v0.4.3

CUDSS v0.4.3

Diff since v0.4.2

Merged pull requests:

• Allow refactorization if a Cholesky factorization fails due to indefiniteness (#68) (@amontoison)
• Support the parameter memory_estimates (#69) (@amontoison)
• [documentation] Add new pages (#70) (@amontoison)
• Add unit tests for the batched solvers (#71) (@amontoison)

v0.4.2

CUDSS v0.4.2

Diff since v0.4.1

Merged pull requests:

• Update batch.md (#66) (@amontoison)
• New Julia interface for the batch API of CUDSS (#67) (@amontoison)

v0.4.1

CUDSS v0.4.1

Diff since v0.4.0

Merged pull requests:

• [documentation] Batched linear systems with CUDSS (#64) (@amontoison)
• Add a function unsafe_cudss_batch (#65) (@amontoison)

Closed issues:

• Package management and type piracy: should this be a part of CUDA.jl? (#31)

v0.4.0

CUDSS v0.4.0

Diff since v0.3.2

Merged pull requests:

• [buildkite] Add CI builds on GPUs (#60) (@amontoison)
• Support cuDSS v0.4.0 (#63) (@amontoison)

Closed issues:

• Fail during precompile: LoadError (#58)
• How to solve Ax=B using cudss, B is a n*m Array (#61)
• New version of cuDSS (#62)

v0.3.2

CUDSS v0.3.2

Diff since v0.3.1

Merged pull requests:

• Add tests with the hybrid mode (#51) (@amontoison)
• Update in-place examples to use refactorization (#56) (@amontoison)

Closed issues:

• Refactorization example (#53)

v0.3.1

CUDSS v0.3.1

Diff since v0.3.0

Merged pull requests:

• Test LU, LDL' and Cholesky decompositions on small linear systems (#48) (@amontoison)
• Support new parameters added in cuDSS v0.3.0 (#49) (@amontoison)
• [documentation] Add an example with the hybrid mode (#50) (@amontoison)

Closed issues:

• Error with small matrices (#45)

v0.3.0

CUDSS v0.3.0

Diff since v0.2.3

Merged pull requests:

• Upgrade to v0.3.0 (#46) (@amontoison)
• Update ci.yml (#47) (@amontoison)

v0.2.3

CUDSS v0.2.3

Diff since v0.2.2

Merged pull requests:

• Upgrade handle support (#43) (@amontoison)
• [documentation] Iterative refinement and user permutation (#44) (@amontoison)

Closed issues:

• [documentation] Add an example with iterative refinement (#37)
• CUDSS.jl is broken with CUDA.jl 5.4 (#41)

v0.1.6

CUDSS v0.1.6

Diff since v0.1.5

Merged pull requests:

• Release 0.2.2 (#42) (@amontoison)
• Upgrade handle support (#43) (@amontoison)
• [documentation] Iterative refinement and user permutation (#44) (@amontoison)

Closed issues:

• [documentation] Add an example with iterative refinement (#37)
• CUDSS.jl is broken with CUDA.jl 5.4 (#41)

v0.2.2

CUDSS v0.2.2

Diff since v0.2.1

Merged pull requests:

• Release 0.2.2 (#42) (@amontoison)