v0.4.0

Metal v0.4.0

Diff since v0.3.0

Closed issues:

• Restore mtlcall (#17)
• mapreduce has poor performance (#87)
• Native code reflection (#95)
• rand! with Bools sometimes fails in tests in 1.9 (#141)
• LLVM assertion failures (#153)
• Time macro similar to CUDA.@time (#160)
• bug in rand!? (#162)
• Why not support threadIdx().x, blockIdx().x, blockDim().x etc? (#163)
• Incorrect(?) darwin version in 1.8 with Metal.versioninfo() (#179)

Merged pull requests:

• Add native code reflection. (#96) (@maleadt)
• Move MPSKernels into a dedicated file (#155) (@tgymnich)
• [LU decomposition] Fix types (#156) (@tgymnich)
• Update manifest (#161) (@github-actions[bot])
• Implement Time macro (#164) (@christiangnrd)
• Fix some references to CUDA (#165) (@christiangnrd)
• Fix GPUArrays RNG interface implementation. (#166) (@maleadt)
• Bump the LLVM back-end. (#169) (@maleadt)
• Update manifest (#170) (@github-actions[bot])
• Update manifest (#171) (@github-actions[bot])
• Update manifest (#172) (@github-actions[bot])
• Bump GPUCompiler to v0.20 (#173) (@christiangnrd)
• Detect mapreduce threadgroup limits instead of guessing. (#176) (@maleadt)
• Remove reference to no longer used library in README.md (#177) (@christiangnrd)
• Report package versions as part of versioninfo() (#180) (@christiangnrd)
• Fix Darwin version indentification (#181) (@christiangnrd)
• Topk for MPSMatrix (#182) (@christiangnrd)
• Update manifest (#183) (@github-actions[bot])
• Don't rely on thread adoption for command buffer callbacks. (#184) (@maleadt)

v0.3.0

Metal v0.3.0

Diff since v0.2.0

Closed issues:

• Migrate to metal C++? (#2)
• Improved errors when calling device functions on CPU (#90)
• Improve Objective-C interfacing (#104)
• Rename grid to groups (#116)
• Add functionality check helper (#121)
• inputing non-isbits types (#128)
• @metal docstring out-of-date (#129)
• mapreduce kernel uses too many threads (#132)
• Powers don't work with complex floats (#142)

Merged pull requests:

• Add contributing documentation (#93) (@max-Hawkins)
• Reduce multiple consecutive values in each thread to improve efficiency (#112) (@maxwindiff)
• Remove libcmt, use native ObjectiveC FFI (#117) (@maleadt)
• Rename grid to groups (#119) (@habemus-papadum)
• Audit MRR (#122) (@maleadt)
• Faster in-place reduction by using broadcasting to initialize partial… (#123) (@maxwindiff)
• Add MPS matrix decompositions (#124) (@tgymnich)
• Minor documentation formatting (#125) (@asinghvi17)
• Switch default mode to private storage (#126) (@christiangnrd)
• Update manifest (#127) (@github-actions[bot])
• Add some MtlArray docs (#130) (@christiangnrd)
• Port MetalKernels (#131) (@maxwindiff)
• Adapt to GPUCompiler 0.18. (#134) (@maleadt)
• Support passing non-isbits arguments, as long as they're unused. (#135) (@maleadt)
• Do not change grain size after pipeline creation (#136) (@maxwindiff)
• Bump GPUArrays. (#137) (@maleadt)
• Specialize GPUArrays' global_size query. (#139) (@maleadt)
• Catch errors that happen during command buffer callbacks. (#140) (@maleadt)
• Call the correct current_device() in reflection (#143) (@maxwindiff)
• Error when calling device functions on CPU (#144) (@christiangnrd)
• Implement MTLGPUFamily and use it to validate gpu (#146) (@christiangnrd)
• Add functional() (#147) (@christiangnrd)
• Update manifest (#148) (@github-actions[bot])
• CompatHelper: add new compat entry for StaticArrays at version 1, (keep existing compat) (#151) (@github-actions[bot])
• Update to LLVM.jl 5 and GPUCompiler 0.19. (#154) (@maleadt)

v0.2.0

Metal v0.2.0

Diff since v0.1.2

Closed issues:

• Threadgroup memory breaks on small datatypes (#26)
• Int64 not supported on AMD GPUs? (#38)
• Base.unsafe_convert is ambiguous (#42)
• Support for multiple devices (#44)
• Add CITATION file (#55)
• XGBoost on Metal.jl (#82)
• first try at metal (#84)
• Copysign intrinsic possibly wrong (#89)
• Metal.jl fails to precompile on Linux (#97)
• Silent failure with unsupported(?) Intel Iris Graphics (#109)
• I have 2 question about Metal.jl and Flux.jl (#110)

Merged pull requests:

• Update manifest (#57) (@github-actions[bot])
• Add GPU profiling capabilities (#58) (@max-Hawkins)
• Automatically detect if we need cmt build from source. (#59) (@maleadt)
• Update manifest (#60) (@github-actions[bot])
• Add queue kernel launch argument (#61) (@tgymnich)
• Update manifest (#63) (@github-actions[bot])
• Switch pipeline to juliaecosystem (#64) (@vchuravy)
• Update manifest (#65) (@github-actions[bot])
• Add a function for setting the current device (#66) (@maxwindiff)
• Add documentation webpage (#67) (@max-Hawkins)
• Wrap simdgroup matrix functions (#70) (@maxwindiff)
• Support loading/saving simdgroup matrix from threadgroup memory (#71) (@maxwindiff)
• Conditionalize the MtlDeviceArray element-type workaround. (#72) (@maleadt)
• Add basic SIMD shuffle up/down (#73) (@max-Hawkins)
• Update manifest (#74) (@github-actions[bot])
• Optimize warp reduction for mapreduce (#75) (@max-Hawkins)
• Specialize GPUArrays.global_index() to improve broadcast performance (#76) (@maxwindiff)
• Update manifest (#78) (@github-actions[bot])
• Add initial performance shader support (matmul) (#80) (@max-Hawkins)
• Use Ninja to build cmt. (#81) (@maleadt)
• Update manifest (#83) (@github-actions[bot])
• Support Julia 1.9 (#85) (@maleadt)
• Add queue parameter to unsafe_copyto (#88) (@tgymnich)
• Update manifest (#91) (@github-actions[bot])
• Add MPS tests. (#92) (@maleadt)
• Support for writing binary archives (#94) (@maleadt)
• Support precompilation and loading on non-Apple hardware (#98) (@maleadt)
• Update manifest (#99) (@github-actions[bot])
• Improve reduce performance by passing CartesianIndices and length statically (#100) (@maxwindiff)
• Do not release objects that are autoreleased. (#102) (@habemus-papadum)
• Fix path the cmt in Hacking Section of the Readme (#105) (@habemus-papadum)
• Add example showing Metal and Gtk4 integration (#106) (@habemus-papadum)
• Fix memory leak. (#107) (@habemus-papadum)
• Add a mtl function for simple recursive data conversions. (#114) (@maleadt)
• Write profile trace in the current folder. (#115) (@maleadt)

v0.1.2

Metal v0.1.2

Diff since v0.1.1

Closed issues:

• installation issue (libz.1.dylib not found) [+workaround] (#51)
• Optimally choosing threads and grid (#54)

Merged pull requests:

• Use Base.active_project. (#43) (@maleadt)
• Update manifest (#45) (@github-actions[bot])
• Add aliases MtlVector and MtlMatrix (#48) (@amontoison)
• Update manifest (#49) (@github-actions[bot])
• Wrap at-metal's output in a let block. (#50) (@maleadt)
• Update manifest (#52) (@github-actions[bot])
• Update manifest (#56) (@github-actions[bot])

v0.1.1

Metal v0.1.1

Diff since v0.1.0

Closed issues:

• Super slow broadcast (#39)

Merged pull requests:

• Fix typos in unified memory example (#37) (@pitmonticone)
• Fix the launch heuristic. (#40) (@maleadt)

v0.1.0

Metal v0.1.0

Diff since v0.0.1

v0.0.1

Metal v0.0.1

Closed issues:

• error when using (#1)
• Argument buffer encoding is fragile (#5)
• LLVMType of MtlDeviceArray needs changing/manipulation (#6)
• Errors running on M1 Max (#14)
• I get this, my name isn't Tim (#16)
• Thanks for the previous fix - had a go (#18)
• Custom IR verification (#25)
• cmt: Release build fails install (#27)

Merged pull requests:

• Add device_code_metallib macro (#3) (@max-Hawkins)
• Update README (#8) (@max-Hawkins)
• Implement GPUArrays launch heuristic (#9) (@max-Hawkins)
• Add docstrings (#12) (@max-Hawkins)
• Rework metadata generation (#13) (@maleadt)
• Add CI (#19) (@maleadt)
• Use sw_vers to query the macOS version. (#20) (@maleadt)
• Updates for macOS 13 (Ventura); use bindless argument buffers (#23) (@maleadt)
• Enable the GPUArrays test suite (#24) (@maleadt)
• Use cmt from pre-built JLL. (#28) (@maleadt)
• Package updates (#29) (@maleadt)
• First test with a locally-built cmt. (#30) (@maleadt)
• Use labels to determine whether to build local deps. (#31) (@maleadt)
• Bump GPUArrays. (#32) (@maleadt)
• MTL wrapper clean-ups (#33) (@maleadt)