Play with CUDA

Need to program on CUDA, so try to compile some examples first.

Installation

I already have CUDA installed on my system, so this section is just a list of commands that might be useful when installation.

Lookup Linux Centos release version:

$cat /etc/redhat-release
Red Hat Enterprise Linux Server release 7.6 (Maipo)

Look up Unix system information:

$uname -a
Linux tehp1308 3.10.0-957.el7.x86_64 #1 SMP Thu Oct 4 20:48:51 UTC 2018 x86_64 x86_64 x86_64 GNU/Linux

List PCI devices, search for Nvidia devices only, case insensitively:

$lspci | grep -i nvidia
2d:00.0 VGA compatible controller: NVIDIA Corporation Device 2204 (rev a1)
2d:00.1 Audio device: NVIDIA Corporation Device 1aef (rev a1)

gcc compiler support:

$gcc -v
Using built-in specs.
COLLECT_GCC=gcc
COLLECT_LTO_WRAPPER=/usr/libexec/gcc/x86_64-redhat-linux/4.8.5/lto-wrapper
Target: x86_64-redhat-linux
Configured with: ../configure --prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info --with-bugurl=http://bugzilla.redhat.com/bugzilla --enable-bootstrap --enable-shared --enable-threads=posix --enable-checking=release --with-system-zlib --enable-__cxa_atexit --disable-libunwind-exceptions --enable-gnu-unique-object --enable-linker-build-id --with-linker-hash-style=gnu --enable-languages=c,c++,objc,obj-c++,java,fortran,ada,go,lto --enable-plugin --enable-initfini-array --disable-libgcj --with-isl=/builddir/build/BUILD/gcc-4.8.5-20150702/obj-x86_64-redhat-linux/isl-install --with-cloog=/builddir/build/BUILD/gcc-4.8.5-20150702/obj-x86_64-redhat-linux/cloog-install --enable-gnu-indirect-function --with-tune=generic --with-arch_32=x86-64 --build=x86_64-redhat-linux
Thread model: posix
gcc version 4.8.5 20150623 (Red Hat 4.8.5-44) (GCC)

Upgrade gcc version temporaryly

$sudo yum -y install centos-release-scl
$sudo yum -y install devtoolset-8-gcc devtoolset-8-gcc-c++ devtoolset-8-binutils
$sudo scl enable devtoolset-8 csh
$which gcc
/opt/rh/devtoolset-8/root/usr/bin/gcc
$gcc --version
gcc (GCC) 8.3.1 20190311 (Red Hat 8.3.1-3)
Copyright (C) 2018 Free Software Foundation, Inc.
This is free software; see the source for copying conditions.  There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.

if let it be permanent

$echo "source /opt/rh/devtoolset-8/enable" >>/etc/profile

After installation:

test nvcc version:

$nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2020 NVIDIA Corporation
Built on Tue_Sep_15_19:10:02_PDT_2020
Cuda compilation tools, release 11.1, V11.1.74
Build cuda_11.1.TC455_06.29069683_0

Compile the examples

try to compile one of the samples

$cd NVIDIA-Sample
$make
...
$cd bin/x86_64/linux/release/ # where the compiled files stored

compilation error: cannot find -lglut

compilation with get failed at some samples and the error message shows:

/opt/rh/devtoolset-8/root/usr/libexec/gcc/x86_64-redhat-linux/8/ld: cannot find -lglut
collect2: error: ld returned 1 exit status

check libglut:

$ls /usr/lib64 |grep glut
libkwinglutils.so.1
libkwinglutils.so.1.0.0

it turns out there is no libglut exist, install by yum

$sudo yum install freeglut
...
$ls /usr/lib64 | grep glut
libglut.so.3
libglut.so.3.10.0
libkwinglutils.so.1
libkwinglutils.so.1.0.0

try compile, the same error exit, gcc does not manage to find the lib, according to solve the problem of “cannot find -lglut”, link this file as libglut.so.

sudo ln -s /usr/lib64/libglut.so.3 /usr/lib64/libglut.so

compile success!

Play with examples

$./vectorAddDrv # a small case 
Vector Addition (Driver API)
> Using CUDA Device [0]: GeForce RTX 3090
> findModulePath found file at <./vectorAdd_kernel64.ptx>
> initCUDA loading module: <./vectorAdd_kernel64.ptx>
> PTX JIT log:

Result = PASS

$./deviceQuery
./deviceQuery Starting...

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

Detected 1 CUDA Capable device(s)

Device 0: "GeForce RTX 3090"
  CUDA Driver Version / Runtime Version          11.2 / 11.1
  CUDA Capability Major/Minor version number:    8.6
  Total amount of global memory:                 24259 MBytes (25437339648 bytes)
  (82) Multiprocessors, (128) CUDA Cores/MP:     10496 CUDA Cores
  GPU Max Clock rate:                            1695 MHz (1.70 GHz)
  Memory Clock rate:                             9751 Mhz
  Memory Bus Width:                              384-bit
  L2 Cache Size:                                 6291456 bytes
  Maximum Texture Dimension Size (x,y,z)         1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384)
  Maximum Layered 1D Texture Size, (num) layers  1D=(32768), 2048 layers
  Maximum Layered 2D Texture Size, (num) layers  2D=(32768, 32768), 2048 layers
  Total amount of constant memory:               65536 bytes
  Total amount of shared memory per block:       49152 bytes
  Total shared memory per multiprocessor:        102400 bytes
  Total number of registers available per block: 65536
  Warp size:                                     32
  Maximum number of threads per multiprocessor:  1536
  Maximum number of threads per block:           1024
  Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
  Max dimension size of a grid size    (x,y,z): (2147483647, 65535, 65535)
  Maximum memory pitch:                          2147483647 bytes
  Texture alignment:                             512 bytes
  Concurrent copy and kernel execution:          Yes with 2 copy engine(s)
  Run time limit on kernels:                     Yes
  Integrated GPU sharing Host Memory:            No
  Support host page-locked memory mapping:       Yes
  Alignment requirement for Surfaces:            Yes
  Device has ECC support:                        Disabled
  Device supports Unified Addressing (UVA):      Yes
  Device supports Managed Memory:                Yes
  Device supports Compute Preemption:            Yes
  Supports Cooperative Kernel Launch:            Yes
  Supports MultiDevice Co-op Kernel Launch:      Yes
  Device PCI Domain ID / Bus ID / location ID:   0 / 45 / 0
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 11.2, CUDA Runtime Version = 11.1, NumDevs = 1
Result = PASS