Sync in portable-simd subtree #99491

workingjubilee · 2022-07-20T03:57:03Z

Co-authored-by: Jacob Lifshay <programmerjake@gmail.com>

…r and mask types This is a documentation-only patch that standardizes the presentation of vector types like `u32x4` and mask types like `mask32x16`. The reasoning behind the patch was as follows: 1. Standardized terminology should be preferred, so `element` instead of `value` and `SIMD vector` instead of `vector`. These terms appear in the rest of the documentation and tutorials. 2. Try to avoid situations where two numbers are next to each other. So `16 elements of 32 bits` instead of `16 32-bit elements`. 4. Try to anticipate what readers are looking for -- so state the full bit-width directly. ### Vector Types - Before: Vector of 32 `i8` values - After: A 256-bit SIMD vector with 32 elements of type `i8`. ### Mask Types - Before: Vector of 16 16-bit masks - After: A mask for SIMD vectors with 16 elements of 32 bits.

A simpler variant of rust-lang/portable-simd#206. * Comparisons are moved to `SimdPartialEq`, `SimdPartialOrd`, and `SimdOrd`. The function names are prefixed with `simd_` to disambiguate from the regular `PartialEq` etc functions. With the functions on traits instead of `Simd` directly, shadowing the function names doesn't work very well. * Floating point `Ord`-like functions are put into a `SimdFloat` trait. The intention is that eventually (some time after this PR) all floating point functions will be moved from `Simd` to `SimdFloat`, and the same goes for future `SimdInt`/`SimdUint` traits.

…vectors

…s, swizzle Working through giving example documentation to every Simd function. The major change in this patch is using doc macros to generate type-specific examples for each function, using a visually-apparent type constructor. This makes it feel nicer to have twelve separate documentation entries for reduce_product(), for example.

…imd_mut() This links to a practical suggestion for how to solve the issues brought up in this section.

Add Mask::cast

Move element-specific functions to traits

Add bitmask array

This fixes poor codegen in some circumstances for `u16x8::splat` on x86_64 https://rust-lang.zulipchat.com/#narrow/stream/257879-project-portable-simd/topic/Very.20bad.20.60u16x8.3A.3Asplat.60.20codegen.20on.20x86_64

Deduplicate to_int_unchecked

Change `Simd::splat` to not generate a loop

It looks like the last time had left some remaining cfg's -- which made me think that the stage0 bump was actually successful. This brings us to a released 1.62 beta though.

rustbot · 2022-07-20T03:57:05Z

Hey! It looks like you've submitted a new PR for the library teams!

If this PR contains changes to any rust-lang/rust public library APIs then please comment with @rustbot label +T-libs-api -T-libs to tag it appropriately. If this PR contains changes to any unstable APIs please edit the PR description to add a link to the relevant API Change Proposal or create one if you haven't already. If you're unsure where your change falls no worries, just leave it as is and the reviewer will take a look and make a decision to forward on if necessary.

Examples of T-libs-api changes:

Stabilizing library features
Introducing insta-stable changes such as new implementations of existing stable traits on existing stable types
Introducing new or changing existing unstable library APIs (excluding permanently unstable features / features without a tracking issue)
Changing public documentation in ways that create new stability guarantees
Changing observable runtime behavior of library APIs

Within core, `use self::` does not work to import these items. And because core is not core_simd, neither does the existing `use`. So, use this quirky hack instead, switching the import on a feature.

workingjubilee · 2022-07-21T01:30:38Z

@bors r+

bors · 2022-07-21T01:30:40Z

📌 Commit f8aa494 has been approved by workingjubilee

It is now in the queue for this repository.

Dylan-DPC · 2022-07-22T05:17:35Z

@bors rollup=never

bors · 2022-07-22T09:48:03Z

⌛ Testing commit f8aa494 with merge 41419e7...

bors · 2022-07-22T12:28:47Z

☀️ Test successful - checks-actions
Approved by: workingjubilee
Pushing 41419e7 to master...

rust-timer · 2022-07-22T13:45:21Z

Finished benchmarking commit (41419e7): comparison url.

Instruction count

Primary benchmarks: 😿 relevant regressions found
Secondary benchmarks: 😿 relevant regressions found

	mean¹	max	count²
Regressions 😿 (primary)	0.5%	1.0%	11
Regressions 😿 (secondary)	0.8%	1.3%	20
Improvements 🎉 (primary)	-0.2%	-0.2%	1
Improvements 🎉 (secondary)	N/A	N/A	0
All 😿🎉 (primary)	0.4%	1.0%	12

Max RSS (memory usage)

Results

Primary benchmarks: 😿 relevant regression found
Secondary benchmarks: mixed results

	mean¹	max	count²
Regressions 😿 (primary)	1.4%	1.4%	1
Regressions 😿 (secondary)	2.7%	4.1%	4
Improvements 🎉 (primary)	N/A	N/A	0
Improvements 🎉 (secondary)	-2.7%	-2.8%	2
All 😿🎉 (primary)	1.4%	1.4%	1

Cycles

Results

Primary benchmarks: 😿 relevant regressions found
Secondary benchmarks: 🎉 relevant improvement found

	mean¹	max	count²
Regressions 😿 (primary)	3.6%	6.1%	3
Regressions 😿 (secondary)	N/A	N/A	0
Improvements 🎉 (primary)	N/A	N/A	0
Improvements 🎉 (secondary)	-2.4%	-2.4%	1
All 😿🎉 (primary)	3.6%	6.1%	3

If you disagree with this performance assessment, please file an issue in rust-lang/rustc-perf.

Next Steps: If you can justify the regressions found in this perf run, please indicate this with @rustbot label: +perf-regression-triaged along with sufficient written justification. If you cannot justify the regressions please open an issue or create a new PR that fixes the regressions, add a comment linking to the newly created issue or PR, and then add the perf-regression-triaged label to this PR.

@rustbot label: +perf-regression

the arithmetic mean of the percent change ↩ ↩² ↩³
number of relevant changes ↩ ↩² ↩³

workingjubilee · 2022-07-23T05:11:57Z

...I got nothin'! I like genuinely have no idea why any of these changes, tbh.

pnkfelix · 2022-07-27T16:40:48Z

All of the regressions here are on doc profiles. I don't think its worth us spending time trying to figure out 1% regressions to rustdoc performance. (And I made a topic for discussing the matter on zulip.)

Marking as triaged

@rustbot label: +perf-regression-triaged

calebzulawski and others added 30 commits March 13, 2022 19:07

Move comparisons to SimdPartialOrd and SimdOrd traits

80469c6

Create SimdFloat trait

2a02c4d

SimdPartialOrd implies SimdPartialEq

60486e0

add bitmask roundtrip test for vector length below 8

50fbfa4

fix big-endian bitmasks smaller than a byte

60555b5

rust-lang/portable-simd#266: reduce Miri test count in round.rs

35e16a1

rust-lang/portable-simd#267: fix big-endian bitmasks smaller than a byte

0711e11

Standardize documentation for SIMD vector and mask types

4e14017

Update crates/core_simd/src/masks.rs

c73f1fb

Co-authored-by: Jacob Lifshay <programmerjake@gmail.com>

Correct the Mask docs, and get them to fit in search results

21b070c

Add a *small* blurb to Mask that is likely unobjectionable

8cd9325

rust-lang/portable-simd#274: Use SIMD equality for PartialEq on SIMD …

7136841

…vectors

rust-lang/portable-simd#276: Mention slice methods as_simd() and as_s…

9718639

…imd_mut() This links to a practical suggestion for how to solve the issues brought up in this section.

Move integer functions to traits.

376957a

Add float trait, and seal traits.

04be48f

Improve copysign documentation

528bc85

Add Copy bound to SIMD traits

62d3b2e

rust-lang/portable-simd#279: Silence clippy false alarms

af53b5d

Add Mask::cast

98cd636

Add mask cast tests

aa11959

Use Mask::cast in From impl

c9f4e0e

Merge pull request rust-lang#251 from rust-lang/mask-cast

939914e

Add Mask::cast

Generically implement ToBitMaskArray

b7fea94

Fix generic_const_exprs feature

1cee930

Remove incorrect comment

bca8dec

Merge pull request rust-lang#278 from rust-lang/feature/simd-traits

c44a608

Move element-specific functions to traits

Merge pull request rust-lang#246 from rust-lang/feature/bitmask_array

5e32004

Add bitmask array

programmerjake and others added 7 commits June 6, 2022 12:16

Change Simd::splat to not generate a loop

c963615

This fixes poor codegen in some circumstances for `u16x8::splat` on x86_64 https://rust-lang.zulipchat.com/#narrow/stream/257879-project-portable-simd/topic/Very.20bad.20.60u16x8.3A.3Asplat.60.20codegen.20on.20x86_64

add workaround comment in Simd::splat

f7412ad

Merge pull request rust-lang#281 from rust-lang/to-int-unchecked

3e7a2ed

Deduplicate to_int_unchecked

Merge pull request rust-lang#284 from programmerjake/fix_splat

0f6399b

Change `Simd::splat` to not generate a loop

Clarify comment

ed8092e

portable-simd: use simd_arith_offset to avoid ptr-int transmutation

64bef29

Finish bumping stage0

bbf31f9

It looks like the last time had left some remaining cfg's -- which made me think that the stage0 bump was actually successful. This brings us to a released 1.62 beta though.

This comment has been minimized.

Sign in to view

workingjubilee added 3 commits July 20, 2022 17:55

Fix doctest imports using as_crate feature

2e081db

Within core, `use self::` does not work to import these items. And because core is not core_simd, neither does the existing `use`. So, use this quirky hack instead, switching the import on a feature.

Sync core::simd up to rust-lang/portable-simd@2e081db

a14404a

Introduce core::simd trait imports in tests

f8aa494

workingjubilee force-pushed the sync-psimd branch from 0578e51 to f8aa494 Compare July 21, 2022 01:08

rustbot added 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 Jul 21, 2022

bors added the S-waiting-on-bors Status: Waiting on bors to run and complete tests. Bors will change the label on completion. label Jul 21, 2022

bors added the merged-by-bors This PR was explicitly merged by bors. label Jul 22, 2022

bors merged commit 41419e7 into rust-lang:master Jul 22, 2022

rustbot added this to the 1.64.0 milestone Jul 22, 2022

rustbot added the perf-regression Performance regression. label Jul 22, 2022

gyscos mentioned this pull request Jul 25, 2022

std::simd::Simd::lanes_eq no longer present in latest nightly jorgecarleitao/arrow2#1184

Closed

rustbot added the perf-regression-triaged The performance regression has been triaged. label Jul 27, 2022

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Sync in portable-simd subtree #99491

Sync in portable-simd subtree #99491

workingjubilee commented Jul 20, 2022

rustbot commented Jul 20, 2022

This comment has been minimized.

workingjubilee commented Jul 21, 2022

bors commented Jul 21, 2022

Dylan-DPC commented Jul 22, 2022

bors commented Jul 22, 2022

bors commented Jul 22, 2022

rust-timer commented Jul 22, 2022

workingjubilee commented Jul 23, 2022

pnkfelix commented Jul 27, 2022

Sync in portable-simd subtree #99491

Sync in portable-simd subtree #99491

Conversation

workingjubilee commented Jul 20, 2022

rustbot commented Jul 20, 2022

This comment has been minimized.

workingjubilee commented Jul 21, 2022

bors commented Jul 21, 2022

Dylan-DPC commented Jul 22, 2022

bors commented Jul 22, 2022

bors commented Jul 22, 2022

rust-timer commented Jul 22, 2022

Instruction count

Max RSS (memory usage)

Cycles

Footnotes

workingjubilee commented Jul 23, 2022

pnkfelix commented Jul 27, 2022