similar to: Opus ARM optimizations

Although I've never used ARM's compiler, I admit I'm very surprised that it's not compatible with the NEON intrinsics. Given that and M. Zanelli's speed tests, it seems clear that M. Zanelli's code is the way to go. I look forward to its inclusion in the opus GIT. --John On 6/10/2013 1:00 PM, opus-request at xiph.org wrote: > Date: Mon, 10 Jun 2013 10:36:34 +0100

Hello, This is a first patch which add macros for ARMv5E. Also, I copy headers from other files and add company name, tell me if I'm wrong. Also, if you have any question or comment about it, feel free to contact me. Best regards, -- Aur?lien Zanelli Parrot SA 174, quai de Jemmapes 75010 Paris France -------------- next part -------------- diff --git a/celt/fixed_arm5e.h

If opus_compare doesn't exist or isn't executable, tests failed normally which could be misleading. So test for existence and mode to avoid this ambiguity. -- Aur?lien Zanelli Parrot SA 174, quai de Jemmapes 75010 Paris France -------------- next part -------------- A non-text attachment was scrubbed... Name: 0001-Check-if-opus_compare-is-executable-in-run_vectors.s.patch Type:

I wrote a proof of concept regarding the cpu capabilities runtime detection and choice of optimized function. I follow design which had been discussed on IRC. Also, i notice a little drawback: we must propagate the arch index through functions which don't have codec state as argument. However, if it's look good, i will continue to implement it. Best regards, -- Aur?lien Zanelli

Please ignore my previous mail and patch, there is a new version :). Patch changes are: - Use MAC16_16 macros instead of (sum += a*b) and unroll a loop by 2. It increase performance when using optimized macros (ex: ARMv5E). A possible side effect of loop unroll is that i don't check for odd length here. - Add NEON version of FIR filter and autocorr - Add a section in autoconf in order to

Unfortunately I don't have a setup that lets me easily profile ARM code, so I really can't tell which method is faster (though I suspect Mr. Zanelli's code is). Let me offer up another intrinsic version of the NEON xcorr_kernel that is almost identical to the SSE version, and more in line with Mr. Zanelli's code: static inline void xcorr_kernel_neon(const opus_val16 *x, const

Hi JM, I have no doubt that Mr. Zanelli's NEON code is faster, since hand tuned assembly is bound to be faster than using intrinsics. However I notice that his code can also read past the y buffer. Cheers, --John On 6/6/2013 9:22 PM, Jean-Marc Valin wrote: > Hi John, > > Thanks for the two fixes. They're in git now. Your SSE version seems to > also be slightly faster than

- Use MAC16_16 macros instead of (sum += a*b) and unroll a loop by 2. It increase performance when using optimized macros (ex: ARMv5E). A possible side effect of loop unroll is that i don't check for odd length here. - Add NEON version of FIR filter and autocorr -- Aur?lien Zanelli Parrot SA 174, quai de Jemmapes 75010 Paris France -------------- next part -------------- diff --git

Hi Arnaud, Thanks for attaching those files. I'll take a look at them. Commit r153483 adds an option to the PBQP allocator, "-pbqp-dump-graphs", to dump the PBQP graph for each round of each function in a compilation unit. The generated files are named "<module id>.<function>.<round>.pbqpgraph", and contain a simple text representation of the PBQP graph.

Hi Lang, > From memory your target is not public, so I won't be able to reproduce > the crash myself. Is that correct? Correct. > If that's the case, I could add functionality to dump the PBQP graphs > during allocation. I think they should give me enough information to > debug the issue. Would you be able to share the PBQP graphs? I can share the pbqp graph if you send

Hi Arnaud, Apologies for the delayed reply. Thank you for the excellent test case - it exposed a subtle bug in the colorability heuristic. This has been fixed in r153958. In case you are curious, the bug was as follows: the PBQP solver applies applies a simplification step to each matrix. When all elements of a matrix row or column are equal, the value for those elements is "pushed

Hi Arnaud, I'm glad to hear that your test case is working. I however still get my wrong allocation in some non trivial cases : the > pairing constraint is not fulfilled. > > I have tried to modify the 'ensure pairable' pass (the pass undoing some > of the coalescer's work) to always insert register copies for > instructions with the pairable constraint, instead of

Hi Lang, I have reduced the testcase as much as possible. The log of the run and the dumped graphes are attached. Cheers, -- Arnaud de Grandmaison On Tuesday, March 27, 2012 01:20:35 Lang Hames wrote: > Hi Arnaud, > > Thanks for attaching those files. I'll take a look at them. > > Commit r153483 adds an option to the PBQP allocator, > "-pbqp-dump-graphs", to

Hi Lang, The assert is not triggered any longer on my testcases :) I however still get my wrong allocation in some non trivial cases : the pairing constraint is not fulfilled. I have tried to modify the 'ensure pairable' pass (the pass undoing some of the coalescer's work) to always insert register copies for instructions with the pairable constraint, instead of being smart and

Hi Lang, Thanks a lot for taking time to look into this. I will test the fix soon and let you know the results. Cheers, -- Arnaud de Grandmaison On Tuesday, April 03, 2012 17:30:33 Lang Hames wrote: > Hi Arnaud, > > Apologies for the delayed reply. > > Thank you for the excellent test case - it exposed a subtle bug in the > colorability heuristic. This has been fixed in

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

As a results of my investigations, the thread is also added to cfe-dev. The context : while porting my company code from the LLVM/Clang releases 3.1 to 3.2, I stumbled on a code size and performance regression. The testcase is : $ cat test.c #include <stdint.h> struct R { uint16_t a; uint16_t b; }; volatile struct R * const addr = (volatile struct R *) 416; void test(uint16_t a) {

Hi, I ''ve got a CentOS 5.2 server running xen 3.0 with 2 DomUs also running CentOS 5.2. All my boxes are up-to date. I''m experiencing trouble with networking. Dom0 can reach the outside world when no DomU are started. It can also reach the outside world when only one DomU is running. The troubles begin when I start the second DomU. At first, this new DomU, called DomU2,

Hello, I was using both version of WTLib 2007 (French and Japanese) under Unbuntu7.10 and Wine 0.9.47 and it worked fine with just an installation of VCRedist and some japanese fonts in windows folder. But recently i moved my system to the new Ubuntu8.04 with the last version of wine : 1.0 RC1. I read that i don't need to install vcredist and font anymore. It's supposed to be a platinum

Hi, I post my message here because I can't debug my problem, I hope you have time to help me to find the problem. I'm trying to join my Samba machine to an ADS domain, but my "net ads join" don't work :( There is my logs, if you need more detail ask me. ~# klist Ticket cache: FILE:/tmp/krb5cc_0 Default principal: administrateur@TEST.LAN Valid starting Expires