v0.2.8

AMDGPU v0.2.8

Diff since v0.2.7

Merged pull requests:

• fixes for delayed codegeneration (#124) (@vchuravy)
• Support GPUCompiler 0.12 (#145) (@vchuravy)

v0.2.7

AMDGPU v0.2.7

Diff since v0.2.6

Closed issues:

• "Spills" from adjacent views of ROCVector (#130)

Merged pull requests:

• Fix copyto! on view; include offset (#131) (@tkf)
• Add support for features (#136) (@vchuravy)

v0.2.6

AMDGPU v0.2.6

Diff since v0.2.5

Closed issues:

• ROCArrays matrix multiplication not working (#103)
• Data race in kernel packet writing? (#121)

Merged pull requests:

• Add mark/wait synchronization system (#116) (@jpsamaroo)
• CompatHelper: bump compat for "GPUCompiler" to "0.11" (#122) (@github-actions[bot])
• Replace arrays with Refs in ccall. (#123) (@chriselrod)
• Fix packet launch (#125) (@jpsamaroo)

v0.2.6 for Zenodo

Merge pull request #116 from JuliaGPU/jps/mark-wait

Add mark/wait synchronization system

v0.2.5

AMDGPU v0.2.5

Diff since v0.2.4

Merged pull requests:

• Allow AMDGPU to load everywhere (#120) (@jpsamaroo)

v0.2.4

AMDGPU v0.2.4

Diff since v0.2.3

Closed issues:

• Implement execution contexts (#16)
• Add/test broadcasting support to ROCArray (#12)
• Add queue/device/system sync functionality (#24)
• Support OpenCL.jl as device runtime (#23)
• Distribute ROCR/ROCT via artifacts (#6)
• Allow setting Private and Group segment sizes manually (#56)
• FATAL ERROR: Symbol "ccalllib_libhsa-runtime64445"not found on AMDGPU (#73)
• test failures and crashes on 580 (#92)
• Tests allocate memory indefinitely (#106)
• Check for invalid workgroup sizes (#110)
• Add example for gridsize usage and workgroup sizing (#113)

Merged pull requests:

• Silence queue destroy finalizer errors (#98) (@jpsamaroo)
• KernelAbstractions support (#100) (@jpsamaroo)
• Fix kernel argument alignment (#101) (@jpsamaroo)
• Fix alloc_local (#102) (@jpsamaroo)
• Add mapreducedim! (#104) (@jpsamaroo)
• Added support for HSA artifacts (#105) (@0x0f0f0f)
• Update to GPUCompiler 0.10 (#107) (@jpsamaroo)
• Fix CompatHelper config (#108) (@jpsamaroo)
• CompatHelper: bump compat for "AbstractFFTs" to "1.0" (#109) (@github-actions[bot])
• Fix loading of AMDGPU in other packages (#114) (@jpsamaroo)
• Check groupsize, add group/grid docs (#115) (@jpsamaroo)
• Fix memory leak (#118) (@jpsamaroo)

v0.2.3

AMDGPU v0.2.3

Diff since v0.2.2

Closed issues:

• Add support for trap handlers (#8)
• Unreachable reached in SIISelLowering.cpp due to unhandled AS (#76)
• Ensure that CI tests all available external libraries (#85)
• Only load libhsa-runtime64 major version 1 (#93)

Merged pull requests:

• Disable unreliable pointerinfo tests (#86) (@jpsamaroo)
• Test extlibs are available under CI (#87) (@jpsamaroo)
• Enable device stacktraces (#88) (@jpsamaroo)
• Add ForwardDiff integrations (#90) (@jpsamaroo)
• Look for libhsa-runtime64.so.1 (#94) (@jpsamaroo)
• Remove annoying target-features for now (#95) (@jpsamaroo)
• Bump to 0.2.3, add MacroTools LB (#96) (@jpsamaroo)

v0.2.2

AMDGPU v0.2.2

Diff since v0.2.1

Closed issues:

• Implement RNGs (#14)
• Allow 0-argument kernels (#10)
• Add tests to match CUDAnative (#22)
• Build fails on OSX (#19)
• Add options to at-roc to allow initializing globals (#36)
• Some errors during test. Are they cause for concern? (#70)

Merged pull requests:

• Implement OCKL wavefront ops (#49) (@jpsamaroo)
• Accept hooks for user-defined globals (#55) (@jpsamaroo)
• Add at-rocprintf support (#61) (@jpsamaroo)
• UB GPUArrays to 5.0/5.1 (#71) (@jpsamaroo)
• rocRAND (#72) (@antholzer)
• Update to Julia 1.6 (#75) (@jpsamaroo)
• Some fixes for Julia 1.6 (#78) (@jpsamaroo)
• Bump GPUArrays to 6 (#79) (@jpsamaroo)
• Add Buildkite CI (#80) (@jpsamaroo)
• Allow 0-argument kernels (#81) (@jpsamaroo)
• Skip build if in AutoMerge (#82) (@jpsamaroo)

v0.2.1

AMDGPU v0.2.1

Diff since v0.2.0

Closed issues:

• Throw error in wait() call on queue error (#7)
• Test code doesn't work (#43)
• Broken build script? (#46)
• HSASignal and HSAKernelInstance references can be accidentally GC'd (#63)

Merged pull requests:

• Made build and initialization quieter (#47) (@jpsamaroo)
• Refcount HSA objects for safe shutdown (#52) (@jpsamaroo)
• Adapt to GPUCompiler disk cache changes (#53) (@jpsamaroo)
• Disable broken GPUArrays tests (#54) (@jpsamaroo)
• Fixed malloc return type (#59) (@jpsamaroo)
• Remove HSA C files from repo (#60) (@jpsamaroo)
• Don't do set_used on GVs (#62) (@jpsamaroo)
• Add barrier packet support (#65) (@jpsamaroo)
• Bump to 0.2.1, use GPUCompiler 0.8 (#66) (@jpsamaroo)

v0.2.0

AMDGPU v0.2.0

Diff since v0.1.2

Merged pull requests:

• Reimplement ROCArray using GPUArrays (#32) (@jpsamaroo)