v0.9.13

KernelAbstractions v0.9.13

Diff since v0.9.12

Merged pull requests:

• Add <0.0.1 compat for all stdlibs outside of julia repo (#434) (@sharanry)
• Simple benchmarks (#435) (@vchuravy)
• EnzymeExt allocate subtape of correct size. (#437) (@michel2323)

v0.9.12

KernelAbstractions v0.9.12

Diff since v0.9.11

Bug fixes

• Fix the new @kernel inbounds=true functionality on the CPU #431

Merged pull requests:

• Allow nightly CI to fail so badge stays green (#427) (@Moelf)
• Change 'A to B' -> 'B to A' in memcopy descriptions (#428) (@johnbcoughlin)
• Fix inbounds codegen for CPU (#431) (@vchuravy)
• modifying test kernel for the flag to call (#432) (@leios)

v0.9.11

KernelAbstractions v0.9.11

Diff since v0.9.10

Merged pull requests:

• adding attempt to force inbounds at the kernel level (#429) (@leios)

v0.9.10

KernelAbstractions v0.9.10

Diff since v0.9.9

v0.9.9

KernelAbstractions v0.9.9

Diff since v0.9.8

Merged pull requests:

• Update the quickstart documentation. (#410) (@GunnarFarneback)
• Ensure NTuple index functions are inlined (#414) (@vchuravy)
• enable dependabot for GitHub actions (#415) (@ranocha)

Closed issues:

• @unroll unrolling the wrong loop (#411)

v0.9.8

KernelAbstractions v0.9.8

Diff since v0.9.7

Closed issues:

• Reverse CI for AMDGPU (#394)

Merged pull requests:

• Add AMDGPU CI (#409) (@pxl-th)
• Fix inactive rule to only mark constructor of one type as inactive, n… (#412) (@wsmoses)

v0.9.7

KernelAbstractions v0.9.7

Diff since v0.9.6

Closed issues:

• Launch kernels and dependencies (#264)

Merged pull requests:

• Enzyme Rules, all functioning (#382) (@wsmoses)
• Fix CUDA CI (#406) (@vchuravy)
• Update CI pipelines (#407) (@vchuravy)

v0.9.6

KernelAbstractions v0.9.6

Diff since v0.9.5

Merged pull requests:

• Don't use Float64 in tests, as some back-ends do not support it. (#402) (@maleadt)

v0.9.5

KernelAbstractions v0.9.5

Diff since v0.9.4

Closed issues:

• Defining timing infrastructure that works with events. (#15)
• Kernels fail on CPU when waiting on kernels that allocate shared memory (#55)
• Use macros in nested functions (#377)
• CPU(static=true) option (#387)
• Need for @inline when using GPU backend (#392)
• KA seems to be broken for CUDA (#400)

Merged pull requests:

• Add kernel cpu=false and context accessor (#389) (@vchuravy)
• Add reverse CI for oneAPI and AMDGPU (#391) (@vchuravy)
• Update readme (#393) (@vchuravy)
• Improve clarity of numa_aware example (#397) (@carstenbauer)
• Docs: numa aware saxpy example (#398) (@carstenbauer)
• Add implementation notes to host functionality (#401) (@vchuravy)

v0.9.4

KernelAbstractions v0.9.4

Diff since v0.9.3

Merged pull requests:

• Add CPU(static=true) (#388) (@vchuravy)
• Update index.md (#390) (@Ruibin-Liu)