Can't compile samples.

Accelerated Computing CUDA CUDA Programming and Performance
1

I can’t compile samples from SDK. Toolkit 3.2, ubuntu 11.04 64 bit. I tried to do everything like in [topic=‘196892’]this topic[/topic] but still get the following error:

make[1]: Entering directory `/home/grigory/NVIDIA_GPU_Computing_SDK/C/common'

make[1]: Leaving directory `/home/grigory/NVIDIA_GPU_Computing_SDK/C/common'

make[1]: Entering directory `/home/grigory/NVIDIA_GPU_Computing_SDK/C/common'

make[1]: Leaving directory `/home/grigory/NVIDIA_GPU_Computing_SDK/C/common'

make[1]: Entering directory `/home/grigory/NVIDIA_GPU_Computing_SDK/C/common'

make[1]: Leaving directory `/home/grigory/NVIDIA_GPU_Computing_SDK/C/common'

make[1]: Entering directory `/home/grigory/NVIDIA_GPU_Computing_SDK/shared'

make[1]: Leaving directory `/home/grigory/NVIDIA_GPU_Computing_SDK/shared'

make -C src/simpleLayeredTexture/ 

make[1]: Entering directory `/home/grigory/NVIDIA_GPU_Computing_SDK/C/src/simpleLayeredTexture'

simpleLayeredTexture.cu(39): error: identifier "cudaTextureType2DLayered" is undefined

simpleLayeredTexture.cu(59): error: identifier "tex2DLayered" is undefined

simpleLayeredTexture.cu(109): error: identifier "cudaArrayLayered" is undefined

simpleLayeredTexture.cu(126): error: no instance of overloaded function "cudaBindTextureToArray" matches the argument list

            argument types are: (texture<float, <error-constant>, cudaReadModeElementType>, cudaArray *, cudaChannelFormatDesc)

4 errors detected in the compilation of "/tmp/tmpxft_00000af6_00000000-4_simpleLayeredTexture.cpp1.ii".

make[1]: *** [obj/x86_64/release/simpleLayeredTexture.cu_20.o] Error 2

make[1]: Leaving directory `/home/grigory/NVIDIA_GPU_Computing_SDK/C/src/simpleLayeredTexture'

make: *** [src/simpleLayeredTexture/Makefile.ph_build] Error 2
2

Oh, I’ve figured that I’ve somehow managed to install toolkit 3.2 and SDK 4.0. I don’t know how it happened but it seems that is the problem.