Program GPU usage
Hello, I installed CUDA on Debian 6.04
DeviceQuery from the CUDA SDK
[quote]

[deviceQuery] starting...

./deviceQuery Starting...

CUDA Device Query (Runtime API) version (CUDART static linking)

Found 1 CUDA Capable device(s)

Device 0: "GeForce 9300 / nForce 730i"
CUDA Driver Version / Runtime Version 4.2 / 4.2
CUDA Capability Major/Minor version number: 1.1
Total amount of global memory: 253 MBytes (265617408 bytes)
( 2) Multiprocessors x ( 8) CUDA C[deviceQuery] starting...

./deviceQuery Starting...

CUDA Device Query (Runtime API) version (CUDART static linking)

Found 1 CUDA Capable device(s)

Device 0: "GeForce 9300 / nForce 730i"
CUDA Driver Version / Runtime Version 4.2 / 4.2
CUDA Capability Major/Minor version number: 1.1
Total amount of global memory: 253 MBytes (265617408 bytes)
( 2) Multiprocessors x ( 8) CUDA Cores/MP: 16 CUDA Cores
GPU Clock rate: 1200 MHz (1.20 GHz)
Memory Clock rate: 800 Mhz
Memory Bus Width: 128-bit
Max Texture Dimension Size (x,y,z) 1D=(8192), 2D=(65536,32768), 3D=(2048,2048,2048)
Max Layered Texture Size (dim) x layers 1D=(8192) x 512, 2D=(8192,8192) x 512
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 16384 bytes
Total number of registers available per block: 8192
Warp size: 32
Maximum number of threads per multiprocessor: 768
Maximum number of threads per block: 512
Maximum sizes of each dimension of a block: 512 x 512 x 64
Maximum sizes of each dimension of a grid: 65535 x 65535 x 1
Maximum memory pitch: 2147483647 bytes
Texture alignment: 256 bytes
Concurrent copy and execution: No with 0 copy engine(s)
Run time limit on kernels: Yes
Integrated GPU sharing Host Memory: Yes
Support host page-locked memory mapping: Yes
Concurrent kernel execution: No
Alignment requirement for Surfaces: Yes
Device has ECC support enabled: No
Device is using TCC driver mode: No
Device supports Unified Addressing (UVA): No
Device PCI Bus ID / PCI location ID: 3 / 0
Compute Mode:
< Default (multiple host threads can viceQuery Starting...

CUDA Device Query (Runtime API) version (CUDART static linking)

Found 1 CUDA Capable device(s)

Device 0: "GeForce 9300 / nForce 730i"
CUDA Driver Version / Runtime Version 4.2 / 4.2
CUDA Capability Major/Minor version number: 1.1
Total amount of global memory: 253 MBytes (265617408 bytes)
( 2) Multiprocessors x ( 8) CUDA C[deviceQuery] starting...

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 4.2, CUDA Runtime Version = 4.2, NumDevs = 1, Device = GeForce 9300 / nForce 730i
[deviceQuery] test results...
PASSED


[/quote]

How I can make shure that the program uses GPU?
Hello, I installed CUDA on Debian 6.04

DeviceQuery from the CUDA SDK





[deviceQuery] starting...



./deviceQuery Starting...



CUDA Device Query (Runtime API) version (CUDART static linking)



Found 1 CUDA Capable device(s)



Device 0: "GeForce 9300 / nForce 730i"

CUDA Driver Version / Runtime Version 4.2 / 4.2

CUDA Capability Major/Minor version number: 1.1

Total amount of global memory: 253 MBytes (265617408 bytes)

( 2) Multiprocessors x ( 8) CUDA C[deviceQuery] starting...



./deviceQuery Starting...



CUDA Device Query (Runtime API) version (CUDART static linking)



Found 1 CUDA Capable device(s)



Device 0: "GeForce 9300 / nForce 730i"

CUDA Driver Version / Runtime Version 4.2 / 4.2

CUDA Capability Major/Minor version number: 1.1

Total amount of global memory: 253 MBytes (265617408 bytes)

( 2) Multiprocessors x ( 8) CUDA Cores/MP: 16 CUDA Cores

GPU Clock rate: 1200 MHz (1.20 GHz)

Memory Clock rate: 800 Mhz

Memory Bus Width: 128-bit

Max Texture Dimension Size (x,y,z) 1D=(8192), 2D=(65536,32768), 3D=(2048,2048,2048)

Max Layered Texture Size (dim) x layers 1D=(8192) x 512, 2D=(8192,8192) x 512

Total amount of constant memory: 65536 bytes

Total amount of shared memory per block: 16384 bytes

Total number of registers available per block: 8192

Warp size: 32

Maximum number of threads per multiprocessor: 768

Maximum number of threads per block: 512

Maximum sizes of each dimension of a block: 512 x 512 x 64

Maximum sizes of each dimension of a grid: 65535 x 65535 x 1

Maximum memory pitch: 2147483647 bytes

Texture alignment: 256 bytes

Concurrent copy and execution: No with 0 copy engine(s)

Run time limit on kernels: Yes

Integrated GPU sharing Host Memory: Yes

Support host page-locked memory mapping: Yes

Concurrent kernel execution: No

Alignment requirement for Surfaces: Yes

Device has ECC support enabled: No

Device is using TCC driver mode: No

Device supports Unified Addressing (UVA): No

Device PCI Bus ID / PCI location ID: 3 / 0

Compute Mode:

< Default (multiple host threads can viceQuery Starting...



CUDA Device Query (Runtime API) version (CUDART static linking)



Found 1 CUDA Capable device(s)



Device 0: "GeForce 9300 / nForce 730i"

CUDA Driver Version / Runtime Version 4.2 / 4.2

CUDA Capability Major/Minor version number: 1.1

Total amount of global memory: 253 MBytes (265617408 bytes)

( 2) Multiprocessors x ( 8) CUDA C[deviceQuery] starting...



deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 4.2, CUDA Runtime Version = 4.2, NumDevs = 1, Device = GeForce 9300 / nForce 730i

[deviceQuery] test results...

PASSED









How I can make shure that the program uses GPU?

#1
Posted 05/02/2012 03:34 AM   
By calling gpu specific functions. You need to explicitly write functions and have the __kernel__ atribbutie which will be executed on gpu.
By calling gpu specific functions. You need to explicitly write functions and have the __kernel__ atribbutie which will be executed on gpu.

#2
Posted 05/02/2012 08:36 AM   
I have another situation, Application Vray must use GPU, but when I start it, program freezes up
Log from console
[quote]
[2012/May/2|17:30:42] Running RTEngine
[2012/May/2|17:30:42] Initializing OpenCL renderer (single kernel version)...
[2012/May/2|17:30:42] Querying for OpenCL devices...
[2012/May/2|17:30:42] warning: Environment variable VRAY_OPENCL_PLATFORMS_x64 not found - using all available devices
[2012/May/2|17:30:42] Using the following OpenCL devices:
[2012/May/2|17:30:42] NVIDIA CUDA GeForce 9300 / nForce 730i
[2012/May/2|17:30:42] cl_nv_compiler_options supported!
[2012/May/2|17:30:42] Building OpenCL trace program for device NVIDIA CUDA_G_Force 9300 / nForce 730i...
[/quote]
And I want to know, Vray use GPU or no?
I have another situation, Application Vray must use GPU, but when I start it, program freezes up

Log from console



[2012/May/2|17:30:42] Running RTEngine

[2012/May/2|17:30:42] Initializing OpenCL renderer (single kernel version)...

[2012/May/2|17:30:42] Querying for OpenCL devices...

[2012/May/2|17:30:42] warning: Environment variable VRAY_OPENCL_PLATFORMS_x64 not found - using all available devices

[2012/May/2|17:30:42] Using the following OpenCL devices:

[2012/May/2|17:30:42] NVIDIA CUDA GeForce 9300 / nForce 730i

[2012/May/2|17:30:42] cl_nv_compiler_options supported!

[2012/May/2|17:30:42] Building OpenCL trace program for device NVIDIA CUDA_G_Force 9300 / nForce 730i...



And I want to know, Vray use GPU or no?

#3
Posted 05/02/2012 10:52 AM   
Hello,

When I run cuda programs I use nvidia-smi to see on which device they run and how much memory are they using.
Hello,



When I run cuda programs I use nvidia-smi to see on which device they run and how much memory are they using.

#4
Posted 05/02/2012 01:52 PM   
Your GPU is CUDA supported and you should be able to run CUDA binaries on it. Try out some of the other samples from the CUDA SDK.
Your GPU is CUDA supported and you should be able to run CUDA binaries on it. Try out some of the other samples from the CUDA SDK.

#5
Posted 05/02/2012 05:07 PM   
Nvidia-smi doesn't support my Video Card. =(
I successfully run example from CUDA SDK.
But I watch the following picture
I run binaries (fluidsGL)
From top
[quote]
Tasks: 158 total, 4 running, 154 sleeping, 0 stopped, 0 zombie
Cpu(s): 29.4%us, 43.6%sy, 0.0%ni, 26.9%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Mem: 2830436k total, 1725668k used, 1104768k free, 35416k buffers
Swap: 3894264k total, 0k used, 3894264k free, 434632k cached

PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
3343 root 20 0 177m 61m 31m R 94 2.2 0:10.79 fluidsGL
[/quote]
It's normall?
Nvidia-smi doesn't support my Video Card. =(

I successfully run example from CUDA SDK.

But I watch the following picture

I run binaries (fluidsGL)

From top



Tasks: 158 total, 4 running, 154 sleeping, 0 stopped, 0 zombie

Cpu(s): 29.4%us, 43.6%sy, 0.0%ni, 26.9%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st

Mem: 2830436k total, 1725668k used, 1104768k free, 35416k buffers

Swap: 3894264k total, 0k used, 3894264k free, 434632k cached



PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND

3343 root 20 0 177m 61m 31m R 94 2.2 0:10.79 fluidsGL



It's normall?

#6
Posted 05/03/2012 03:43 AM   
The examples would not run without the gpu. If yuo can monitor the temperature of the card you should see and increase in the temperature followed by a ventilator increase of rpms.
The examples would not run without the gpu. If yuo can monitor the temperature of the card you should see and increase in the temperature followed by a ventilator increase of rpms.

#7
Posted 05/03/2012 06:51 AM   
Scroll To Top