5700XT/5700XT 50th Anniversary thread

Message boards : Number crunching : 5700XT/5700XT 50th Anniversary thread
Message board moderation

To post messages, you must log in.


Send message
Joined: 22 Mar 18
Posts: 1
Credit: 4,399,664
RAC: 82
Message 2005508 - Posted: 3 Aug 2019, 14:51:44 UTC

Sorry in advance if such a thread already exist, but I can't seem to find it.
Mine is the 50th anni version. I gave it a run last night with the latest driver, 19.7.5, to see how it goes.
Invalids most parts, only got 12 valids so far. Nothing modified, just attached to Seti and go.
Host: https://setiathome.berkeley.edu/results.php?hostid=8784349

One of the invalid result so experts can take a look to see what we can do to make it works:
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
0 slot of 64 used for this instance
Info: BOINC provided OpenCL device ID used
Info: CPU affinity mask used: 1; system mask is ff

Build features: SETI8	Non-graphics	OpenCL	USE_OPENCL_HD5xxx	OCL_ZERO_COPY	OCL_CHIRP3	FFTW	AMD specific	USE_SSE2	x86	
     CPUID: AMD Ryzen 5 2400G with Radeon Vega Graphics     

     Cache: L1=64K L2=512K

OpenCL-kernels filename : MultiBeam_Kernels_r3584.cl 
ar=0.012741  NumCfft=109437  NumGauss=0  NumPulse=39804018560  NumTriplet=52767418528
Currently allocated 185 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 3584 , Ported by : Raistmer, JDWhale

SETI8 update by Raistmer

OpenCL version by Raistmer, r3584

AMD HD5 version by Raistmer

Number of OpenCL platforms:				 1

 OpenCL Platform Name:					 AMD Accelerated Parallel Processing
Number of devices:				 1
  Max compute units:				 20
  Max work group size:				 256
  Max clock frequency:				 1830Mhz
  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:				 65536
  Queue properties:				 
    Out-of-Order:				 No
  Name:						 gfx1010
  Vendor:					 Advanced Micro Devices, Inc.
  Driver version:				 2906.10 (PAL,LC)
  Version:					 OpenCL 1.2 AMD-APP (2906.10)
  Extensions:					 cl_khr_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_media_ops cl_amd_media_ops2 cl_khr_d3d10_sharing cl_khr_d3d11_sharing cl_khr_dx9_media_sharing cl_khr_image2d_from_buffer cl_khr_gl_event cl_amd_liquid_flash cl_amd_copy_buffer_p2p 

Work Unit Info:
Credit multiplier is :  2.85
WU true angle range is :  0.012741
Used GPU device parameters are:
	Number of compute units: 20
	Single buffer allocation size: 128MB
	Total device global memory: 3072MB
	max WG size: 256
	local mem type: Real
	LotOfMem path: no
	LowPerformanceGPU path: no
	HighPerformanceGPU path: no
Spike: peak=24.27136, time=26.22, d_freq=4165068710.22, chirp=0, fft_len=2k
Spike: peak=34.64487, time=26.4, d_freq=4165062770.25, chirp=0, fft_len=2k
Spike: peak=25.19971, time=34.45, d_freq=4165063217.28, chirp=0, fft_len=2k
Spike: peak=24.82417, time=36.06, d_freq=4165063077.58, chirp=0, fft_len=2k
Spike: peak=35.17019, time=38.39, d_freq=4165068715.81, chirp=0, fft_len=2k
Spike: peak=26.30072, time=39.64, d_freq=4165065938.61, chirp=0, fft_len=2k
Spike: peak=30.43611, time=42.86, d_freq=4165068805.22, chirp=0, fft_len=2k
Spike: peak=25.10494, time=44.83, d_freq=4165071358.9, chirp=0, fft_len=2k
Spike: peak=28.56355, time=57, d_freq=4165068626.4, chirp=0, fft_len=2k
Spike: peak=24.62983, time=57.71, d_freq=4165060272.44, chirp=0, fft_len=2k
Spike: peak=35.54539, time=60.04, d_freq=4165062770.25, chirp=0, fft_len=2k
Spike: peak=26.19414, time=65.23, d_freq=4165069118.14, chirp=0, fft_len=2k
Spike: peak=27.92791, time=76.68, d_freq=4165062954.65, chirp=0, fft_len=2k
Spike: peak=26.3976, time=78.83, d_freq=4165066251.53, chirp=0, fft_len=2k
Spike: peak=28.05597, time=79.9, d_freq=4165068671.11, chirp=0, fft_len=2k
Spike: peak=26.8378, time=83.48, d_freq=4165068849.92, chirp=0, fft_len=2k
Spike: peak=28.8213, time=86.53, d_freq=4165063127.88, chirp=0, fft_len=2k
Spike: peak=25.06996, time=87.06, d_freq=4165066352.11, chirp=0, fft_len=2k
Spike: peak=24.20463, time=2.326, d_freq=4165063130.67, chirp=0, fft_len=4k
Spike: peak=28.69148, time=3.4, d_freq=4165062773.04, chirp=0, fft_len=4k
Spike: peak=24.33282, time=4.474, d_freq=4165066078.31, chirp=0, fft_len=4k
Spike: peak=26.97396, time=5.906, d_freq=4165068492.29, chirp=0, fft_len=4k
Spike: peak=29.54967, time=6.621, d_freq=4165068495.09, chirp=0, fft_len=4k
Spike: peak=25.03596, time=10.92, d_freq=4165068492.29, chirp=0, fft_len=4k
Spike: peak=25.22779, time=13.42, d_freq=4165068760.51, chirp=0, fft_len=4k
Spike: peak=24.64411, time=14.14, d_freq=4165060177.45, chirp=0, fft_len=4k
Spike: peak=26.12588, time=17.72, d_freq=4165065673.18, chirp=0, fft_len=4k
Spike: peak=29.23288, time=18.07, d_freq=4165065634.06, chirp=0, fft_len=4k
Spike: peak=26.53574, time=19.15, d_freq=4165063085.97, chirp=0, fft_len=4k
Spike: peak=25.22096, time=19.51, d_freq=4165068844.33, chirp=0, fft_len=4k
OpenCL queue synchronized
SETI@Home Informational message -9 result_overflow
NOTE: The number of results detected equals the storage space allocated.

Best spike: peak=35.54539, time=60.04, d_freq=4165062770.25, chirp=0, fft_len=2k
Best autocorr: peak=0, time=-2.124e+011, delay=0, d_freq=0, chirp=0, fft_len=0 
Best gaussian: peak=0, mean=0, ChiSq=0, time=-2.124e+011, d_freq=0,
	score=-12, null_hyp=0, chirp=0, fft_len=0 
Best pulse: peak=2.027598, time=45.82, period=4.302, d_freq=4165069878.1, score=0.8488, chirp=0, fft_len=128 
Best triplet: peak=0, time=-2.124e+011, period=0, d_freq=0, chirp=0, fft_len=0 
Spike count:    30
Autocorr count: 0
Pulse count:    0
Triplet count:  0
Gaussian count: 0
Wallclock time elapsed since last restart: 8.4 seconds
Fftlength=32,pass=3:Tune: sum=15.236(ms); min=15.24(ms); max=15.24(ms); mean=15.24(ms); s_mean=15.24; sleep=15(ms); delta=110; N=1; usual
Fftlength=64,pass=3:Tune: sum=183.113(ms); min=2.462(ms); max=6.948(ms); mean=6.104(ms); s_mean=4.921; sleep=0(ms); delta=109; N=30; usual
Fftlength=64,pass=4:Tune: sum=139.101(ms); min=3.279(ms); max=6.013(ms); mean=5.35(ms); s_mean=5.071; sleep=0(ms); delta=105; N=26; usual
Fftlength=128,pass=3:Tune: sum=49.5382(ms); min=1.473(ms); max=3.656(ms); mean=3.096(ms); s_mean=2.678; sleep=0(ms); delta=95; N=16; usual
Fftlength=128,pass=4:Tune: sum=31.2999(ms); min=2.874(ms); max=3.831(ms); mean=3.478(ms); s_mean=3.431; sleep=0(ms); delta=128; N=9; usual
Fftlength=256,pass=3:Tune: sum=17.9976(ms); min=0.7001(ms); max=2.401(ms); mean=  2(ms); s_mean=1.773; sleep=0(ms); delta=88; N=9; usual
Fftlength=256,pass=4:Tune: sum=15.39(ms); min=0.6447(ms); max=2.479(ms); mean=1.924(ms); s_mean=1.714; sleep=0(ms); delta=87; N=8; usual
Fftlength=256,pass=5:Tune: sum=8.39088(ms); min=0.6021(ms); max=1.429(ms); mean=1.199(ms); s_mean=1.128; sleep=0(ms); delta=86; N=7; usual
Fftlength=512,pass=3:Tune: sum=7.51472(ms); min=0.554(ms); max=1.103(ms); mean=0.9393(ms); s_mean=0.8805; sleep=0(ms); delta=47; N=8; usual
Fftlength=512,pass=4:Tune: sum=6.94772(ms); min=0.2831(ms); max=1.032(ms); mean=0.8685(ms); s_mean=0.7757; sleep=0(ms); delta=47; N=8; usual
Fftlength=512,pass=5:Tune: sum=3.93944(ms); min=0.2594(ms); max=0.669(ms); mean=0.5628(ms); s_mean=0.525; sleep=0(ms); delta=46; N=7; usual
Fftlength=1024,pass=3:Tune: sum=3.66732(ms); min=0.199(ms); max=0.5578(ms); mean=0.4584(ms); s_mean=0.4184; sleep=0(ms); delta=27; N=8; usual
Fftlength=1024,pass=4:Tune: sum=2.99612(ms); min=0.2727(ms); max=0.5129(ms); mean=0.428(ms); s_mean=0.4065; sleep=0(ms); delta=26; N=7; usual
Fftlength=1024,pass=5:Tune: sum=1.9314(ms); min=0.104(ms); max=0.3393(ms); mean=0.2759(ms); s_mean=0.2544; sleep=0(ms); delta=26; N=7; usual
Fftlength=2048,pass=3:Tune: sum=1.24764(ms); min=1.248(ms); max=1.248(ms); mean=1.248(ms); s_mean=1.248; sleep=0(ms); delta=1; N=1; high_perf

class Gaussian_transfer_not_needed:		total=0,	N=0,	<>=0,	min=0	max=0
class Gaussian_transfer_needed:		total=0,	N=0,	<>=0,	min=0	max=0

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=0,	<>=0,	min=0	max=0
class Gaussian_skip6_low_power:		total=0,	N=0,	<>=0,	min=0	max=0

class Gaussian_new_best:		total=0,	N=0,	<>=0,	min=0	max=0
class Gaussian_report:		total=0,	N=0,	<>=0,	min=0	max=0
class Gaussian_miss:		total=0,	N=0,	<>=0,	min=0	max=0

class PC_triplet_find_hit:		total=4,	N=4,	<>=1,	min=1	max=1
class PC_triplet_find_miss:		total=4,	N=4,	<>=1,	min=1	max=1

class PC_pulse_find_hit:		total=4,	N=4,	<>=1,	min=1	max=1
class PC_pulse_find_miss:		total=3,	N=3,	<>=1,	min=1	max=1
class PC_pulse_find_early_miss:		total=3,	N=3,	<>=1,	min=1	max=1
class PC_pulse_find_2CPU:		total=0,	N=0,	<>=0,	min=0	max=0

class PoT_transfer_not_needed:		total=4,	N=4,	<>=1,	min=1	max=1
class PoT_transfer_needed:		total=5,	N=5,	<>=1,	min=1	max=1

class SleepQuantum:		total=0,	N=0,	<>=0,	min=0	max=0

GPU device sync requested...  ...GPU device synched
05:19:04 (6092): called boinc_finish(0)

ID: 2005508 · Report as offensive
Profile Jord
Volunteer tester

Send message
Joined: 9 Jun 99
Posts: 14887
Credit: 4,141,823
RAC: 1,229
Message 2005509 - Posted: 3 Aug 2019, 15:00:47 UTC - in response to Message 2005508.  

https://www.anandtech.com/show/14618/the-amd-radeon-rx-5700-xt-rx-5700-review/13 says it all really. And that was a month ago, no real fixes to the problem yet.
ID: 2005509 · Report as offensive
Profile Wiggo "Democratic Socialist"

Send message
Joined: 24 Jan 00
Posts: 16926
Credit: 234,954,571
RAC: 180,895
Message 2005511 - Posted: 3 Aug 2019, 15:05:20 UTC

I'm sorry, but until AMD release a new driver with a fixed OpenCL stack those GPU's are useless for compute functions.

ID: 2005511 · Report as offensive

Message boards : Number crunching : 5700XT/5700XT 50th Anniversary thread

©2019 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.