* Rework IR and resolver to use nested lookup tables
* Integrate types into IR
* Make components prefer IR, slimmed down AST
* Implement `export *`
* Add `@lazy` annotation and remove `--noTreeShaking`
* Add `@start` annotation and remove magic `main`
* Related refactoring, cleanup and docs
Looking at our existing tests it seems that inlining these can be performed by reusing locals most of the time, and sometimes enables erasing quite a bit of unnecessary code when optimizing.
When specifying -O3 or -Oz, asc now automatically increases the optimize level to 4, then including costly non-LLVM optimizations for blocky code, in turn achieving similar results as an LLVM-based generator.
Starting with explicit loads and stores as part of the respective type namespaces. Might become handy for use with portable code, because these can be polyfilled, while load<T> and store<T> can't.
Remaining implementations of JavaScript's Math functions (except sin/cos/tan), both double (Math) and single (Mathf) precision, ported from musl incl. tests from libc-test, plus some changes to match JS semantics. Also binds fmod to `%` and pow to `**`.
