use asm_offsets with vp8_regular_quantize_b_sse2
remove helper function and avoid shadowing all the arguments to the
stack on 64bit systems
when running with --good --cpu-used=0:
~2% on linux x86 and x86_64
~2% on win32 x86 msys and visual studio
more on darwin10 x86_64
significantly more on
x86_64-win64-vs9
Change-Id: Ib7be12edf511fbf2922f191afd5b33b19a0c4ae6
diff --git a/vp8/encoder/x86/x86_csystemdependent.c b/vp8/encoder/x86/x86_csystemdependent.c
index 8327fad..2b6bd98 100644
--- a/vp8/encoder/x86/x86_csystemdependent.c
+++ b/vp8/encoder/x86/x86_csystemdependent.c
@@ -106,30 +106,6 @@
);
}
-
-int vp8_regular_quantize_b_impl_sse2(short *coeff_ptr, short *zbin_ptr,
- short *qcoeff_ptr,short *dequant_ptr,
- const int *default_zig_zag, short *round_ptr,
- short *quant_ptr, short *dqcoeff_ptr,
- unsigned short zbin_oq_value,
- short *zbin_boost_ptr,
- short *quant_shift_ptr);
-
-static void regular_quantize_b_sse2(BLOCK *b,BLOCKD *d)
-{
- d->eob = vp8_regular_quantize_b_impl_sse2(b->coeff,
- b->zbin,
- d->qcoeff,
- d->dequant,
- vp8_default_zig_zag1d,
- b->round,
- b->quant,
- d->dqcoeff,
- b->zbin_extra,
- b->zrun_zbin_boost,
- b->quant_shift);
-}
-
int vp8_mbblock_error_xmm_impl(short *coeff_ptr, short *dcoef_ptr, int dc);
static int mbblock_error_xmm(MACROBLOCK *mb, int dc)
{
@@ -317,9 +293,7 @@
cpi->rtcd.encodemb.submby = vp8_subtract_mby_sse2;
cpi->rtcd.encodemb.submbuv = vp8_subtract_mbuv_sse2;
-#if ARCH_X86
- cpi->rtcd.quantize.quantb = regular_quantize_b_sse2;
-#endif
+ cpi->rtcd.quantize.quantb = vp8_regular_quantize_b_sse2;
cpi->rtcd.quantize.fastquantb = fast_quantize_b_sse2;
#if !(CONFIG_REALTIME_ONLY)
