i8 and u8::to_string() specialisation (far less asm).
Take 2. Around 1/6th of the assembly to without specialisation.
https://godbolt.org/z/bzz8Mq
(partially fixes#73533 )
[Arm64] use isb instruction instead of yield in spin loops
On arm64 we have seen on several databases that ISB (instruction synchronization
barrier) is better to use than yield in a spin loop. The yield instruction is a
nop. The isb instruction puts the processor to sleep for some short time. isb
is a good equivalent to the pause instruction on x86.
Below is an experiment that shows the effects of yield and isb on Arm64 and the
time of a pause instruction on x86 Intel processors. The micro-benchmarks use
https://github.com/google/benchmark.git
```
$ cat a.cc
static void BM_scalar_increment(benchmark::State& state) {
int i = 0;
for (auto _ : state)
benchmark::DoNotOptimize(i++);
}
BENCHMARK(BM_scalar_increment);
static void BM_yield(benchmark::State& state) {
for (auto _ : state)
asm volatile("yield"::);
}
BENCHMARK(BM_yield);
static void BM_isb(benchmark::State& state) {
for (auto _ : state)
asm volatile("isb"::);
}
BENCHMARK(BM_isb);
BENCHMARK_MAIN();
$ g++ -o run a.cc -O2 -lbenchmark -lpthread
$ ./run
--------------------------------------------------------------
Benchmark Time CPU Iterations
--------------------------------------------------------------
AWS Graviton2 (Neoverse-N1) processor:
BM_scalar_increment 0.485 ns 0.485 ns 1000000000
BM_yield 0.400 ns 0.400 ns 1000000000
BM_isb 13.2 ns 13.2 ns 52993304
AWS Graviton (A-72) processor:
BM_scalar_increment 0.897 ns 0.874 ns 801558633
BM_yield 0.877 ns 0.875 ns 800002377
BM_isb 13.0 ns 12.7 ns 55169412
Apple Arm64 M1 processor:
BM_scalar_increment 0.315 ns 0.315 ns 1000000000
BM_yield 0.313 ns 0.313 ns 1000000000
BM_isb 9.06 ns 9.06 ns 77259282
```
```
static void BM_pause(benchmark::State& state) {
for (auto _ : state)
asm volatile("pause"::);
}
BENCHMARK(BM_pause);
Intel Skylake processor:
BM_scalar_increment 0.295 ns 0.295 ns 1000000000
BM_pause 41.7 ns 41.7 ns 16780553
```
Tested on Graviton2 aarch64-linux with `./x.py test`.
Be stricter about rejecting LLVM reserved registers in asm!
LLVM will silently produce incorrect code if these registers are used as operands.
cc `@rust-lang/wg-inline-asm`
Add std::os::unix::fs::chroot to change the root directory of the current process
This is a straightforward wrapper that uses the existing helpers for C
string handling and errno handling.
Having this available is convenient for UNIX utility programs written in
Rust, and avoids having to call the unsafe `libc::chroot` directly and
handle errors manually, in a program that may otherwise be entirely safe
code.
Reuse `sys::unix::cmath` on other platforms
Reuse `sys::unix::cmath` on all non-`windows` platforms.
`unix` is chosen as the canonical location instead of `unsupported` or `common` because `unsupported` doesn't make sense semantically and `common` is reserved for code that is supported on all platforms. Also `unix` is already the home of some non-`windows` code that is technically not exclusive to `unix` like `unix::path`.
This is a straightforward wrapper that uses the existing helpers for C
string handling and errno handling.
Having this available is convenient for UNIX utility programs written in
Rust, and avoids having to call the unsafe `libc::chroot` directly and
handle errors manually, in a program that may otherwise be entirely safe
code.
Drop alias `reduce` for `fold` - we have a `reduce` function
Searching for "reduce" currently puts the `reduce` alias for `fold`
above the actual `reduce` function. The `reduce` function already has a
cross-reference for `fold`, and vice versa.
Link between std::env::{var, var_os} and std::env::{vars, vars_os}
In #84551 I linked between `std::env::{args, args_os}` and this PR does the same but for `std::env::{var, var_os}` and `std::env::{vars, vars_os}`. Now all of `std::env::{var, var_os, vars, vars_os, args, args_os}` should each mention their `_os` or non-`_os` equivalent in the docs so that you can easily navigate between them.
Minor grammar tweaks for readability to btree internals
I was reading through the btree implementation and I noticed some grammar that could be improved in Node.rs so here is what I think would be a minor improvement.
Point out that behavior might be switched on 2015 and 2018 too one day
Reword documentation to make it clear that behaviour can be switched on older editions too, one day in the future. It doesn't *have* to be switched, but I think it's good to have it as an option and re-evaluate it a few months/years down the line when e.g. the crates that showed up in crater were broken by different changes in the language already.
cc #25725, #65819, #66145, #84147 , and https://github.com/rust-lang/rust/issues/84133#issuecomment-818005314
On arm64 we have seen on several databases that ISB (instruction synchronization
barrier) is better to use than yield in a spin loop. The yield instruction is a
nop. The isb instruction puts the processor to sleep for some short time. isb
is a good equivalent to the pause instruction on x86.
Below is an experiment that shows the effects of yield and isb on Arm64 and the
time of a pause instruction on x86 Intel processors. The micro-benchmarks use
https://github.com/google/benchmark.git
$ cat a.cc
static void BM_scalar_increment(benchmark::State& state) {
int i = 0;
for (auto _ : state)
benchmark::DoNotOptimize(i++);
}
BENCHMARK(BM_scalar_increment);
static void BM_yield(benchmark::State& state) {
for (auto _ : state)
asm volatile("yield"::);
}
BENCHMARK(BM_yield);
static void BM_isb(benchmark::State& state) {
for (auto _ : state)
asm volatile("isb"::);
}
BENCHMARK(BM_isb);
BENCHMARK_MAIN();
$ g++ -o run a.cc -O2 -lbenchmark -lpthread
$ ./run
--------------------------------------------------------------
Benchmark Time CPU Iterations
--------------------------------------------------------------
AWS Graviton2 (Neoverse-N1) processor:
BM_scalar_increment 0.485 ns 0.485 ns 1000000000
BM_yield 0.400 ns 0.400 ns 1000000000
BM_isb 13.2 ns 13.2 ns 52993304
AWS Graviton (A-72) processor:
BM_scalar_increment 0.897 ns 0.874 ns 801558633
BM_yield 0.877 ns 0.875 ns 800002377
BM_isb 13.0 ns 12.7 ns 55169412
Apple Arm64 M1 processor:
BM_scalar_increment 0.315 ns 0.315 ns 1000000000
BM_yield 0.313 ns 0.313 ns 1000000000
BM_isb 9.06 ns 9.06 ns 77259282
static void BM_pause(benchmark::State& state) {
for (auto _ : state)
asm volatile("pause"::);
}
BENCHMARK(BM_pause);
Intel Skylake processor:
BM_scalar_increment 0.295 ns 0.295 ns 1000000000
BM_pause 41.7 ns 41.7 ns 16780553
Tested on Graviton2 aarch64-linux with `./x.py test`.
Searching for "reduce" currently puts the `reduce` alias for `fold`
above the actual `reduce` function. The `reduce` function already has a
cross-reference for `fold`, and vice versa.
use correct feature flag for impl-block-level trait bounds on const fn
I am not sure what that special hack was needed for, but it doesn't seem needed any more...
This removes the last use of the `const_fn` feature flag -- Cc https://github.com/rust-lang/rust/issues/84510
r? `@oli-obk`
Remove `DropGuard` in `sys::windows::process` and use `StaticMutex` instead
`StaticMutex` is a mutex that when locked provides a guard that unlocks the mutex again when dropped, thus provides the exact same functionality as `DropGuard`. `StaticMutex` is used in more places, and is thus preferred over an ad-hoc construct like `DropGuard`.
````@rustbot```` label: +T-libs-impl
Simplify `Mutex::into_inner`
Thanks to #77147, `Mutex` do not implement `Drop` directly, so the old unsafe implementation of `into_inner` is not relevant anymore.
Adds feature-gated `#[no_coverage]` function attribute, to fix derived Eq `0` coverage issue #83601
Derived Eq no longer shows uncovered
The Eq trait has a special hidden function. MIR `InstrumentCoverage`
would add this function to the coverage map, but it is never called, so
the `Eq` trait would always appear uncovered.
Fixes: #83601
The fix required creating a new function attribute `no_coverage` to mark
functions that should be ignored by `InstrumentCoverage` and the
coverage `mapgen` (during codegen).
Adding a `no_coverage` feature gate with tracking issue #84605.
r? `@tmandry`
cc: `@wesleywiser`
The Eq trait has a special hidden function. MIR `InstrumentCoverage`
would add this function to the coverage map, but it is never called, so
the `Eq` trait would always appear uncovered.
Fixes: #83601
The fix required creating a new function attribute `no_coverage` to mark
functions that should be ignored by `InstrumentCoverage` and the
coverage `mapgen` (during codegen).
While testing, I also noticed two other issues:
* spanview debug file output ICEd on a function with no body. The
workaround for this is included in this PR.
* `assert_*!()` macro coverage can appear covered if followed by another
`assert_*!()` macro. Normally they appear uncovered. I submitted a new
Issue #84561, and added a coverage test to demonstrate this issue.
