Displaying 20 results from an estimated 43 matches for "restore_stack".
2015 Mar 04
0
[RFC PATCH v1] armv7(float): Optimize decode usecase using NE10 library
...# endif /* OPUS_ARM_NEON_INTR */
# endif /* FIXED_POINT */
diff --git a/celt/arm/celt_ne10_fft.c b/celt/arm/celt_ne10_fft.c
index b592f19..d354502 100644
--- a/celt/arm/celt_ne10_fft.c
+++ b/celt/arm/celt_ne10_fft.c
@@ -118,3 +118,29 @@ void opus_fft_float_neon(const kiss_fft_state *st,
}
RESTORE_STACK;
}
+
+void opus_ifft_float_neon(const kiss_fft_state *st,
+ const kiss_fft_cpx *fin,
+ kiss_fft_cpx *fout)
+{
+ ne10_fft_state_float32_t state;
+ ne10_fft_cfg_float32_t cfg = &state;
+ VARDECL(ne10_fft_cpx_float32_t, buffer);
+ SAVE_STA...
2015 Apr 28
0
[RFC PATCH v1 2/8] armv7(float): Optimize decode usecase using NE10 library
...# endif /* OPUS_ARM_NEON_INTR */
# endif /* FIXED_POINT */
diff --git a/celt/arm/celt_ne10_fft.c b/celt/arm/celt_ne10_fft.c
index b592f19..d354502 100644
--- a/celt/arm/celt_ne10_fft.c
+++ b/celt/arm/celt_ne10_fft.c
@@ -118,3 +118,29 @@ void opus_fft_float_neon(const kiss_fft_state *st,
}
RESTORE_STACK;
}
+
+void opus_ifft_float_neon(const kiss_fft_state *st,
+ const kiss_fft_cpx *fin,
+ kiss_fft_cpx *fout)
+{
+ ne10_fft_state_float32_t state;
+ ne10_fft_cfg_float32_t cfg = &state;
+ VARDECL(ne10_fft_cpx_float32_t, buffer);
+ SAVE_STA...
2015 Mar 04
1
[RFC PATCH v1] Decode(float) optimize using libNe10
Hello All,
I extended the libNE10 optimizations for float towards
mdct_backwards/opus_ifft.
I am able to get about 14.26% improvement for Decode use
case now on my Beaglebone Black. Please see [1] for measurements.
Questions
1. Since this patch needs to go in after Encode [2] patch)
should I submit this as patch series?
2. Since Jonathan Lennox posted intrinsics cleanup [3]
patch, should
2013 Jun 07
2
Bug fix in celt_lpc.c and some xcorr_kernel optimizations
Hi JM,
At line 221 in celt_lpc.c (the celt_iir function) I think you really
want the RESTORE_STACK statement to be before the #endif instead of
after it. Also, I couldn't help notice that your SSE code for
xcorr_kernel reads more than "len" elements of "_x". I don't know if
that's really a problem when running the codec, but a tool like valgrind
will have a fi...
2015 May 15
0
[RFC V3 4/8] aarch64: Enable intrinsics for aarch64
...celt/arm/celt_ne10_fft.c
@@ -44,6 +44,7 @@
#include "os_support.h"
#include "stack_alloc.h"
+#if !defined(FIXED_POINT)
#ifdef CUSTOM_MODES
/* nfft lengths in NE10 that support scaled fft */
@@ -144,3 +145,4 @@ void opus_ifft_float_neon(const kiss_fft_state *st,
}
RESTORE_STACK;
}
+#endif /* !defined(FIXED_POINT) */
diff --git a/celt/arm/celt_ne10_mdct.c b/celt/arm/celt_ne10_mdct.c
index 0979cbe..938fc93 100644
--- a/celt/arm/celt_ne10_mdct.c
+++ b/celt/arm/celt_ne10_mdct.c
@@ -43,6 +43,8 @@
#include "os_support.h"
#include "stack_alloc.h"
+#if !d...
2014 Jun 04
3
opus_multistream_encode_float not working in libopus 1.1
...amp;
200*frame_size != st->Fs && 100*frame_size != st->Fs &&
50*frame_size != st->Fs && 25*frame_size != st->Fs &&
50*frame_size != 3*st->Fs)
|| (400*frame_size < st->Fs)
|| max_data_bytes<=0
)
{
RESTORE_STACK;
return OPUS_BAD_ARG;
}
---inside---
opus_encode_native(...)
---on---
line 970 inside opus_encoder.c
---where the debugger says---
!st->variable_duration evaluates as false
400*frame_size != st->Fs evaluates as true
200*frame_size != st->Fs evaluates as true
100*frame_size !=...
2013 Jun 07
0
Bug fix in celt_lpc.c and some xcorr_kernel optimizations
...he code Aur?lien Zanelli posted at
http://darkosphere.fr/public/0002-Add-optimized-NEON-version-of-celt_fir-celt_iir-and-.patch
Cheers,
Jean-Marc
On 06/06/2013 08:07 PM, John Ridges wrote:
> Hi JM,
>
> At line 221 in celt_lpc.c (the celt_iir function) I think you really
> want the RESTORE_STACK statement to be before the #endif instead of
> after it. Also, I couldn't help notice that your SSE code for
> xcorr_kernel reads more than "len" elements of "_x". I don't know if
> that's really a problem when running the codec, but a tool like valgrind...
2013 May 21
0
[PATCH] 02-
...@ void _celt_autocorr(
while (lag>=0)
{
for (i = lag, d = 0; i < n; i++)
- d += xx[i] * xx[i-lag];
+ d = MAC16_16(d, xx[i], xx[i-lag]);
ac[lag] = d;
/*printf ("%f ", ac[lag]);*/
lag--;
@@ -186,3 +197,4 @@ void _celt_autocorr(
RESTORE_STACK;
}
+#endif
diff --git a/celt/celt_lpc_neon.h b/celt/celt_lpc_neon.h
new file mode 100644
index 0000000..72de8e0
--- /dev/null
+++ b/celt/celt_lpc_neon.h
@@ -0,0 +1,485 @@
+/* Copyright (c) 2013 Parrot */
+/*
+ Redistribution and use in source and binary forms, with or without
+ modification, a...
2011 Apr 15
4
Can I use VBR option to change byte_per_packet dynamically ?
Hi,I have been trying some different sample rate and bitrate combinations to get a feel for how CELT behaves,too, like Andrew Lentvorski. But I want to use VBR option.I want to ask a question about VBR in CELT codec.Can we use VBR option in CELT ??? "byte_per_packet" variable in code means constant bit rate, does not it ?In this code : bytes_per_packet is constant.len =
2013 May 21
2
[PATCH] 02-Add CELT filter optimizations
...@ void _celt_autocorr(
while (lag>=0)
{
for (i = lag, d = 0; i < n; i++)
- d += xx[i] * xx[i-lag];
+ d = MAC16_16(d, xx[i], xx[i-lag]);
ac[lag] = d;
/*printf ("%f ", ac[lag]);*/
lag--;
@@ -186,3 +197,4 @@ void _celt_autocorr(
RESTORE_STACK;
}
+#endif
diff --git a/celt/celt_lpc_neon.h b/celt/celt_lpc_neon.h
new file mode 100644
index 0000000..e9f76c6
--- /dev/null
+++ b/celt/celt_lpc_neon.h
@@ -0,0 +1,485 @@
+/* Copyright (c) 2013 Parrot */
+/*
+ Redistribution and use in source and binary forms, with or without
+ modification, a...
2015 May 08
8
[RFC PATCH v2]: Ne10 fft fixed and previous 0/8]
Hi All,
As per Timothy's suggestion, disabling mdct_forward
for fixed point. Only effects
armv7,armv8: Extend fixed fft NE10 optimizations to mdct
Rest of patches are same as in [1]
For reference, latest wip code for opus is at [2]
Still working with NE10 team at ARM to get corner cases of
mdct_forward. Will update with another patch
when issue in NE10 gets fixed.
Regards,
Vish
[1]:
2015 May 15
11
[RFC V3 0/8] Ne10 fft fixed and previous
Hi All,
Changes from RFC v2 [1]
armv7,armv8: Extend fixed fft NE10 optimizations to mdct
- Overflow issue fixed by Phil at ARM. Ne10 wip at [2]. Should be upstream soon.
- So, re-enabled using fixed fft for mdct_forward which was disabled in RFCv2
armv7,armv8: Optimize fixed point fft using NE10 library
- Thanks to Jonathan Lennox, fixed some build fixes on iOS and some copy-paste errors
Rest
2015 Apr 28
10
[RFC PATCH v1 0/8] Ne10 fft fixed and previous
Hello Timothy / Jean-Marc / opus-dev,
This patch series is follow up on work I posted on [1].
In addition to what was posted on [1], this patch series mainly
integrates Fixed point FFT implementations in NE10 library into opus.
You can view my opus wip code at [2].
Note that while I found some issues both with the NE10 library(fixed fft)
and with Linaro toolchain (armv8 intrinsics), the work
2015 May 15
0
[RFC V3 7/8] armv7, armv8: Optimize fixed point fft using NE10 library
...ut,
+ (NE10_FFT_CPX_TYPE_T *)fin,
+ cfg, 0);
+#else
+ NE10_FFT_C2C_1D_TYPE_NEON((NE10_FFT_CPX_TYPE_T *)fout,
+ (NE10_FFT_CPX_TYPE_T *)fin,
+ cfg, 0, 1);
+#endif
}
RESTORE_STACK;
}
-void opus_ifft_float_neon(const kiss_fft_state *st,
- const kiss_fft_cpx *fin,
- kiss_fft_cpx *fout)
+void opus_ifft_neon(const kiss_fft_state *st,
+ const kiss_fft_cpx *fin,
+ kiss_fft_cpx *fout)
{
-...
2013 May 23
2
ASM runtime detection and optimizations
...void celt_iir(const opus_val32 *x,
}
}
-#ifndef OVERRIDE_CELT_AUTOCORR
void _celt_autocorr(
const opus_val16 *x, /* in: [0...n-1] samples x */
opus_val32 *ac, /* out: [0...lag-1] ac values */
@@ -198,4 +207,3 @@ void _celt_autocorr(
RESTORE_STACK;
}
-#endif
diff --git a/celt/celt_lpc.h b/celt/celt_lpc.h
index 2baa77e..dcd9666 100644
--- a/celt/celt_lpc.h
+++ b/celt/celt_lpc.h
@@ -29,12 +29,16 @@
#define PLC_H
#include "arch.h"
+#include "cpu_support.h"
#define LPC_ORDER 24
+void (* const celt_fir[OPUS_ARCHMASK+...
2014 Jun 04
3
opus_multistream_encode_float not working in libopus 1.1
>
> This is as expected. The build system is trying to get a git revision
> string out of the source tree to compile in for reference. If you're
> building from a downloaded source .zip, there won't be any git
> information available and it will fall back to the hard-coded release
> string. That's why the error isn't fatal to the build.
Ok, this seems
2015 Mar 18
5
[RFC PATCH v1 0/4] Enable aarch64 intrinsics/Ne10
Hi All,
Since I continue to base my work on top of Jonathan's patch,
and my previous Ne10 fft/ifft/mdct_forward/backward patches,
I thought it would be better to just post all new patches
as a patch series. Please let me know if anyone disagrees
with this approach.
You can see wip branch of all latest patches at
https://git.linaro.org/people/viswanath.puttagunta/opus.git
Branch:
2015 Mar 31
6
[RFC PATCH v1 0/5] aarch64: celt_pitch_xcorr: Fixed point series
Hi Timothy,
As I mentioned earlier [1], I now fixed compile issues
with fixed point and resubmitting the patch.
I also have new patch that does intrinsics optimizations
for celt_pitch_xcorr targetting aarch64.
You can find my latest work-in-progress branch at [2]
For reference, you can use the Ne10 pre-built libraries
at [3]
Note that I am working with Phil at ARM to get my patch at [4]
2016 Jun 17
5
ARM NEON optimization -- celt_fir()
Hi all,
This is Linfeng Zhang from Google. I'll work on ARM NEON optimization in the
next few months.
I'm submitting 2 patches in the following couple of emails, which have the new
created celt_fir_neon().
I revised celt_fir_c() to not pass in argument "mem" in Patch 1. If there are
concerns to this change, please let me know.
Many thanks to your comments.
Linfeng Zhang
2016 Jul 28
0
[PATCH] Optimize silk_LPC_analysis_filter() for ARM NEON
...if (leftover >= 2) {
+ vst1_lane_s16(out + ix + 1, out32_Q12_s16x4, 1);
+ if (leftover == 3) {
+ vst1_lane_s16(out + ix + 2, out32_Q12_s16x4, 2);
+ }
+ }
+ }
+ }
+ }
+ RESTORE_STACK;
+#endif
+
+ /* Set first d output samples to zero */
+ silk_memset( out, 0, d * sizeof( opus_int16 ) );
+}
diff --git a/silk/arm/arm_silk_map.c b/silk/arm/arm_silk_map.c
index 59ceb6e..b1783c7 100644
--- a/silk/arm/arm_silk_map.c
+++ b/silk/arm/arm_silk_map.c
@@ -36,6 +36,20 @@ POSSIBILITY O...