By splitting the `FnSig` within `TyKind::FnPtr` into `FnSigTys` and
`FnHeader`, which can be packed more efficiently. This reduces the size
of the hot `TyKind` type from 32 bytes to 24 bytes on 64-bit platforms.
This reduces peak memory usage by a few percent on some benchmarks. It
also reduces cache misses and page faults similarly, though this doesn't
translate to clear cycles or wall-time improvements on CI.

…clif-2024-08-09

I rarely need a debug build of cg_clif, and even if I actually need one,
using package overrides in Cargo.toml to only do a debug build for the
rustc_codegen_cranelift crate works much better.

To avoid overriding the source for coretests every time.

…ouxu,Amanieu,Jubilee

nontemporal_store: make sure that the intrinsic is truly just a hint

The `!nontemporal` flag for stores in LLVM *sounds* like it is just a hint, but actually, it is not -- at least on x86, non-temporal stores need very special treatment by the programmer or else the Rust memory model breaks down. LLVM still treats these stores as-if they were normal stores for optimizations, which is [highly dubious](llvm/llvm-project#64521). Let's avoid all that dubiousness by making our own non-temporal stores be truly just a hint, which is possible on some targets (e.g. ARM). On all other targets, non-temporal stores become regular stores.

~~Blocked on rust-lang/stdarch#1541 propagating to the rustc repo, to make sure the `_mm_stream` intrinsics are unaffected by this change.~~

Fixes rust-lang#114582
Cc `@Amanieu` `@workingjubilee`

…st as array)

…ompiler-errors

Shrink `TyKind::FnPtr`.

By splitting the `FnSig` within `TyKind::FnPtr` into `FnSigTys` and `FnHeader`, which can be packed more efficiently. This reduces the size of the hot `TyKind` type from 32 bytes to 24 bytes on 64-bit platforms. This reduces peak memory usage by a few percent on some benchmarks. It also reduces cache misses and page faults similarly, though this doesn't translate to clear cycles or wall-time improvements on CI.

r? `@compiler-errors`

…rkingjubilee

simd_shuffle intrinsic: allow argument to be passed as vector

See rust-lang#128738 for context.

I'd like to get rid of [this hack](https://github.com/rust-lang/rust/blob/6c0b89dfac65be9a5be12f938f23098ebc36c635/compiler/rustc_codegen_ssa/src/mir/block.rs#L922-L935). rust-lang#128537 almost lets us do that since constant SIMD vectors will then be passed as immediate arguments. However, simd_shuffle for some reason actually takes an *array* as argument, not a vector, so the hack is still required to ensure that the array becomes an immediate (which then later stages of codegen convert into a vector, as that's what LLVM needs).

This PR prepares simd_shuffle to also support a vector as the `idx` argument. Once this lands, stdarch can hopefully be updated to pass `idx` as a vector, and then support for arrays can be removed, which finally lets us get rid of that hack.

initially starting with `-Z mir-include-spans` because we want them in
the NLL mir dump pass

…albertlarsan68

Distribute rustc_codegen_cranelift for Windows

With support for raw-dylib recently added to cg_clif, and inline assembly support working on Windows for quite a while now, all blockers for distributing cg_clif on Windows that I mentioned in rust-lang#81746 (comment) are fixed now.

Also reduce visibility of a couple of statics

It no longer saves much download time while still complicating the code
and requiring curl and tar to be installed.

FreeBSD by default doesn't install bash.

This avoids pulling in perl.

… this function

This avoids removing the directory, which may conflict with sandbox
systems like Landlock.

For whatever reason someone decided to make the default if-changed
always checkout the llvm-project submodule, which takes a while.

This avoids some repetitive boilerplate code.

…rust-lang#1533)

This was forgotten. Without it, ptr_mask just always returns null.

…clif-2024-09-22