Update the minimum external LLVM to 19
With this change, we'll have stable support for LLVM 19 and 20.
For reference, the previous increase to LLVM 18 was #130487.
cc `@rust-lang/wg-llvm`
r? nikic
Implement `SliceIndex` for `ByteStr`
Implement `Index` and `IndexMut` for `ByteStr` in terms of `SliceIndex`. Implement it for the same types that `&[u8]` supports (a superset of those supported for `&str`, which does not have `usize` and `ops::IndexRange`).
At the same time, move compare and index traits to a separate file in the `bstr` module, to give it more space to grow as more functionality is added (e.g., iterators and string-like ops). Order the items in `bstr/traits.rs` similarly to `str/traits.rs`.
cc `@joshtriplett`
`ByteStr`/`ByteString` tracking issue: https://github.com/rust-lang/rust/issues/134915
Apply `Recovery::Forbidden` when reparsing pasted macro fragments.
Fixes#137874.
The changes to the output of `tests/ui/associated-consts/issue-93835.rs`
partly undo the changes seen when `NtTy` was removed in #133436, which
is good.
r? ``@petrochenkov``
Autodiff batching
Enzyme supports batching, which is especially known from the ML side when training neural networks.
There we would normally have a training loop, where in each iteration we would pass in some data (e.g. an image), and a target vector. Based on how close we are with our prediction we compute our loss, and then use backpropagation to compute the gradients and update our weights.
That's quite inefficient, so what you normally do is passing in a batch of 8/16/.. images and targets, and compute the gradients for those all at once, allowing better optimizations.
Enzyme supports batching in two ways, the first one (which I implemented here) just accepts a Batch size,
and then each Dual/Duplicated argument has not one, but N shadow arguments. So instead of
```rs
for i in 0..100 {
df(x[i], y[i], 1234);
}
```
You can now do
```rs
for i in 0..100.step_by(4) {
df(x[i+0],x[i+1],x[i+2],x[i+3], y[i+0], y[i+1], y[i+2], y[i+3], 1234);
}
```
which will give the same results, but allows better compiler optimizations. See the testcase for details.
There is a second variant, where we can mark certain arguments and instead of having to pass in N shadow arguments, Enzyme assumes that the argument is N times longer. I.e. instead of accepting 4 slices with 12 floats each, we would accept one slice with 48 floats. I'll implement this over the next days.
I will also add more tests for both modes.
For any one preferring some more interactive explanation, here's a video of Tim's llvm dev talk, where he presents his work. https://www.youtube.com/watch?v=edvaLAL5RqU
I'll also add some other docs to the dev guide and user docs in another PR.
r? ghost
Tracking:
- https://github.com/rust-lang/rust/issues/124509
- https://github.com/rust-lang/rust/issues/135283
Use the span of the whole bound when the diagnostic talks about a bound
While it makes sense that the host predicate only points to the `~const` part, as whether the actual trait bound is satisfied is checked separately, the user facing diagnostic is talking about the entire trait bound, at which point it makes more sense to just highlight the entire bound
r? `@compiler-errors` or `@fee1-dead`
Fix `Debug` impl for `LateParamRegionKind`.
It uses `Br` prefixes which are inappropriate and appear to have been incorrectly copy/pasted from the `Debug` impl for `BoundRegionKind`.
r? `@BoxyUwU`
add `TypingMode::Borrowck`
Shares the first commit with #138499, doesn't really matter which PR to land first 😊😁
Introduces `TypingMode::Borrowck` which unlike `TypingMode::Analysis`, uses the hidden type computed by HIR typeck as the initial value of opaques instead of an unconstrained infer var. This is a part of https://github.com/rust-lang/types-team/issues/129.
Using this new `TypingMode` is unfortunately a breaking change for now, see tests/ui/impl-trait/non-defining-uses/as-projection-term.rs. Using an inference variable as the initial value results in non-defining uses in the defining scope. We therefore only enable it if with `-Znext-solver=globally` or `-Ztyping-mode-borrowck`
To do that the PR contains the following changes:
- `TypeckResults::concrete_opaque_type` are already mapped to the definition of the opaque type
- writeback now checks that the non-lifetime parameters of the opaque are universal
- for this, `fn check_opaque_type_parameter_valid` is moved from `rustc_borrowck` to `rustc_trait_selection`
- we add a new `query type_of_opaque_hir_typeck` which, using the same visitors as MIR typeck, attempts to merge the hidden types from HIR typeck from all defining scopes
- done by adding a `DefiningScopeKind` flag to toggle between using borrowck and HIR typeck
- the visitors stop checking that the MIR type matches the HIR type. This is trivial as the HIR type are now used as the initial hidden types of the opaque. This check is useful as a safeguard when not using `TypingMode::Borrowck`, but adding it to the new structure is annoying and it's not soundness critical, so I intend to not add it back.
- add a `TypingMode::Borrowck` which behaves just like `TypingMode::Analysis` except when normalizing opaque types
- it uses `type_of_opaque_hir_typeck(opaque)` as the initial value after replacing its regions with new inference vars
- it uses structural lookup in the new solver
fixes#112201, fixes#132335, fixes#137751
r? `@compiler-errors` `@oli-obk`
Pass correct param-env to `error_implies`
Duplicated comment from the test:
In the error reporting code, when reporting fulfillment errors for goals A and B, we try to see if elaborating A will result in another goal that can equate with B. That would signal that B is "implied by" A, allowing us to skip reporting it, which is beneficial for cutting down on the number of diagnostics we report.
In the new trait solver especially, but even in the old trait solver through things like defining opaque type usages, this `can_equate` call was not properly taking the param-env of the goals, resulting in nested obligations that had empty param-envs. If one of these nested obligations was a `ConstParamHasTy` goal, then we would ICE, since those goals are particularly strict about the param-env they're evaluated in.
This is morally a fix for <https://github.com/rust-lang/rust/issues/139314>, but that repro uses details about how defining usages in the `check_opaque_well_formed` code can spring out of type equality, and will likely stop failing soon coincidentally once we start using `PostBorrowck` mode in that check. Instead, we use lazy normalization to end up generating an alias-eq goal whose nested goals woul trigger the ICE instead, since this is a lot more stable.
Fixes https://github.com/rust-lang/rust/issues/139314
r? ``@oli-obk`` or reassign
Fixes#137874.
Removes `tests/crashes/137874.rs`; the new test is simpler (defines its
own macro) but tests the same thing.
The changes to the output of `tests/ui/associated-consts/issue-93835.rs`
partly undo the changes seen when `NtTy` was removed in #133436, which
is good.
Initial support for auto traits with default bounds
This PR is part of ["MCP: Low level components for async drop"](https://github.com/rust-lang/compiler-team/issues/727)
Tracking issue: #138781
Summary: https://github.com/rust-lang/rust/pull/120706#issuecomment-1934006762
### Intro
Sometimes we want to use type system to express specific behavior and provide safety guarantees. This behavior can be specified by various "marker" traits. For example, we use `Send` and `Sync` to keep track of which types are thread safe. As the language develops, there are more problems that could be solved by adding new marker traits:
- to forbid types with an async destructor to be dropped in a synchronous context a trait like `SyncDrop` could be used [Async destructors, async genericity and completion futures](https://sabrinajewson.org/blog/async-drop).
- to support [scoped tasks](https://without.boats/blog/the-scoped-task-trilemma/) or in a more general sense to provide a [destruction guarantee](https://zetanumbers.github.io/book/myosotis.html) there is a desire among some users to see a `Leak` (or `Forget`) trait.
- Withoutboats in his [post](https://without.boats/blog/changing-the-rules-of-rust/) reflected on the use of `Move` trait instead of a `Pin`.
All the traits proposed above are supposed to be auto traits implemented for most types, and usually implemented automatically by compiler.
For backward compatibility these traits have to be added implicitly to all bound lists in old code (see below). Adding new default bounds involves many difficulties: many standard library interfaces may need to opt out of those default bounds, and therefore be infected with confusing `?Trait` syntax, migration to a new edition may contain backward compatibility holes, supporting new traits in the compiler can be quite difficult and so forth. Anyway, it's hard to evaluate the complexity until we try the system on a practice.
In this PR we introduce new optional lang items for traits that are added to all bound lists by default, similarly to existing `Sized`. The examples of such traits could be `Leak`, `Move`, `SyncDrop` or something else, it doesn't matter much right now (further I will call them `DefaultAutoTrait`'s). We want to land this change into rustc under an option, so it becomes available in bootstrap compiler. Then we'll be able to do standard library experiments with the aforementioned traits without adding hundreds of `#[cfg(not(bootstrap))]`s. Based on the experiments, we can come up with some scheme for the next edition, in which such bounds are added in a more targeted way, and not just everywhere.
Most of the implementation is basically a refactoring that replaces hardcoded uses of `Sized` with iterating over a list of traits including both `Sized` and the new traits when `-Zexperimental-default-bounds` is enabled (or just `Sized` as before, if the option is not enabled).
### Default bounds for old editions
All existing types, including generic parameters, are considered `Leak`/`Move`/`SyncDrop` and can be forgotten, moved or destroyed in generic contexts without specifying any bounds. New types that cannot be, for example, forgotten and do not implement `Leak` can be added at some point, and they should not be usable in such generic contexts in existing code.
To both maintain this property and keep backward compatibility with existing code, the new traits should be added as default bounds _everywhere_ in previous editions. Besides the implicit `Sized` bound contexts that includes supertrait lists and trait lists in trait objects (`dyn Trait1 + ... + TraitN`). Compiler should also generate implicit `DefaultAutoTrait` implementations for foreign types (`extern { type Foo; }`) because they are also currently usable in generic contexts without any bounds.
#### Supertraits
Adding the new traits as supertraits to all existing traits is potentially necessary, because, for example, using a `Self` param in a trait's associated item may be a breaking change otherwise:
```rust
trait Foo: Sized {
fn new() -> Option<Self>; // ERROR: `Option` requires `DefaultAutoTrait`, but `Self` is not `DefaultAutoTrait`
}
// desugared `Option`
enum Option<T: DefaultAutoTrait + Sized> {
Some(T),
None,
}
```
However, default supertraits can significantly affect compiler performance. For example, if we know that `T: Trait`, the compiler would deduce that `T: DefaultAutoTrait`. It also implies proving `F: DefaultAutoTrait` for each field `F` of type `T` until an explicit impl is be provided.
If the standard library is not modified, then even traits like `Copy` or `Send` would get these supertraits.
In this PR for optimization purposes instead of adding default supertraits, bounds are added to the associated items:
```rust
// Default bounds are generated in the following way:
trait Trait {
fn foo(&self) where Self: DefaultAutoTrait {}
}
// instead of this:
trait Trait: DefaultAutoTrait {
fn foo(&self) {}
}
```
It is not always possible to do this optimization because of backward compatibility:
```rust
pub trait Trait<Rhs = Self> {}
pub trait Trait1 : Trait {} // ERROR: `Rhs` requires `DefaultAutoTrait`, but `Self` is not `DefaultAutoTrait`
```
or
```rust
trait Trait {
type Type where Self: Sized;
}
trait Trait2<T> : Trait<Type = T> {} // ERROR: `???` requires `DefaultAutoTrait`, but `Self` is not `DefaultAutoTrait`
```
Therefore, `DefaultAutoTrait`'s are still being added to supertraits if the `Self` params or type bindings were found in the trait header.
#### Trait objects
Trait objects requires explicit `+ Trait` bound to implement corresponding trait which is not backward compatible:
```rust
fn use_trait_object(x: Box<dyn Trait>) {
foo(x) // ERROR: `foo` requires `DefaultAutoTrait`, but `dyn Trait` is not `DefaultAutoTrait`
}
// implicit T: DefaultAutoTrait here
fn foo<T>(_: T) {}
```
So, for a trait object `dyn Trait` we should add an implicit bound `dyn Trait + DefaultAutoTrait` to make it usable, and allow relaxing it with a question mark syntax `dyn Trait + ?DefaultAutoTrait` when it's not necessary.
#### Foreign types
If compiler doesn't generate auto trait implementations for a foreign type, then it's a breaking change if the default bounds are added everywhere else:
```rust
// implicit T: DefaultAutoTrait here
fn foo<T: ?Sized>(_: &T) {}
extern "C" {
type ExternTy;
}
fn forward_extern_ty(x: &ExternTy) {
foo(x); // ERROR: `foo` requires `DefaultAutoTrait`, but `ExternTy` is not `DefaultAutoTrait`
}
```
We'll have to enable implicit `DefaultAutoTrait` implementations for foreign types at least for previous editions:
```rust
// implicit T: DefaultAutoTrait here
fn foo<T: ?Sized>(_: &T) {}
extern "C" {
type ExternTy;
}
impl DefaultAutoTrait for ExternTy {} // implicit impl
fn forward_extern_ty(x: &ExternTy) {
foo(x); // OK
}
```
### Unresolved questions
New default bounds affect all existing Rust code complicating an already complex type system.
- Proving an auto trait predicate requires recursively traversing the type and proving the predicate for it's fields. This leads to a significant performance regression. Measurements for the stage 2 compiler build show up to 3x regression.
- We hope that fast path optimizations for well known traits could mitigate such regressions at least partially.
- New default bounds trigger some compiler bugs in both old and new trait solver.
- With new default bounds we encounter some trait solver cycle errors that break existing code.
- We hope that these cases are bugs that can be addressed in the new trait solver.
Also migration to a new edition could be quite ugly and enormous, but that's actually what we want to solve. For other issues there's a chance that they could be solved by a new solver.
Dedup `&mut *` reborrow suggestion in loops
#73534 added a reborrow suggestion in loops; #127579 generalized this to generic parameters, making the suggestion triggers twice:
```rs
use std::io::Read;
fn decode_scalar(_reader: impl Read) {}
fn decode_array(reader: &mut impl Read) {
for _ in 0.. {
decode_scalar(reader);
}
}
```
```
error[E0382]: use of moved value: `reader`
--> src/lib.rs:6:23
|
4 | fn decode_array(reader: &mut impl Read) {
| ------ move occurs because `reader` has type `&mut impl Read`, which does not implement the `Copy` trait
5 | for _ in 0.. {
| ------------ inside of this loop
6 | decode_scalar(reader);
| ^^^^^^ value moved here, in previous iteration of loop
|
help: consider creating a fresh reborrow of `reader` here
|
6 | decode_scalar(&mut *reader);
| ++++++
help: consider creating a fresh reborrow of `reader` here
|
6 | decode_scalar(&mut *reader);
| ++++++
```
This PR removes the suggestion in loops, as it requires generic parameters anyway (i.e., the reborrow is automatic if there is no generic params).
`@rustbot` label +A-borrow-checker +A-diagnostics +A-suggestion-diagnostics +D-papercut
Experimental feature gate for `super let`
This adds an experimental feature gate, `#![feature(super_let)]`, for the `super let` experiment.
Tracking issue: https://github.com/rust-lang/rust/issues/139076
Liaison: ``@nikomatsakis``
## Description
There's a rough (inaccurate) description here: https://blog.m-ou.se/super-let/
In short, `super let` allows you to define something that lives long enough to be borrowed by the tail expression of the block. For example:
```rust
let a = {
super let b = temp();
&b
};
```
Here, `b` is extended to live as long as `a`, similar to how in `let a = &temp();`, the temporary will be extended to live as long as `a`.
## Properties
During the temporary lifetimes work we did last year, we explored the properties of "super let" and concluded that the fundamental property should be that these two are always equivalent in any context:
1. `& $expr`
2. `{ super let a = & $expr; a }`
And, additionally, that these are equivalent in any context when `$expr` is a temporary (aka rvalue):
1. `& $expr`
2. `{ super let a = $expr; & a }`
This makes it possible to give a name to a temporary without affecting how temporary lifetimes work, such that a macro can transparently use a block in its expansion, without that having any effect on the outside.
## Implementing pin!() correctly
With `super let`, we can properly implement the `pin!()` macro without hacks: ✨
```rust
pub macro pin($value:expr $(,)?) {
{
super let mut pinned = $value;
unsafe { $crate::pin::Pin::new_unchecked(&mut pinned) }
}
}
```
This is important, as there is currently no way to express it without hacks in Rust 2021 and before (see [hacky definition](2a06022951/library/core/src/pin.rs (L1947))), and no way to express it at all in Rust 2024 (see [issue](https://github.com/rust-lang/rust/issues/138718)).
## Fixing format_args!()
This will also allow us to express `format_args!()` in a way where one can assign the result to a variable, fixing a [long standing issue](https://github.com/rust-lang/rust/issues/92698):
```rust
let f = format_args!("Hello {name}!"); // error today, but accepted in the future! (after separate FCP)
```
## Experiment
The precise definition of `super let`, what happens for `super let x;` (without initializer), and whether to accept `super let _ = _ else { .. }` are still open questions, to be answered by the experiment.
Furthermore, once we have a more complete understanding of the feature, we might be able to come up with a better syntax. (Which could be just a different keywords, or an entirely different way of naming temporaries that doesn't involve a block and a (super) let statement.)
Rollup of 6 pull requests
Successful merges:
- #138992 (literal pattern lowering: use the pattern's type instead of the literal's in `const_to_pat`)
- #139211 (interpret: add a version of run_for_validation for &self)
- #139235 (`AstValidator` tweaks)
- #139237 (Add a dep kind for use of the anon node with zero dependencies)
- #139260 (Add dianqk to codegen reviewers)
- #139264 (Fix two incorrect turbofish suggestions)
r? `@ghost`
`@rustbot` modify labels: rollup
Fix two incorrect turbofish suggestions
This fixes#121901
This is my contribution to Rust, and my first contribution to a language parser that I didn't write myself.
I am a bit outside my depth here, so any constructive criticism is appreciated.
`AstValidator` tweaks
When I read through `AstValidator` there were several things that tripped me up, and made the code harder to understand than I would have liked. This PR addresses them. Best reviewed one commit at a time.
r? ``@davidtwco``
literal pattern lowering: use the pattern's type instead of the literal's in `const_to_pat`
This has two purposes:
- First, it enables removing the `treat_byte_string_as_slice` fields from `TypeckResults` and `ConstToPat`. A byte string pattern's type will be `&[u8]` when matching on a slice reference, so `const_to_pat` will lower it to a slice ref pattern. I believe this is tested by `tests/ui/match/pattern-deref-miscompile.rs`.
- Second, it will simplify the implementation of byte string literals in deref patterns. If byte string patterns can be given the type `[u8; N]` or `[u8]` during HIR typeck, then nothing needs to be changed in `const_to_pat` in order to lower the patterns `deref!(b"..."): Vec<u8>` and `deref!(b"..."): Box<[u8; 3]>`.
Implementation-wise, this uses `lit_to_const` to make a const with the pattern's type and the literal's valtree; that feels to me like the best way to make sure that the valtree representations of the pattern type and literal are the same. Though it may necessitate later changes to `lit_to_const` to accommodate giving byte string literal patterns non-reference types—would that be reasonable?
This unfortunately doesn't work for the `string_deref_patterns` feature (since that gives string literal patterns the `String` type), so I added a workaround for that. However, once `deref_patterns` supports string literals, it may be able to replace `string_deref_patterns`; the special case for `String` can removed at that point.
r? ``@oli-obk``
Various local trait item iteration cleanups
Adding a trait impl for `Foo` unconditionally affected all queries that are interested in a completely independent trait `Bar`. Perf has no effect on this. We probably don't have a good perf test for this tho.
r? `@compiler-errors`
I am unsure about 9d05efb66f as it doesn't improve anything wrt incremental, because we still do all the checks for valid `Drop` impls, which subsequently will still invoke many queries and basically keep the depgraph the same.
I want to do
9549077a47/compiler/rustc_middle/src/ty/trait_def.rs (L141)
but would leave that to a follow-up PR, this one changes enough things as it is
Rollup of 14 pull requests
Successful merges:
- #135295 (Check empty SIMD vector in inline asm)
- #138003 (Add the new `amx` target features and the `movrs` target feature)
- #138823 (rustc_target: RISC-V: add base `I`-related important extensions)
- #138913 (Remove even more instances of `@ts-expect-error` from search.js)
- #138941 (Do not mix normalized and unnormalized caller bounds when constructing param-env for `receiver_is_dispatchable`)
- #139060 (replace commit placeholder in vendor status with actual commit)
- #139102 (coverage: Avoid splitting spans during span extraction/refinement)
- #139191 (small opaque type/borrowck cleanup)
- #139200 (Skip suggest impl or dyn when poly trait is not a real trait)
- #139208 (fix dead link netbsd.md)
- #139210 (chore: remove redundant backtick)
- #139212 (Update mdbook to 0.4.48)
- #139214 (Tell rustfmt to use the 2024 edition in ./x.py fmt)
- #139225 (move autodiff from EnzymeAD/Enzyme to our rust-lang/Enzyme soft-fork)
r? `@ghost`
`@rustbot` modify labels: rollup
Skip suggest impl or dyn when poly trait is not a real trait
Fixes#139174
When `poly_trait_ref` is not a real trait, we should stop suggesting `impl` and `dyn` to avoid false positives. 3 cases were added to the ui test.
0b45675cfc/compiler/rustc_hir_analysis/src/hir_ty_lowering/lint.rs (L88-L93)
In the first commit, I submitted the test and passed it. In the second commit, I modified the code and we can see the changes in the test.
r? compiler
Do not mix normalized and unnormalized caller bounds when constructing param-env for `receiver_is_dispatchable`
See comments in code and in test I added.
r? `@BoxyUwU` since you reviewed the last PR, or reassign
Fixes#138937
rustc_target: RISC-V: add base `I`-related important extensions
Of ratified RISC-V features defined, this commit adds extensions satisfying following criteria:
* Formerly a part of the `I` extension and splitted thereafter (now ratified as `I` + `Zifencei` + `Zicsr` + `Zicntr` + `Zihpm`) or
* Dicoverable from newer versions of the Linux kernel and implemented as a part of `std_detect`'s feature (`Zihintpause`) and
* Available on LLVM 18.
This is based on [the latest ratified ISA Manuals (version 20240411)](https://lf-riscv.atlassian.net/wiki/spaces/HOME/pages/16154769/RISC-V+Technical+Specifications).
LLVM Definitions:
* [`Zifencei`](https://github.com/llvm/llvm-project/blob/llvmorg-20.1.0/llvm/lib/Target/RISCV/RISCVFeatures.td#L133-L137)
* [`Zicsr`](https://github.com/llvm/llvm-project/blob/llvmorg-20.1.0/llvm/lib/Target/RISCV/RISCVFeatures.td#L116-L120)
* [`Zicntr`](https://github.com/llvm/llvm-project/blob/llvmorg-20.1.0/llvm/lib/Target/RISCV/RISCVFeatures.td#L122-L124)
* [`Zihpm`](https://github.com/llvm/llvm-project/blob/llvmorg-20.1.0/llvm/lib/Target/RISCV/RISCVFeatures.td#L153-L155)
* [`Zihintpause`](https://github.com/llvm/llvm-project/blob/llvmorg-20.1.0/llvm/lib/Target/RISCV/RISCVFeatures.td#L139-L144)
Additional (1):
One of those, `Zicsr`, is a dependency of many other ISA extensions and this commit adds correct dependencies to `Zicsr`.
Additional (2):
In RISC-V, `G` is an abbreviation of following extensions:
* `I`
* `M`
* `A`
* `F`
* `D`
* `Zicsr` (although implied by `F`)
* `Zifencei`
and all RISC-V targets with the `G` abbreviation and targets for Android / VxWorks are updated accordingly.
Note:
Android will require RVA22 (likely RVA22U64) and some more extensions, which is a superset of RV64GC. For VxWorks, all BSPs currently distributed by Wind River are for boards with RV64GC (this commit also updates `riscv32-wrs-vxworks` though).
--------
This is the version 4.
`Ztso` in the original proposal is removed on the PR version 2 due to the minimum LLVM version (non-experimental `Ztso` requires LLVM 19 while minimum LLVM version of Rust is 18). This is not back in PR version 3 and 4 after noticing adding `Ztso` is possible by checking host LLVM version because PR version 3 introduces compiler target changes (and adding more extensions would complicate the problems; sorry `Zihintpause`).
Version 4:
* Fixed some commit messages,
* Added Android / VxWorks targets to imply `G` and
* Added an implication from `Zve32x` to `Zicsr` (which makes all vector extension subsets to imply `Zicsr`)
since #138742 is now merged.
Related:
* #44839
(`riscv_target_feature`)
* #114544
(This PR can be a prerequisite of resolving a part of that tracking issue)
* #138742
(Touches the same place and vector extensions depend on `Zicsr`)
NOT Related but linked:
* #132618
(This PR won't be blocked by this issue since none of those extensions do not change the ABI)
`@rustbot` r? `@Amanieu`
`@rustbot` label +T-compiler +O-riscv +A-target-feature
Add the new `amx` target features and the `movrs` target feature
Adds 5 new `amx` target features included in LLVM20. These are guarded under `x86_amx_intrinsics` (#126622)
- `amx-avx512`
- `amx-fp8`
- `amx-movrs`
- `amx-tf32`
- `amx-transpose`
Adds the `movrs` target feature (from #137976).
`@rustbot` label O-x86_64 O-x86_32 T-compiler A-target-feature
r? `@Amanieu`
