similar to: Real time audio encoding - cpu usage

Building svn 10958 on amd64, gcc-4.1: gcc -DHAVE_CONFIG_H -I. -I. -I.. -I../include -I../include -I.. -I/usr/include -O2 -fPIC -funswitch-loops -fvisibility-inlines-hidden -march=k8 -ftree-vectorize -pipe -mfpmath=sse -O3 -msse -MT filters.lo -MD -MP -MF .deps/filters.Tpo -c filters.c -fPIC -DPIC -o .libs/filters.o cc1: warning: command line option "-fvisibility-inlines-hidden" is

>What frequency is the ARM processor? The phone shows ARM720 no freq. I'm going to have to guess around 100 Mhz. I ran the same code on an XSCALE ARM 400 mhz. Toshiba e740. Runs about .33 -> .4x realtime. This is the using the generic fixed point defines. Around 5 times faster than I am seeing with the Orange SPV e100. I am using the 1.1.3 codebase. Thanks for taking the time to

Hello! I'v downloaded speex lib 1.1.11.1. I am trying to port speex lib to Blackfin processor. I am using VisualDSP++ 4.0. If I am compiling source codes with using floating point everything ok. When I am compiling with FIXED_POINT defined everything's ok and code works about two times faster. But when I am defining BFIN_ASM I am getting several compiling errors in Blackfin assembler

Hello there I've developed a p2p voice application using Speex and I'm looking for ways to reduce Speex's cpu usage. My K6-2 300 MHz can't even encode 16 bit audio at 16KHz in realtime using Speex in narrowband mode. I've tried to lower the quality to 2 and complexity to 2 also but it's still way too slow. Which other ways are there to make encoding faster? Is there a

I am studying the speex 1.0.5 C source code ,but i feel it is hard to understand the code ,especially the ltp.c and filters.c file. may you tell me the detail algorithm or the more detail notation of the source code of this two file.including below functions void open_loop_nbest_pitch(float *sw, int start, int end, int len, int *pitch, float *gain, int N, char *stack); float

Le jeu 15/01/2004 à 15:30, Daniel Vogel a écrit : > Unrelated, but please use SSE/MMX/... intrinsics on Windows instead of using > inline assembly so you also get the speed benefit on Win64. OK, so here's a first start. I've translated to intrinsics the asm I sent 1-2 days ago. The result is about 5% slower than the pure asm approach, so it's not too bad (SSE asm is 2x faster

I don't think a compiler is going to be enough. I tried perl scripting the output of a linux gcc cross-compiler to convert into something the assembler under eVC would consume. It errors on all the MAC type of instructions. I looked at www.arm.com (I never knew there could be so many arms) It does not look like the ARM720 has the MAC instructions. It also lists 75Mhz and 100Mhz as possible

Jean-Marc, There is a big difference between SSE and SSEFP. The SSEFP means that the CPU supports the xmm registers. All Intel chips with SSE support do, however no current 32 bit AMD chips support the XMM registers. They will support the SSE instructions but not those registers. You are right about the SSE2 not being used. The AMD Opterons are the first AMD CPU's which support

Hello Greg If money isn't a problem Intel has an optimized compiler for eVC and XScale processors http://www.intel.com/software/products/compilers/techtopics/PCA_Optimization_WP.pdf If you have any luck getting the eVC compiler closer to realtime I'd really like to know. I'm still far from realtime when using Speex 1.1.3 on a HP iPAQ (Intel pxa255). Best regards Bjoern D.

I'm trying to get speex to encode a bit faster, mainly by rewriting a few functions in SSE and translating the GCC __asm__ to VC __asm. There's 2 functions I'm targeting, first is vq_nbest which consumes 40% of the time at high complexity and split_cb_search_shape_sign. Which consumes just over 30%. I've split out two functions from: cb_search_precompute_energy - loop at the

I'm not sure what you're trying to achieve here, but SSE and fixed-point are mutually exclusive. Jean-Marc On Sat, 2006-02-25 at 19:02 -0500, sean darcy wrote: > Building svn 10958 on amd64, gcc-4.1: > > gcc -DHAVE_CONFIG_H -I. -I. -I.. -I../include -I../include -I.. > -I/usr/include -O2 -fPIC -funswitch-loops -fvisibility-inlines-hidden > -march=k8 -ftree-vectorize

Hello there I'm having trouble decoding speex frames when using 32KHz audio and quality setting 4. If I encode three frames and then decode the three frames then the speex_bits_remaining() still reports that there are bits remaining. All other band modes and qualities reports that the buffer is emptied. Here's an example that shows 4 bits remaing in the buffer after the frames have

> There is a big difference between SSE and SSEFP. The SSEFP means > that the CPU supports the xmm registers. All Intel chips with SSE support > do, however no current 32 bit AMD chips support the XMM registers. They > will support the SSE instructions but not those registers. You are right > about the SSE2 not being used. I'm still not sure I get it. On an Athlon

<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"> <html> <head> <meta content="text/html;charset=ISO-8859-1" http-equiv="Content-Type"> <title></title> </head> <body bgcolor="#ffffff" text="#000000"> <b></b>Hi,<br> <br> I also tried to build speex

I received a segmentation violation whilst using openssh-2.2.9p2 today: Kernel 2.2.19-6.2.7 (Redhat 6.2) Gcc version egcs-2.91.66 glibc-2.1.3-22 Hardware is 333MHz K6-3Dnow with 64MB RAM if that matters Here is what happened along with a stack dump... # ssh -L 80:someplace.net:80 -l charlie someplace.net Password: (works for a while, then seems to freeze) ^C Segmentation violation (core

A user at a Windows PC uses our SSH client software (Anzio) to access a Linux sshd. User would like the banner from the server to display BEFORE entering a login name. According to the SSH spec, this should be allowed. But the OpenSSH source seems to have specifically prevented this. Is there a good reason for this? Regards, ....Bob Rasmussen, President, Rasmussen Software, Inc.

Hi.. i have an expression of the form: model1<-nls(y~beta1*(x1+(k1*x2)+(k1*k1*x3)+(k2*x4)+(k2*k1*x5)+(k2*k2*x6)+(k3*x7)+(k3*k4*x8)+(k3*k2*x9)+(k3*k3*x10)+ (k4*x11)+(k4*k1*x12)+(k4*k2*x13)+(k4*k3*x14)+(k4*k4*x15)+(k5*x16)+(k5*k1*x17)+(k5*k2*x18)+(k5*k3*x19)+

It depends how you "kill" the SSH server. If you kill it by sending it a SIGKILL signal, it will NOT notify the client, so the client will stay running until the client discovers the connection is broken. What happens if you send the SSH server a SIGHUP signal? This should cause an orderly shutdown on the server, which should notify the client, which should cause the client to do

On Tue, 5 Nov 2013, Rafael Espíndola wrote: > Please include a testcase with the patch. I'm sending testcase here. Compile it with "clang -O2 -march=k6-2 -c loop.c" > gas uses " nopl 0x0(%eax)" for k6_2. Are you sure it is a gas bug? Yes, it is gas bug. I should report it to binutils maintainers. Mikulas > On 3 November 2013 13:50, Mikulas Patocka >

Please include a testcase with the patch. gas uses " nopl 0x0(%eax)" for k6_2. Are you sure it is a gas bug? On 3 November 2013 13:50, Mikulas Patocka <mikulas at artax.karlin.mff.cuni.cz> wrote: > Hi > > This patch fixes code generation bug - 586-class CPUs don't support the > nopl instruction and some 686-class CPUs don't support it too. > > I