@RichardH: roger that.

That notwithstanding, there's one thing more that needs to be done: open the floodgates from Seti WU server by allowing v8 WU in preferences for the project.

Hi all, finally i realized that was a issue caused by Comodo Internet Security 2015.

Marco.

Ah, that makes sense. Thanks for reporting back.

I wonder what AV/security product Brent Norman - Canada uses?

Edit - I assume that taking Comodo out into the back yard and forcefully re-educating it has allowed SETI v8 to run normally?

Yes Richard you assumption it's correct.
May Comodo lock-in Seti@home processes.
I brought it back to the dark side of the force as Lord Palpatine did....

Marco.

---

Is there something different about libfftw3f-3-3-4_x86.dll? The one on my system was created 14 Mar 15 w/ 2259 KB. That's the same size as the one available in the download link.

I s'pose it can't hurt just to replace it anyways, eh?

I'm using my own compiled version of the x86 library (32 bit) libfftw3f-3-3-4_x86.dll.
Cross compiled under Ubuntu with GCC 5.2 and optimized for various simd instructions set and cpu architectures.
The 2259 KiB version was compiled directly by autors of fftw library with MinGW toolchain.

Marco.

---

Would yours function better on an SSE based CPU? And if so, how to get me hands on that?

I'm using my own compiled version of the x86 library (32 bit) libfftw3f-3-3-4_x86.dll.
Cross compiled under Ubuntu with GCC 5.2 and optimized for various simd instructions set and cpu architectures.
The 2259 KiB version was compiled directly by autors of fftw library with MinGW toolchain.

Marco.

Would you share it with others?

Would yours function better on an SSE based CPU? And if so, how to get me hands on that?

Only fftw 3.3.4 x86 for SSE4.2 simd instruction set (the only one available on my Pentium 2117U and Celeron B830) and fftw 3.3.4 x64 in ssse3,avx and avx3 flavours (awaiting for next 3.3.5 version).
Compiled with --enable-float switch (i.e sse2 and "bigger").
I'm in the middle of uploading this four files on one of my Google Drive.

Marco.

---

You are welcome Jord.
I see you catched V8 tasks already.

All looks good.

First output (I cheated and suspended some v7 and AP tasks for the moment), https://setiathome.berkeley.edu/result.php?resultid=4647307288

<core_client_version>7.6.23</core_client_version>
<![CDATA[
<stderr_txt>
Priority of worker thread raised successfully
Priority of process adjusted successfully, below normal priority class used
OpenCL platform detected: Intel(R) Corporation
OpenCL platform detected: Advanced Micro Devices, Inc.
BOINC assigns device 0
0 slot of 64 used for this instance
Info: BOINC provided OpenCL device ID used
Info: CPU affinity mask used: 1

Build features: SETI8	Non-graphics	OpenCL	USE_OPENCL_HD5xxx	OCL_ZERO_COPY	OCL_CHIRP3	FFTW	AMD specific	USE_SSE2	x86	
     CPUID:        Intel(R) Core(TM) i5-2500K CPU @ 3.30GHz 

     Cache: L1=64K L2=256K

CPU features: FPU TSC PAE CMPXCHG8B APIC SYSENTER MTRR CMOV/CCMP MMX FXSAVE/FXRSTOR SSE SSE2 HT SSE3 SSSE3 SSE4.1 SSE4.2 AVX 
OpenCL-kernels filename : MultiBeam_Kernels_r3299.cl 
INFO: can't open binary kernel file: C:\ProgramData\BOINC/projects/setiathome.berkeley.edu\MultiBeam_Kernels_r3299.clHD5_Pitcairn.bin_V7_19125VM, continue with recompile...
Info : Building Program (binary, clBuildProgram):main kernels: OK code 0
INFO: binary kernel file created
WARNING: can't open binary kernel file for oclFFT plan: C:\ProgramData\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Pitcairn_524288_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r3299.bin_19125VM, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\ProgramData\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Pitcairn_8_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r3299.bin_19125VM, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\ProgramData\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Pitcairn_16_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r3299.bin_19125VM, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\ProgramData\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Pitcairn_32_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r3299.bin_19125VM, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\ProgramData\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Pitcairn_64_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r3299.bin_19125VM, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\ProgramData\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Pitcairn_128_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r3299.bin_19125VM, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\ProgramData\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Pitcairn_256_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r3299.bin_19125VM, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\ProgramData\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Pitcairn_512_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r3299.bin_19125VM, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\ProgramData\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Pitcairn_1024_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r3299.bin_19125VM, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\ProgramData\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Pitcairn_2048_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r3299.bin_19125VM, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\ProgramData\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Pitcairn_4096_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r3299.bin_19125VM, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\ProgramData\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Pitcairn_8192_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r3299.bin_19125VM, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\ProgramData\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Pitcairn_16384_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r3299.bin_19125VM, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\ProgramData\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Pitcairn_32768_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r3299.bin_19125VM, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\ProgramData\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Pitcairn_65536_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r3299.bin_19125VM, continue with recompile...
WARNING: can't open binary kernel file for oclFFT plan: C:\ProgramData\BOINC/projects/setiathome.berkeley.edu\MB_clFFTplan_Pitcairn_131072_gr64_lr16_wg256_tw0_ls1024_bn16_cw16_r3299.bin_19125VM, continue with recompile...
ar=0.364688  NumCfft=213351  NumGauss=1296555392  NumPulse=226326848360  NumTriplet=452716804136
Currently allocated 209 MB for GPU buffers
In v_BaseLineSmooth: NumDataPoints=1048576, BoxCarLength=8192, NumPointsInChunk=32768

Windows optimized setiathome_v8 application
Based on Intel, Core 2-optimized v8-nographics V5.13 by Alex Kan
SSE2xj Win32 Build 3299 , Ported by : Raistmer, JDWhale

SETI8 update by Raistmer

OpenCL version by Raistmer, r3299

AMD HD5 version by Raistmer

Number of OpenCL platforms:				 2


 OpenCL Platform Name:					 Intel(R) OpenCL
Number of devices:				 0


 OpenCL Platform Name:					 AMD Accelerated Parallel Processing
Number of devices:				 1
  Max compute units:				 20
  Max work group size:				 256
  Max clock frequency:				 1000Mhz
  Max memory allocation:			 1408867653
  Cache type:					 Read/Write
  Cache line size:				 64
  Cache size:					 16384
  Global memory size:				 2147483648
  Constant buffer size:				 65536
  Max number of constant args:			 8
  Local memory type:				 Scratchpad
  Local memory size:				 32768
  Queue properties:				 
    Out-of-Order:				 No
  Name:						 Pitcairn
  Vendor:					 Advanced Micro Devices, Inc.
  Driver version:				 1912.5 (VM)
  Version:					 OpenCL 1.2 AMD-APP (1912.5)
  Extensions:					 cl_khr_fp64 cl_amd_fp64 cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_3d_image_writes cl_khr_byte_addressable_store cl_khr_gl_sharing cl_ext_atomic_counters_32 cl_amd_device_attribute_query cl_amd_vec3 cl_amd_printf cl_amd_media_ops cl_amd_media_ops2 cl_amd_popcnt cl_khr_d3d10_sharing cl_khr_d3d11_sharing cl_khr_dx9_media_sharing cl_khr_image2d_from_buffer cl_khr_spir cl_khr_gl_event 


Work Unit Info:
...............
Credit multiplier is :  2.85
WU true angle range is :  0.364688
Used GPU device parameters are:
	Number of compute units: 20
	Single buffer allocation size: 128MB
	Total device global memory: 2048MB
	max WG size: 256
	local mem type: Real
	LotOfMem path: no
period_iterations_num=40
Spike: peak=24.24861, time=60.4, d_freq=1419492342.18, chirp=7.6483, fft_len=128k
Spike: peak=24.49896, time=60.4, d_freq=1419490222.18, chirp=9.6798, fft_len=128k
Spike: peak=24.35214, time=60.4, d_freq=1419490222.18, chirp=9.6835, fft_len=128k
Pulse: peak=3.732793, time=29.47, period=1.314, d_freq=1419493764.01, score=1.011, chirp=19.839, fft_len=128 
Pulse: peak=3.734237, time=29.47, period=1.314, d_freq=1419493763.99, score=1.012, chirp=22.427, fft_len=128 
Pulse: peak=6.521638, time=51.57, period=2.825, d_freq=1419491412.39, score=1.018, chirp=-22.427, fft_len=128 
Pulse: peak=6.68015, time=51.57, period=2.825, d_freq=1419491399.75, score=1.043, chirp=-24.152, fft_len=128 
Triplet: peak=10.59272, time=34.08, period=3.015, d_freq=1419495927.42, chirp=25.23, fft_len=512 
Triplet: peak=11.02193, time=34.08, period=3.015, d_freq=1419495926.71, chirp=25.769, fft_len=512 
Triplet: peak=11.38824, time=34.08, period=3.015, d_freq=1419495926.03, chirp=26.309, fft_len=512 
Triplet: peak=10.97368, time=34.08, period=3.015, d_freq=1419495929.68, chirp=26.416, fft_len=512 
Triplet: peak=10.65, time=34.08, period=3.015, d_freq=1419495929, chirp=26.956, fft_len=512 
Triplet: peak=9.757073, time=104.4, period=1.091, d_freq=1419488171.44, chirp=-79.358, fft_len=64 
Pulse: peak=10.31565, time=51.57, period=4.253, d_freq=1419491007.12, score=1.054, chirp=-87.983, fft_len=128 
Pulse: peak=11.27053, time=51.57, period=4.253, d_freq=1419490994.42, score=1.151, chirp=-89.709, fft_len=128 
Gaussian: peak=2.928084, mean=0.4939085, ChiSq=1.373683, time=79.69, d_freq=1419491523.97,
	score=0.6865219, null_hyp=2.274402, chirp=-89.799, fft_len=16k
Pulse: peak=11.06721, time=51.57, period=4.253, d_freq=1419490981.78, score=1.13, chirp=-91.433, fft_len=128 
Pulse: peak=9.896175, time=51.57, period=4.253, d_freq=1419491000.9, score=1.011, chirp=-94.021, fft_len=128 
Pulse: peak=10.43157, time=51.57, period=4.253, d_freq=1419490988.21, score=1.065, chirp=-95.747, fft_len=128 

Best spike: peak=24.49896, time=60.4, d_freq=1419490222.18, chirp=9.6798, fft_len=128k
Best autocorr: peak=17.07711, time=46.98, delay=4.7897, d_freq=1419493472.98, chirp=27.365, fft_len=128k
Best gaussian: peak=2.928084, mean=0.4939085, ChiSq=1.373683, time=79.69, d_freq=1419491523.97,
	score=0.6865219, null_hyp=2.274402, chirp=-89.799, fft_len=16k
Best pulse: peak=11.27053, time=51.57, period=4.253, d_freq=1419490994.42, score=1.151, chirp=-89.709, fft_len=128 
Best triplet: peak=11.38824, time=34.08, period=3.015, d_freq=1419495926.03, chirp=26.309, fft_len=512 


Flopcounter: 22698736825307.012000

Spike count:    3
Autocorr count: 0
Pulse count:    9
Triplet count:  6
Gaussian count: 1
Wallclock time elapsed since last restart: 982.5 seconds

class Gaussian_transfer_not_needed:		total=118664,	N=118664,	<>=1,	min=1	max=1
class Gaussian_transfer_needed:		total=16,	N=16,	<>=1,	min=1	max=1


class Gaussian_skip1_no_peak:		total=0,	N=0,	<>=0,	min=0	max=0
class Gaussian_skip2_bad_group_peak:		total=0,	N=0,	<>=0,	min=0	max=0
class Gaussian_skip3_too_weak_peak:		total=0,	N=0,	<>=0,	min=0	max=0
class Gaussian_skip4_too_big_ChiSq:		total=0,	N=52,	<>=0,	min=0	max=0
class Gaussian_skip6_low_power:		total=30,	N=52,	<>=0.57692308,	min=0	max=1


class Gaussian_new_best:		total=29,	N=29,	<>=1,	min=1	max=1
class Gaussian_report:		total=1,	N=1,	<>=1,	min=1	max=1
class Gaussian_miss:		total=23,	N=23,	<>=1,	min=1	max=1


class PC_triplet_find_hit:		total=29389,	N=29389,	<>=1,	min=1	max=1
class PC_triplet_find_miss:		total=254,	N=254,	<>=1,	min=1	max=1


class PC_pulse_find_hit:		total=14804,	N=14804,	<>=1,	min=1	max=1
class PC_pulse_find_miss:		total=15,	N=15,	<>=1,	min=1	max=1
class PC_pulse_find_early_miss:		total=13,	N=13,	<>=1,	min=1	max=1
class PC_pulse_find_2CPU:		total=1,	N=1,	<>=1,	min=1	max=1


class PoT_transfer_not_needed:		total=29376,	N=29376,	<>=1,	min=1	max=1
class PoT_transfer_needed:		total=268,	N=268,	<>=1,	min=1	max=1

GPU device sync requested...  ...GPU device synched
23:36:39 (3028): called boinc_finish(0)

</stderr_txt>
]]>

I understand that the recompiling of the oclFFT only happens once, yes?

Oh, and temperatures look good too.
With HD5_r2929 v7 I'd run at 58-62C for MBs, up to 65C for _r2742 APs.
The two that ran thus far do 60-61C, nothing more. So perfectly in line.

---

Yeah, It's been a few years, but transition periods do take a while to feel for the right way to head. That's possibly why some of us that have been here longer appear less panicked than some might expect for such a sudden change. We know that the shift takes time, and things have to shake out.

Yeah Jason,
Slow, steady, and incremental...after all, this is a Scientific Experiment.
Cheers from NZ, and keep up the good work!
Stephen W

Link at my fftw 3.3.4 versions....

https://drive.google.com/open?id=0B9iU4E_jpim0X3ZyQmo3dUUxZFE

The three version named avx,avx2,ssse3 must be renamed to libfftw3f-3-3-4_x64.
Erase any old .wisdom file and standard fftw dll library.
The avx2 version was compiled with --enable-fma switch (e.g Haswell fma3 and upper).
Personally i used optimized libfftw3f-3-3-4_x86 for OpenCL gpu apps too.

Marco.

---

Link at my fftw 3.3.4 versions....

https://drive.google.com/open?id=0B9iU4E_jpim0X3ZyQmo3dUUxZFE

The three version named avx,avx2,ssse3 must be renamed to libfftw3f-3-3-4_x64.
Erase any old .wisdom file and standard fftw dll library.
The avx2 version was compiled with --enable-fma switch (e.g Haswell fma3 and upper).
Personally i used optimized libfftw3f-3-3-4_x86 for OpenCL gpu apps too.

Marco.

your link requires permission granting for access.

Really? I could save a lot of Watthours just dropping SETI and BOINC. WTH is up with this new app?! I have followed all of the instructions I have found.

I need a functional app_info and a functional app_config.

Any help is appreciated.

---

Really? I could save a lot of Watthours just dropping SETI and BOINC. WTH is up with this new app?! I have followed all of the instructions I have found.

I need a functional app_info and a functional app_config.

Any help is appreciated.

On the other hand, screw it. I shouldn't have to understand anything about code, app files or jack shit to volunteer for this work.

I'll check back in a few weeks, maybe....

---

Really? I could save a lot of Watthours just dropping SETI and BOINC. WTH is up with this new app?! I have followed all of the instructions I have found.

I need a functional app_info and a functional app_config.

Any help is appreciated.

On the other hand, screw it. I shouldn't have to understand anything about code, app files or jack shit to volunteer for this work.

I'll check back in a few weeks, maybe....

Perhaps you should not overestimate own capabilities that's all.
There is path for fully automatic app and work deployment, there is path for tuned up to the limits apps. And one should estimate own caps what path to take.
It's quite similar as burning own hardware because of excessive OCing and then blame vendor...

I need a functional app_info and a functional app_config.
Any help is appreciated.

For CPU work, the info is present, earlier in this chain, that I used to get that running. For GPU work, there is no app yet. If you want to do the CPU part it's very easy, following Richard's message to paste this new segment into your App_Info.xml:

<app>
<name>setiathome_v8</name>
</app>
<file_info>
<name>setiathome_8.00_windows_intelx86.exe</name>
<executable/>
</file_info>
<file_info>
<name>libfftw3f-3-3-4_x86.dll</name>
<executable/>
</file_info>
<app_version>
<app_name>setiathome_v8</app_name>
<version_num>800</version_num>
<file_ref>
<file_name>setiathome_8.00_windows_intelx86.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>libfftw3f-3-3-4_x86.dll</file_name>
</file_ref>
</app_version>

Then be sure to download the new executable:
http://boinc2.ssl.berkeley.edu/sah/download_fanout/setiathome_8.00_windows_intelx86.exe
and put it in in the project directory.
Stop BOINC and restart. That's it.

On the other hand, screw it. I shouldn't have to understand anything about code, app files or jack shit to volunteer for this work.

But I thought I remembered you were here to learn as well? Isn't that some of the fun?

---

I see that Raistmer (thank you as always) linked to fresh v8 MB apps including an NV OpenCL. Before I go tinkering to get it working, is there actually any work available for it currently?

Just don't want to install it untested and then in a worst case scenario trash hundreds of work units while I'm off working tomorrow. :^p

---

I see that Raistmer (thank you as always) linked to fresh v8 MB apps including an NV OpenCL.

Haven't been able to get to it, as the Google drive share requires a password.

Before I go tinkering to get it working, is there actually any work available for it currently?

That would be the interesting question. Perhaps someone that's involved with Beta would know ...

---

Thanks ageless very handy and easy to edit many thanks

---

Link at my fftw 3.3.4 versions....

https://drive.google.com/open?id=0B9iU4E_jpim0X3ZyQmo3dUUxZFE

The three version named avx,avx2,ssse3 must be renamed to libfftw3f-3-3-4_x64.
Erase any old .wisdom file and standard fftw dll library.
The avx2 version was compiled with --enable-fma switch (e.g Haswell fma3 and upper).
Personally i used optimized libfftw3f-3-3-4_x86 for OpenCL gpu apps too.

Marco.

your link requires permission granting for access.

Try this...


https://drive.google.com/folderview?id=0B9iU4E_jpim0X3ZyQmo3dUUxZFE&usp=sharing

---

I see that Raistmer (thank you as always) linked to fresh v8 MB apps including an NV OpenCL.

Haven't been able to get to it, as the Google drive share requires a password.

Before I go tinkering to get it working, is there actually any work available for it currently?

That would be the interesting question. Perhaps someone that's involved with Beta would know ...

1) Links (and apps)were updated and posted in http://setiweb.ssl.berkeley.edu/beta/forum_thread.php?id=2266&postid=55600
2) It's no way google drive, it's dropbox storage.And if it gives 404 then file deleted. And deleted it because beta became outdated and replaced to another beta.
3) And most important part: it's OPEN BETA. That is, mainly to run on beta site to check if apps work OK on wide set of different hosts or some issues arise. So consumer approach to these binaries unacceptable. I have no objections that they will be used on main too but only by persons who knows what [s]he does and how to revert/fix/properly report in case something goes wrong. So I strongly suggest to all who wanna use it on main first join (if not already) to SETI beta project, crunch few tasks there with wanted app and then reproduce working setup from beta to main project. Why running on beta important: beta results don't get deleted after few days as results on main do. So they can be referred later to analyse issue in the case issue appeared.