Anything relating to AstroPulse tasks

Message boards : Number crunching : Anything relating to AstroPulse tasks
Message board moderation

To post messages, you must log in.

Previous · 1 . . . 71 · 72 · 73 · 74 · 75 · 76 · 77 . . . 120 · Next

AuthorMessage
Profile Wiggo
Avatar

Send message
Joined: 24 Jan 00
Posts: 34744
Credit: 261,360,520
RAC: 489
Australia
Message 1874620 - Posted: 23 Jun 2017, 11:10:26 UTC

33 so far out of this batch.

Cheers.
ID: 1874620 · Report as offensive
Profile Wiggo
Avatar

Send message
Joined: 24 Jan 00
Posts: 34744
Credit: 261,360,520
RAC: 489
Australia
Message 1874632 - Posted: 23 Jun 2017, 12:17:59 UTC - in response to Message 1874630.  

33 so far out of this batch.

Cheers.

No AP at all this batch.
Zero, zilch, zip, nil, nought, nothing.

41 now.

Cheers.
ID: 1874632 · Report as offensive
Profile Wiggo
Avatar

Send message
Joined: 24 Jan 00
Posts: 34744
Credit: 261,360,520
RAC: 489
Australia
Message 1874708 - Posted: 23 Jun 2017, 20:10:20 UTC - in response to Message 1874637.  

33 so far out of this batch.

Cheers.

No AP at all this batch.
Zero, zilch, zip, nil, nought, nothing.

41 now.

Cheers.

Yeah, rub it in :-)

51 have now made it my way.

Cheers.
ID: 1874708 · Report as offensive
Profile Mike Special Project $75 donor
Volunteer tester
Avatar

Send message
Joined: 17 Feb 01
Posts: 34253
Credit: 79,922,639
RAC: 80
Germany
Message 1874725 - Posted: 23 Jun 2017, 21:29:39 UTC

31 so far.


With each crime and every kindness we birth our future.
ID: 1874725 · Report as offensive
Profile Karsten Vinding
Volunteer tester

Send message
Joined: 18 May 99
Posts: 239
Credit: 25,201,931
RAC: 11
Denmark
Message 1874733 - Posted: 23 Jun 2017, 21:55:38 UTC - in response to Message 1874503.  

Invalid from my system.

https://setiathome.berkeley.edu/show_host_detail.php?hostid=862199

I'm seing many AP invalids from my GPU's, almost every single AP crunched on my GPU's are invalid, or validation inconclusive..

Warning, long post ahead....

Host 1 (7377999)

<core_client_version>7.6.33</core_client_version>
<![CDATA[
<stderr_txt>

Build features: Non-graphics BLANKIT TWINDECHIRP USE_LRINT FFTW USE_INCREASED_PRECISION USE_SSE2 x64
CPUID: Intel(R) Core(TM) i5-4570 CPU @ 3.20GHz

Cache: L1=64K L2=256K

CPU features: FPU TSC PAE CMPXCHG8B APIC SYSENTER MTRR CMOV/CCMP MMX FXSAVE/FXRSTOR SSE SSE2 HT SSE3 SSSE3 FMA3 SSE4.1 SSE4.2 AVX
AstroPulse v7 Windows x64 rev 2603, V7 match, by Raistmer with support of Lunatics.kwsn.net team.
by Lunatics team. state.fold_buf_size_short=65536; state.fold_buf_size_long=262144

single pulses: 0
repetitive pulses: 0
percent blanked: 0.00

class T_remove_radar: total=6.12e+008, N=1, <>=6.12e+008, min=6.12e+008, max=6.12e+008
class T_main_loop_L1: total=5.62e+013, N=111, <>=5.06e+011, min=4.54e+011, max=5.93e+011
class T_FFT_forward: total=1.10e+012, N=1817736, <>=6.03e+005, min=4.30e+005, max=1.90e+008
class T_remove_radar_randomize: total=2.88e+009, N=1817736, <>=1.58e+003, min=5.92e+002, max=4.99e+007
class T_build_chirp_table: total=7.12e+010, N=888, <>=8.01e+007, min=6.95e+007, max=2.78e+008
class T_dechirp: total=9.67e+012, N=58167552, <>=1.66e+005, min=1.80e+001, max=2.17e+008
class T_FFT_inverse: total=2.07e+013, N=58167552, <>=3.56e+005, min=2.92e+005, max=5.18e+008
class T_ffa: total=1.30e+013, N=1998, <>=6.49e+009, min=2.25e+009, max=5.66e+010

FFA blocks counters:
class T_FFA_fetch: total=1.08e+013, N=121016862, <>=8.89e+004, min=3.42e+004, max=1.59e+008
class T_FFA_tt_build: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_FFA_compare: total=1.08e+012, N=5115545778, <>=2.10e+002, min=1.80e+001, max=1.46e+008
class T_FFA_coadd: total=5.92e+011, N=5115545778, <>=1.15e+002, min=1.80e+001, max=1.37e+008
class T_FFA_stride_add: total=5.89e+010, N=1036948902, <>=5.60e+001, min=1.80e+001, max=1.26e+008
USE_INCREASED_PRECISION SMALL_CHIRP_TABLE BLANKIT TWINDECHIRP USE_LRINT
rev 2603
07:03:59 (1908): called boinc_finish(0)

</stderr_txt>
]]>

Host 2 (862199) (My host)

<core_client_version>7.6.33</core_client_version>
<![CDATA[
<stderr_txt>
Running on device number: 1
Priority of worker thread raised successfully
Priority of process adjusted successfully, below normal priority class used
OpenCL platform detected: Advanced Micro Devices, Inc.
BOINC assigns device 1
Info: BOINC provided OpenCL device ID used
Used GPU device parameters are:
Number of compute units: 36
Single buffer allocation size: 256MB
Total device global memory: 3072MB
max WG size: 256
local mem type: Real
-unroll default value used: 18
-ffa_block default value used: 9216
-ffa_block_fetch default value used: 4608

Build features: Non-graphics BLANKIT OpenCL TWIN_FFA OCL_ZERO_COPY COMBINED_DECHIRP_KERNEL FFTW USE_INCREASED_PRECISION USE_SSE2 x86
CPUID: AMD FX(tm)-8150 Eight-Core Processor

Cache: L1=64K L2=2048K

CPU features: FPU TSC PAE CMPXCHG8B APIC SYSENTER MTRR CMOV/CCMP MMX FXSAVE/FXRSTOR SSE SSE2 HT SSE3 SSSE3 SSE4.1 SSE4.2 AVX SSE4A XOP FMA4
AstroPulse v7 Windows x86 rev 2742, V7 match, by Raistmer with support of Lunatics.kwsn.net team. SSE2

OpenCL version by Raistmer

oclFFT fix for ATI GPUs by Urs Echternacht
ffa threshold mods by Joe Segur
SSE3 dechirping by JDWhale
Combined dechirp kernel by Frizz
Number of OpenCL platforms: 1


OpenCL Platform Name: AMD Accelerated Parallel Processing
Number of devices: 2
Max compute units: 10
Max work group size: 256
Max clock frequency: 1000Mhz
Max memory allocation: 603979776
Cache type: Read/Write
Cache line size: 64
Cache size: 16384
Global memory size: 1073741824
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: Capeverde
Vendor: Advanced Micro Devices, Inc.
Driver version: 2348.4
Version: OpenCL 1.2 AMD-APP (2348.4)
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_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 cl_amd_liquid_flash
Max compute units: 36
Max work group size: 256
Max clock frequency: 1288Mhz
Max memory allocation: 3221225472
Cache type: Read/Write
Cache line size: 64
Cache size: 16384
Global memory size: 3221225472
Constant buffer size: 3221225472
Max number of constant args: 8
Local memory type: Scratchpad
Local memory size: 32768
Queue properties:
Out-of-Order: No
Name: Ellesmere
Vendor: Advanced Micro Devices, Inc.
Driver version: 2348.4
Version: OpenCL 1.2 AMD-APP (2348.4)
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_fp16 cl_khr_gl_sharing 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 cl_amd_liquid_flash


state.fold_buf_size_short=65536; state.fold_buf_size_long=262144

single pulses: 2
repetitive pulses: 0
percent blanked: 0.00
Single pulse: peak_power=33.6619 dm=-2717 fft_num=6078464 peak_bin=6079078 scale=1
Single pulse: peak_power=38.2188 dm=-2720 fft_num=6078464 peak_bin=6079076 scale=2

class T_remove_radar: total=2.29e+009, N=1, <>=2.29e+009, min=2.29e+009, max=2.29e+009
class T_main_loop_L1: total=5.09e+012, N=111, <>=4.58e+010, min=4.51e+010, max=5.05e+010
class T_FFT_forward: total=5.57e+009, N=101232, <>=5.50e+004, min=3.40e+004, max=3.34e+006
class T_remove_radar_randomize: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_build_chirp_table: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_DataWrite: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_DataWrite_ns: total=0, N=0, <>=0, min=0 max=0
class T_oclReadBuf: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_ChirpWrite: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_ChirpWrite_ns: total=0, N=0, <>=0, min=0 max=0
class T_dechirp: total=6.54e+009, N=101232, <>=6.46e+004, min=4.68e+004, max=2.02e+007
class Dechirp_ns: total=0, N=0, <>=0, min=0 max=0
class Half_ns: total=0, N=0, <>=0, min=0 max=0
class T_PC_single_pulse_kernel_FFA_update: total=3.99e+012, N=101232, <>=3.94e+007, min=3.65e+007, max=3.52e+009
class PC_ns: total=0, N=0, <>=0, min=0 max=0
class T_oclReadBuf: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_oclWriteBuf: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_FFT_inverse: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_ffa: total=1.05e+012, N=999, <>=1.05e+009, min=5.08e+008, max=6.20e+009

FFA blocks counters:
class T_FFA_fetch: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_FFA_tt_build: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_FFA_compare: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_FFA_coadd: total=4.22e+008, N=53613, <>=7.86e+003, min=4.71e+003, max=8.55e+005
class T_FFA_stride_add: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_GPU_buffer_read_backs: total=101, N=101, <>=1, min=1 max=1
TWIN_FFA OCL_ZERO_COPY USE_OPENCL OPENCL_WRITE USE_INCREASED_PRECISION SMALL_CHIRP_TABLE COMBINED_DECHIRP_KERNEL BLANKIT
rev 2742
GPU device sync requested... ...GPU device synched
21:25:10 (10732): called boinc_finish(0)

</stderr_txt>
]]>

Host 3 (7443807)

<core_client_version>7.6.33</core_client_version>
<![CDATA[
<stderr_txt>
Running on device number: 0
Priority of worker thread raised successfully
Priority of process adjusted successfully, below normal priority class used
OpenCL platform detected: Advanced Micro Devices, Inc.
BOINC assigns device 0
Info: BOINC provided OpenCL device ID used
Used GPU device parameters are:
Number of compute units: 6
Single buffer allocation size: 256MB
Total device global memory: 2047MB
max WG size: 256
local mem type: Real
-unroll default value used: 6
-ffa_block default value used: 1536
-ffa_block_fetch default value used: 768

Build features: Non-graphics BLANKIT OpenCL TWIN_FFA OCL_ZERO_COPY COMBINED_DECHIRP_KERNEL FFTW USE_INCREASED_PRECISION USE_SSE2 x86
CPUID: AMD FX-7500 Radeon R7, 10 Compute Cores 4C+6G

Cache: L1=64K L2=2048K

CPU features: FPU TSC PAE CMPXCHG8B APIC SYSENTER MTRR CMOV/CCMP MMX FXSAVE/FXRSTOR SSE SSE2 HT SSE3 SSSE3 FMA3 SSE4.1 SSE4.2 AVX SSE4A XOP FMA4
AstroPulse v7 Windows x86 rev 2742, V7 match, by Raistmer with support of Lunatics.kwsn.net team. SSE2

OpenCL version by Raistmer

oclFFT fix for ATI GPUs by Urs Echternacht
ffa threshold mods by Joe Segur
SSE3 dechirping by JDWhale
Combined dechirp kernel by Frizz
Number of OpenCL platforms: 1


OpenCL Platform Name: AMD Accelerated Parallel Processing
Number of devices: 2
Max compute units: 6
Max work group size: 256
Max clock frequency: 553Mhz
Max memory allocation: 603193344
Cache type: Read/Write
Cache line size: 64
Cache size: 16384
Global memory size: 2146959360
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: Spectre
Vendor: Advanced Micro Devices, Inc.
Driver version: 1411.4 (VM)
Version: OpenCL 1.2 AMD-APP (1411.4)
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_dx9_media_sharing cl_khr_image2d_from_buffer cl_khr_spir
Max compute units: 6
Max work group size: 256
Max clock frequency: 553Mhz
Max memory allocation: 1073741824
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: Oland
Vendor: Advanced Micro Devices, Inc.
Driver version: 1411.4 (VM)
Version: OpenCL 1.2 AMD-APP (1411.4)
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_dx9_media_sharing cl_khr_image2d_from_buffer cl_khr_spir


state.fold_buf_size_short=65536; state.fold_buf_size_long=262144

single pulses: 0
repetitive pulses: 0
percent blanked: 0.00

class T_remove_radar: total=2.49e+009, N=1, <>=2.49e+009, min=2.49e+009, max=2.49e+009
class T_main_loop_L1: total=5.20e+013, N=111, <>=4.68e+011, min=4.03e+011, max=5.67e+011
class T_FFT_forward: total=1.32e+010, N=303696, <>=4.34e+004, min=1.70e+004, max=7.23e+006
class T_remove_radar_randomize: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_build_chirp_table: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_DataWrite: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_DataWrite_ns: total=0, N=0, <>=0, min=0 max=0
class T_oclReadBuf: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_ChirpWrite: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_ChirpWrite_ns: total=0, N=0, <>=0, min=0 max=0
class T_dechirp: total=1.88e+010, N=303696, <>=6.20e+004, min=2.52e+004, max=5.75e+006
class Dechirp_ns: total=0, N=0, <>=0, min=0 max=0
class Half_ns: total=0, N=0, <>=0, min=0 max=0
class T_PC_single_pulse_kernel_FFA_update: total=4.55e+013, N=303696, <>=1.50e+008, min=9.45e+007, max=5.11e+008
class PC_ns: total=0, N=0, <>=0, min=0 max=0
class T_oclReadBuf: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_oclWriteBuf: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_FFT_inverse: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_ffa: total=6.38e+012, N=999, <>=6.38e+009, min=1.66e+009, max=5.41e+010

FFA blocks counters:
class T_FFA_fetch: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_FFA_tt_build: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_FFA_compare: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_FFA_coadd: total=4.49e+009, N=318459, <>=1.41e+004, min=3.44e+003, max=1.93e+007
class T_FFA_stride_add: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_GPU_buffer_read_backs: total=0, N=0, <>=0, min=0 max=0
TWIN_FFA OCL_ZERO_COPY USE_OPENCL OPENCL_WRITE USE_INCREASED_PRECISION SMALL_CHIRP_TABLE COMBINED_DECHIRP_KERNEL BLANKIT
rev 2742
GPU device sync requested... ...GPU device synched
09:58:11 (24204): called boinc_finish(0)

</stderr_txt>
]]>

Host 1 and 3 validated against each other.
ID: 1874733 · Report as offensive
Profile Wiggo
Avatar

Send message
Joined: 24 Jan 00
Posts: 34744
Credit: 261,360,520
RAC: 489
Australia
Message 1874741 - Posted: 23 Jun 2017, 22:17:28 UTC

67 of them now.

Cheers.
ID: 1874741 · Report as offensive
Profile Tom M
Volunteer tester

Send message
Joined: 28 Nov 02
Posts: 5124
Credit: 276,046,078
RAC: 462
Message 1874748 - Posted: 23 Jun 2017, 22:37:22 UTC - in response to Message 1874733.  

Invalid from my system.

https://setiathome.berkeley.edu/show_host_detail.php?hostid=862199

I'm seing many AP invalids from my GPU's, almost every single AP crunched on my GPU's are invalid, or validation inconclusive..

Warning, long post ahead....


Are you using the Beta6 Lunatics distro?

Is it possible that your ATI AP app isn't the "current" lunatics version?

How hot is your GPU running?

Don't know, just scratching my head.

HTH,
Tom
A proud member of the OFA (Old Farts Association).
ID: 1874748 · Report as offensive
Profile Karsten Vinding
Volunteer tester

Send message
Joined: 18 May 99
Posts: 239
Credit: 25,201,931
RAC: 11
Denmark
Message 1874760 - Posted: 23 Jun 2017, 23:49:46 UTC - in response to Message 1874748.  
Last modified: 23 Jun 2017, 23:55:56 UTC

I'm running the Beta 6 lunatics version.

Both my GPU's are running at about 70 degress C, the fan profiles are set to maintain that temperature.

It seems that the WU's crunched on my R7770 (device 0) get validated ( I just got one validated now "https://setiathome.berkeley.edu/workunit.php?wuid=2578079182"), and that the ones crunched on my RX480 (device 1) are invalid.

Both GPU's never produce a single invalid WU running MB WU's. I don't OC, or do anything special.
ID: 1874760 · Report as offensive
Profile Wiggo
Avatar

Send message
Joined: 24 Jan 00
Posts: 34744
Credit: 261,360,520
RAC: 489
Australia
Message 1874762 - Posted: 24 Jun 2017, 0:01:23 UTC

Sorry, but I can't offer you any help there Karsten as I'm a Nvidia user.

73 of them now.

Cheers.
ID: 1874762 · Report as offensive
Profile Brent Norman Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester

Send message
Joined: 1 Dec 99
Posts: 2786
Credit: 685,657,289
RAC: 835
Canada
Message 1874763 - Posted: 24 Jun 2017, 0:05:27 UTC - in response to Message 1874760.  

Karsten, I would worry too much at the moment. You only have 1 invalid task.

If it continues then look at it further. I will note the one card has 50% the memory of the other, so if you are running multiple tasks you may run out of mem.
ID: 1874763 · Report as offensive
Profile Karsten Vinding
Volunteer tester

Send message
Joined: 18 May 99
Posts: 239
Credit: 25,201,931
RAC: 11
Denmark
Message 1874764 - Posted: 24 Jun 2017, 0:07:18 UTC - in response to Message 1874762.  

Thats OK Wiggo.

Perhaps someone else has an idea.

If I don't find an answer I'll probably disable AP WU's for my GPU's. I don't like producing invalid results.

I was hoping Raistmer would have something to say, he knows the innards of the apps.
ID: 1874764 · Report as offensive
Profile Karsten Vinding
Volunteer tester

Send message
Joined: 18 May 99
Posts: 239
Credit: 25,201,931
RAC: 11
Denmark
Message 1874766 - Posted: 24 Jun 2017, 0:12:53 UTC - in response to Message 1874763.  

Thanks for you answer, Brent.

Sadly this is not the only invalid I have had. In the last week I have crunched about 20 AP WU's with my GPU's, and about 4 out of 5 have been invalids.

Something is wrong, and I'm wondering what it is.
ID: 1874766 · Report as offensive
woohoo
Volunteer tester

Send message
Joined: 30 Oct 13
Posts: 972
Credit: 165,671,404
RAC: 5
United States
Message 1874779 - Posted: 24 Jun 2017, 1:14:03 UTC - in response to Message 1874766.  

i think for some newer amd cards all drivers after 15.12 produce invalid ap results
ID: 1874779 · Report as offensive
Profile Wiggo
Avatar

Send message
Joined: 24 Jan 00
Posts: 34744
Credit: 261,360,520
RAC: 489
Australia
Message 1874811 - Posted: 24 Jun 2017, 6:19:13 UTC

122 of them now out of this batch so far.

Cheers.
ID: 1874811 · Report as offensive
Profile Karsten Vinding
Volunteer tester

Send message
Joined: 18 May 99
Posts: 239
Credit: 25,201,931
RAC: 11
Denmark
Message 1874817 - Posted: 24 Jun 2017, 7:23:41 UTC - in response to Message 1874779.  

Do you have any more info on this?

15.12 is 1½ years old drivers.

I would think this would have been fixed by now, either by AMD or Lunatics?
ID: 1874817 · Report as offensive
woohoo
Volunteer tester

Send message
Joined: 30 Oct 13
Posts: 972
Credit: 165,671,404
RAC: 5
United States
Message 1874822 - Posted: 24 Jun 2017, 8:52:43 UTC - in response to Message 1874817.  

dirk posted something about that in the Radeon Software Crimson thread.

in an ideal world, one should be able to both mb/ap apps as well as multiple work units/gpu without producing invalids. the last time i was able to run multiple wu(s)/gpu without producing invalids was driver 14.4, but that driver is not as fast as the newer drivers. 14.4 works with my 290x/295x2 but not my 390x/radeon pro duo. i had similar problems on einstein as well.

so now i'm using a driver from this year but i only run one wu per gpu and i don't run ap at all. but i only speak of my own cards; cards less expensive than mine(like the 280x) don't have the same problem. and i don't have anything new like a rx480 so i can't speak to that either.
ID: 1874822 · Report as offensive
Profile Wiggo
Avatar

Send message
Joined: 24 Jan 00
Posts: 34744
Credit: 261,360,520
RAC: 489
Australia
Message 1874836 - Posted: 24 Jun 2017, 11:01:01 UTC

Up to 143 now.

Cheers.
ID: 1874836 · Report as offensive
Profile HAL9000
Volunteer tester
Avatar

Send message
Joined: 11 Sep 99
Posts: 6534
Credit: 196,805,888
RAC: 57
United States
Message 1874887 - Posted: 24 Jun 2017, 17:01:14 UTC - in response to Message 1874822.  

dirk posted something about that in the Radeon Software Crimson thread.

in an ideal world, one should be able to both mb/ap apps as well as multiple work units/gpu without producing invalids. the last time i was able to run multiple wu(s)/gpu without producing invalids was driver 14.4, but that driver is not as fast as the newer drivers. 14.4 works with my 290x/295x2 but not my 390x/radeon pro duo. i had similar problems on einstein as well.

so now i'm using a driver from this year but i only run one wu per gpu and i don't run ap at all. but i only speak of my own cards; cards less expensive than mine(like the 280x) don't have the same problem. and i don't have anything new like a rx480 so i can't speak to that either.

I've not been having problems with 15.12 on my 390x. Each time I have tried a 16.x+ driver I have had issues. Like a BSOD while windows is sitting at the desktop.
SETI@home classic workunits: 93,865 CPU time: 863,447 hours
Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[
ID: 1874887 · Report as offensive
Profile Karsten Vinding
Volunteer tester

Send message
Joined: 18 May 99
Posts: 239
Credit: 25,201,931
RAC: 11
Denmark
Message 1874890 - Posted: 24 Jun 2017, 17:47:59 UTC - in response to Message 1874887.  

I havent had any problems with crashes and that sort with any of the recent drivers on my RX480. Currently running 17.6.2, and its rock solid.

But there are problems with AP crunching, and the oldest driver (16.6.2) which supports the RX480 is never than 15.12, so the situation is difficult.

As things are now, owners off newer hardware are out of luck. Something should be done about this.
ID: 1874890 · Report as offensive
Profile Karsten Vinding
Volunteer tester

Send message
Joined: 18 May 99
Posts: 239
Credit: 25,201,931
RAC: 11
Denmark
Message 1874891 - Posted: 24 Jun 2017, 18:01:36 UTC - in response to Message 1874890.  
Last modified: 24 Jun 2017, 18:06:56 UTC

By the way, I tried to do some optimisations following the tips in the included readmes in the Lunatics installer.

Using these settings:
-unroll 18 -ffa_block 16384 -ffa_block_fetch 8192

it seems that my results now validate. At least I have 4 valid WU's (but also 2 inconclusives) since I put in these settings yesterday. No invalids yet.

That is a much higher succes rate than before, allthough it could be down to chance.

I'll keep an eye on it.
ID: 1874891 · Report as offensive
Previous · 1 . . . 71 · 72 · 73 · 74 · 75 · 76 · 77 . . . 120 · Next

Message boards : Number crunching : Anything relating to AstroPulse tasks


 
©2024 University of California
 
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.