> ## Documentation Index
> Fetch the complete documentation index at: https://klyne-research.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Changelog

> New features, improvements, and fixes to Enigma.

<Update label="April 2025" tags={["New release"]}>
  ## v0.1.0 — Initial Release

  First public release of Enigma DSL for Apple Metal.

  ### New features

  <CardGroup cols={2}>
    <Card title="Layout Algebra" icon="function">
      CuTe-style primitives: `Layout`, `coalesce`, `complement`, `zipped_divide`, `recast_layout`, `make_layout_tv`, `tensor_zipped_divide`, `tensor_composition`.
    </Card>

    <Card title="Compiler Pipeline" icon="microchip">
      Trace pipeline for `@enigma.kernel` and `@enigma.jit`. MLIR + Metal emission via `xcrun metal` / `xcrun metallib`. Vectorized codegen with `vec_width` (`float4` paths).
    </Card>

    <Card title="Metal Runtime" icon="play">
      `MetalRuntime` dispatch via Swift dylib bridge. `PreparedKernel` for pre-allocated repeated dispatch. `dispatch_timed()` for benchmarking.
    </Card>

    <Card title="Device Capabilities" icon="cpu">
      `DeviceCapabilities` reporting including M3+ feature detection. Scalar parameter packing via `enigma.Scalar(...)`.
    </Card>
  </CardGroup>

  ### DSL surface

  * Full set of thread, threadgroup, and SIMD index query ops
  * Extended dtypes: `bf16`, `i64`, `u64`, `i8`, `u8`, `i16`, `u16`, `b1`
  * Arithmetic, float math, integer math, and bit manipulation ops
  * SIMD group and quad group reductions, prefix scans, and shuffle ops
  * Atomic operations with full memory ordering: `relaxed`, `acquire`, `release`, `acq_rel`
  * Threadgroup shared memory via `threadgroup_alloc` and barriers
  * Simdgroup matrix ops: `simdgroup_matrix_load`, `simdgroup_multiply_accumulate`, `simdgroup_matrix_store`
  * Control-flow tracing: `for_range`, `if_`, `while_`
  * Predicated load/store: `load_if`, `store_if`
  * Register/pipeline primitives: `register_tensor`, `copy`, `pipeline`

  ### Export

  * `CompiledKernel.export_metal()` — export generated MSL source
  * `keep_metal_source=True` — retain `.metal` artifact after compilation

  ### Testing

  * Portable CI: tracing, layout algebra, and compile surfaces under `tests/portable`
  * Metal runtime execution tests under `tests/metal`
</Update>