LL with OpenCL - Page 2

msft · 2013-06-18, 22:17

Quote:

Originally Posted by kracker

I tried booting linux after not using it for around a month I think... for some reason wouldn't boot, so I tried reinstalling both Ubuntu and Fedora.. no luck, it boots to a black screen, the fallback graphic mode and nomodeset didn't work either... damn linux :P

My System installed

Quote:

AMD-APP-SDK-v2.8-lnx64.tgz
amd-driver-installer-catalyst-13.1-linux-x86.x86_64.zip
clAmdFft-1.10.321.tar.gz

msft · 2013-06-19, 18:59

New Version.

Quote:

$ pwd
/opt/AMDAPP/samples/opencl/cl/0.29
$ tar -xvf 0.29.tar.bz2
0.29/
0.29/clFFTPlans.h
0.29/sq_herm.h
0.29/balance.c
---
$ sh -x ./run.sh
+ make
---
+ export LD_LIBRARY_PATH=:/opt/clAmdFft-1.10.321/lib64/:/opt/clAmdFft-1.10.321/lib64
+ time ./CUDALucas 1398269

start M1398269 fft length = 73728
Platform :Advanced Micro Devices, Inc.
Device 0 : Capeverde

Build Options are : -D KHR_DP_EXTENSION
Platform :Advanced Micro Devices, Inc.
Device 0 : Capeverde

Build Options are : -D KHR_DP_EXTENSION
Platform :Advanced Micro Devices, Inc.
Device 0 : Capeverde

Build Options are : -D KHR_DP_EXTENSION
Iteration 10000 M( 1398269 )C, 0xa4a6d2f0e34629db, n = 73728, CUDALucas v1.66 err =0.09375 (0:43 real, 4.2660 ms/iter, ETA 1:38:07)
---
Iteration 1380000 M( 1398269 )C, 0x6650b95f00196d18, n = 73728, CUDALucas v1.66 err= 0.1108 (0:41 real, 4.0327 ms/iter, ETA 0:40)
Iteration 1390000 M( 1398269 )C, 0x554ae339bfea8fae, n = 73728, CUDALucas v1.66 err= 0.1108 (0:40 real, 4.0330 ms/iter, ETA 0:00)
M( 1398269 )P, n = 73728, CUDALucas v1.66
687.79user 2473.43system 1:34:07elapsed 55%CPU (0avgtext+0avgdata 218272maxresident)

kracker · 2013-06-19, 23:23

Trying to compile on Win, I get this:

msft · 2013-06-20, 14:54

Quote:

Originally Posted by kracker

Trying to compile on Win, I get this:

It is difficult.

msft · 2013-06-20, 17:51

Speed UP.

Quote:

Iteration 1390000 M( 1398269 )C, 0x554ae339bfea8fae, n = 73728, CUDALucas v1.66 err = 0.1108 (0:26 real, 2.5899 ms/iter, ETA 0:00)
M( 1398269 )P, n = 73728, CUDALucas v1.66
587.65user 2329.16system 1:01:45elapsed 78%CPU (0avgtext+0avgdata 218592maxresident)

2048K 20ms/iter
4096K 40ms/iter

kracker · 2013-06-20, 19:23

Quote:

Originally Posted by msft

Can you compile MatrixMulImage on linux ?

Not sure on linux, but I compiled and got it working on Win.

Code:

$MatrixMulImage.exe

Platform 0 : Advanced Micro Devices, Inc.

Input0
0.147705 6.39597 7.74612 4.39893 10.864 1.09604 10.3222 10.9698 3.27637 9.4209 6.85788 0.25177 1.50391 1.29678 10.2148 6.2392 10.3253 10.6062 10.5968 8.26813 5.3909 0.917786 0.235992 1.33136 4.15689 6.0643 9.53101 10.0379 8.87674 5.54062 3.7309 3.94003 3.49826 1.18869 0.755646 7.44366 4.80847 8.13654 6.25027 10.0198 8.67062 8.46451 5.46643 2.93967 7.69577 9.56323 4.06088 1.24945 9.19531 2.65265 5.41071 3.20285 9.75424 7.43527 4.53354 9.87308 9.27386 9.3457 7.21069 2.16019 9.82339 8.37085 0.403839 8.914 5.14484 7.90491 3.56204 9.39136 5.15927 8.61255 5.90921 1.76541 2.31226 0.765717 7.30939 2.90643 1.10376 9.0231 0.800964 3.15451 6.65244 7.12341 4.39456 4.29822 5.62589 9.45715 2.22968 10.4834 0.394104 2.99103 1.68082 1.26825 8.74011 4.50702 0.509247 9.54242 1.97421 5.6326 4.65338 3.53082 1.79999 2.62344 0.751282 3.60098 0.767731 5.37244 1.99133 1.08966 3.66611 2.61203 5.37848 10.8724 8.69312 8.77805 1.0195 0.889923 5.74841 4.505 3.51035 8.35339 8.69412 6.21973 4.03033 9.84622 0.9245 10.806 0.22525 9.03955 


Input1
0.147705 6.39597 7.74612 4.39893 10.864 1.09604 10.3222 10.9698 3.27637 9.4209 6.85788 0.25177 1.50391 1.29678 10.2148 6.2392 10.3253 10.6062 10.5968 8.26813 5.3909 0.917786 0.235992 1.33136 4.15689 6.0643 9.53101 10.0379 8.87674 5.54062 3.7309 3.94003 3.49826 1.18869 0.755646 7.44366 4.80847 8.13654 6.25027 10.0198 8.67062 8.46451 5.46643 2.93967 7.69577 9.56323 4.06088 1.24945 9.19531 2.65265 5.41071 3.20285 9.75424 7.43527 4.53354 9.87308 9.27386 9.3457 7.21069 2.16019 9.82339 8.37085 0.403839 8.914 5.14484 7.90491 3.56204 9.39136 5.15927 8.61255 5.90921 1.76541 2.31226 0.765717 7.30939 2.90643 1.10376 9.0231 0.800964 3.15451 6.65244 7.12341 4.39456 4.29822 5.62589 9.45715 2.22968 10.4834 0.394104 2.99103 1.68082 1.26825 8.74011 4.50702 0.509247 9.54242 1.97421 5.6326 4.65338 3.53082 1.79999 2.62344 0.751282 3.60098 0.767731 5.37244 1.99133 1.08966 3.66611 2.61203 5.37848 10.8724 8.69312 8.77805 1.0195 0.889923 5.74841 4.505 3.51035 8.35339 8.69412 6.21973 4.03033 9.84622 0.9245 10.806 0.22525 9.03955 

Platform found : Advanced Micro Devices, Inc.

Selected Platform Vendor : Advanced Micro Devices, Inc.
Device 0 : Capeverde Device ID is 0x8ec4d0
Device 1 : BeaverCreek Device ID is 0x34b09b0
Executing kernel for 1 iterations
-------------------------------------------
KernelTime (ms) : 3.16022
GFlops achieved : 1.32722


Output
4070.06 4055.82 3914.63 3753.9 3543.83 3205.83 4237.34 3715.33 4061.83 3850.64 3407.55 4258.17 3823.28 3539.98 3902.99 4123.69 3570.19 3734.44 3766.67 3739.24 3704.56 3864.23 4041.88 3494.53 3700.65 4063.3 3201.17 3518.79 3883.79 3485.72 3963.27 3603.28 3719.9 3845.7 3684.77 3723.82 3508.69 3637.38 3505.94 3912.07 4131.47 4280.45 4194.81 3894.24 3736.4 4046.39 4159.46 3579.6 3773.27 4306.03 4185.79 4242.53 3874.78 3626.98 3903.28 3692.06 3829.39 3842.35 3716.04 3381.77 4025.64 3950.11 3740.09 3901.27 3896.64 3632.36 3866.18 3869.26 4110.71 3529.9 3667.95 4074.95 4023.75 3957.75 3577.93 3923.34 3650.11 3882.57 4061.06 3900.33 3890.95 3314.55 4085.9 4045.29 3790.43 3773.83 3830.33 3803.7 3807.46 3652.57 3591.75 3841.75 3600.75 3728.28 3621.29 3237.11 3847.58 3974.57 3677.6 3947.93 3846.74 3851.45 3864.61 3693.4 3829.65 3972.65 4163.19 3459.57 3580.74 3405.98 3975.2 3954.54 3956.8 3676.24 3344.48 3837.72 3749.86 4217.71 3597.83 3480.95 3708.84 3495.84 3869.3 4426.98 3329.74 4228.3 3947.93 4270.1

~~EDIT: I don't know why it complains about SDKApplication.hpp, it's THERE..~~

EDIT: Fixed that, stupid user error... now getting.. damn

msft · 2013-06-20, 22:01

Quote:

Originally Posted by kracker

EDIT: Fixed that, stupid user error... now getting.. damn

We need Windows Guru.

msft · 2013-06-21, 07:02

Profile
HD7750:

Quote:

2048K all 19.2 ms/iter
FFT 14.2 ms/iter
mul 1.5 ms/ier
norm 3.5 ms/iter

kracker · 2013-06-21, 14:45

http://devgurus.amd.com/thread/166951

Well, cygwin it is.

pinhodecarlos · 2013-06-21, 19:45

Can I help testing the windows version?

kracker · 2013-06-21, 19:54

Quote:

Originally Posted by pinhodecarlos

Can I help testing the windows version?

Yes, if I can get it compiled!

:soap box:

Still in the process or setting up Cygwin

2013-06-19, 23:23	#14
kracker "Mr. Meeseeks" Jan 2012 California, USA 2⁷·17 Posts	Trying to compile on Win, I get this: Attached Thumbnails

Similar Threads
Thread	Thread Starter	Forum	Replies	Last Post
mfakto: an OpenCL program for Mersenne prefactoring	Bdot	GPU Computing	1719	2023-01-16 15:51
Can't get OpenCL to work on HD7950 Ubuntu 14.04.5 LTS	VictordeHolland	Linux	4	2018-04-11 13:44
OpenCL accellerated lattice siever	pstach	Factoring	1	2014-05-23 01:03
OpenCL for FPGAs	TObject	GPU Computing	2	2013-10-12 21:09
AMD's Graphics Core Next- a reason to accelerate towards OpenCL?	Belteshazzar	GPU Computing	19	2012-03-07 18:58

2013-06-21, 14:45	#20
kracker "Mr. Meeseeks" Jan 2012 California, USA 2⁷×17 Posts	http://devgurus.amd.com/thread/166951 Well, cygwin it is.

2013-06-21, 19:45	#21
pinhodecarlos "Carlos Pinho" Oct 2011 Milton Keynes, UK 2×3³×5×19 Posts	Can I help testing the windows version?