out cruft. lavfi: bump minor to mark stabilizing the ABI. FATE: add tests for yadif. FATE: add a test for delogo video filter. FATE: add a test for amix audio filter. audiogen: allow specifying random seed as a commandline parameter. vc1dec: Override invalid macroblock quantizer vc1: avoid reading beyond the last line in vc1_draw_sprites() vc1dec: check that coded slice positions and interlacing match. vc1dec: Do not ignore ff_vc1_parse_frame_header_adv return value configure: Move parts that should not be user-selectable to CONFIG_EXTRA lavf: remove commented out cruft in avformat_find_stream_info() ... Conflicts: Makefile configure libavcodec/vc1dec.c libavcodec/x86/h264_deblock.asm libavcodec/x86/h264_deblock_10bit.asm libavcodec/x86/h264dsp_mmx.c libavfilter/version.h libavformat/mp3dec.c libavformat/utils.c libavformat/wv.c libavutil/x86/x86inc.asm Merged-by: Michael Niedermayer <michaelni@gmx.at>
Diffstat (limited to 'libavcodec/x86/vp56dsp.asm')
-rw-r--r--libavcodec/x86/vp56dsp.asm36
1 files changed, 17 insertions, 19 deletions
diff --git a/libavcodec/x86/vp56dsp.asm b/libavcodec/x86/vp56dsp.asm
index 2d409bfca1..21ff041d61 100644
--- a/libavcodec/x86/vp56dsp.asm
+++ b/libavcodec/x86/vp56dsp.asm
@@ -27,7 +27,8 @@ cextern pw_64
SECTION .text
-%macro DIAG4_MMX 6
+%macro DIAG4 6
+%if mmsize == 8
movq m0, [%1+%2]
movq m1, [%1+%3]
movq m3, m0
@@ -64,9 +65,7 @@ SECTION .text
psraw m3, 7
packuswb m0, m3
movq [%6], m0
-%endmacro
-
-%macro DIAG4_SSE2 6
+%else ; mmsize == 16
movq m0, [%1+%2]
movq m1, [%1+%3]
punpcklbw m0, m7
@@ -86,9 +85,11 @@ SECTION .text
psraw m0, 7
packuswb m0, m0
movq [%6], m0
+%endif ; mmsize == 8/16
%endmacro
-%macro SPLAT4REGS_MMX 0
+%macro SPLAT4REGS 0
+%if mmsize == 8
movq m5, m3
punpcklwd m3, m3
movq m4, m3
@@ -102,9 +103,7 @@ SECTION .text
movq [rsp+8*12], m4
movq [rsp+8*13], m5
movq [rsp+8*14], m2
-%endmacro
-
-%macro SPLAT4REGS_SSE2 0
+%else ; mmsize == 16
pshuflw m4, m3, 0x0
pshuflw m5, m3, 0x55
pshuflw m6, m3, 0xAA
@@ -113,15 +112,16 @@ SECTION .text
punpcklqdq m5, m5
punpcklqdq m6, m6
punpcklqdq m3, m3
+%endif ; mmsize == 8/16
%endmacro
-%macro vp6_filter_diag4 2
+%macro vp6_filter_diag4 0
; void ff_vp6_filter_diag4_<opt>(uint8_t *dst, uint8_t *src, int stride,
; const int16_t h_weight[4], const int16_t v_weights[4])
-cglobal vp6_filter_diag4_%1, 5, 7, %2
+cglobal vp6_filter_diag4, 5, 7, 8
mov r5, rsp ; backup stack pointer
and rsp, ~(mmsize-1) ; align stack
-%ifidn %1, sse2
+%if mmsize == 16
sub rsp, 8*11
%else
sub rsp, 8*15
@@ -162,12 +162,10 @@ cglobal vp6_filter_diag4_%1, 5, 7, %2
RET
%endmacro
-INIT_MMX
-%define DIAG4 DIAG4_MMX
-%define SPLAT4REGS SPLAT4REGS_MMX
-vp6_filter_diag4 mmx, 0
+%if ARCH_X86_32
+INIT_MMX mmx
+vp6_filter_diag4
+%endif
-INIT_XMM
-%define DIAG4 DIAG4_SSE2
-%define SPLAT4REGS SPLAT4REGS_SSE2
-vp6_filter_diag4 sse2, 8
+INIT_XMM sse2
+vp6_filter_diag4