Tagged with windows - NVIDIA Developer Forums

Tesla vs GTX560M this is wierd!

Bleiner — Wed, 16 May 2012 16:32:03 -0400

Hello Everyone,

So I have been working on porting over a lot of the more computationally intensive portions of my code from matlab to .ptx gpu code. I have been doing the development on my laptop where I have made HUGE increases in speed. Achieving at least a 10X speed up in a lot of areas. Now all my work is double precision, and involves millions of objects. My laptop with a gaming GPU (that by design has hampered double precision performance, and fewer processing cores) can complete a task in about 46 seconds.

I have a desktop with a Tesla C2075, that typically outperforms my laptop by a factor of two. When I bring this code over to the Tesla machine it is running anywhere from 42-48 seconds to complete the same task. Does anyone have any idea why this would be?

The only thing that comes to mind on this is that I upgraded my laptop to the 301.40 driver version to use Nsight visual studio, while the Tesla machine is still on 301.32 (or someething like that. When I attempted to upgrade the tesla machine it appears that the 301.40 drivers have been removed from the website. When I upgraded to the Beta Cuda 5 version drivers 301.53 (i think) Matlab no longer recognizes that there is a GPU attached to the system.

Could the issues be the driver? Did it improve that much from 301.27 to 301.4? Does it have anything to do with the GPU on the laptop being compute level 2.1 while tesla is 2.0? Is there a memory manager issue that 2.1 does a lot better?

The strange thing is that TESLA USED to perform at twice the speed of the laptop (and that includes all the overhead in matlab that is taking place on the CPU. So Tesla must have been significantly more than 2x faster.

Any thoughts?

Thanks
Ben

As an after thought here are the specs of the machines in question..
Tesla Work station
Dell Precision T5500
Xeon E5620 2.4ghz
12gb ram
Telsa C2075 with 6gb ram driver 301.32

Laptop
Asus G74S
Core I7 2670QM 2.2ghz
12gb Ram
GTX 560M 3gb ram Driver 301.40

DisplayLink BVU195 USB adapter

tnoonkes — Wed, 16 May 2012 12:54:21 -0400

I have a Lenovo T410 with the NVIDIA NVS 3100M. I recently bought a USB to DVI adapter so that i could use a 3rd monitor with my laptop. *(Laptop monitor is primary with 2 other samsung monitors attached, one via DVI input from laptop dock, second from the USB adapter.) I have updated my video drivers to the latest drivers but when i install the DisplayLink software for my USB to DVI, my computer crashes every time when i reboot windows. Please let me know if there is any fix for that adapter and NVS 3100M. Thanks.

downloading of the installer doesn't complete

mathiapeter — Wed, 16 May 2012 05:59:53 -0400

Hi, I had Nsight Visual Studio RC2 installed and everything worked fine, but now whet I try do download the final version 64bit, it shows that the installer has about 950MB but the downloading ends always at 51% so I can't run the installer. What would be the problem? I have tried 3 internet browsers but still the same.

Cuda, PTX and Debugging symbols

Bleiner — Wed, 28 Mar 2012 13:08:21 -0400

Hello everyone,

I have a question about .ptx files and debugging in Visual studio 10 professional. I am attempting to write some ptx code to integrate into Matlab. However I am ONLY writing the __global__ functions and I have not written a main function or any host code. The functions are fairly simple, but what I want to do is be able to debug my code when matlab is running it. I am compiling my code using nvcc -ptx 'functionname.cu'. and when I try to use nvcc -G -ptx 'functionname.cu' to get debugging information nothing else is returned except the .ptx file. I should mention that I am relatively new to visual studio and that is why I am compiling using the command line.

I believe that if I had the symbols generated I could attach the process to Matlab and debug it. Since .ptx is supposed to be just in time compiled code does it not allow me to have debugging symbols?

Any help would be greatly appreciated
Ben

Breakpoint don't be hit using Nsight Visual Studio

froure — Tue, 15 May 2012 08:49:16 -0400

Hi!

I'm trying to debug with Nsight. I put some breakpoints but debugger don't stop the execution there. During the debugging, this breakpoints appers with a warning icon, and when I put the mouse over, it says: "The breakpoint will not currently bye hit. CUDA: no source correspondence for breakpoint".

I try to find some solution inside the other forums, but I can't.

Can you help me please?

Thanks!! :D

Linker Issue in building a CUDA application in Visual Studio 2010

gladman — Thu, 16 Feb 2012 03:56:49 -0500

Reposted from old forum.

I am trying to build an application with Visual Studio 2010 and Nsight 2.1 hosted on Windows 7 (x64) using the 4.0 and/or the 4.1 build customisation rules.

I am using object file output format with the default filename for the output object files - $(IntDir)%(FileName)%(Extension).obj, which correctly generates all the object files in the $(IntDir) directory. But after all the files have compiled correctly, the linker build step then fails with the message:

LINK : fatal error LNK1181: cannot open input file '..\.obj'

It appears that the file listing inputs for the linker is not being generated.

If I perform the linker step manually, the application builds correctly and runs without problems. So it seems that there is an issue with the way the build customisations are producing the input file lists for the linker.

I would appreciate any advice that people can offer on what might be going wrong.

Kepler Quadro?

Bleiner — Tue, 15 May 2012 15:43:41 -0400

Hello Everyone,

Not to be a starting rumors, but has anyone heard anything about when the new Kepler Quadro cards will be coming out? I am responsible for selecting new laptops for the design department at my company. The 5010M looks to be a great card don't get me wrong, but with my code starting to rely more on CUDA, I want to get the most powerful GPU for double precision work I can find. I would hate to drop a LARGE sum of money on a laptop only to have the GPU be obsolete a month later, especially when the GPU is a major component of the cost.

Any rumors? Any employees around who can deny knowing anything while winking at the same time?

Thanks
Ben

Help adding external force to particles

dartwing17 — Sat, 12 May 2012 10:29:45 -0400

Hi,

I have run a wind simulation in Flow-3D and have exported a set of wind-vectors, which describe
a position and a velocity. I want to use these wind-vectors in my particle system, so that when a particle is inside a wind-vector position (lets say +- 0.5), the velocity of the wind-vector should be added to the particle.

I have implemented a way to do this, but it is very inefficient. I was just wondering if anyone had any suggestion on how to make the algorithm more efficient.

This is my implementation (sorry for the ugly code):

glm::vec3 checkWindPosition(glm::vec3 particlepos)
{
for(int i = 0; i < flowWindGrid.size(); i++)
if(particlepos.x < flowWindGrid[i].position.x+0.5f && particlepos.x > flowWindGrid[i].position.x-0.5f
&& particlepos.y < flowWindGrid[i].position.y+0.5f && particlepos.y > flowWindGrid[i].position.y-0.5f
&& particlepos.z < flowWindGrid[i].position.z+0.5f && particlepos.z > flowWindGrid[i].position.z-0.5f)
return flowWindGrid[i].velocity;
return glm::vec3(99,99,99);
}

void update()
{
physx::PxParticleFluidReadData* rd = pf->lockParticleFluidReadData();
if (rd->validParticleRange > 0)
{
physx::PxStrideIterator particleFlags(rd->flagsBuffer);
// iterate over valid particle bitmap
for (physx::PxU32 w = 0; w <= (rd->validParticleRange-1) >> 5; w++)
{
for (physx::PxU32 b = rd->validParticleBitmap[w]; b; b &= b-1)
{
physx::PxU32 index = (w << 5 | physx::lowestSetBit(b));
const physx::PxVec3& position = rd->positionBuffer[index];

if (particleFlags[index] & physx::PxParticleFlag::eVALID)
{
glm::vec3 newvelocity = checkWindPosition(glm::vec3(position.x,position.y,position.z));
if(newvelocity != glm::vec3(99,99,99))
{
windIndexBuffer.push_back(index);
windForce.push_back(physx::PxVec3(newvelocity.x,newvelocity.y,newvelocity.z));
}
}
}
}
}

rd->unlock();

physx::PxStrideIterator forceBuffer(&windForce[0]);
physx::PxStrideIterator indexData(&windIndexBuffer[0]);
pf->addForces(windForce.size(), indexData, forceBuffer, physx::PxForceMode::eFORCE);
}

ArrayFire + Nsight???

sizheng — Wed, 09 May 2012 21:08:48 -0400

i'm trying ArrayFire, but it seems that i cannot debug arrayfire code by nsight~~~

anybody knows how to?

Parallel Nsight 2.2 RC2 - No Source Available

wdrozd — Fri, 04 May 2012 16:35:28 -0400

When selecting CUDA Debugging with memory checker enabled I get a kernel crash with a window in Nsight that says "No Source Available". When I click on the link "Browse to Find Source", a message says "The source code cannot be displayed".

My application compiles fine, so clearly it can find the source (for both the C code and the Cuda code)

Also I have no problem stopping at a breakpoint set in my Kernel prior to the crash (grid launch failure)

The call-stack says "No active Cuda Kernels".

Can you please me determine how to set Nsight to detect the source?

Thanks.

Can I incorporate volume data into PhyX?

chloe5608 — Wed, 09 May 2012 11:53:28 -0400

Hi, I'm new to PhysX and I'm trying to do some fluid simulation with volumetric data. I have my old SPH code written in C++ and the particles can collide with volume data. But I'm thinking of apply phsX for my simulation since I want to use more particles and my old implementation of SPH is not quite robust.

Can I extract the property of particle(e.g. position, velocity, acceleration) and do the collision myself then send the data back? All the volume data is available on both CPU and GPU(texture).

UI Composer studio

gandlaf — Mon, 14 May 2012 07:52:59 -0400

I started with the T20 Colibri board my development. As a part of the Demos software I found the UI Composer Demo. Now I am questioning from where I can get the UI Composer studio.
Thanks

I want to display 3d pictures through 3D TV which is connected to my pc by HDMI port.

zhaiwenguo — Mon, 14 May 2012 06:15:17 -0400

I want to write a program to display 3D pictures(Or play 3D movies) through 3D TV which is connected to my PC by HDMI port. Just like NVIDIA 3D vision. Which APIs can I use? Thank you in advance. Are there some examples?
(GeForce GT 555M , Visual Studio 2008)

Double Double or Arbitrary Precision

rdunn — Sun, 13 May 2012 21:43:53 -0400

I need to compare a high precision (i.e at least 2x that of double) with results from my CUDA kernels in double and single precision to establish how accurate they are compared to other implementations.

I have struggled and failed at getting GMP/MPIR to build on a windows platform with visual studio 2010. I've tried building GMP/MPIR with mingw to no avail too.

Does nVidia have a double-double library?, I saw a forum post to it (http://forums.nvidia.com/index.php?showtopic=218452), but are unable to find the actual file.

Trouble with processing image in rows

laz007 — Sun, 13 May 2012 05:29:07 -0400

Hello!
I'm making an image filter that is processing the image in rows.
Two weeks I'm trying to figure out why it's not working when executed in parallel.
I use only threads in the Y dimension. Is that a problem?

Here is part of the code:
BLOCKDIM_Y=16;
....
dim3 threads(1, BLOCKDIM_Y);
dim3 grid(1, iDivUp(h, BLOCKDIM_Y));

my_CUDA_filter<<< grid, threads>>>(sumR, sumG, sumB, mask,h,w, inD, outD, test);
...

__global__ void my_CUDA_filter_simple222(int* sumR, int* sumG, int* sumB, int mask,int h,int w, u_int8_t *in, u_int8_t *out, int* test){
...
int iy = blockDim.y * blockIdx.y + threadIdx.y;
int ix=0;

if (iy>=m && iy<(h-m)) {

//for(iy=m; iy
...
for(ix=m+1;ix ...
}
}

The result image is messed up...
If I use for(iy=m; iyand run the kernel with one single thread (that means there is no parallelization) everything is OK.

Any ideas?

Please Help! I have two display adapters...

boomer88 — Fri, 11 May 2012 12:21:43 -0400

Just bought a new Dell Inspiron 2320, it has integrated and dedicated video card. Under display adapters i see "Intel(R) HD Graphics Family" and "NVIDIA Geforce GT 525M", if i disable Intel driver, the Nvidia driver doesnt work. I need Nvidia to be responsible for my desktop display, as i cant calibrate colors properly with a crappy Intel HD controls. The colors look horrible and over saturated... i need it to be better for work. Thank.

Linker error with c function in .cu file

basementscientist — Fri, 04 May 2012 16:08:40 -0400

I've created a kernel inside a .cu file. Also inside the .cu file is a c++ function that calls
the kernal. Everything compiles ok, but on the final linking, the c++ function is not visible to the rest of the program. How do I make the function visible?

I am using Visual Studio 2010 on Windows 8, and the newest SDK and Toolkit.

Visual C++ 2010 with PhysX SDK

Kronus980 — Mon, 09 Apr 2012 14:13:12 -0400

I was wondering if someone could help me set up the SDK with Visual C++ 2010? Having a lot of trouble doing this. Thanks!

Brand new NVIDIA card!! What is the Error code: 3?

renia — Thu, 10 May 2012 15:08:08 -0400

Hello everyone,
I will try to be as short as possible.
I have a brand new NVIDIA GeForce 8400MG 256 MB and running Windows 7 Professional x64.
I am an architect and using AutoCAD, Rhino, Photoshop etc.
The problem is that everyday since I bought this display card my computer stops workings. I see a black screen for a few seconds and then the following message:

"The NVIDIA OpenGL driver detected a problem with the display driver and is unable to continue. The application must close.
Error code: 3"

This has happened when I was working in photoshop but also when I just had my internet browser open. I have updated my drivers and really don't know what else to do.

Thank you in advance

Quadro FX3700 reporting "GDI Generic" version 1.1.0 ?!?

bsenftner — Thu, 03 May 2012 15:17:21 -0400

I have a combo web server / hi-compute server inside a Windows Server 2008 R2 machine. The physical machine is in a collocation, and I access it via the web sites it serves and via Remote Desktop Commection (RDC) when installing, configuring & maintaining the system.

I have a few programs which attempt to create OpenGL contexts, render into the framebuffer, copy the results, and write them to an image file. However, the rendered results are black or noise filled images.

I installed the "Geeks3D GPU Caps Viewer" (build 1.16.0 from April 11, 2012) and it is reporting, from a RDC connection, GL_RENDERER: "GDI Generic", GL_VERSION: 1.1.0, GLSL version: N.A.

It looks like something additional, or extra is required to get Accelerated 3D Rendering in a headless context under Windows Server 2008 R2. Can anyone point out any information or references to help out?

[PhysX 3.2 beta-3] Cannot convert binary data from 32 to 64 bit

Budai — Wed, 25 Apr 2012 18:52:35 -0400

Hi,

I have been experiencing an access violation when I deserialize a repx file, convert it from 32 to 64 bit, and deserialize the result on a 64-bit platform.

I have attached a vs2010 project as a test case. You might have to check the platform toolset on x64, as I'm using vs express.

Thank you for your time,
Budai

nvstereo.h

colneilens — Wed, 09 May 2012 17:41:39 -0400

Is there an updated version of nvstereo.h for dx11? The one in SDK 11 only deals with DX9 and DX10?
Thanks,
Colin Neilens
Digital Extremes.

GPU-aware hash cell size ???

man82bs — Wed, 09 May 2012 03:01:19 -0400

Hi guys..

Recently I am working on a project which uses hash table.

And I am trying to use gpu for computations on the data in each cell.

My problem is which cell size gives me best performance.

For example, if there are normalized 1M points which has uniform distribution,

how much points should be included in a cell??

Generally, heuristic experiments decide the cell size but I really need ideas.

If there are anyone who have an idea, help me plz...

Thanks.

MassFX warning with 3ds Max scenes installed with PhysX

hotdoggyurkeyam — Tue, 08 May 2012 14:39:23 -0400

Hi, I get a warning when I open another max scene on another machine here at work, it says:

“The MassFX authored in this file was created with a newer version of the plugins. Forward compatibility is not supported so things might not behave properly.”

I am currently using PhysX for Max version: 2.7.1.0202.1800 and PhysX System Software 9.11.0621 abd I have noticed inside my Max install location, MassFX has been moved into a folder named "DISABLED_BY_NVIDIA_PHYSX_PLUGINS"

Third party plugins installed for Max being used in the scene are: Rayfire 1.57.10; Orbaz Particle Flow Box #2 ver. 1.07 and #3 ver. 1.53. I’ve gotten this warning in scenes saved from another PC, opened in another, and not even using any PhysX or PhysX capable plugins.

Thanks.

Infrared(Nvidia) Box Office Set

joonkp1976 — Fri, 04 May 2012 23:40:24 -0400

Infrared communications device attached to back of your video card, plus infrared receptor with 3 colored video and stereo audio input and/or more then 1 of these, for TV and the home theater sound systems, plus software suite that comes with the video card that installs and works with these and the last remote controller that works on TV infrared connector unit. Call it 'Nvidia Box Office Set' and price it at the box set price of let us say 10 dollars for the remote controller unit and 10 dollars more for the software suite and 5 dollars for the convinience, making it an attractive buy and convinient solution to PC to TV media trasfer... Software suite that works with all the media formats and remote controller unit that can pause, rewind, fast forward, stop, play, etc where the TV unit will send wire- less infrared signals to do these options through the video card's communications device and then through video card then to the software suite... Nvidia could be the first to venture into the wire-less infrared Home Box Office Set business and it would have to be Nvidia if you ask me since Nvidia video cards chop less on MMORPGs and that is why I am a supporter of Nvidia... :> I hate the Ati video cards and lag chops. Really do. Passionately do... I currently have a system with Ati and next one for sure will be an Nvidia system that I promise myself everyday. Anyways, if anyone was interested with my idea of Infrared Box Office Set, leave me a line and if anyone from Nvidia sees this an interest, also leave me a line. Thanks a bunch people and enjoy great computing~!
\(-_-)/

CUDA integration in vs 11 beta.

m227 — Sat, 07 Apr 2012 19:04:21 -0400

Hi,
Sorry if this question was asked before but here it is: is there a way to integrate CUDA in vs 11 beta the same way it is in vs 2010?
Thanks,
G.

Which version of the NVAPI should I use with my Quadro FX 570 card?

braggo — Fri, 04 May 2012 15:19:38 -0400

Dell desktop, Windows 7
Nvidia Quadro FX 570

I am currently using R295 February 2012 release of the NVAPI and some of the functions are returning an error code -9 NVAPI_INCOMPATIBLE_STRUCT_VERSION.

Specifcally, the NvAPI_DISP_SetDisplayConfig() and NvAPI_DISP_GetDisplayConfig() when I pass in a NV_DISPLAYCONFIG_PATH_INFO struct.

Here are my debug print outs:

NvAPI_Initialize(): mStatus = NVAPI_OK
STRUCT Versions:
NV_DISPLAY_DRIVER_VERSION_VER = 65676
NV_DISPLAY_PORT_INFO_VER = 65580
NV_DISPLAYCONFIG_PATH_INFO_VER = 131100
NV_DISPLAYCONFIG_PATH_ADVANCED_TARGET_INFO_VER = 65664
NvAPI_SYS_GetChipSetInfo(&mChipSetInfo): mStatus = NVAPI_OK
-- ChipSet Info --
Device Id = 10720
HBdeviceId = 10720
Vendor Name = Intel
struct version = 262376
NvAPI_GetInterfaceVersionString(): mStatus = NVAPI_OK
NvAPI Version = NVidia Complete Version 1.10
NvAPI_SYS_GetDriverAndBranchVersion(): mStatus = NVAPI_OK
GPU Driver Version = 27533
Branch String = r275_21

Is the GPU driver version incompatible with the API version macros?

Thank you in advance for your help!

Issue using NSight 2.2 rc2 with VS11

diver182 — Wed, 02 May 2012 15:19:27 -0400

Hi,

I installed VS11 (Ultimate) beta on my Win7 machine,
after that the 4.2x SDK and then Parallel NSight 2.2 rc2.
The NSight installer claimed to have made modifications to the VS11 installation.
But I can neither find the NSight menu on the upper pane nor the templates
for creating a cuda 4.2 project.

Do I have to adjust anything to make it work or what did I miss?

Cuda Kernels Stop Running After Few Iterations

Eman — Sat, 21 Apr 2012 14:15:31 -0400

Hello,

I am writing a code that calls a number of kernels inside a for loop. The number of the loop iterations is 1000. When I run the program, the kernels stop running after a number of iterations. I tried to use cudaGetLastError(); but it didn't give me any information as the output was "Error: unknown error". AS I increase the size of the blocks and the number of threads, the kernels stop running sooner. For example, when the block size is 8 it stopped at iteration 740, while when the size of the block is 16, it stopped at iteration 440. In each iteration the same resources is being re-used so I really don't understand what is the problem!.

Any help will be appreciated.

Thanks,

GAI sample games don't work, GT240 CC1.2

Pawe — Thu, 03 May 2012 08:07:03 -0400

Hi,
I am working on parallel AI game-tree-search project and just wanted to run examples from NVIDIA GAI project as there is everything I would need. Unfortuanately sample applications do not work proparly on my PC (with CC=1.2, windows x64, and latest drivers installed). Actually I can only run a game with CPU AI. When GPU is toggle only random player plays and always wins. I must be sure that these libraries work proparly so I can write similliar one for another game in my project. Please help!

pfnIaSetIndexBuffer in NVIDIA display driver

gzMarshall — Thu, 03 May 2012 05:46:50 -0400

Hi,

I'm trying to render overlay in game via hooking the NVIDIA display driver. I hooked the pfnPresent and render the overlay in the function. When I called the NVIDIA's native function pfnIaSetIndexBuffer, it returns device removed error. The MSDN about the WDDM is too simple to debug. Does anyone in this forum know the issue?

D3D10DDIARG_CREATERESOURCE mtxResource;
mtxResource.pInitialDataUP = NULL;
mtxResource.ResourceDimension = D3D10DDIRESOURCE_BUFFER;
mtxResource.Usage = D3D10_DDI_USAGE_DEFAULT;
mtxResource.MapFlags = 0;
mtxResource.MiscFlags = 0;
mtxResource.Format = DXGI_FORMAT_UNKNOWN;
mtxResource.SampleDesc.Count = 1;
mtxResource.SampleDesc.Quality = 0;
mtxResource.MipLevels = 1;
mtxResource.ArraySize = 1;
mtxResource.pPrimaryDesc = NULL;

D3D10DDI_MIPINFO indiciesSize;
indiciesSize.PhysicalWidth = indiciesSize.TexelWidth = sizeof(ovlIndicies);
indiciesSize.PhysicalDepth = indiciesSize.PhysicalHeight = indiciesSize.TexelDepth = indiciesSize.TexelHeight = 1;
mtxResource.pMipInfoList = &indiciesSize;

D3D10_DDIARG_SUBRESOURCE_UP indiciesInitialData;
indiciesInitialData.pSysMem = ovlIndicies;
indiciesInitialData.SysMemPitch = 0;
indiciesInitialData.SysMemSlicePitch = 0;
mtxResource.pInitialDataUP = &indiciesInitialData;

mtxResource.BindFlags = D3D10_DDI_BIND_INDEX_BUFFER;
SIZE_T szIndicies = m_pDevice->m_deviceFuncs.pfnCalcPrivateResourceSize(m_pDevice->GetDrv(), &mtxResource);
m_hIndicies.pDrvPrivate = (void *)(new char[szIndicies]);

D3D10DDI_HRTRESOURCE hrtNull;
hrtNull.handle = new char[szIndicies];

m_pDevice->m_deviceFuncs.pfnCreateResource(m_pDevice->GetDrv(), &mtxResource, m_hIndicies, hrtNull);

m_pDevice->m_deviceFuncs.pfnIaSetIndexBuffer(m_pDevice->GetDrv(), m_hIndicies, DXGI_FORMAT_R32_UINT, 0);

LNK2001 Undefined symbol not found

ronthompson — Wed, 02 May 2012 15:58:17 -0400

I'm using cuda 4.1 and Visual Studio 2008 C++. I have several routines in C that are called from my main program in C++. The C and CUDA routines are compiled with nvcc and the C++ is compiled with the compiler supplied in VS 2008. It all compiles fine. It won't link because it can't find the routines in C. I use the extern "C" with the C routines in the global area of my main. It does not help. I believe it is linking using the VS2008 linker and not nvcc. What am I doing wrong?

Ron

Shared memory usage

man82bs — Wed, 02 May 2012 02:07:18 -0400

Hi, I have a question about the basic usage for the shared memory.

Each multiprocessor has own shared memory, right?
and my gpu has 48KB shared memory.

Then, my question is, each multiprocessor has shared memory of 48KB or summation of 8 multiprocessor is 48KB.

It's so confusing.

Thanks in advance.

cheers.

HW Debug Support

Vector — Tue, 01 May 2012 19:41:18 -0400

Which gpus have hardware debug support to use with NSight 2.2's single gpu debug feature?
Thanks

2 GTX265 cards not detected for debugging

vinaybgavirangaswamy — Mon, 09 Apr 2012 01:11:30 -0400

Hi,

Thank you for reading this and taking time to help me configure for debugging

I am trying to do code line by line debugging on a system with 2 gtx 265 cards. I have tried to list my system configuration below if thinking it might help

Mother board gigabyte 990fxa-ud3
graphics card gtx265 (one from zotech and other is from asus)
OS: Windows 7 (64 bit)
graphics driver: devdriver_4.1_winvista-win7_64_286.19_general
CUDE toolkit: cudatoolkit_4.1.28_win_64
parallel nsight: Parallel_Nsight_Win64_2.1.0.12046
SLI: disabled
WDDM TDR enabled: false
wpf hardware acceleration: disabled by running registry file in nsight common folder

I am not able to make other graphics card as headless as I do not have that option in nvidia controller. I have attached few pictures of what I see in the controller screen

Please help me as I am trying to use this for a course project...

Thank you in advance!

SOLVED Problem in Optix and HD graphics ? No srgb support

Conkal — Sat, 28 Apr 2012 12:11:11 -0400

Hello ,

I am programming a Bidirectional Path tracer in Optix and I have encountered a problem , which is also the same using the "Path tracer" sample from the Nvidia Optix Samples.

(My computer is using intel i5-2500K (with iGpu intel HD-3000)and GTX560ti+ GTX460 , monitor is Samsung P2270, but the same happened in a couple of other computers. The drivers are the official ones with default parameters )

The problem is this :

1. When i connent my monitor to the GTX 560ti or GTX 460 graphics cards that i have, then the colors in the rendering are a lot brighter than when connecting the monitor to the iGPU of the processor.

2. The result of the "printscreen function"(pressing s in the rendering window) is the same with the result in the igpu .

What is happening ? Is it a bug from the sample code that copied by mistake or is it a problem with optix ? And more importantly WHICH RENDERING IS THE RIGHT ONE ?

I have uploaded the rendering of the default path tracer example and the same scene(almost) in mine.

Each one has three pictures , printscreen using the gtx , another one using the intel HD and the optix output from the "s" command.

Level of detail in Nsight profiling?

obuzko — Thu, 26 Apr 2012 20:00:54 -0400

Hi all,
I'm trying to optimize a fairly complex kernel that includes quite a few functions. Is Parallel Nsight capable of determining function-level performance bottlenecks within a kernel?
I'm using version 2.0 with VS2010 and a Tesla2050, and it appears to be limited to the kernel as a unit with no further breakdown. Can the latest version provide function-level profiling? If not, could someone suggest an alternative (if available)?
Thanks in advance

Sasha

Running program in VS2010: Loading symbols from NVIDIA detoured.dll very slow

smash85 — Wed, 25 Apr 2012 09:41:02 -0400

I have a program which I am working on my Dell Laptop XPS 502X. At work, I usually have another monitor plugged in my DVI port and everything is fine. When I work from home, I only have the laptop screen. When I start the program in VS2010, it is very slow and I notice in the bottom of the screen Loading symbols for ...\NVIDIA Corporation\coprocmanager\detourel.dll... which takes around 10-20 seconds every time. Any idea on why this is happening ?

Origin of CUDA_ERROR_INVALID_IMAGE when calling cuModuleLoad - invalid nvcc call?

mkastrop — Thu, 15 Mar 2012 04:59:27 -0400

I always get the CUDA_ERROR_INVALID_IMAGE CUresult when calling cuModuleLoad on my .cubin-file. Even if I break it down to the following most simple kernel:


// minimal.cu

__global__ void
minimal()
{
}

My compiler call looks like the following:


nvcc.exe -cubin -arch=sm_21 -o "minimal.cubin" "minimal.cu"

Its output looks good, doesn't it?


minimal.cu
minimal.cu
tmpxft_00000b38_00000000-3_minimal.cudafe1.gpu
tmpxft_00000b38_00000000-10_minimal.cudafe2.gpu

My system is a Win7 machine with one NVIDIA Quadro 600 in it. Can you please explain what I am doin' wrong? Unfortunately there are no concrete explanations to the CUDA error codes like I know them from OpenCL... That would be preferable.

286.16 driver crash in matlab running .ptx file

Bleiner — Wed, 28 Mar 2012 13:15:17 -0400

Hello everyone,

I am attempting to integrate some cuda code into my matlab work using .ptx code. The code I have written so far appears to work initially. This code is getting run in a loop with the input data changing each time. After the first run it appears to have the correct answer. When it hits the second time the driver crashes, and my screen flickers on and off for a second. It then lets me know that the driver crashed but it recovered. Then as far as matlab is concerned the GPU is busy until I reboot matlab.

The only thing I can think of is that it doesn't like the fact that the various inputs and outputs are changing in size. On each pass the size of the input and output arrays are getting smaller. I tried clearing the data off the GPU using both clear and reset, but it doesn't seem to make a difference.

Any thoughts?
Ben

Why is a GTX680 even slower than a GTX480 when using CUDA?

nepluno — Tue, 17 Apr 2012 07:39:41 -0400

I've tested several Apps in the GPU Computing SDK, such as the GrabCutNPP. Surprisingly I found the GTX680 is even slower than my old GTX480 (about 0.9x). Why could this happen? In contrast, the test on 3DMark11 reported that the GTX680 is 2x faster.

The installed driver is 301.10, with a CUDA Toolkit 4.26. My OS is Windows 7 SP1. I even compile the code using compute_30 and sm_30, but the result kept the same.

ps: I couldn't find a developer version driver that supports GTX680.

Cannot find Reduce1.sln

celebisait — Mon, 23 Apr 2012 05:21:04 -0400

Hi,

I'm new at GPU programming and CUDA. I read the CUDA C Programming Guide. It was very helpful for me. And now I'm reading that tutorial* from Cyril Zeller. However, it says "Open up reduce\src\reduce1.sln" on the page 36/157, and I couldn't find that visual studio solution file.

I have NVIDIA GPU Computing SDK 4.1. I searched in the SDK and found something at:

"C:\ProgramData\NVIDIA Corporation\NVIDIA GPU Computing SDK 4.1\C\src\reduction"

but I'm not sure is that the same thing with the PDF because it doesn't have the solution files separate like reduce1.sln, reduce2.sln etc.

I will be appreciated for any help,
Sait.

*http://people.maths.ox.ac.uk/~gilesm/hpc/NVIDIA/NVIDIA_CUDA_Tutorial_No_NDA_Apr08.pdf

PBO + glTexSubImage2D hangs

attilaafra — Tue, 24 Apr 2012 18:02:43 -0400

I'm uploading frames into a texture using a pixel buffer object. I'm using an NVS 5100M and Windows 7 x64. With driver version 275.33 or older it works fine, but with 296.10, 296.35 and 301.27 the glTexSubImage2D call hangs for a few seconds. Sometimes it recovers, but usually TDR kicks in or even causes a BSOD. The problem is not specific to my code, and it can be easily reproduced using this PBO sample code: http://www.songho.ca/opengl/files/pboUnpack.zip

Do you have any idea what's wrong? Many thanks!

PhysX Lab unable to open .apb files

dgermain — Tue, 24 Apr 2012 09:55:49 -0400

I can import .obj files, save them as .apb, use them in the sample demo without much problems.

However I'm unable to open/import .apb files, neither the files that used in the SimpleDestruction demo nor the files I created/exported with physx Lab.

When I do an 'import 3d Mesh' and try opening a .apb file, I receive no error, but nothing happen in the editor as if I did not do anything.

Is that a known issue, or I am the only one experiencing this problem ?

Thanks,
DG

nppiHistogramRange_16u_C1R really slow

candreoli — Thu, 01 Mar 2012 03:20:57 -0500

I'm trying to migrate from my IPP based program to a NPP based program....i have to get the histogram of a 16 bit unsigned images but the function nppiHistogramRange_16u_C1R is really slow....for me it's faster to

1) convert the image to 32f

2) calculate the histogram using nppiHistogramRange_32f_C1R
and go on with my code....

There is maybe some issue to fix?

Thanks in advance, Carlo

Crash with the new LLVM compiler

Tofic — Mon, 02 Apr 2012 06:41:37 -0400

Hi,

OpenCL 1.1, drivers 296.10, GTX 580, 64-bits compiler, Windows 7 64-bits.

100% crash inside the compiler, when trying to compile this construction (well-compilable with the old compiler):
const struct BBox bbox = { (float4)(-.5f,-.5f,-.5f,0), (float4)(.5f,.5f,.5f,0) };

....

Error: OpenCL error 'Invalid binary': compilation error
ptxas application ptx input, line 13; error : Module-scoped variables in .local state space are not allowed with ABI

or

UNREACHABLE executed.

Fix: remove the "const" modifier. Started with new LLVM compiler.

Best wishes,
Anton

openCL equivalent for "cudaMallocPitch"..?

HariniS — Tue, 24 Apr 2012 03:01:59 -0400

Hi every one,
I am very new to openCL and strated converting on eof the cuda code to opencl but got stuck in this part of code.My PC is having AMD processor with ATI graphics card which doesnt support openCL, but other codes are running fine here by falling back to CPU. someone please give me some suggestion so that i can get rid of this problem. the cuda code is

size_t pitch = 0;
cudaError error = cudaMallocPitch( (void**)&gpu_data, (size_t*)&pitch, instances->cols * sizeof(float), instances->rows);

for( int i = 0; i < instances->rows; i++ ){
///error = cudaMemcpy((void*)(gpu_data + (pitch/sizeof(float))*i), (void*)(instances->data + (instances->cols*i)), instances->cols * sizeof(float) ,cudaMemcpyHostToDevice);

My converted openCL code is

gpu_data = clCreateBuffer(context, CL_MEM_READ_WRITE, ((instances->cols)*(instances->rows))*sizeof(float), NULL, &ret);

for( int i = 0; i < instances->rows; i++ ){
ret = clEnqueueWriteBuffer(command_queue, gpu_data , CL_TRUE, 0, ((instances->cols)*(instances->rows))*sizeof(float),(void*)(instances->data + (instances->cols*i)) , 0, NULL, NULL);
if(ret != CL_SUCCESS)
break;
}

some times it works fine but some times it stucks. But every time it stucks in reading part i.e.

ret = clEnqueueReadBuffer(command_queue, gpu_data, CL_TRUE, 0,sizeof( float ) * instances->cols* 1 , instances->data, 0, NULL, NULL);

where "gpu_data" is a device memory of type cl_mem and "instances" is a "matrix".
For both case its giving
Unhandled exception at 0x10001098 in CL_kmeans.exe: 0xC000001D: Illegal Instruction.
when break is pressed
No symbols are loaded for any call stack frame. The source code cannot be displayed.

and in Call stack,

> OCL8CA9.tmp.dll!10001098()
[Frames below may be incorrect and/or missing, no symbols loaded for OCL8CA9.tmp.dll]
amdocl.dll!5c39de16()

is displayed. Someone please help me in getting out of this.
Thanks in advance

Issues with using CUDA specifically on a version of Linux, Mac or a particular Windows release?

Nadeem Mohammad — Mon, 29 Aug 2011 18:06:16 -0400

We have a comprehensive QA procedure to test all our supported configurations - but sometimes you may need to tweak your installation or there even some bugs or issues. Use these forums with the correct TAGs to ask a question or share some ideas.

PhysX SDK 3.2: Physx Visual indicator shows PHYSX>CPU

buzzfan — Thu, 12 Apr 2012 08:32:16 -0400

This almost feels like a dumb question because I can't seem to find a definitive answer. I'm using PhysX SDK 3.2 and have a single GTX550Ti using PhysX v9.12 and 296.10 drivers. When I run either my own code or the SDK samples I see PHYSX>CPU on the top left. I seem to recall that it used to show PHYSX>GPU at some point in the past. Can someone tell me whether I should expect to see PhysX running on the GPU and if so, any ideas why it might not be working (with the 3.2 SDK samples at least).

Thanks, Mark