Make `Rc<T>::deref` and `Arc<T>::deref` zero-cost #132553

EFanZh · 2024-11-03T07:48:34Z

Currently, Rc<T> and Arc<T> store pointers to RcInner<T> and ArcInner<T>. This PR changes the pointers so that they point to T directly instead.

This is based on the assumption that we access the T value more frequently than accessing reference counts. With this change, accessing the data can be done without offsetting pointers from RcInner<T> and ArcInner<T> to their contained data. This change might also enables some possibly useful future optimizations, such as:

Convert &[Rc<T>] into &[&T] within O(1) time.
Convert &[Rc<T>] into Vec<&T> utilizing memcpy.
Convert &Option<Rc<T>> into Option<&T> without branching.
Make Rc<T> and Arc<T> FFI compatible types where T: Sized.

rustbot · 2024-11-03T07:48:42Z

r? @jhpratt

rustbot has assigned @jhpratt.
They will have a look at your PR within the next two weeks and either review your PR or reassign to another reviewer.

Use r? to explicitly pick a reviewer

marmeladema · 2024-11-03T09:22:09Z

Would it potentially enable those types to have an ffi compatible ABI? So that they could be returned and passed directly from /to ffi function, like Box?

EFanZh · 2024-11-03T10:36:08Z

Would it potentially enable those types to have an ffi compatible ABI? So that they could be returned and passed directly from /to ffi function, like Box?

I think in theory it is possible, at least for sized types, but I am not familiar with how to formally make it so.

jhpratt · 2024-11-03T23:07:24Z

r? libs

joboet · 2024-11-07T16:17:52Z

@EFanZh Is this ready for review? If so, please un-draft the PR.

EFanZh · 2024-11-07T17:12:22Z

@joboet: The source code part is mostly done, but I haven’t finished updating LLDB and CDB pretty printers. The CI doesn’t seem to run those tests.

joboet · 2024-11-08T12:56:42Z

No worries! I just didn't want to keep you waiting in case you had forgotten to change the state.
@rustbot author

Kobzol · 2025-08-10T06:13:25Z

@bors try @rust-timer queue

rust-bors · 2025-08-10T06:13:29Z

⌛ Trying commit d54c877 with merge 38a5d4f…

To cancel the try build, run the command @bors try cancel.

Make `Rc<T>::deref` and `Arc<T>::deref` zero-cost

rust-bors · 2025-08-10T08:26:31Z

☀️ Try build successful (CI)
Build commit: 38a5d4f (38a5d4f4c9ded25243c2946db27e12396bfed6a4, parent: 915a766b2f9fd53a8cd7b1fad003d3f8e488ff4b)

rust-timer · 2025-08-10T09:36:55Z

Finished benchmarking commit (38a5d4f): comparison URL.

Overall result: ❌✅ regressions and improvements - please read the text below

Benchmarking this pull request means it may be perf-sensitive – we'll automatically label it not fit for rolling up. You can override this, but we strongly advise not to, due to possible changes in compiler perf.

Next Steps: If you can justify the regressions found in this try perf run, please do so in sufficient writing along with @rustbot label: +perf-regression-triaged. If not, please fix the regressions and do another perf run. If its results are neutral or positive, the label will be automatically removed.

@bors rollup=never
@rustbot label: -S-waiting-on-perf +perf-regression

Instruction count

Our most reliable metric. Used to determine the overall result above. However, even this metric can be noisy.

	mean	range	count
Regressions ❌ (primary)	2.2%	[0.3%, 14.7%]	11
Regressions ❌ (secondary)	0.6%	[0.1%, 2.6%]	22
Improvements ✅ (primary)	-0.5%	[-1.5%, -0.2%]	28
Improvements ✅ (secondary)	-1.1%	[-3.0%, -0.1%]	26
All ❌✅ (primary)	0.3%	[-1.5%, 14.7%]	39

Max RSS (memory usage)

Results (primary 1.0%, secondary -0.8%)

A less reliable metric. May be of interest, but not used to determine the overall result above.

	mean	range	count
Regressions ❌ (primary)	3.2%	[1.6%, 5.6%]	5
Regressions ❌ (secondary)	2.9%	[2.6%, 3.1%]	4
Improvements ✅ (primary)	-2.6%	[-3.3%, -2.0%]	3
Improvements ✅ (secondary)	-3.3%	[-6.1%, -2.1%]	6
All ❌✅ (primary)	1.0%	[-3.3%, 5.6%]	8

Cycles

Results (primary 5.1%, secondary -0.7%)

A less reliable metric. May be of interest, but not used to determine the overall result above.

	mean	range	count
Regressions ❌ (primary)	5.1%	[2.1%, 13.3%]	4
Regressions ❌ (secondary)	2.4%	[2.1%, 2.8%]	2
Improvements ✅ (primary)	-	-	0
Improvements ✅ (secondary)	-3.8%	[-4.2%, -3.3%]	2
All ❌✅ (primary)	5.1%	[2.1%, 13.3%]	4

Binary size

Results (primary 0.5%, secondary 0.6%)

A less reliable metric. May be of interest, but not used to determine the overall result above.

	mean	range	count
Regressions ❌ (primary)	0.5%	[0.0%, 2.2%]	77
Regressions ❌ (secondary)	0.6%	[0.0%, 5.6%]	96
Improvements ✅ (primary)	-0.3%	[-0.4%, -0.2%]	2
Improvements ✅ (secondary)	-	-	0
All ❌✅ (primary)	0.5%	[-0.4%, 2.2%]	79

Bootstrap: 463.478s -> 463.036s (-0.10%)
Artifact size: 377.38 MiB -> 377.46 MiB (0.02%)

tgross35 · 2025-08-13T02:00:04Z

The results here seem to be pretty mixed. Any idea why this seems to hurt some incremental builds? I suppose it could cause more work to do at build time, but the 14% increase building clif seems like something more substantial. Unless, is that code super Arc-heavy or something?

(cranelift-codegen is a benchmark testing building rustc_codgen_cranelift and not a benchmark of the time clif takes to do codegen, right?)

scottmcm · 2025-08-13T02:57:28Z

Those icount results look entirely mergeable to me, at least. Notably, the checks are comfortably green, including 100% green in the primary benchmarks, which I find is often the best measure we have of how this impacts code at runtime. And IIRC there's a bunch of Arcs in the query system. (Sometimes doc can do that too, but here that's very quiet.) Then debug is mixed but still comfortably green, also 100% green in primary.

Opt isn't trivially-fine, but I think it's ok. Lots of them are incr anyway, which is relatively rare with opt. And the one big outlier in icount shuffled its codegen schedule massively:

So with that I think the icounts are misleading, and its wall time result is still within reasonableness: +1.93% but that's below the significance threshold since it looks like that happens a ton for it:

Since this makes Deref simpler and thus changes the inliner cost estimates for something quite common, it seems entirely plausible that this would thus permute the opt results a whole bunch.

I think I might actually be more curious about the binary size changes. Dropping 126KiB off rustc_driver.so looks great, but then image and cargo get materially bigger in binary size for opt-full, which seems weird. I would have expected this to help drop size a bit by reducing the need for offsetting loads, but almost everything is bigger instead.

Any idea where that extra binary size is coming from?

EFanZh · 2025-08-13T02:59:21Z

@tgross35: There isn’t any significant change since the last perf run (https://perf.rust-lang.org/compare.html?start=b88076097751f7677b850b94b20faf5679fca321&end=1a76f3df0b6373e760df2514a5af2587f3e01aff&stat=instructions:u). But my local development environment is currently broken, and I’ll need some time to analyze the perf result.

tgross35 · 2025-08-13T03:40:13Z

Oh yeah that the wins definitely outweigh the losses here, no disagreement. I’m just wondering what makes clif such an outlier.

The cargo changes have to be inlining, maybe this just tips the scale for something commonly-called medium-sized function to be inlined.

rustbot · 2025-08-16T06:37:03Z

This PR was rebased onto a different master commit! Check out the changes with our range-diff.

programmerjake · 2025-08-16T08:44:19Z

library/alloc/src/raw_rc/rc_layout.rs

+    pub(crate) fn new_array<T>(length: usize) -> Self {
+        #[inline]
+        fn inner(value_layout: Layout, length: usize) -> RcLayout {
+            // We can use `repeat_packet` here because the outer function passes `T::LAYOUT` as the


Suggested change

// We can use `repeat_packet` here because the outer function passes `T::LAYOUT` as the

// We can use `repeat_packed` here because the outer function passes `T::LAYOUT` as the

EFanZh · 2025-08-16T09:43:21Z

@tgross35: I have marked some functions #[inline] with a new commit, can I have another perf run to see if there is any improvement?

Kobzol · 2025-08-16T10:33:03Z

@bors try @rust-timer queue

Make `Rc<T>::deref` and `Arc<T>::deref` zero-cost

rust-bors · 2025-08-16T12:45:25Z

☀️ Try build successful (CI)
Build commit: 585da62 (585da6216db2cba34c79bb89dfc04b0f27630ad9, parent: 1ae7c4907275f10b3db9e886bc8809ec063e45ee)

rust-timer · 2025-08-16T13:56:14Z

Finished benchmarking commit (585da62): comparison URL.

Overall result: ❌✅ regressions and improvements - please read the text below

Benchmarking this pull request means it may be perf-sensitive – we'll automatically label it not fit for rolling up. You can override this, but we strongly advise not to, due to possible changes in compiler perf.

Next Steps: If you can justify the regressions found in this try perf run, please do so in sufficient writing along with @rustbot label: +perf-regression-triaged. If not, please fix the regressions and do another perf run. If its results are neutral or positive, the label will be automatically removed.

@bors rollup=never
@rustbot label: -S-waiting-on-perf +perf-regression

Instruction count

Our most reliable metric. Used to determine the overall result above. However, even this metric can be noisy.

	mean	range	count
Regressions ❌ (primary)	0.5%	[0.3%, 0.8%]	8
Regressions ❌ (secondary)	1.1%	[0.0%, 2.4%]	7
Improvements ✅ (primary)	-0.4%	[-3.0%, -0.2%]	75
Improvements ✅ (secondary)	-0.4%	[-1.5%, -0.2%]	39
All ❌✅ (primary)	-0.3%	[-3.0%, 0.8%]	83

Max RSS (memory usage)

Results (primary -0.1%, secondary 0.8%)

A less reliable metric. May be of interest, but not used to determine the overall result above.

	mean	range	count
Regressions ❌ (primary)	2.8%	[1.6%, 4.8%]	4
Regressions ❌ (secondary)	2.8%	[2.2%, 4.6%]	5
Improvements ✅ (primary)	-3.9%	[-4.7%, -3.2%]	3
Improvements ✅ (secondary)	-4.3%	[-6.0%, -2.7%]	2
All ❌✅ (primary)	-0.1%	[-4.7%, 4.8%]	7

Cycles

Results (primary -2.6%, secondary -1.3%)

A less reliable metric. May be of interest, but not used to determine the overall result above.

	mean	range	count
Regressions ❌ (primary)	-	-	0
Regressions ❌ (secondary)	2.5%	[2.3%, 2.8%]	2
Improvements ✅ (primary)	-2.6%	[-3.0%, -2.3%]	2
Improvements ✅ (secondary)	-3.2%	[-4.9%, -1.8%]	4
All ❌✅ (primary)	-2.6%	[-3.0%, -2.3%]	2

Binary size

Results (primary 0.3%, secondary -0.4%)

A less reliable metric. May be of interest, but not used to determine the overall result above.

	mean	range	count
Regressions ❌ (primary)	0.7%	[0.0%, 2.8%]	35
Regressions ❌ (secondary)	1.9%	[0.0%, 6.2%]	7
Improvements ✅ (primary)	-0.3%	[-0.7%, -0.1%]	18
Improvements ✅ (secondary)	-0.8%	[-6.7%, -0.1%]	33
All ❌✅ (primary)	0.3%	[-0.7%, 2.8%]	53

Bootstrap: 469.963s -> 472.368s (0.51%)
Artifact size: 377.54 MiB -> 377.32 MiB (-0.06%)

rustbot assigned jhpratt Nov 3, 2024

rustbot added S-waiting-on-review Status: Awaiting review from the assignee but also interested parties. T-compiler Relevant to the compiler team, which will review and decide on the PR/issue. T-libs Relevant to the library team, which will review and decide on the PR/issue. labels Nov 3, 2024

EFanZh force-pushed the zero-cost-rc-arc-deref branch from b283c44 to ae36f44 Compare November 3, 2024 09:14

This comment has been minimized.

Sign in to view

EFanZh force-pushed the zero-cost-rc-arc-deref branch from ae36f44 to 0d6165f Compare November 3, 2024 11:21

This comment has been minimized.

Sign in to view

EFanZh force-pushed the zero-cost-rc-arc-deref branch from 0d6165f to 98edd5b Compare November 3, 2024 13:06

This comment has been minimized.

Sign in to view

rustbot assigned joboet and unassigned jhpratt Nov 3, 2024

EFanZh force-pushed the zero-cost-rc-arc-deref branch from 98edd5b to 8beb51d Compare November 4, 2024 16:29

This comment has been minimized.

Sign in to view

EFanZh force-pushed the zero-cost-rc-arc-deref branch from 8beb51d to d7879fa Compare November 4, 2024 17:26

This comment has been minimized.

Sign in to view

EFanZh force-pushed the zero-cost-rc-arc-deref branch from d7879fa to 317aa0e Compare November 4, 2024 18:40

rustbot added S-waiting-on-author Status: This is awaiting some action (such as code changes or more information) from the author. and removed S-waiting-on-review Status: Awaiting review from the assignee but also interested parties. labels Nov 8, 2024

EFanZh force-pushed the zero-cost-rc-arc-deref branch 3 times, most recently from f243654 to 1308bf6 Compare November 11, 2024 18:35

This comment has been minimized.

Sign in to view

rust-bors bot added a commit that referenced this pull request Aug 10, 2025

Auto merge of #132553 - EFanZh:zero-cost-rc-arc-deref, r=<try>

38a5d4f

Make `Rc<T>::deref` and `Arc<T>::deref` zero-cost

rustbot added the S-waiting-on-perf Status: Waiting on a perf run to be completed. label Aug 10, 2025

This comment has been minimized.

Sign in to view

rustbot removed the S-waiting-on-perf Status: Waiting on a perf run to be completed. label Aug 10, 2025

EFanZh force-pushed the zero-cost-rc-arc-deref branch from d54c877 to 3a7fd56 Compare August 16, 2025 06:37

EFanZh and others added 3 commits August 16, 2025 14:54

Make Rc<T>::deref zero-cost

4c93012

Make Arc<T>::deref zero-cost

efc831a

Inline some functions

fc33db3

EFanZh force-pushed the zero-cost-rc-arc-deref branch from 3a7fd56 to fc33db3 Compare August 16, 2025 06:54

programmerjake reviewed Aug 16, 2025

View reviewed changes

This comment has been minimized.

Sign in to view

rust-bors bot added a commit that referenced this pull request Aug 16, 2025

Auto merge of #132553 - EFanZh:zero-cost-rc-arc-deref, r=<try>

585da62

Make `Rc<T>::deref` and `Arc<T>::deref` zero-cost

rustbot added the S-waiting-on-perf Status: Waiting on a perf run to be completed. label Aug 16, 2025

This comment has been minimized.

Sign in to view

rustbot removed the S-waiting-on-perf Status: Waiting on a perf run to be completed. label Aug 16, 2025

	// We can use `repeat_packet` here because the outer function passes `T::LAYOUT` as the
	// We can use `repeat_packed` here because the outer function passes `T::LAYOUT` as the

Make Rc<T>::deref and Arc<T>::deref zero-cost #132553

Are you sure you want to change the base?

Make Rc<T>::deref and Arc<T>::deref zero-cost #132553

Uh oh!

Conversation

EFanZh commented Nov 3, 2024 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

rustbot commented Nov 3, 2024

Uh oh!

This comment has been minimized.

marmeladema commented Nov 3, 2024

Uh oh!

This comment has been minimized.

EFanZh commented Nov 3, 2024

Uh oh!

This comment has been minimized.

This comment has been minimized.

jhpratt commented Nov 3, 2024

Uh oh!

This comment has been minimized.

This comment has been minimized.

joboet commented Nov 7, 2024

Uh oh!

EFanZh commented Nov 7, 2024 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

joboet commented Nov 8, 2024

Uh oh!

Kobzol commented Aug 10, 2025

Uh oh!

This comment has been minimized.

rust-bors bot commented Aug 10, 2025

Uh oh!

rust-bors bot commented Aug 10, 2025

Uh oh!

This comment has been minimized.

rust-timer commented Aug 10, 2025

Overall result: ❌✅ regressions and improvements - please read the text below

Uh oh!

tgross35 commented Aug 13, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

scottmcm commented Aug 13, 2025

Uh oh!

EFanZh commented Aug 13, 2025

Uh oh!

tgross35 commented Aug 13, 2025

Uh oh!

rustbot commented Aug 16, 2025

Uh oh!

Choose a reason for hiding this comment

Uh oh!

EFanZh commented Aug 16, 2025

Uh oh!

Kobzol commented Aug 16, 2025

Uh oh!

This comment has been minimized.

This comment has been minimized.

rust-bors bot commented Aug 16, 2025

Uh oh!

This comment has been minimized.

rust-timer commented Aug 16, 2025

Overall result: ❌✅ regressions and improvements - please read the text below

Uh oh!

Uh oh!

Make `Rc<T>::deref` and `Arc<T>::deref` zero-cost #132553

Make `Rc<T>::deref` and `Arc<T>::deref` zero-cost #132553

EFanZh commented Nov 3, 2024 •

edited

Loading

EFanZh commented Nov 7, 2024 •

edited

Loading

tgross35 commented Aug 13, 2025 •

edited

Loading