v1.1.6

AMDGPU v1.1.6

Diff since v1.1.5

v1.1.5

AMDGPU v1.1.5

Diff since v1.1.4

v1.1.4

AMDGPU v1.1.4

Diff since v1.1.3

Merged pull requests:

• Take fewer locks (#705) (@pxl-th)
• [rocSOLVER] Update gesvd! (#706) (@amontoison)
• [rocSPARSE] Interface additional sparse routines (#707) (@amontoison)
• Add caching memory allocator (#708) (@pxl-th)

Closed issues:

• task switch not allowed from inside gc finalizer (#697)

v1.1.3

AMDGPU v1.1.3

Diff since v1.1.2

Merged pull requests:

• Update ROCSparse for Julia v1.10 (#613) (@amontoison)
• [ROCSOLVER] Interface gesvd and gebrd (#699) (@amontoison)
• fix Vararg{<:Any, N} (#700) (@oscardssmith)
• Add Atomix.jl v1 compat (#701) (@christiangnrd)
• Add findnz & fix broadcasting (#704) (@pxl-th)

Closed issues:

• floor function triggers a host (#702)
• SparseArrays.findnz not defined for ROCSparseMatrixCSC (#703)

v1.1.2

AMDGPU v1.1.2

Diff since v1.1.1

v1.1.1

AMDGPU v1.1.1

Diff since v1.1.0

Merged pull requests:

• [Experimental] Add memory recording which can then be bulk-freed (#698) (@pxl-th)

Closed issues:

• Version incompatibilities with the JuliaGPU stack (#694)

v1.1.0

AMDGPU v1.1.0

Diff since v1.0.5

Merged pull requests:

• Prefer librocalution_hip over librocalution (#691) (@vchuravy)
• Adapt ROCDeviceArray to DenseArray interface (#692) (@pxl-th)
• Update to [email protected] (#693) (@pxl-th)

Closed issues:

• System librocalution can cause issue due to implicit loading of UCX (#690)

v1.0.5

AMDGPU v1.0.5

Diff since v1.0.4

Merged pull requests:

• Avoid constructing MulAddMuls (#623) (@dkarrasch)
• Use AcceleratedKernels for sorting (#688) (@pxl-th)
• Fix FFT execution on separate Julia task (#689) (@jipolanco)

Closed issues:

• (2nd) AMDGPU does not load any more without error when installation not functional (#687)

v1.0.4

AMDGPU v1.0.4

Diff since v1.0.3

Merged pull requests:

• Generate librocsolver.jl with Clang.jl (#617) (@amontoison)
• [rocSPARSE] Update the interface for sparse triangular solves (#682) (@amontoison)
• Fix import on non-functional machines (#686) (@pxl-th)

Closed issues:

• Unable to find correct HIP path (#671)
• AMDGPU does not load any more without error when installation not functional (#685)

v1.0.3

AMDGPU v1.0.3

Diff since v1.0.2

Merged pull requests:

• Fix workspace size calculation for fwd conv (#678) (@pxl-th)