similar to: Compilation for iPhone (celt 0.7.1)

Hi all I have spent the last three days evaluating CELT on our supported platforms. I found a bug in quant_bands.c, that due to processor/compilation differences did not cause an issue on x86 platforms, but is a problem on the MIPS processor embedded devices. When decoding on the MIPS devices, there was a lot of noise added during the decoding, the noise is mainly in the 15 khz to 21 khz range.

Tim, et al, I have run into several problems with V0.8.0. I will address them seperately. 1. My compiler is complaining about the following code in celt.c which seems to define metric first as celt_word32, then as celt_word16. Am I mis-interpreting something? ?? VARDECL(celt_word32, metric); ?? ALLOC(metric, len, celt_word16); Thx MikeH -------------- next part -------------- An HTML attachment

Hi, We are testing CELT 0.7.1 on an iPod touch and it seems we are already reaching the CPU limit of the machine for a 1 channel both directions stream. The CELT README says that the code should be compiled with fixed-point support, but it it not clear how it has to be used later on. We currently use celt_encode_float/celt_decode_float functions. Can we still use them with the fixed point version

> -----Message d'origine----- > De : Jean-Marc Valin [mailto:jean-marc.valin at usherbrooke.ca] > Envoy? : lundi, 15. juin 2009 01:30 > ? : Stephane Lesage > Cc : speex-dev at xiph.org > Objet : Re: [Speex-dev] Resampler saturation, blackfin performance > > - are there buffers who could be placed in scratch memory ? > > (I don't see any speex_scratch_alloc

Hi, I'm using CELT encoder/decoder from several threads (but *different* encoder/decoder objects from the different threads) and I have various crash or "abort" (like ec_byte_write_at_end calling "celt_fatal("byte buffer collision");" It there any threading issues to known when using CELT? Thanks Stephane Letz

These were used because the entropy coder originally came from outside libcelt, and thus did not have a common type system. It's now undergone enough modification that it's not ever likely to be used as-is in another codec without some porting effort, so there's no real reason to maintain the typedefs separately. Hopefully we'll replace these all again somedate with a common set

Le 5 juil. 2013 à 17:23, Arnold Schwaighofer <aschwaighofer at apple.com> a écrit : > > On Jul 5, 2013, at 9:50 AM, Stéphane Letz <letz at grame.fr> wrote: > >> >> Le 5 juil. 2013 à 04:11, Tobias Grosser <tobias at grosser.es> a écrit : >> >>> On 07/04/2013 01:39 PM, Stéphane Letz wrote: >>>> Hi, >>>>

On Sat, May 29, 2010 at 1:23 AM, Stéphane Letz <letz at grame.fr> wrote: >> >> <32 x float> takes up 8 SSE registers; you're likely running into >> issues with register pressure.  Does it work better if you use >> something smaller like <4 x float>? >> >> Besides that, I don't see any obvious issues. >> >> -Eli > >

On Tue, Jul 16, 2013 at 8:16 AM, Stéphane Letz <letz at grame.fr> wrote: > Hi, > > Our DSL emit sub-optimal LLVM IR that we optimize later on (LLVM IR ==> LLVM IR) before dynamically compiling it with the JIT. We would like to simply follow what clang/clang++ does when compiling with -O1/-O2/-O3 options. Our strategy up to now what to look at the opt.cpp code and take part of it

> ------------------------------ > > Message: 4 > Date: Wed, 2 Jun 2010 11:07:39 -0700 > From: Dale Johannesen <dalej at apple.com> > Subject: Re: [LLVMdev] Generating Floating point constants > To: St?phane Letz <letz at free.fr> > Cc: llvmdev at cs.uiuc.edu > Message-ID: <AEC895CC-E887-4329-8743-FA606BD401F6 at apple.com> > Content-Type:

> > <32 x float> takes up 8 SSE registers; you're likely running into > issues with register pressure. Does it work better if you use > something smaller like <4 x float>? > > Besides that, I don't see any obvious issues. > > -Eli You are right yes. The code works faster with <4 x float> types, with still works a bit slower than the scalar

On Thu, Jul 18, 2013 at 9:07 AM, Stéphane Letz <letz at grame.fr> wrote: > Hi, > > Our DSL LLVM IR emitted code (optimized with -O3 kind of IR ==> IR passes) runs slower when executed with the LLVM 3.3 JIT, compared to what we had with LLVM 3.1. What could be the reason? > > I tried to play with TargetOptions without any success… > > Here is the kind of code we use to

On Jul 5, 2013, at 9:50 AM, Stéphane Letz <letz at grame.fr> wrote: > > Le 5 juil. 2013 à 04:11, Tobias Grosser <tobias at grosser.es> a écrit : > >> On 07/04/2013 01:39 PM, Stéphane Letz wrote: >>> Hi, >>> >>> Our DSL can generate C or directly generate LLVM IR. With LLVM 3.3, we can vectorize the C produced code using clang with -O3, or

Le 18 juil. 2013 à 19:07, Eli Friedman <eli.friedman at gmail.com> a écrit : > On Thu, Jul 18, 2013 at 9:07 AM, Stéphane Letz <letz at grame.fr> wrote: >> Hi, >> >> Our DSL LLVM IR emitted code (optimized with -O3 kind of IR ==> IR passes) runs slower when executed with the LLVM 3.3 JIT, compared to what we had with LLVM 3.1. What could be the reason? >>

Hi, We have a web page on our "LLVM backend for Faust" project available here: http://www.grame.fr/~letz/faust_llvm.html. Best Regards Stephane Letz

On Jul 5, 2013, at 10:43 AM, Stéphane Letz <letz at grame.fr> wrote > > 1) "entry" block is the first block of the function right? Yes. > > 2) do you mean *all* "alloca" in a function always have to be in the fist entry block? If you want them converted into ssa variables early on, yes.

Le 5 juil. 2013 à 17:48, Arnold Schwaighofer <aschwaighofer at apple.com> a écrit : > > On Jul 5, 2013, at 10:43 AM, Stéphane Letz <letz at grame.fr> wrote >> >> 1) "entry" block is the first block of the function right? > > Yes. OK > >> >> 2) do you mean *all* "alloca" in a function always have to be in the fist entry

Hi, Our DSL LLVM IR emitted code (optimized with -O3 kind of IR ==> IR passes) runs slower when executed with the LLVM 3.3 JIT, compared to what we had with LLVM 3.1. What could be the reason? I tried to play with TargetOptions without any success… Here is the kind of code we use to allocate the JIT: EngineBuilder builder(fResult->fModule);

Le 5 juil. 2013 à 04:11, Tobias Grosser <tobias at grosser.es> a écrit : > On 07/04/2013 01:39 PM, Stéphane Letz wrote: >> Hi, >> >> Our DSL can generate C or directly generate LLVM IR. With LLVM 3.3, we can vectorize the C produced code using clang with -O3, or clang with -O1 then opt -O3 -vectorize-loops. But the same program generating LLVM IR version cannot be

Hi, Our DSL emit sub-optimal LLVM IR that we optimize later on (LLVM IR ==> LLVM IR) before dynamically compiling it with the JIT. We would like to simply follow what clang/clang++ does when compiling with -O1/-O2/-O3 options. Our strategy up to now what to look at the opt.cpp code and take part of it in order to implement our optimization code. It appears to be rather difficult to follow