[FFmpeg-devel] [PATCH] h264_i386: Optimize decode_significance_8x8_x86 for 64 bit.
Reimar Döffinger
Reimar.Doeffinger at gmx.de
Sat Nov 15 18:16:03 CET 2014
11674 -> 10877 decicycles on my Phenom II.
Overall speedup was unfortunately within measurement error.
Signed-off-by: Reimar Döffinger <Reimar.Doeffinger at gmx.de>
---
libavcodec/x86/h264_i386.h | 30 ++++++++++++++++++------------
1 file changed, 18 insertions(+), 12 deletions(-)
diff --git a/libavcodec/x86/h264_i386.h b/libavcodec/x86/h264_i386.h
index ef65cf8..dcba42d 100644
--- a/libavcodec/x86/h264_i386.h
+++ b/libavcodec/x86/h264_i386.h
@@ -36,6 +36,12 @@
#if HAVE_INLINE_ASM
+#if ARCH_X86_64
+#define REG64 "r"
+#else
+#define REG64 "m"
+#endif
+
//FIXME use some macros to avoid duplicating get_cabac (cannot be done yet
//as that would make optimization work hard)
#if HAVE_7REGS && !BROKEN_COMPILER
@@ -140,7 +146,7 @@ static int decode_significance_8x8_x86(CABACContext *c,
"3: \n\t"
"mov %10, %0 \n\t"
- "movzbl (%0, %6), %k6 \n\t"
+ "movzb (%0, %6), %6 \n\t"
"add %9, %6 \n\t"
BRANCHLESS_GET_CABAC("%4", "%q4", "(%6)", "%3", "%w3",
@@ -151,14 +157,14 @@ static int decode_significance_8x8_x86(CABACContext *c,
AV_STRINGIFY(H264_MLPS_STATE_OFFSET),
"%15")
- "mov %1, %k6 \n\t"
+ "mov %1, %6 \n\t"
"test $1, %4 \n\t"
" jz 4f \n\t"
#ifdef BROKEN_RELOCATIONS
- "movzbl %c14(%15, %q6), %k6\n\t"
+ "movzb %c14(%15, %q6), %6\n\t"
#else
- "movzbl "MANGLE(ff_h264_cabac_tables)"+%c14(%k6), %k6\n\t"
+ "movzb "MANGLE(ff_h264_cabac_tables)"+%c14(%6), %6\n\t"
#endif
"add %11, %6 \n\t"
@@ -171,8 +177,8 @@ static int decode_significance_8x8_x86(CABACContext *c,
"%15")
"mov %2, %0 \n\t"
- "mov %1, %k6 \n\t"
- "movl %k6, (%0) \n\t"
+ "mov %1, %6 \n\t"
+ "mov %6, (%0) \n\t"
"test $1, %4 \n\t"
" jnz 5f \n\t"
@@ -180,19 +186,19 @@ static int decode_significance_8x8_x86(CABACContext *c,
"add"OPSIZE" $4, %2 \n\t"
"4: \n\t"
- "addl $1, %k6 \n\t"
- "mov %k6, %1 \n\t"
- "cmpl $63, %k6 \n\t"
+ "add $1, %6 \n\t"
+ "mov %6, %1 \n\t"
+ "cmp $63, %6 \n\t"
" jb 3b \n\t"
"mov %2, %0 \n\t"
- "movl %k6, (%0) \n\t"
+ "mov %6, (%0) \n\t"
"5: \n\t"
"addl %8, %k0 \n\t"
"shr $2, %k0 \n\t"
- : "=&q"(coeff_count), "+m"(last), "+m"(index), "+&r"(c->low),
+ : "=&q"(coeff_count), "+"REG64(last), "+"REG64(index), "+&r"(c->low),
"=&r"(bit), "+&r"(c->range), "=&r"(state)
: "r"(c), "m"(minusindex), "m"(significant_coeff_ctx_base),
- "m"(sig_off), "m"(last_coeff_ctx_base),
+ REG64(sig_off), REG64(last_coeff_ctx_base),
"i"(offsetof(CABACContext, bytestream)),
"i"(offsetof(CABACContext, bytestream_end)),
"i"(H264_LAST_COEFF_FLAG_OFFSET_8x8_OFFSET) TABLES_ARG
--
2.1.3
More information about the ffmpeg-devel
mailing list