| Age | Commit message (Collapse) | Author | Lines |
|---|
|
optimize str.replace
Adds a fast path for str.replace for the ascii to ascii case. This allows for autovectorizing the code. Also should this instead be done with specialization? This way we could remove one branch. I think it is the kind of branch that is easy to predict though.
Benchmark for the fast path (replace all "a" with "b" in the rust wikipedia article, using criterion) :
| N | Speedup | Time New (ns) | Time Old (ns) |
|----------|---------|---------------|---------------|
| 2 | 2.03 | 13.567 | 27.576 |
| 8 | 1.73 | 17.478 | 30.259 |
| 11 | 2.46 | 18.296 | 45.055 |
| 16 | 2.71 | 17.181 | 46.526 |
| 37 | 4.43 | 18.526 | 81.997 |
| 64 | 8.54 | 18.670 | 159.470 |
| 200 | 9.82 | 29.634 | 291.010 |
| 2000 | 24.34 | 81.114 | 1974.300 |
| 20000 | 30.61 | 598.520 | 18318.000 |
| 1000000 | 29.31 | 33458.000 | 980540.000 |
|
|
|
|
|
|
Bump bootstrap compiler to 1.83.0-beta.1
https://forge.rust-lang.org/release/process.html#master-bootstrap-update-tuesday
|
|
Optimize `Box::default` and `Arc::default` to construct more types in place
Both the `Arc` and `Box` `Default` impls currently call `T::default()` before allocating, and then moving the resulting `T` into the allocation.
Most `Default` impls are trivial, which should in theory allow
LLVM to construct `T: Default` directly in the `Box` allocation when calling
`<Box<T>>::default()`.
However, the allocation may fail, which necessitates calling `T`'s destructor if it has one.
If the destructor is non-trivial, then LLVM has a hard time proving that it's
sound to elide, which makes it construct `T` on the stack first, and then copy it into the allocation.
Change both of these impls to allocate first, and then call `T::default` into the uninitialized allocation, so that LLVM doesn't have to prove that it's sound to elide the destructor/initial stack copy.
For example, given the following Rust code:
```rust
#[derive(Default, Clone)]
struct Foo {
x: Vec<u8>,
z: String,
y: Vec<u8>,
}
#[no_mangle]
pub fn src() -> Box<Foo> {
Box::default()
}
```
<details open>
<summary>Before this PR:</summary>
```llvm
`@__rust_no_alloc_shim_is_unstable` = external global i8
; drop_in_place() generated in case the allocation fails
; core::ptr::drop_in_place<playground::Foo>
; Function Attrs: nounwind nonlazybind uwtable
define internal fastcc void `@"_ZN4core3ptr36drop_in_place$LT$playground..Foo$GT$17hff376aece491233bE"(ptr` noalias nocapture noundef readonly align 8 dereferenceable(72) %_1) unnamed_addr #0 personality ptr `@rust_eh_personality` {
start:
%_1.val = load i64, ptr %_1, align 8
%0 = icmp eq i64 %_1.val, 0
br i1 %0, label %bb6, label %"_ZN63_$LT$alloc..alloc..Global$u20$as$u20$core..alloc..Allocator$GT$10deallocate17heaa87468709346b1E.exit.i.i.i4.i"
"_ZN63_$LT$alloc..alloc..Global$u20$as$u20$core..alloc..Allocator$GT$10deallocate17heaa87468709346b1E.exit.i.i.i4.i": ; preds = %start
%1 = getelementptr inbounds i8, ptr %_1, i64 8
%_1.val6 = load ptr, ptr %1, align 8, !nonnull !3, !noundef !3
tail call void `@__rust_dealloc(ptr` noundef nonnull %_1.val6, i64 noundef %_1.val, i64 noundef 1) #8
br label %bb6
bb6: ; preds = %"_ZN63_$LT$alloc..alloc..Global$u20$as$u20$core..alloc..Allocator$GT$10deallocate17heaa87468709346b1E.exit.i.i.i4.i", %start
%2 = getelementptr inbounds i8, ptr %_1, i64 24
%.val9 = load i64, ptr %2, align 8
%3 = icmp eq i64 %.val9, 0
br i1 %3, label %bb5, label %"_ZN63_$LT$alloc..alloc..Global$u20$as$u20$core..alloc..Allocator$GT$10deallocate17heaa87468709346b1E.exit.i.i.i4.i.i11"
"_ZN63_$LT$alloc..alloc..Global$u20$as$u20$core..alloc..Allocator$GT$10deallocate17heaa87468709346b1E.exit.i.i.i4.i.i11": ; preds = %bb6
%4 = getelementptr inbounds i8, ptr %_1, i64 32
%.val10 = load ptr, ptr %4, align 8, !nonnull !3, !noundef !3
tail call void `@__rust_dealloc(ptr` noundef nonnull %.val10, i64 noundef %.val9, i64 noundef 1) #8
br label %bb5
bb5: ; preds = %"_ZN63_$LT$alloc..alloc..Global$u20$as$u20$core..alloc..Allocator$GT$10deallocate17heaa87468709346b1E.exit.i.i.i4.i.i11", %bb6
%5 = getelementptr inbounds i8, ptr %_1, i64 48
%.val4 = load i64, ptr %5, align 8
%6 = icmp eq i64 %.val4, 0
br i1 %6, label %"_ZN4core3ptr46drop_in_place$LT$alloc..vec..Vec$LT$u8$GT$$GT$17hb5ca95423e113cf7E.exit16", label %"_ZN63_$LT$alloc..alloc..Global$u20$as$u20$core..alloc..Allocator$GT$10deallocate17heaa87468709346b1E.exit.i.i.i4.i15"
"_ZN63_$LT$alloc..alloc..Global$u20$as$u20$core..alloc..Allocator$GT$10deallocate17heaa87468709346b1E.exit.i.i.i4.i15": ; preds = %bb5
%7 = getelementptr inbounds i8, ptr %_1, i64 56
%.val5 = load ptr, ptr %7, align 8, !nonnull !3, !noundef !3
tail call void `@__rust_dealloc(ptr` noundef nonnull %.val5, i64 noundef %.val4, i64 noundef 1) #8
br label %"_ZN4core3ptr46drop_in_place$LT$alloc..vec..Vec$LT$u8$GT$$GT$17hb5ca95423e113cf7E.exit16"
"_ZN4core3ptr46drop_in_place$LT$alloc..vec..Vec$LT$u8$GT$$GT$17hb5ca95423e113cf7E.exit16": ; preds = %bb5, %"_ZN63_$LT$alloc..alloc..Global$u20$as$u20$core..alloc..Allocator$GT$10deallocate17heaa87468709346b1E.exit.i.i.i4.i15"
ret void
}
; Function Attrs: nonlazybind uwtable
define noalias noundef nonnull align 8 ptr `@src()` unnamed_addr #1 personality ptr `@rust_eh_personality` {
start:
; alloca to place `Foo` in.
%_1 = alloca [72 x i8], align 8
call void `@llvm.lifetime.start.p0(i64` 72, ptr nonnull %_1)
store i64 0, ptr %_1, align 8
%_2.sroa.4.0._1.sroa_idx = getelementptr inbounds i8, ptr %_1, i64 8
store ptr inttoptr (i64 1 to ptr), ptr %_2.sroa.4.0._1.sroa_idx, align 8
%_2.sroa.5.0._1.sroa_idx = getelementptr inbounds i8, ptr %_1, i64 16
%_3.sroa.4.0..sroa_idx = getelementptr inbounds i8, ptr %_1, i64 32
call void `@llvm.memset.p0.i64(ptr` noundef nonnull align 8 dereferenceable(16) %_2.sroa.5.0._1.sroa_idx, i8 0, i64 16, i1 false)
store ptr inttoptr (i64 1 to ptr), ptr %_3.sroa.4.0..sroa_idx, align 8
%_3.sroa.5.0..sroa_idx = getelementptr inbounds i8, ptr %_1, i64 40
%_4.sroa.4.0..sroa_idx = getelementptr inbounds i8, ptr %_1, i64 56
call void `@llvm.memset.p0.i64(ptr` noundef nonnull align 8 dereferenceable(16) %_3.sroa.5.0..sroa_idx, i8 0, i64 16, i1 false)
store ptr inttoptr (i64 1 to ptr), ptr %_4.sroa.4.0..sroa_idx, align 8
%_4.sroa.5.0..sroa_idx = getelementptr inbounds i8, ptr %_1, i64 64
store i64 0, ptr %_4.sroa.5.0..sroa_idx, align 8
%0 = load volatile i8, ptr `@__rust_no_alloc_shim_is_unstable,` align 1, !noalias !4
%_0.i.i.i = tail call noalias noundef align 8 dereferenceable_or_null(72) ptr `@__rust_alloc(i64` noundef 72, i64 noundef 8) #8, !noalias !4
%1 = icmp eq ptr %_0.i.i.i, null
br i1 %1, label %bb2.i, label %"_ZN5alloc5boxed12Box$LT$T$GT$3new17h0864de14f863a27aE.exit"
bb2.i: ; preds = %start
; invoke alloc::alloc::handle_alloc_error
invoke void `@_ZN5alloc5alloc18handle_alloc_error17h98142d0d8d74161bE(i64` noundef 8, i64 noundef 72) #9
to label %.noexc unwind label %cleanup.i
.noexc: ; preds = %bb2.i
unreachable
cleanup.i: ; preds = %bb2.i
%2 = landingpad { ptr, i32 }
cleanup
; call core::ptr::drop_in_place<playground::Foo>
call fastcc void `@"_ZN4core3ptr36drop_in_place$LT$playground..Foo$GT$17hff376aece491233bE"(ptr` noalias noundef nonnull align 8 dereferenceable(72) %_1) #10
resume { ptr, i32 } %2
"_ZN5alloc5boxed12Box$LT$T$GT$3new17h0864de14f863a27aE.exit": ; preds = %start
; Copy from stack to heap if allocation is successful
call void `@llvm.memcpy.p0.p0.i64(ptr` noundef nonnull align 8 dereferenceable(72) %_0.i.i.i, ptr noundef nonnull align 8 dereferenceable(72) %_1, i64 72, i1 false)
call void `@llvm.lifetime.end.p0(i64` 72, ptr nonnull %_1)
ret ptr %_0.i.i.i
}
```
</details>
<details>
<summary>After this PR</summary>
```llvm
; Notice how there's no `drop_in_place()` generated as well
define noalias noundef nonnull align 8 ptr `@src()` unnamed_addr #0 personality ptr `@rust_eh_personality` {
start:
; no stack allocation
%0 = load volatile i8, ptr `@__rust_no_alloc_shim_is_unstable,` align 1
%_0.i.i.i.i.i = tail call noalias noundef align 8 dereferenceable_or_null(72) ptr `@__rust_alloc(i64` noundef 72, i64 noundef 8) #5
%1 = icmp eq ptr %_0.i.i.i.i.i, null
br i1 %1, label %bb3.i, label %"_ZN5alloc5boxed16Box$LT$T$C$A$GT$13new_uninit_in17h80d6355ef4b73ea3E.exit"
bb3.i: ; preds = %start
; call alloc::alloc::handle_alloc_error
tail call void `@_ZN5alloc5alloc18handle_alloc_error17h98142d0d8d74161bE(i64` noundef 8, i64 noundef 72) #6
unreachable
"_ZN5alloc5boxed16Box$LT$T$C$A$GT$13new_uninit_in17h80d6355ef4b73ea3E.exit": ; preds = %start
; construct `Foo` directly into the allocation if successful
store i64 0, ptr %_0.i.i.i.i.i, align 8
%_8.sroa.4.0._1.sroa_idx = getelementptr inbounds i8, ptr %_0.i.i.i.i.i, i64 8
store ptr inttoptr (i64 1 to ptr), ptr %_8.sroa.4.0._1.sroa_idx, align 8
%_8.sroa.5.0._1.sroa_idx = getelementptr inbounds i8, ptr %_0.i.i.i.i.i, i64 16
%_8.sroa.7.0._1.sroa_idx = getelementptr inbounds i8, ptr %_0.i.i.i.i.i, i64 32
tail call void `@llvm.memset.p0.i64(ptr` noundef nonnull align 8 dereferenceable(16) %_8.sroa.5.0._1.sroa_idx, i8 0, i64 16, i1 false)
store ptr inttoptr (i64 1 to ptr), ptr %_8.sroa.7.0._1.sroa_idx, align 8
%_8.sroa.8.0._1.sroa_idx = getelementptr inbounds i8, ptr %_0.i.i.i.i.i, i64 40
%_8.sroa.10.0._1.sroa_idx = getelementptr inbounds i8, ptr %_0.i.i.i.i.i, i64 56
tail call void `@llvm.memset.p0.i64(ptr` noundef nonnull align 8 dereferenceable(16) %_8.sroa.8.0._1.sroa_idx, i8 0, i64 16, i1 false)
store ptr inttoptr (i64 1 to ptr), ptr %_8.sroa.10.0._1.sroa_idx, align 8
%_8.sroa.11.0._1.sroa_idx = getelementptr inbounds i8, ptr %_0.i.i.i.i.i, i64 64
store i64 0, ptr %_8.sroa.11.0._1.sroa_idx, align 8
ret ptr %_0.i.i.i.i.i
}
```
</details>
|
|
|
|
rename RcBox to RcInner for consistency
Arc uses ArcInner too (created in collaboration with `@aDotInTheVoid` and `@WaffleLapkin` )
|
|
Implemented `FromStr` for `CString` and `TryFrom<CString>` for `String`
The motivation of this change is making it possible to use `CString` in generic methods with `FromStr` and `TryInto<String>` trait bounds. The same traits are already implemented for `OsString` which is an FFI type too.
|
|
Add `#[track_caller]` to allocating methods of `Vec` & `VecDeque`
Part 4 in a lengthy saga.
r? `@joshtriplett` because they were the reviewer the last 3 times.
`@bors` rollup=never "[just in case this has perf effects, Vec is hot](https://github.com/rust-lang/rust/pull/79323#issuecomment-731866746)"
This was first attempted in #79323 by `@nvzqz.` It got approval from `@joshtriplett,` but rotted with merge conflicts and got closed.
Then it got picked up by `@Dylan-DPC-zz` in #83359. A benchmark was run[^perf], the results (after a bit of thinking[^thinking]) were deemed ok[^ok], but there was a typo[^typo] and the PR was made from a wrong remote in the first place[^remote], so #83909 was opened instead.
By the time #83909 rolled around, the methods in question had received some optimizations[^optimizations], so another perf run was conducted[^perf2]. The results were ok[^ok2]. There was a suggestion to add regression tests for panic behavior [^tests], but before it could be addressed, the PR fell victim to merge conflicts[^conflicts] and died again[^rip].
3 years have passed, and (from what I can tell) this has not been tried again, so here I am now, reviving this old effort.
Given how much time has passed and the fact that I've also touched `VecDeque` this time, it probably makes sense to
`@bors` try `@rust-timer`
[^perf]: https://github.com/rust-lang/rust/pull/83359#issuecomment-804450095
[^thinking]: https://github.com/rust-lang/rust/pull/83359#issuecomment-805286704
[^ok]: https://github.com/rust-lang/rust/pull/83359#issuecomment-812739031
[^typo]: https://github.com/rust-lang/rust/pull/83359#issuecomment-812750205
[^remote]: https://github.com/rust-lang/rust/pull/83359#issuecomment-814067119
[^optimizations]: https://github.com/rust-lang/rust/pull/83909#issuecomment-813736593
[^perf2]: https://github.com/rust-lang/rust/pull/83909#issuecomment-813825552
[^ok2]: https://github.com/rust-lang/rust/pull/83909#issuecomment-813831341
[^tests]: https://github.com/rust-lang/rust/pull/83909#issuecomment-825788964
[^conflicts]: https://github.com/rust-lang/rust/pull/83909#issuecomment-851173480
[^rip]: https://github.com/rust-lang/rust/pull/83909#issuecomment-873569771
|
|
|
|
Stabilize `const_option`
This makes the following API stable in const contexts:
```rust
impl<T> Option<T> {
pub const fn as_mut(&mut self) -> Option<&mut T>;
pub const fn expect(self, msg: &str) -> T;
pub const fn unwrap(self) -> T;
pub const unsafe fn unwrap_unchecked(self) -> T;
pub const fn take(&mut self) -> Option<T>;
pub const fn replace(&mut self, value: T) -> Option<T>;
}
impl<T> Option<&T> {
pub const fn copied(self) -> Option<T>
where T: Copy;
}
impl<T> Option<&mut T> {
pub const fn copied(self) -> Option<T>
where T: Copy;
}
impl<T, E> Option<Result<T, E>> {
pub const fn transpose(self) -> Result<Option<T>, E>
}
impl<T> Option<Option<T>> {
pub const fn flatten(self) -> Option<T>;
}
```
The following functions make use of the unstable `const_precise_live_drops` feature:
- `expect`
- `unwrap`
- `unwrap_unchecked`
- `transpose`
- `flatten`
Fixes: <https://github.com/rust-lang/rust/issues/67441>
|
|
This makes the following API stable in const contexts:
impl<T> Option<T> {
pub const fn as_mut(&mut self) -> Option<&mut T>;
pub const fn expect(self, msg: &str) -> T;
pub const fn unwrap(self) -> T;
pub const unsafe fn unwrap_unchecked(self) -> T;
pub const fn take(&mut self) -> Option<T>;
pub const fn replace(&mut self, value: T) -> Option<T>;
}
impl<T> Option<&T> {
pub const fn copied(self) -> Option<T>
where T: Copy;
}
impl<T> Option<&mut T> {
pub const fn copied(self) -> Option<T>
where T: Copy;
}
impl<T, E> Option<Result<T, E>> {
pub const fn transpose(self) -> Result<Option<T>, E>
}
impl<T> Option<Option<T>> {
pub const fn flatten(self) -> Option<T>;
}
The following functions make use of the unstable
`const_precise_live_drops` feature:
- `expect`
- `unwrap`
- `unwrap_unchecked`
- `transpose`
- `flatten`
Fixes: <https://github.com/rust-lang/rust/issues/67441>
|
|
remove const_cow_is_borrowed feature gate
The two functions guarded by this are still unstable, and there's no reason to require a separate feature gate for their const-ness -- we can just have `cow_is_borrowed` cover both kinds of stability.
Cc #65143
|
|
|
|
Const-stabilizes:
- `write`
- `write_bytes`
- `write_unaligned`
In the following paths:
- `core::ptr`
- `core::ptr::NonNull`
- pointer `<*mut T>`
Const-stabilizes the internal `core::intrinsics`:
- `write_bytes`
- `write_via_move`
|
|
Port sort-research-rs test suite to Rust stdlib tests
This PR is a followup to https://github.com/rust-lang/rust/pull/124032. It replaces the tests that test the various sort functions in the standard library with a test-suite developed as part of https://github.com/Voultapher/sort-research-rs. The current tests suffer a couple of problems:
- They don't cover important real world patterns that the implementations take advantage of and execute special code for.
- The input lengths tested miss out on code paths. For example, important safety property tests never reach the quicksort part of the implementation.
- The miri side is often limited to `len <= 20` which means it very thoroughly tests the insertion sort, which accounts for 19 out of 1.5k LoC.
- They are split into to core and alloc, causing code duplication and uneven coverage.
- ~~The randomness is tied to a caller location, wasting the space exploration capabilities of randomized testing.~~ The randomness is not repeatable, as it relies on `std::hash::RandomState::new().build_hasher()`.
Most of these issues existed before https://github.com/rust-lang/rust/pull/124032, but they are intensified by it. One thing that is new and requires additional testing, is that the new sort implementations specialize based on type properties. For example `Freeze` and non `Freeze` execute different code paths.
Effectively there are three dimensions that matter:
- Input type
- Input length
- Input pattern
The ported test-suite tests various properties along all three dimensions, greatly improving test coverage. It side-steps the miri issue by preferring sampled approaches. For example the test that checks if after a panic the set of elements is still the original one, doesn't do so for every single possible panic opportunity but rather it picks one at random, and performs this test across a range of input length, which varies the panic point across them. This allows regular execution to easily test inputs of length 10k, and miri execution up to 100 which covers significantly more code. The randomness used is tied to a fixed - but random per process execution - seed. This allows for fully repeatable tests and fuzzer like exploration across multiple runs.
Structure wise, the tests are previously found in the core integration tests for `sort_unstable` and alloc unit tests for `sort`. The new test-suite was developed to be a purely black-box approach, which makes integration testing the better place, because it can't accidentally rely on internal access. Because unwinding support is required the tests can't be in core, even if the implementation is, so they are now part of the alloc integration tests. Are there architectures that can only build and test core and not alloc? If so, do such platforms require sort testing? For what it's worth the current implementation state passes miri `--target mips64-unknown-linux-gnuabi64` which is big endian.
The test-suite also contains tests for properties that were and are given by the current and previous implementations, and likely relied upon by users but weren't tested. For example `self_cmp` tests that the two parameters `a` and `b` passed into the comparison function are never references to the same object, which if the user is sorting for example a `&mut [Mutex<i32>]` could lead to a deadlock.
Instead of using the hashed caller location as rand seed, it uses seconds since unix epoch / 10, which given timestamps in the CI should be reasonably easy to reproduce, but also allows fuzzer like space exploration.
---
Test run-time changes:
Setup:
```
Linux 6.10
rustc 1.83.0-nightly (f79a912d9 2024-09-18)
AMD Ryzen 9 5900X 12-Core Processor (Zen 3 micro-architecture)
CPU boost enabled.
```
master: e9df22f
Before core integration tests:
```
$ LD_LIBRARY_PATH=build/x86_64-unknown-linux-gnu/stage0-std/x86_64-unknown-linux-gnu/release/deps/ hyperfine build/x86_64-unknown-linux-gnu/stage0-std/x86_64-unknown-linux-gnu/release/deps/coretests-219cbd0308a49e2f
Time (mean ± σ): 869.6 ms ± 21.1 ms [User: 1327.6 ms, System: 95.1 ms]
Range (min … max): 845.4 ms … 917.0 ms 10 runs
# MIRIFLAGS="-Zmiri-disable-isolation" to get real time
$ MIRIFLAGS="-Zmiri-disable-isolation" ./x.py miri library/core
finished in 738.44s
```
After core integration tests:
```
$ LD_LIBRARY_PATH=build/x86_64-unknown-linux-gnu/stage0-std/x86_64-unknown-linux-gnu/release/deps/ hyperfine build/x86_64-unknown-linux-gnu/stage0-std/x86_64-unknown-linux-gnu/release/deps/coretests-219cbd0308a49e2f
Time (mean ± σ): 865.1 ms ± 14.7 ms [User: 1283.5 ms, System: 88.4 ms]
Range (min … max): 836.2 ms … 885.7 ms 10 runs
$ MIRIFLAGS="-Zmiri-disable-isolation" ./x.py miri library/core
finished in 752.35s
```
Before alloc unit tests:
```
LD_LIBRARY_PATH=build/x86_64-unknown-linux-gnu/stage0-std/x86_64-unknown-linux-gnu/release/deps/ hyperfine build/x86_64-unknown-linux-gnu/stage0-std/x86_64-unknown-linux-gnu/release/deps/alloc-19c15e6e8565aa54
Time (mean ± σ): 295.0 ms ± 9.9 ms [User: 719.6 ms, System: 35.3 ms]
Range (min … max): 284.9 ms … 319.3 ms 10 runs
$ MIRIFLAGS="-Zmiri-disable-isolation" ./x.py miri library/alloc
finished in 322.75s
```
After alloc unit tests:
```
LD_LIBRARY_PATH=build/x86_64-unknown-linux-gnu/stage0-std/x86_64-unknown-linux-gnu/release/deps/ hyperfine build/x86_64-unknown-linux-gnu/stage0-std/x86_64-unknown-linux-gnu/release/deps/alloc-19c15e6e8565aa54
Time (mean ± σ): 97.4 ms ± 4.1 ms [User: 297.7 ms, System: 28.6 ms]
Range (min … max): 92.3 ms … 109.2 ms 27 runs
$ MIRIFLAGS="-Zmiri-disable-isolation" ./x.py miri library/alloc
finished in 309.18s
```
Before alloc integration tests:
```
$ LD_LIBRARY_PATH=build/x86_64-unknown-linux-gnu/stage0-std/x86_64-unknown-linux-gnu/release/deps/ hyperfine build/x86_64-unknown-linux-gnu/stage0-std/x86_64-unknown-linux-gnu/release/deps/alloctests-439e7300c61a8046
Time (mean ± σ): 103.2 ms ± 1.7 ms [User: 135.7 ms, System: 39.4 ms]
Range (min … max): 99.7 ms … 107.3 ms 28 runs
$ MIRIFLAGS="-Zmiri-disable-isolation" ./x.py miri library/alloc
finished in 231.35s
```
After alloc integration tests:
```
$ LD_LIBRARY_PATH=build/x86_64-unknown-linux-gnu/stage0-std/x86_64-unknown-linux-gnu/release/deps/ hyperfine build/x86_64-unknown-linux-gnu/stage0-std/x86_64-unknown-linux-gnu/release/deps/alloctests-439e7300c61a8046
Time (mean ± σ): 379.8 ms ± 4.7 ms [User: 4620.5 ms, System: 1157.2 ms]
Range (min … max): 373.6 ms … 386.9 ms 10 runs
$ MIRIFLAGS="-Zmiri-disable-isolation" ./x.py miri library/alloc
finished in 449.24s
```
In my opinion the results don't change iterative library development or CI execution in meaningful ways. For example currently the library doc-tests take ~66s and incremental compilation takes 10+ seconds. However I only have limited knowledge of the various local development workflows that exist, and might be missing one that is significantly impacted by this change.
|
|
|
|
|
|
Same rationale as in the previous commit.
|
|
The `Box<T: Default>` impl currently calls `T::default()` before allocating
the `Box`.
Most `Default` impls are trivial, which should in theory allow
LLVM to construct `T: Default` directly in the `Box` allocation when calling
`<Box<T>>::default()`.
However, the allocation may fail, which necessitates calling `T's` destructor if it has one.
If the destructor is non-trivial, then LLVM has a hard time proving that it's
sound to elide, which makes it construct `T` on the stack first, and then copy it into the allocation.
Create an uninit `Box` first, and then write `T::default` into it, so that LLVM now only needs to prove
that the `T::default` can't panic, which should be trivial for most `Default` impls.
|
|
liballoc: introduce String, Vec const-slicing
This change `const`-qualifies many methods on `Vec` and `String`, notably `as_slice`, `as_str`, `len`. These changes are made behind the unstable feature flag `const_vec_string_slice`.
## Motivation
This is to support simultaneous variance over ownership and constness. I have an enum type that may contain either `String` or `&str`, and I want to produce a `&str` from it in a possibly-`const` context.
```rust
enum StrOrString<'s> {
Str(&'s str),
String(String),
}
impl<'s> StrOrString<'s> {
const fn as_str(&self) -> &str {
match self {
// In a const-context, I really only expect to see this variant, but I can't switch the implementation
// in some mode like #[cfg(const)] -- there has to be a single body
Self::Str(s) => s,
// so this is a problem, since it's not `const`
Self::String(s) => s.as_str(),
}
}
}
```
Currently `String` and `Vec` don't support this, but can without functional changes. Similar logic applies for `len`, `capacity`, `is_empty`.
## Changes
The essential thing enabling this change is that `Unique::as_ptr` is `const`. This lets us convert `RawVec::ptr` -> `Vec::as_ptr` -> `Vec::as_slice` -> `String::as_str`.
I had to move the `Deref` implementations into `as_{str,slice}` because `Deref` isn't `#[const_trait]`, but I would expect this change to be invisible up to inlining. I moved the `DerefMut` implementations as well for uniformity.
|
|
This change `const`-qualifies many methods on Vec and String, notably
`as_slice`, `as_str`, `len`. These changes are made behind the unstable
feature flag `const_vec_string_slice` with the following tracking issue:
https://github.com/rust-lang/rust/issues/129041
|
|
This includes [1], which should help resolve an infinite recusion issue
on WASM and SPARC (possibly other platforms). See [2] and [3] for
further details.
[1]: https://github.com/rust-lang/compiler-builtins/pull/708
[2]: https://rust-lang.zulipchat.com/#narrow/stream/131828-t-compiler/topic/sparc-unknown-none-elf.20regresssion.20between.20compiler-built.2E.2E.2E
[3]: https://rust-lang.zulipchat.com/#narrow/stream/131828-t-compiler/topic/.5Bwasm32.5D.20Infinite.20recursion.20.60compiler-builtins.60.20.60__multi3.60
|
|
Update compiler-builtins to 0.1.132
This commit updates compiler-builtins from 0.1.130 to 0.1.132.
PRs in the delta:
- rust-lang/compiler-builtins#698
- rust-lang/compiler-builtins#699
- rust-lang/compiler-builtins#701
- rust-lang/compiler-builtins#704
- rust-lang/compiler-builtins#627
- rust-lang/compiler-builtins#706
|
|
eduardosm:stabilize-const_slice_from_raw_parts_mut, r=workingjubilee
Stabilize `const_slice_from_raw_parts_mut`
Stabilizes https://github.com/rust-lang/rust/issues/67456, since https://github.com/rust-lang/rust/issues/57349 has been stabilized.
Stabilized const API:
```rust
// core::ptr
pub const fn slice_from_raw_parts_mut<T>(data: *mut T, len: usize) -> *mut [T];
// core::slice
pub const unsafe fn from_raw_parts_mut<'a, T>(data: *mut T, len: usize) -> &'a mut [T];
// core::ptr::NonNull
pub const fn slice_from_raw_parts(data: NonNull<T>, len: usize) -> Self
```
Closes https://github.com/rust-lang/rust/issues/67456.
r? libs-api
|
|
This commit updates compiler-builtins from 0.1.130 to 0.1.132.
PRs in the delta:
- rust-lang/compiler-builtins#698
- rust-lang/compiler-builtins#699
- rust-lang/compiler-builtins#701
- rust-lang/compiler-builtins#704
- rust-lang/compiler-builtins#627
- rust-lang/compiler-builtins#706
|
|
|
|
|
|
|
|
Mark some more types as having insignificant dtor
These were caught by https://github.com/rust-lang/rust/pull/129864#issuecomment-2376658407, which is implementing a lint for some changes in drop order for temporaries in tail expressions.
Specifically, the destructors of `CString` and the bitpacked repr for `std::io::Error` are insignificant insofar as they don't have side-effects on things like locking or synchronization; they just free memory.
See some discussion on #89144 for what makes a drop impl "significant"
|
|
This commit is a followup to https://github.com/rust-lang/rust/pull/124032. It
replaces the tests that test the various sort functions in the standard library
with a test-suite developed as part of
https://github.com/Voultapher/sort-research-rs. The current tests suffer a
couple of problems:
- They don't cover important real world patterns that the implementations take
advantage of and execute special code for.
- The input lengths tested miss out on code paths. For example, important safety
property tests never reach the quicksort part of the implementation.
- The miri side is often limited to `len <= 20` which means it very thoroughly
tests the insertion sort, which accounts for 19 out of 1.5k LoC.
- They are split into to core and alloc, causing code duplication and uneven
coverage.
- The randomness is not repeatable, as it
relies on `std::hash::RandomState::new().build_hasher()`.
Most of these issues existed before
https://github.com/rust-lang/rust/pull/124032, but they are intensified by it.
One thing that is new and requires additional testing, is that the new sort
implementations specialize based on type properties. For example `Freeze` and
non `Freeze` execute different code paths.
Effectively there are three dimensions that matter:
- Input type
- Input length
- Input pattern
The ported test-suite tests various properties along all three dimensions,
greatly improving test coverage. It side-steps the miri issue by preferring
sampled approaches. For example the test that checks if after a panic the set of
elements is still the original one, doesn't do so for every single possible
panic opportunity but rather it picks one at random, and performs this test
across a range of input length, which varies the panic point across them. This
allows regular execution to easily test inputs of length 10k, and miri execution
up to 100 which covers significantly more code. The randomness used is tied to a
fixed - but random per process execution - seed. This allows for fully
repeatable tests and fuzzer like exploration across multiple runs.
Structure wise, the tests are previously found in the core integration tests for
`sort_unstable` and alloc unit tests for `sort`. The new test-suite was
developed to be a purely black-box approach, which makes integration testing the
better place, because it can't accidentally rely on internal access. Because
unwinding support is required the tests can't be in core, even if the
implementation is, so they are now part of the alloc integration tests. Are
there architectures that can only build and test core and not alloc? If so, do
such platforms require sort testing? For what it's worth the current
implementation state passes miri `--target mips64-unknown-linux-gnuabi64` which
is big endian.
The test-suite also contains tests for properties that were and are given by the
current and previous implementations, and likely relied upon by users but
weren't tested. For example `self_cmp` tests that the two parameters `a` and `b`
passed into the comparison function are never references to the same object,
which if the user is sorting for example a `&mut [Mutex<i32>]` could lead to a
deadlock.
Instead of using the hashed caller location as rand seed, it uses seconds since
unix epoch / 10, which given timestamps in the CI should be reasonably easy to
reproduce, but also allows fuzzer like space exploration.
|
|
resolve #130122: reword 'sort-by' edge-conditions documentation
See #130122 for rationale & preliminary discussion.
|
|
r=the8472
Improve autovectorization of to_lowercase / to_uppercase functions
Refactor the code in the `convert_while_ascii` helper function to make it more suitable for auto-vectorization and also process the full ascii prefix of the string. The generic case conversion logic will only be invoked starting from the first non-ascii character.
The runtime on a microbenchmark with a small ascii-only input decreases from ~55ns to ~18ns per iteration. The new implementation also reduces the amount of unsafe code and encapsulates all unsafe inside the helper function.
Fixes #123712
|
|
This includes the following which add `__divtf3` and `__powtf2`, and do
some feature cleanup:
- https://github.com/rust-lang/compiler-builtins/pull/622
- https://github.com/rust-lang/compiler-builtins/pull/692
- https://github.com/rust-lang/compiler-builtins/pull/614
- https://github.com/rust-lang/compiler-builtins/pull/694
The `cc` bump [1] was previously included but was reverted due to
problems updating.
[1]: https://github.com/rust-lang/compiler-builtins/pull/690
|
|
|
|
|
|
update `compiler-builtins` to 0.1.126
this requires the addition of a bootstrap variant of the new `naked_asm!` macro
r? `@tgross35`
extracted from https://github.com/rust-lang/rust/pull/128651
|
|
|
|
Since the stabilization in #127679 has reached stage0, 1.82-beta, we can
start using `&raw` freely, and even the soft-deprecated `ptr::addr_of!`
and `ptr::addr_of_mut!` can stop allowing the unstable feature.
I intentionally did not change any documentation or tests, but the rest
of those macro uses are all now using `&raw const` or `&raw mut` in the
standard library.
|
|
|
|
Refactor the code in the `convert_while_ascii` helper function to make
it more suitable for auto-vectorization and also process the full ascii
prefix of the string. The generic case conversion logic will only be
invoked starting from the first non-ascii character.
The runtime on microbenchmarks with ascii-only inputs improves between
1.5x for short and 4x for long inputs on x86_64 and aarch64.
The new implementation also encapsulates all unsafe inside the
`convert_while_ascii` function.
Fixes #123712
|
|
Add str.as_str() for easy Deref to string slices
Working with `Box<str>` is cumbersome, because in places like `iter.filter()` it can end up being `&Box<str>` or even `&&Box<str>`, and such type doesn't always get auto-dereferenced as expected.
Dereferencing such box to `&str` requires ugly syntax like `&**boxed_str` or `&***boxed_str`, with the exact amount of `*`s.
`Box<str>` is [not easily comparable with other string types](https://github.com/rust-lang/rust/pull/129852) via `PartialEq`. `Box<str>` won't work for lookups in types like `HashSet<String>`, because `Borrow<String>` won't take types like `&Box<str>`. OTOH `set.contains(s.as_str())` works nicely regardless of levels of indirection.
`String` has a simple solution for this: the `as_str()` method, and `Box<str>` should too.
|
|
|
|
#130122
|
|
Avoid re-validating UTF-8 in `FromUtf8Error::into_utf8_lossy`
Part of the unstable feature `string_from_utf8_lossy_owned` - #129436
Refactor `FromUtf8Error::into_utf8_lossy` to copy valid UTF-8 bytes into the buffer, avoiding double validation of bytes.
Add tests that mirror the `String::from_utf8_lossy` tests.
|
|
Refactor `into_utf8_lossy` to copy valid UTF-8 bytes into the buffer,
avoiding double validation of bytes.
Add tests that mirror the `String::from_utf8_lossy` tests
|
|
Rollup of 7 pull requests
Successful merges:
- #128209 (Remove macOS 10.10 dynamic linker bug workaround)
- #130526 (Begin experimental support for pin reborrowing)
- #130611 (Address diagnostics regression for `const_char_encode_utf8`.)
- #130614 (Add arm64e-apple-tvos target)
- #130617 (bail if there are too many non-region infer vars in the query response)
- #130619 (Fix scraped examples height)
- #130624 (Add `Vec::as_non_null`)
r? `@ghost`
`@rustbot` modify labels: rollup
|
|
Disallow hidden references to mutable static
Closes #123060
Tracking:
- https://github.com/rust-lang/rust/issues/123758
|
|
|
|
|
