Source: starpu Priority: optional Maintainer: Samuel Thibault Build-Depends: debhelper-compat (= 13), pkg-config, libnuma-dev [linux-any], libglpk-dev, mpi-default-dev, libgl1-mesa-dev | libgl-dev, libglu1-mesa-dev | libglu-dev, freeglut3-dev, libx11-dev, libblas-dev, libfftw3-dev, libhwloc-dev, libleveldb-dev, libhdf5-dev, valgrind-if-available, # guile-2.2, opencl-c-headers, ocl-icd-opencl-dev | opencl-dev, gfortran, help2man, doxygen, # nvidia-cuda-toolkit-gcc (>= 10.1), Rules-Requires-Root: no Standards-Version: 4.6.0 Section: libs Homepage: https://starpu.gitlabpages.inria.fr/ Vcs-Git: https://salsa.debian.org/debian/starpu.git Vcs-Browser: https://salsa.debian.org/debian/starpu Package: libstarpu-dev Section: libdevel Architecture: any Depends: libstarpu-1.3-9 (= ${binary:Version}) | libstarpu-any-1.3-9, libstarpufft-1.3-2 (= ${binary:Version}) | libstarpu-anyfft-1.3-2, libstarpumpi-1.3-3 (= ${binary:Version}) | libstarpu-anympi-1.3-3, libsocl-1.3-0 (= ${binary:Version}) | libsocl-any-1.3-0, libstarpurm-1.3-2 (= ${binary:Version}) | libstarpu-anyrm-1.3-2, ${misc:Depends}, libhwloc-dev, opencl-headers, ocl-icd-opencl-dev Conflicts: libstarpu-contrib-dev Provides: libstarpu-any-dev Description: Task scheduler for heterogeneous multicore machines - dev StarPU is a runtime system that offers support for heterogeneous multicore machines. While many efforts are devoted to design efficient computation kernels for those architectures (e.g. to implement BLAS kernels on GPUs or on Cell's SPUs), StarPU not only takes care of offloading such kernels (and implementing data coherency across the machine), but it also makes sure the kernels are executed as efficiently as possible. . This package contains development headers and libraries. # This "contrib" version is built against CUDA. Package: libstarpu-1.3-9 Architecture: any Multi-Arch: same Depends: ${shlibs:Depends}, ${misc:Depends} Conflicts: libstarpu-contrib-1.3-9 Provides: libstarpu-any-1.3-9 Description: Task scheduler for heterogeneous multicore machines StarPU is a runtime system that offers support for heterogeneous multicore machines. While many efforts are devoted to design efficient computation kernels for those architectures (e.g. to implement BLAS kernels on GPUs or on Cell's SPUs), StarPU not only takes care of offloading such kernels (and implementing data coherency across the machine), but it also makes sure the kernels are executed as efficiently as possible. . This package contains the main StarPU library # This "contrib" version is built against CUDA. Package: libstarpufft-1.3-2 Architecture: any Multi-Arch: same Depends: ${shlibs:Depends}, ${misc:Depends} Conflicts: libstarpu-contribfft-1.3-2 Provides: libstarpu-anyfft-1.3-2 Description: Task scheduler for heterogeneous multicore machines StarPU is a runtime system that offers support for heterogeneous multicore machines. While many efforts are devoted to design efficient computation kernels for those architectures (e.g. to implement BLAS kernels on GPUs or on Cell's SPUs), StarPU not only takes care of offloading such kernels (and implementing data coherency across the machine), but it also makes sure the kernels are executed as efficiently as possible. . This package contains a hybrid CPU+GPU FFT library. # This "contrib" version is built against CUDA. Package: libstarpumpi-1.3-3 Architecture: any Multi-Arch: same Depends: ${shlibs:Depends}, ${misc:Depends} Conflicts: libstarpu-contribmpi-1.3-3 Provides: libstarpu-anympi-1.3-3 Description: Task scheduler for heterogeneous multicore machines StarPU is a runtime system that offers support for heterogeneous multicore machines. While many efforts are devoted to design efficient computation kernels for those architectures (e.g. to implement BLAS kernels on GPUs or on Cell's SPUs), StarPU not only takes care of offloading such kernels (and implementing data coherency across the machine), but it also makes sure the kernels are executed as efficiently as possible. . This package contains MPI extensions for StarPU. # This "contrib" version is built against CUDA. Package: starpu-tools Section: utils Architecture: any Multi-Arch: foreign Depends: ${shlibs:Depends}, ${misc:Depends} Conflicts: starpu-contrib-tools Provides: starpu-any-tools Recommends: python3:any Description: Task scheduler for heterogeneous multicore machines - tools StarPU is a runtime system that offers support for heterogeneous multicore machines. While many efforts are devoted to design efficient computation kernels for those architectures (e.g. to implement BLAS kernels on GPUs or on Cell's SPUs), StarPU not only takes care of offloading such kernels (and implementing data coherency across the machine), but it also makes sure the kernels are executed as efficiently as possible. . This package contains StarPU tools. # This "contrib" version is built against CUDA. Package: starpu-examples Section: science Architecture: any Multi-Arch: same Depends: ${shlibs:Depends}, ${misc:Depends} Conflicts: starpu-contrib-examples Provides: starpu-any-examples Description: Task scheduler for heterogeneous multicore machines - exs StarPU is a runtime system that offers support for heterogeneous multicore machines. While many efforts are devoted to design efficient computation kernels for those architectures (e.g. to implement BLAS kernels on GPUs or on Cell's SPUs), StarPU not only takes care of offloading such kernels (and implementing data coherency across the machine), but it also makes sure the kernels are executed as efficiently as possible. . This package contains application examples. # This "contrib" version is built against CUDA. Package: libsocl-1.3-0 Architecture: any Multi-Arch: same Depends: ${shlibs:Depends}, ${misc:Depends} Conflicts: libsocl-contrib-1.3-0 Provides: libsocl-any-1.3-0 Description: Task scheduler for heterogeneous multicore machines StarPU is a runtime system that offers support for heterogeneous multicore machines. While many efforts are devoted to design efficient computation kernels for those architectures (e.g. to implement BLAS kernels on GPUs or on Cell's SPUs), StarPU not only takes care of offloading such kernels (and implementing data coherency across the machine), but it also makes sure the kernels are executed as efficiently as possible. . This package contains an OpenCL-compatible library interface to StarPU. # This "contrib" version is built against CUDA. Package: libstarpurm-1.3-2 Architecture: any Multi-Arch: same Depends: ${shlibs:Depends}, ${misc:Depends} Conflicts: libstarpu-contribrm-1.3-2 Provides: libstarpu-anyrm-1.3-2 Description: Task scheduler for heterogeneous multicore machines StarPU is a runtime system that offers support for heterogeneous multicore machines. While many efforts are devoted to design efficient computation kernels for those architectures (e.g. to implement BLAS kernels on GPUs or on Cell's SPUs), StarPU not only takes care of offloading such kernels (and implementing data coherency across the machine), but it also makes sure the kernels are executed as efficiently as possible. . This package contains the resource management library. # This "contrib" version is built against CUDA.