How to Compile & run PortAudio, and GPU FIR.

9:53 PM 8/21/2008 Install McAfee
10:27 PM 8/21/2008 Install VisualStudio 2005 Pro, VC++
11:18 PM 8/21/2008 Windows Update. too many...

6:38 PM 8/22/2008 Download CUDA files.
1. NVIDIADisplayWin2K(177_84)Int.exe
2. NVIDIA_CUDA_toolkit_2.0_win32.exe
3. NVIDIA_CUDA_SDK_2.02.0811.0240_win32.exe
and install by this order.

also downlaod these documents.
SDK_Rel_Notes_Win_2.0beta2.pdf
Toolkit_Rel_Notes_Win_2.0beta2.pdf

There are installation instructions in SDK_Rel_Notes_Win_2.0beta2.pdf

1. Do not run virus protection software in the background while installing the drivers.
2. Uninstall any previous versions of the NVIDIA CUDA Toolkit and NVIDIA CUDA SDK.
3. Install version 2.0 of the NVIDIA CUDA Toolkit.
4. Install version 2.0 of the NVIDIA CUDA SDK.
5. Build Cutil. C:\Program Files\NVIDIA Corporation\NVIDIA CUDA SDK\common\cutil.sln
5. Build SDK Project Example. *.sln for VS2005.
6. simpleD3D example requires to have a Direct3D SDK installed and the
VC++ directory paths (located in Tools->Options...) properly setup.

Also see SDK_Rel_Notes_Win_2.0beta2.pdf to write your own CUDA program.

7:31 PM 8/22/2008 install NVIDIADisplayWin2K(177_84)Int.exe
7:39 PM 8/22/2008 install NVIDIA_CUDA_toolkit_2.0_win32.exe to C:\CUDA
documentations...
"The default compilation mode for host code is now C++. To restore the old
behavior, use the option --host-compilation=c"

7:45 PM 8/22/2008 install NVIDIA_CUDA_SDK_2.02.0811.0240_win32.exe

7:48 PM 8/22/2008 apply syntax highliting. see SDK folder, doc, syntax_highlighting

7:56 PM 8/22/2008 check sample programs can work or not.

Using device 0: GeForce 9500 GT
Input data size           : 1000 x 1000
Convolution kernel size   : 7 x 7
Padded image size         : 1006 x 1006
Aligned padded image size : 1024 x 1024
Allocating memory...
Generating random input data...
Creating FFT plan for 1024 x 1024...
Uploading to GPU and padding convolution kernel and input data...
...initializing padded kernel and data storage with zeroes...
...copying input data and convolution kernel from host to CUDA arrays
...binding CUDA arrays to texture references
...padding convolution kernel
...padding input data array
Transforming convolution kernel...
Running GPU FFT convolution...
GPU time: 37.396652 msecs. //26.740362 MPix/s
Reading back GPU FFT results...
Checking GPU results...
...running reference CPU convolution
...comparing the results
Max delta / CPU value 4.415584E-006
L2 norm: 1.889930E-007
TEST PASSED
Shutting down...

Press ENTER to exit...
=============================================

7:59 PM 8/22/2008 Check sample program can be built and run.

1>------ Build started: Project: histogram256, Configuration: Debug Win32 ------
1>Compiling CUDA file
1>histogram256_SM12.cu
1>tmpxft_00000d4c_00000000-3_histogram256_SM12.cudafe1.gpu
1>tmpxft_00000d4c_00000000-8_histogram256_SM12.cudafe2.gpu
1>tmpxft_00000d4c_00000000-3_histogram256_SM12.cudafe1.cpp
1>tmpxft_00000d4c_00000000-12_histogram256_SM12.ii
1>Compiling CUDA file
1>histogram256_SM11.cu
1>tmpxft_00000078_00000000-3_histogram256_SM11.cudafe1.gpu
1>tmpxft_00000078_00000000-8_histogram256_SM11.cudafe2.gpu
1>tmpxft_00000078_00000000-3_histogram256_SM11.cudafe1.cpp
1>tmpxft_00000078_00000000-12_histogram256_SM11.ii
1>Compiling CUDA file
1>histogram256_SM10.cu
1>tmpxft_00000e6c_00000000-3_histogram256_SM10.cudafe1.gpu
1>tmpxft_00000e6c_00000000-8_histogram256_SM10.cudafe2.gpu
1>tmpxft_00000e6c_00000000-3_histogram256_SM10.cudafe1.cpp
1>tmpxft_00000e6c_00000000-12_histogram256_SM10.ii
1>Compiling...
1>histogram256_gold.cpp
1>Compiling...
1>histogram256.cpp
1>Linking...
1>Embedding manifest...
1>Performing Post-Build Event...
1>Build log was saved at "file://c:\Program Files\NVIDIA Corporation\NVIDIA CUDA SDK\projects\histogram256\Debug\BuildLog.htm"
1>histogram256 - 0 error(s), 0 warning(s)
========== Build: 1 succeeded, 0 failed, 0 up-to-date, 0 skipped ==========

Using device 0: GeForce 9500 GT
Initializing data...
...allocating CPU memory.
...generating input data
...allocating GPU memory and copying input data
Running CPU histogram...
histogramCPU() time : 676.763123 msec // 140.917004 MB/sec
Running GPU histogram using SM10...
histogram256_SM10() time : 91.387901 msec // 1043.545483 MB/sec
TEST PASSED
Running GPU histogram using SM11...
histogram256_SM11() time : 90.132439 msec // 1058.081120 MB/sec
TEST PASSED
Shutting down...

Press ENTER to exit...

=============================================

9:10 PM 8/22/2008 PortAudio

download http://www.portaudio.com/archives/pa_stable_v19_20071207.tar.gz
Extract to C:\PortAudio

See http://www.portaudio.com/trac/wiki/TutorialDir/Compile/Windows
Resister at Steinberg, and Get ASIO SDK.

See C:\portaudio\build\msvc\readme.txt
Download
Platform SDK
     http://www.microsoft.com/msdownload/platformsdk/sdkupdate/psdk-full.htm

DirectX 9.0 SDK Update - (Summer 2003)
Latest known URL
http://www.microsoft.com/downloads/details.aspx?familyid=9216652f-51e0-402e-b7b5-feb68d00f298&displaylang=en
Add DirectX Include and Lib folder to VisualStudio Folder Path.

9:42 PM 8/22/2008 Build PortAudio
C:\portaudio\build\msvc\portaudio.sln
Build Debug, and Release.

9:46 PM 8/22/2008 Build GPU FIR
Add
C:\CUDA\INC, C:\CUDA\INC\CRT, C:\CUDA\LIB
C:\Program Files\NVIDIA Corporation\NVIDIA CUDA SDK\common\inc
C:\Program Files\NVIDIA Corporation\NVIDIA CUDA SDK\common\lib
C:\portaudio\include
to VisualStudio Folder Path.

WaveX05.cu(374) : warning C4003: not enough actual parameters for macro 'CUT_DEVICE_INIT'
Changed to CUT_DEVICE_INIT(ARGC, ARGV).

copy cutil32D.dll to C:\GPUFIR\Programs.

Add C:\GPUFIR\Params\WaveX.ini to Debugging, command argument.

10:11 PM 8/22/2008 What is this??

Run-Time Check Failure #0
"The value of ESP was not properly saved across a function call."

11:26 PM 8/22/2008 It looks like DLL and EXE problem?

6:23 AM 8/23/2008 .... I kept old DLL, for CUDA1.1 .
remove cudart.dll (11/30/2007), cutil32.dll, from C:\GPUFIR\Programs.

6:29 AM 8/23/2008 by change of CUT_DEVICE_INIT()

stream started.
Error when parsing command line argument string.
Using device 0: GeForce 9500 GT

modified to call     CUDA_SAFE_CALL(cudaSetDevice(dev));

6:58 AM 8/23/2008 OK, now I'm running re-builded GPU FIR, on CUDA2.0
CUDA device check should be moved to another function.

Long run test = there are error, stream stops suddenly.

12:02 PM 8/23/2008 Code organized to see how error happen.