Jump to content

How to know if OpenCL is working properly?


1 post in this topic

Recommended Posts

Hi everyone,

 

I would like to know if OpenCL is working properly on my MacOS 10.6.6 with my ATI HD 5870. Is there any way to know if everything is fine?

 

I'm able to play Amnesia FULL, to run some OpenCL benchmarkers such as OpenCLBench_Displacement_V2 etc. And everything seems to work, but I've got some stange things happening.

 

For example regarding OpenCLBench_Displacement_V2 debug says "GLUT Warning: GL error: invalid operation" even if the bench is running nicely.

 

Also, I tried to run pyrit, a WPA/WPA2-PSK cracker which uses OpenCL, but I've not been able to make it work because of wrong computation :/ (https://code.google.com/p/pyrit/issues/detail?id=242). Someone told me it computes wrong values :/

 

So the question is... How to know if OpenCL is working properly?

 

Regards,

Thi.

 

PS: I've got EVOenabler into my Extra folder (see: http://www.kexts.com/downloads.php?do=file&id=160) and my video card is well recognized:

ATI Radeon HD 4870 :

 Jeu de composants :	ATI Radeon HD 4870
 Type :	Processeur graphique (GPU)
 Bus :	PCIe
 Logement :	Slot-1
 Longueur de la voie PCIe :	x16
 VRAM (totale) :	1024 Mo
 Fournisseur :	ATI (0x1002)
 Identifiant du périphérique :	0x9440
 Identifiant de révision :	0x0000
 Révision de la ROM :	113-B7710C-176
 Version du gestionnaire EFI :	01.00.318
 Moniteurs :
W2261 :
 Résolution :	1920 x 1080 @ 60 Hz
 Profondeur de pixels :	Couleurs 32 bits (ARGB8888)
 Moniteur principal :	Oui
 Miroir :	Désactivé
 Connecté :	Oui
 Rotation :	Géré
Connecteur pour le moniteur :
 État :	Aucun moniteur branché

 

 

 

 

EDIT: Here are some information I get from SmallluxGPU :

 

INITIALISING: 1 OpenCL platform found!

[Platform 0]
Name: 		Apple
Vendor: 	Apple
Version: 	OpenCL 1.0 (Aug 22 2010 18:08:16)
Profile: 	FULL_PROFILE


[OpenCL-only Context]
2 OpenCL devices found!

[Device 0]
Name: 			Radeon HD 4870
Vendor: 		AMD
Type: 			GPU 
Device Version: 	OpenCL 1.0 
Driver Version: 	1.0
Compute Units: 		10
Work Group Size: 	1024
Clock: 			750 MHz
Global Memory: 		512 MB
Local Memory: 		16 KB
Cache Size: 		0 KB
Cache Line Size: 	0 Bytes
Available: 		Yes
Double-Precision: 	No
Extensions: 
			cl_APPLE_gl_sharing

[Device 1]
Name: 			Pentium(R) Dual-Core  CPU	  E6500  @ 2.93GHz
Vendor: 		Intel
Type: 			CPU 
Device Version: 	OpenCL 1.0 
Driver Version: 	1.0
Compute Units: 		2
Work Group Size: 	1
Clock: 			3916 MHz
Global Memory (Total): 	8192 MB
Global Memory (Host): 	6144 MB
Global Memory (PCIe): 	2048 MB
Local Memory: 		16 KB
Cache Size: 		2048 KB
Cache Line Size: 	64 Bytes
Available: 		Yes
Double-Precision: 	Yes
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_byte_addressable_store
			cl_APPLE_gl_sharing
			cl_APPLE_SetMemObjectDestructor
			cl_APPLE_ContextLoggingFunctions

[shared OpenCL+OpenGL Context]
2 OpenCL devices found!

[Device 0]
Name: 			Radeon HD 4870
Vendor: 		AMD
Type: 			GPU 
Device Version: 	OpenCL 1.0 
Driver Version: 	1.0
Compute Units: 		10
Work Group Size: 	1024
Clock: 			750 MHz
Global Memory: 		512 MB
Local Memory: 		16 KB
Cache Size: 		0 KB
Cache Line Size: 	0 Bytes
Available: 		Yes
Double-Precision: 	No
Extensions: 
			cl_APPLE_gl_sharing

[Device 1]
Name: 			Pentium(R) Dual-Core  CPU	  E6500  @ 2.93GHz
Vendor: 		Intel
Type: 			CPU 
Device Version: 	OpenCL 1.0 
Driver Version: 	1.0
Compute Units: 		2
Work Group Size: 	1
Clock: 			3916 MHz
Global Memory (Total): 	8192 MB
Global Memory (Host): 	6144 MB
Global Memory (PCIe): 	2048 MB
Local Memory: 		16 KB
Cache Size: 		2048 KB
Cache Line Size: 	64 Bytes
Available: 		Yes
Double-Precision: 	Yes
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_byte_addressable_store
			cl_APPLE_gl_sharing
			cl_APPLE_SetMemObjectDestructor
			cl_APPLE_ContextLoggingFunctions

RUNNING PICELBENCH: LuxRays Simple PixelDevice Benchmark v0.1alpha7dev
Usage (easy mode): ./benchpixel
OpenCL Platform 0: Apple
Device 0 NativeThread name: NativeThread-000
Device 1 NativeThread name: NativeThread-001
Device 2 OpenCL name: Radeon HD 4870
Device 2 OpenCL type: GPU
Device 2 OpenCL units: 10
Device 2 OpenCL max allocable memory: 128MBytes
Device 3 OpenCL name: Pentium(R) Dual-Core  CPU	  E6500  @ 2.93GHz
Device 3 OpenCL type: CPU
Device 3 OpenCL units: 2
Device 3 OpenCL max allocable memory: 1536MBytes
Selected pixel device: Radeon HD 4870Creating 1 pixel device(s)
Allocating pixel device 0: Radeon HD 4870 (Type = OPENCL)
[OpenCL device::Radeon HD 4870Pixel] GammaTable buffer size: 4Kbytes
[OpenCL device::Radeon HD 4870Pixel] FilterTable buffer size: 1Kbytes
[OpenCL device::Radeon HD 4870Pixel] SampleFrameBuffer buffer size: 4800Kbytes
[OpenCL device::Radeon HD 4870Pixel] FrameBuffer buffer size: 3600Kbytes
AddSample[FILTER_NONE] Benchmark
Running the benchmark for 10 seconds...
[OpenCL device::Radeon HD 4870Pixel] SampleBuffer buffer size: 1280Kbytes (*6)
1/10secs
2/10secs
3/10secs
4/10secs
5/10secs
6/10secs
7/10secs
8/10secs
9/10secs
Test total time: 10.0433
Test total sample buffer count: 5208
[Radeon HD 4870Pixel][Samples/sec 1131.52M]
Test performance: 33.99M sample/sec
AddSample[FILTER_PREVIEW] Benchmark
Running the benchmark for 10 seconds...
1/10secs
2/10secs
3/10secs
4/10secs
5/10secs
6/10secs
7/10secs
8/10secs
9/10secs
Test total time: 10.02
Test total sample buffer count: 3406
[Radeon HD 4870Pixel][Samples/sec 221.72M]
Test performance: 22.28M sample/sec
AddSample[FILTER_GAUSSIAN] Benchmark
Running the benchmark for 10 seconds...
1/10secs
2/10secs
3/10secs
4/10secs
5/10secs
6/10secs
7/10secs
8/10secs
9/10secs
Test total time: 10.14
Test total sample buffer count: 1764
[Radeon HD 4870Pixel][Samples/sec 78.29M]
Test performance: 11.41M sample/sec
Done.

×
×
  • Create New...