build: introduce FLB_SIMD with 'Auto' value option (default)

[edsiper]

• x86_64, aarch64: Auto enables SIMD.
• riscv64: Auto disables SIMD, On requires RVV compiler support.
• arm32 and other unsupported targets: Auto disables SIMD, On keeps the scalar fallback instead of breaking
  configure.

---

Fluent Bit is licensed under Apache 2.0, by submitting this pull request I understand that this code will be released under the terms of that license.

Summary by CodeRabbit

Release Notes

• Build & Configuration
  • SIMD support option now features automatic detection (On/Off/Auto) for improved flexibility across architectures
  • Enhanced RISC-V 64 architecture support with compiler-aware SIMD feature selection
  • Build-time validation provides clear errors when requested SIMD features are unavailable

[coderabbitai]

📝 Walkthrough

Walkthrough

The FLB_SIMD option transforms from a boolean to a tri-state cached string (On/Off/Auto) with input validation. Configuration logic now includes architecture-specific SIMD enablement: unconditionally enabled for x86_64 and aarch64/arm64, conditionally enabled for riscv64 with compiler capability detection, and configure-time failures when FLB_SIMD=On cannot be satisfied. Compiler flags are conditionally applied based on SIMD enablement status.

Changes

Cohort / File(s)	Summary
SIMD Configuration Logic CMakeLists.txt	Refactored FLB_SIMD from boolean option to tri-state cached string with validation. Added architecture-aware SIMD enablement detection (x86_64 and aarch64/arm64 always enabled, riscv64 conditional on compiler support). Implements configuration-time error handling and conditional FLB_HAVE_SIMD definition.
RISC-V SIMD Flags cmake/riscv64.cmake	Updated SIMD flag handling to use FLB_SIMD_RISCV_C_FLAGS variable instead of hardcoded -march=rv64gcv_zba, with conditional application based on FLB_SIMD_ENABLED status.

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~25 minutes

Suggested labels

docs-required

Poem

🐰 A tri-state option now takes the stage,
SIMD features dance across each page,
x86 and ARM embrace the call,
While RISC-V checks compiler support for all,
Configuration wise, we march forward true! 🚀

🚥 Pre-merge checks | ✅ 3

✅ Passed checks (3 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately reflects the main change: converting FLB_SIMD from a boolean to a tri-state option with 'Auto' as the default value, which aligns with the primary objective of the pull request.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

📝 Generate docstrings

• Create stacked PR
• Commit on current branch

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch simd_on

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 27b82dec27

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Don't auto-enable RVV from compiler support alone

On riscv64, Auto now flips on FLB_HAVE_SIMD whenever the compiler accepts -march=rv64gcv_zba. That only proves the toolchain can emit RVV instructions, not that the target CPU has RVV; include/fluent-bit/flb_simd.h:88-102 and the hot paths in src/flb_pack.c/src/flb_utils.c then compile unconditional RVV intrinsics. A generic riscv64 package built with a modern compiler will therefore SIGILL on the many riscv64 systems that lack the optional V extension, so Auto is no longer safe for that architecture.

Useful? React with 👍 / 👎.

[chatgpt-codex-connector]

Preserve arm32 FLB_SIMD=On package builds

This new fatal-error branch turns every non-x86_64/aarch64/riscv64 -DFLB_SIMD=On build into a configure failure. That breaks an existing repo build path: packaging/distros/raspbian/Dockerfile:66-81 still passes -DFLB_SIMD=On, packaging/README.md:49-51 documents those targets as arm32v7, and .github/workflows/call-build-linux-packages.yaml:105-130 still runs the raspbian/* package jobs. Before this change those builds fell back to the scalar FLB_SIMD_NONE path in include/fluent-bit/flb_simd.h, so the packaging workflow now stops at CMake configure time.

Useful? React with 👍 / 👎.

[edsiper]

CI errors are associated to TCP ports

[mabrarov]

This check seems to enable SIMD support (FLB_SIMD_ENABLED == Yes) for x86 32bit Windows build which breaks it. Refer to https://github.com/fluent/fluent-bit/actions/runs/23405338585/job/68083237733#logs:

flb_pack.c.obj : error LNK2019: unresolved external symbol _flb_vector8_eq referenced in function _is_float
..\bin\fluent-bit.dll : fatal error LNK1120: 1 unresolved externals

According to CMAKE_SYSTEM_PROCESSOR documentation:

When not cross-compiling, this variable has the same value as the CMAKE_HOST_SYSTEM_PROCESSOR variable.

It means that if CI uses x86 64bit hardware (which seems to be so), then x86 32bit Windows build gets SIMD enabled in all places which rely on FLB_HAVE_SIMD macro.

Maybe it can be fixed this way:

Suggested change

	if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(x86_64|AMD64|amd64)$")
	if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(x86_64|AMD64|amd64)$" AND (CMAKE_SIZEOF_VOID_P GREATER 4))

[mabrarov]

Included this fix into #11604