similar to: [ARM][FFT][NEON] Integrate Ne10 into Opus?

Hi everyone, I am working on Ne10 project. Ne10 provides NEON optimized FFT routines that are much faster (compared to those without NEON), on most ARMv7-A and all ARMv8-A devices. How about integrate it into Opus? I am not familiar with configure script, but I find "Optinal Packages" in it. If we provides --with-ne10-fft option, the one extra thing that users need to do is to

Hi Ralph, I have pushed patches to enable radix 3 and radix 5. Github: https://github.com/projectNe10/Ne10/releases/tag/v1.2.0 Best Regards, Phil Wang > Date: Thu, 11 Dec 2014 10:46:50 -0800 > From: Ralph Giles <giles at thaumas.net> > Subject: Re: [opus] [ARM][FFT][NEON] Integrate Ne10 into Opus? > To: opus at xiph.org > Message-ID: <5489E69A.5000305 at thaumas.net>

Hello Timothy, Just FYI, Phil at ARM is still looking into why mdct is failing.. will keep you posted. In the mean time, do you want me to disable NE10 for mdct_forward and re-submit the patchset so we may make progress? Regards, Vish On 30 April 2015 at 09:33, Viswanath Puttagunta <viswanath.puttagunta at linaro.org> wrote: > > On 29 April 2015 at 17:22, Timothy B. Terriberry

On 29 April 2015 at 17:22, Timothy B. Terriberry <tterribe at xiph.org> wrote: > > Viswanath Puttagunta wrote: >> >> 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]. >

Hello Jean-Marc, **Resending.. not sure why subject got removed earlier** Below are the results that show test_unit_dft passes, but test_unit_mdct fails (only for nfft=480, 960, 1920) Note: Tested on BeagleboneBlack(Cortex-A8) fixed point on branch [1] ./test_unit_dft nfft=32 inverse=0,snr = 88.394372 nfft=32 inverse=1,snr = 93.896470 nfft=128 inverse=0,snr = 89.185895 nfft=128 inverse=1,snr =

Hi Timothy, Sorry for late reply. I have upstreamed the patch to fix the regression here: https://github.com/projectNe10/Ne10/commit/ee5d856cd9cb8c4a15ace567df4239f4e788d043 I have tested it with Vish's branch: http://git.linaro.org/people/viswanath.puttagunta/opus.git/shortlog/refs/heads/rfcv3_fft_fixed) Both unit test dft and unit test mdct passed on ARM v7/v8, floating point/fixed

Hi, I am working on DSP module of Ne10. I see there are fixed-point and floating-point FFT inside Opus. Is fixed-point FFT only a fall back for CPU without VFP? On ARMv7-A and ARMv8-A, benchmark result shows that fixed-point (int32) and floating-point (float32) FFT have similar performance. I guess fixed-point version is not often used on these platforms. Is it worth the effort to NEON-optimize

Uses NEON optimized fixed point fft routines in NE10 library Signed-off-by: Viswanath Puttagunta <viswanath.puttagunta at linaro.org> Signed-off-by: Jonathan Lennox <jonathan at vidyo.com> --- Makefile.am | 12 +- celt/arm/arm_celt_map.c | 46 ++-- celt/arm/celt_ne10_fft.c | 98 +++++---- celt/arm/fft_arm.h |

There is definitely some use for a Neon fixed-point FFT. How much exactly I'm not sure. Fixed-point is a bit more than just a fall-back for CPUs with no FPU. There are CPUs for which fixed-point is still faster. It depends on the exact model but also on what you run. For example, even on x86 I believe that SILK encoding is slightly faster in fixed-point, even though CELT is faster in float.

> I am working on DSP module of Ne10. I see there are fixed-point and > floating-point FFT inside Opus. Is fixed-point FFT only a fall back for CPU > without VFP? On ARMv7-A and ARMv8-A, benchmark result shows that fixed-point > (int32) and floating-point (float32) FFT have similar performance. I guess > fixed-point version is not often used on these platforms. Is it worth the >

Hello Timothy, Great to hear from you! Fired up my hardware today and this issue looks like a regression in Ne10 library. The commit in Ne10 [1] that I tested to be working successfully back in May 5b63074db45000f9688460990ee3f5e147d93782 which is the Patch Phil at ARM added to fix the overflow issue in nfft=60 case. After git-bisect, looks like the culprit patch in Ne10 [1] is

Hello Thomas, I use the following configure command to link against Ne10 Eg: configure --host=arm-linux-gnueabihf --enable-intrinsics --with-NE10-libraries=${BUILD_NE10_LIB} --with-NE10-includes=${BUILD_NE10_INC}" So, in my normal testing, I explicitly specify where the NE10 header files are installed and where the NE10 libraries are installed. Looking back at configure.ac

Hi Timothy, Appreciate the comprehensive code review. The biggest issue I see is the peak stack usage.... rest looks like fairly straight forward cleanup. Is the peak stack usage a complete blocker in current form? If it is indeed a blocker, would it be acceptable if we can reduce additional buffer requirement from 2 buffers (current) to 1, possibly by moving scaling inside

Optimize opus encode (float only) usecase using ARM NE10 library. Mainly effects opus_fft and ctl_mdct_forward and related functions. This optimization can be used for ARM CPUs that have NEON VFP unit. This patch only enables optimizations for ARMv7. Official ARM NE10 library page available at http://projectne10.github.io/Ne10/ To enable this optimization, use --enable-intrinsics

I'm trying to get these cleaned up and landed, but I'm running into some trouble with this patch. Using commit a08b29d88e3c (July 21) of Ne10, I'm seeing test failures for 60-point FFTs: nfft=60 inverse=0,snr = -3.312408 ** poor snr: -3.312408 ** nfft=60 inverse=1,snr = -16.079597 ** poor snr: -16.079597 ** All other sizes tested appear to work fine (84 to 140 dB of SNR). This

On 25 February 2015 at 19:54, Timothy B. Terriberry <tterribe at xiph.org> wrote: > Viswanath Puttagunta wrote: >> >> Can we please have review on RFCv2? We have quite a few optimizations >> (Eg: ifft/mdct_backwards, fixed point fft/ifft mdct_forward/backward >> etc) that are in my pipeline that depend on this patch series being >> accepted. > > >

Viswanath Puttagunta wrote: > 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]. Thanks, and I apologize for being slow here. > - This was surprising to me because test_unit_dft passes for all

Hello opus-dev, Can we please have review on RFCv2? We have quite a few optimizations (Eg: ifft/mdct_backwards, fixed point fft/ifft mdct_forward/backward etc) that are in my pipeline that depend on this patch series being accepted. Regards, Vish On 4 February 2015 at 12:21, Viswanath Puttagunta <viswanath.puttagunta at linaro.org> wrote: > Changes from RFC PATCH v1: > - passing

Viswanath Puttagunta wrote: > Can we please have review on RFCv2? We have quite a few optimizations > (Eg: ifft/mdct_backwards, fixed point fft/ifft mdct_forward/backward > etc) that are in my pipeline that depend on this patch series being > accepted. So, trying to make progress on this... On an armv7l board running Ubuntu, you've broken the build with just --enable-intrinsics

Hi, Can you apply this change to the MDCT test and run it again. See if more (all) sizes pass. Given the results, I strongly suspect an overflow. Jean-Marc On 08/05/15 01:21 PM, Viswanath Puttagunta wrote: > Hello Jean-Marc, > > Below are the results that show test_unit_dft passes, but > test_unit_mdct fails (only for nfft=480, 960, 1920) > Note: Tested on