v1.1.0

GPUCompiler v1.1.0

Diff since v1.0.1

• Validator: it is now permitted to pass fieldless objects to kernels, even if they are mutable (#650). This should make it possible to e.g. pass symbols.
• Metal: fix emission of global constants (#648)
• Compatibility with Julia 1.12 (#651, #656)

Merged pull requests:

• [Metal] Add correct addrspace to global constants (#648) (@tgymnich)
• Validator: Permit all fieldless objects. (#650) (@maleadt)
• Fixes for nightly (#651) (@maleadt)
• Avoid calling specialize_method again for typeinf_type inference (#653) (@wsmoses)
• Bump codecov/codecov-action from 4 to 5 (#654) (@dependabot[bot])
• Updates for Julia 1.12 (#656) (@maleadt)

v1.0.1

GPUCompiler v1.0.1

Diff since v1.0.0

Merged pull requests:

• Adapt to removal of CombineMulAdd pass. (#645) (@maleadt)

Closed issues:

• Release 1.0 (#641)

v1.0.0

GPUCompiler v1.0.0

Diff since v0.27.8

Merged pull requests:

• Fix and test mangling (#632) (@maleadt)
• Extend non-isbits argument error text. (#638) (@maleadt)
• Fix GPU/CPU pass confusing, leading to broken PTLS getters. (#643) (@maleadt)

Closed issues:

• problem in Woodpecker CI (#640)

v0.27.8

GPUCompiler v0.27.8

Diff since v0.27.7

Merged pull requests:

• Add exceptions to check_ir_values (#630) (@tgymnich)

v0.27.7

GPUCompiler v0.27.7

Diff since v0.27.6

Merged pull requests:

• Re-enable nightly testing. (#631) (@maleadt)

v0.27.6

GPUCompiler v0.27.6

Diff since v0.27.5

Merged pull requests:

• Update to LLVM.jl v9.1. (#626) (@maleadt)
• Fix CI. (#627) (@maleadt)

Closed issues:

• [AMDGPU] Broken sincos intrinsic on GPUCompiler 0.24 (#523)

v0.27.5

GPUCompiler v0.27.5

Diff since v0.27.4

Merged pull requests:

• Replace current, not global logger in safe loggers (#622) (@danielwe)

v0.27.4

GPUCompiler v0.27.4

Diff since v0.27.3

Merged pull requests:

• Metal: switch order of unreachable rewrite passes. (#623) (@maleadt)

v0.27.3

GPUCompiler v0.27.3

Diff since v0.27.2

Merged pull requests:

• Fix Report exception issue on nested codegen (#619) (@wsmoses)

v0.27.2

GPUCompiler v0.27.2

Diff since v0.27.1

Merged pull requests:

• Metal: Replace unreachable control flow with exit block branches (on macOS <15) (#618) (@maleadt)