Build and Install

cuSZ is distributed in source code, and there are two methods to build cuSZ,

1. from git-cloned source code
2. from Spack automated installation.

build cuSZ

• NVIDIA GPU with CUDA 11.3 onward
  • see detailed compatibility matrix below
  • Spack installation can work for 11.0 onward
• cmake 3.18 onward
• C++14 enabled compiler, GCC 8 onward

git clone https://github.com/szcompressor/cuSZ.git cusz-latest
cd cusz-latest && mkdir build && cd build

# Example architectures (";"-separated when specifying)
#   Volta        : 70
#   Turing       : 75
#   Ampere       : 80 86
#   Ada Lovelace : 89 (as of CUDA 11.8)
#   Hopper       : 90 (as of CUDA 11.8)
cmake .. -DCUSZ_BUILD_EXAMPLES=on \
    -DCMAKE_BUILD_TYPE=Release \
    -DBUILD_TESTING=on \
    -DCMAKE_CUDA_ARCHITECTURES="75;80;86" \
    -DCMAKE_INSTALL_PREFIX=[/path/to/install/dir]
make -j8
# Install to [/path/to/install/dir]
make install
# `ctest` can perform testings.

Spack install

We are working on updating cuSZ distributed by Spack.

After setting up Spack, run

spack install cusz +cuda cuda_arch=[your CUDA gpu arch]
spack load cusz

compatibility

The table gives a quick view of toolchain compatibility (i.e., GCC or LLVM only serves as host compiler)

• corresponding to 1dd0b8a
• more reference: CUDA compilers, and CUDA architectures & gencode.

CUDA		11.0	11.1	11.2	11.3	11.4	11.5	11.6	11.7	11.8	12.0	12.1	12.2
GCC	8.5	^	^	^	ok	ok	ok	ok	ok	ok	todo	todo	todo
	9.3	^	^	^	ok	ok	ok	ok	ok	ok	ok	ok	todo
	10.2	^	^	^	ok	ok	ok	ok	ok	ok	todo	todo	todo
	11.2	!	!	!	!	!	ok	ok	ok	ok	todo	todo	todo

 # only accessible using spack
 ! GCC version too high for CUDA SDK