LLVM Weekly - #670, November 2nd 2026
LLVM Weekly - #670, November 2nd 2026
=====================================
If you prefer, you can read a HTML version of this email at
<https://llvmweekly.org/issue/670>.
Welcome to the six hundred and seventieth issue of LLVM Weekly, a weekly newsletter (published every Monday) covering developments in LLVM, Clang, and related projects. LLVM Weekly is brought to you by [Alex Bradbury](https://www.linkedin.com/in/alex-bradbury/). Subscribe to future issues at <https://llvmweekly.org> and pass it on to anyone else you think may be interested. Please send any tips or feedback via email: <[email protected]>, or Mastodon: [@[email protected]](https://fosstodon.org/@llvmweekly) / [@[email protected]](https://fosstodon.org/@asb), or Bluesky: [@llvmweekly.org](https://bsky.app/profile/llvmweekly.org) / [@asbradbury.org](https://bsky.app/profile/asbradbury.org).
## News and articles from around the web and events
Timm Baeder gave a [Clang bytecode interpreter update on the Red Hat blog](https://developers.redhat.com/articles/2026/10/19/clang-bytecode-interpreter-update-2026).
Saleem Abdulrasool [wrote about ABIs](https://speakinginswift.substack.com/p/the-catalog-what-a-library-promises) on the Browser Company Speaking in Swift blog.
According to the [LLVM
Calendar](https://calendar.google.com/calendar/u/0/[email protected])
in the coming week there will be the following:
* Office hours with the following hosts: Quentin Colombet, Renato Golin.
* Online sync-ups on the following topics: formal specification, MLIR C/C++
frontend working group, pointer authentication, lifetime safety, Clang
static analysis, OpenMP, Clang C and C++ language working group, Flang,
RISC-V, LLVM embedded toolchains, HLSL, MLGO, LLVM libc math.
* For more details see the [LLVM
calendar](https://calendar.google.com/calendar/u/0/[email protected]),
getting involved documentation on [online sync
ups](https://llvm.org/docs/GettingInvolved.html#online-sync-ups) and [office
hours](https://llvm.org/docs/GettingInvolved.html#office-hours).
## On the forums
* Anton Korobeynikov noted that [the Graphite review tool will be disabled for the LLVM
project](https://discourse.llvm.org/t/graphite-will-be-disabled-asap/92689)
as they no longer offer discounted or free plans for open source
organisations.
* Notes are available from various round tables / workshops at last week's Dev
Meeting: [debug
info](https://discourse.llvm.org/t/llvm-2026-dev-conf-debug-info-round-table/92500/7),
[LLVM hearts
ML](https://discourse.llvm.org/t/llvm-dev26-llvm-ml-workshop/91148/2), and
the [RISC-V
roundtable](https://discourse.llvm.org/t/llvm-dev-meeting-2026-risc-v-roundtable-notes/92659/3).
* Michael Kruse provided an [update on the effort to improve Flang compilation
speed by
de-templatising](https://discourse.llvm.org/t/rfc-the-cost-of-templates-when-building-flang/91197/12)
noting that a key PR will land soon. "Flang should not behave any
differently, but builds up to 46% faster (gcc, without precompiled headers)".
* Ralf Jung started an RFC discussion on [adding a freezing
memcpy](https://discourse.llvm.org/t/rfc-add-a-freezing-memcpy/92637) which
would be part of the story for exposing `freeze` to programmers in Rust.
* Joshua Haberman posted an RFC on [`tail_chaincc`, a maximum efficiency
tailcall
convention](https://discourse.llvm.org/t/rfc-tail-chaincc-a-maximum-efficiency-tail-call-convention/92661).
It combines the callee-cleanup mechanics of `tailcc` with the register
optimisations of `preserve_none` and is intended to be used with
`[[clang::musttail]]`.
* paperchalice wrote a v2 RFC on [TableGen support for
RegisterBankInfo](https://discourse.llvm.org/t/rfc-tablegen-support-for-registerbankinfo-v2/92662),
providing a way to define register bank mapping rules by matching
`TypedOperand`s.
* Federico Bruzzone posted an MLIR RFC on [unifying masking in the Vector
dialect](https://discourse.llvm.org/t/rfc-unify-masking-in-the-vector-dialect/92675).
* Konstantin Zhuravlyov started a discussion on [vendor-owned pre-merge
testing for LLVM
PRs](https://discourse.llvm.org/t/rfc-vendor-owned-pre-merge-testing-for-llvm-prs/92624).
## LLVM commits
* LoopStrengthReduce learned to rewrite branches to eq/ne with an immediate for
targets like RISC-V with the Zibi (immediate branch extension) enabled.
[0b56c8e](https://github.com/llvm/llvm-project/commit/0b56c8e2a5b4).
* llvm-dwarfutil now supports `--compress-debug-sections`.
[cc6b3b5](https://github.com/llvm/llvm-project/commit/cc6b3b5a1d0f).
* An X86 pass was added to insert `sfence` after non-temporal stores.
[238ef21](https://github.com/llvm/llvm-project/commit/238ef21c3564).
* A number of fixes were made to tail call support on AArch64 Windows.
[3c956bd](https://github.com/llvm/llvm-project/commit/3c956bd6bc50).
* The 'debugger-tuning' module flag was introduced.
[738215b](https://github.com/llvm/llvm-project/commit/738215bc1122).
* LLVM's AI contribution policy is now referenced on the 'how to submit a bug'
page. [5661d4f](https://github.com/llvm/llvm-project/commit/5661d4fdb9c0).
* `llvm.raw.sections` named metadata was added for embedding arbitrary binary
data into named sections of the output object file.
[39cd74f](https://github.com/llvm/llvm-project/commit/39cd74fb6ea2).
* The `LiveVariables` analysis was removed, described as "12 years overdue" in
the commit message!
[93f05d7](https://github.com/llvm/llvm-project/commit/93f05d753ad3).
* Malloc promotion was removed due to being buggy and rarely profitable.
[e2089b0d](https://github.com/llvm/llvm-project/commit/e2089b0ddf1a).
* VPlan now computes branch costs.
[999b73d](https://github.com/llvm/llvm-project/commit/999b73deef74).
## Clang commits
* `std::meta::is_type` support was implemented.
[6006957](https://github.com/llvm/llvm-project/commit/6006957c522e).
* Clang's DepScan gained a new API to find modulemaps without loading.
[ff065cf](https://github.com/llvm/llvm-project/commit/ff065cf32589).
## Other project commits
* Bolt's webpage styling was updated.
[d35f657b](https://github.com/llvm/llvm-project/commit/d35f657bba4c).
* LLVM's libc now has double precision sinh, cosh, and tanh correctly rounded
for all rounding modes.
[1866d4c](https://github.com/llvm/llvm-project/commit/1866d4cc5634),
[075a6cb](https://github.com/llvm/llvm-project/commit/075a6cb14025),
[ff9ad99](https://github.com/llvm/llvm-project/commit/ff9ad993c2b9).
* LLVM libc's regex implementation is being fleshed out.
[ad46922](https://github.com/llvm/llvm-project/commit/ad46922aac46),
[adb8031](https://github.com/llvm/llvm-project/commit/adb80317aa28).