Version 3.0.0

Version 3.0.0

Upgrade guidance:

• The mux spec has been bumped:
  • 0.74.0: to account for changes to BaseModule.
  • 0.75.0: to remove code supporting cl_codeplay_program_snapshot.
  • 0.76.0: to add code supporting cl_intel_required_subgroup_size.
• The cl_codeplay_program_snapshot extension has been removed.
• cl::binary::ProgramInfo and cl::binary::KernelInfo have been removed and
  replaced with equivalent structures in the compiler namespace.
• compiler::Module::finalize no longer takes a callback to populate program
  info - it now takes compiler::ProgramInfo by pointer and populates it
  itself if passed a non-null address.

Feature additions:

• muxc now supports OpenCL C inputs, before running a (now optional) pass
  pipeline. A device is required for this to work.The file type is worked out
  from the file extension, and LLVM IR is assumed otherwise. Options can be
  provided to this step with -cl-options. This also provides the ability to
  select a device based on its index from 0, using --device-idx <idx>.
• The cl_intel_required_subgroup_size OpenCL extension is now supported. Note
  that no in-tree targets currently report any supported sub-group sizes so no
  kernels compiled with a required sub-group size will successfully compile.
• The SPIR-V SubgroupSize execution mode is now supported via the
  SubgroupDispatch capability. Note that other aspects of this capability are
  not supported.
• The SPIR-V OptNoneINTEL capability is now supported.
• compiler::BaseModulePassMachinery can now be given compiler options to
  guide its decisions.
• A new method - compiler::BaseModulePassMachinery::handlePipelineElement -
  has been added to allow more customizable target-specific pipeline component

Future feature dropping for next major release (4.0.0):

• SPIR 1.2 is deprecated and will be removed.
• LLVM 15 support will switch to LLVM 17.

Version 2.0.0

This is the first public release of the oneAPI Construction Kit, a framework to provide implementations of open standards, enabling SYCL to run on custom architectures for HPC and AI.

This release includes:

• Support for host and RISC-V devices.
• clik - simple compute library that demonstrates how offloading code to an accelerator works.
• ComputeMux - runtime and compiler modules enabling code written in SYCL to run on custom architectures through DPC++.
• RefSi - reference RISC-V architecture supporting simulation.
• Vecz - whole function vectorizer enabling automatic SIMD vectorization across hardware lanes.
• Cargo - STL-like container library with strict memory requirements.

The full historical changelog for the project can be viewed here.