On Monday 02 February 2009 17:20:56 ext Marcel Holtmann wrote:
> Hi Siarhei,
>
> > > > > > > cases.
> > > > > >
> > > > > > patch has been applied. Thanks.
> > > > >
> > > > > The tests have passed all.
> > > > > http://net.cs.uni-tuebingen.de/html/nexgenvoip/html/
> > > >
> > > > Thanks a lot for keeping an eye on bluez sbc implementation quality.
> > >
> > > are all patches applied now or am I missing one?
> >
> > Yes, thanks, all the patches have been applied except for this one:
> > http://marc.info/?l=linux-bluetooth&m=123319235104928&w=2
> >
> > It should work fine, but I'm still considering how to better optimize
> > processing of joint stereo, which might also require changing this code
> > a bit. For now it's more like a demonstration that scale factors
> > processing can be SIMD optimized quite fine.
> >
> > I will provide a more complete patch with optimizations for both scale
> > factors and joint stereo a bit later.
>
> please re-sent this one with a proper commit message and I apply it.
> Then you can start from there is you like. Or send me a complete new
> one.
Done. Commit message added and patch attached.
time ./sbcenc tesfile.au > /dev/null
before:
real 0m6.404s
user 0m6.152s
sys 0m0.244s
after:
real 0m5.630s
user 0m5.376s
sys 0m0.248s
--
Best regards,
Siarhei Siamashka
From 83bece7b4642dde20b76253b7d18228d6654fa70 Mon Sep 17 00:00:00 2001
From: Siarhei Siamashka <siarhei.siamashka@xxxxxxxxx>
Date: Mon, 16 Mar 2009 21:10:32 +0200
Subject: [PATCH] sbc: MMX optimization for scale factors calculation
---
sbc/sbc_primitives_mmx.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 54 insertions(+), 0 deletions(-)
diff --git a/sbc/sbc_primitives_mmx.c b/sbc/sbc_primitives_mmx.c
index 08e9ca2..d8373b3 100644
--- a/sbc/sbc_primitives_mmx.c
+++ b/sbc/sbc_primitives_mmx.c
@@ -275,6 +275,59 @@ static inline void sbc_analyze_4b_8s_mmx(int16_t *x, int32_t *out,
asm volatile ("emms\n");
}
+static void sbc_calc_scalefactors_mmx(
+ int32_t sb_sample_f[16][2][8],
+ uint32_t scale_factor[2][8],
+ int blocks, int channels, int subbands)
+{
+ static const SBC_ALIGNED int32_t consts[2] = {
+ 1 << SCALE_OUT_BITS,
+ 1 << SCALE_OUT_BITS,
+ };
+ int ch, sb;
+ intptr_t blk;
+ for (ch = 0; ch < channels; ch++) {
+ for (sb = 0; sb < subbands; sb += 2) {
+ blk = (blocks - 1) * (((char *) &sb_sample_f[1][0][0] -
+ (char *) &sb_sample_f[0][0][0]));
+ asm volatile (
+ "movq (%4), %%mm0\n"
+ "1:\n"
+ "movq (%1, %0), %%mm1\n"
+ "pxor %%mm2, %%mm2\n"
+ "pcmpgtd %%mm2, %%mm1\n"
+ "paddd (%1, %0), %%mm1\n"
+ "pcmpgtd %%mm1, %%mm2\n"
+ "pxor %%mm2, %%mm1\n"
+
+ "por %%mm1, %%mm0\n"
+
+ "sub %2, %0\n"
+ "jns 1b\n"
+
+ "movd %%mm0, %k0\n"
+ "psrlq $32, %%mm0\n"
+ "bsrl %k0, %k0\n"
+ "subl %5, %k0\n"
+ "movl %k0, (%3)\n"
+
+ "movd %%mm0, %k0\n"
+ "bsrl %k0, %k0\n"
+ "subl %5, %k0\n"
+ "movl %k0, 4(%3)\n"
+ : "+r" (blk)
+ : "r" (&sb_sample_f[0][ch][sb]),
+ "i" ((char *) &sb_sample_f[1][0][0] -
+ (char *) &sb_sample_f[0][0][0]),
+ "r" (&scale_factor[ch][sb]),
+ "r" (&consts),
+ "i" (SCALE_OUT_BITS)
+ : "memory");
+ }
+ }
+ asm volatile ("emms\n");
+}
+
static int check_mmx_support(void)
{
#ifdef __amd64__
@@ -313,6 +366,7 @@ void sbc_init_primitives_mmx(struct sbc_encoder_state *state)
if (check_mmx_support()) {
state->sbc_analyze_4b_4s = sbc_analyze_4b_4s_mmx;
state->sbc_analyze_4b_8s = sbc_analyze_4b_8s_mmx;
+ state->sbc_calc_scalefactors = sbc_calc_scalefactors_mmx;
state->implementation_info = "MMX";
}
}
--
1.5.6.5
