GPUEngine: Kernel: invalid device function

[mahi2406]

any help?

GPUEngine: Kernel: invalid device function

root@my-pc:/home/van# ./vs -gpu 1ffff Difficulty: 264104224 Search: 1ffff [Compressed] Start Sat Aug 24 00:00:19 2019 Base Key:CFAA17E3291B6B89DEBD839F00BAB73587E85F29ED7CFECD04E72328A51A6C30 Number of CPU thread: 1 GPU: GPU #0 GeForce RTX 2060 SUPER (34x64 cores) Grid(272x128) GPUEngine: Kernel: invalid device function

root@my-pc:/home/van# ./vs -l GPU #0 GeForce RTX 2060 SUPER (34x64 cores) (Cap 7.5) (7952.3 MB) (Multiple host threads)

root@my-pc:/home/van# ldd ./vs linux-vdso.so.1 => (0x00007ffcca289000) libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 (0x00007f988568b000) libcudart.so.8.0 => /usr/local/cuda-8.0/targets/x86_64-linux/lib/libcudart.so.8.0 (0x00007f9885425000) libstdc++.so.6 => /usr/lib/x86_64-linux-gnu/libstdc++.so.6 (0x00007f98850a3000) libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007f9884d9a000) libgcc_s.so.1 => /lib/x86_64-linux-gnu/libgcc_s.so.1 (0x00007f9884b84000) libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007f98847ba000) /lib64/ld-linux-x86-64.so.2 (0x00007f9885b2b000) libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 (0x00007f98845b6000) librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 (0x00007f98843ae000)

root@my-pc:/home/van# gcc -v Using built-in specs. COLLECT_GCC=gcc COLLECT_LTO_WRAPPER=/usr/lib/gcc/x86_64-linux-gnu/5/lto-wrapper Target: x86_64-linux-gnu Configured with: ../src/configure -v --with-pkgversion='Ubuntu 5.4.0-6ubuntu1-16.04.11' --with-bugurl=file:///usr/share/doc/gcc-5/README.Bugs --enable-languages=c,ada,c++,java,go,d,fortran,objc,obj-c++ --prefix=/usr --program-suffix=-5 --enable-shared --enable-linker-build-id --libexecdir=/usr/lib --without-included-gettext --enable-threads=posix --libdir=/usr/lib --enable-nls --with-sysroot=/ --enable-clocale=gnu --enable-libstdcxx-debug --enable-libstdcxx-time=yes --with-default-libstdcxx-abi=new --enable-gnu-unique-object --disable-vtable-verify --enable-libmpx --enable-plugin --with-system-zlib --disable-browser-plugin --enable-java-awt=gtk --enable-gtk-cairo --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-5-amd64/jre --enable-java-home --with-jvm-root-dir=/usr/lib/jvm/java-1.5.0-gcj-5-amd64 --with-jvm-jar-dir=/usr/lib/jvm-exports/java-1.5.0-gcj-5-amd64 --with-arch-directory=amd64 --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --enable-objc-gc --enable-multiarch --disable-werror --with-arch-32=i686 --with-abi=m64 --with-multilib-list=m32,m64,mx32 --enable-multilib --with-tune=generic --enable-checking=release --build=x86_64-linux-gnu --host=x86_64-linux-gnu --target=x86_64-linux-gnu Thread model: posix gcc version 5.4.0 20160609 (Ubuntu 5.4.0-6ubuntu1 16.04.11)

[iMilnb]

I figured out this one, you have to change the value of ccap to a value corresponding to your GPU. Values can be found here https://en.wikipedia.org/wiki/CUDA#Supported_GPUs My GTX 970 for example has a CC version of 5.2, so I set ccap=52. Works now.

[ratijas]

Hi. I am new to this topic of CUDA programming.

Based on what I read, ccap is the Compute capability (version). So, few questions.

• Is it safe to compile and distribute against the oldest available version a.k.a. lowest common denominator?
• Would it run on newer systems?
• Would it hurt the performance?

Thanks in advance!

[ratijas]

The link @iMilnb provided is slightly outdated. Current # location is https://en.wikipedia.org/wiki/CUDA#GPUs_supported.