mirror of
https://github.com/rust-lang/rust.git
synced 2026-05-16 21:15:18 +03:00
Manish Goregaokar
b860765355
The issue of passing around SIMD types as values between functions has seen [quite a lot] of [discussion], and although we thought [we fixed it][quite a lot] it [wasn't]! This PR is a change to rustc to, again, try to fix this issue. The fundamental problem here remains the same, if a SIMD vector argument is passed by-value in LLVM's function type, then if the caller and callee disagree on target features a miscompile happens. We solve this by never passing SIMD vectors by-value, but LLVM will still thwart us with its argument promotion pass to promote by-ref SIMD arguments to by-val SIMD arguments. This commit is an attempt to thwart LLVM thwarting us. We, just before codegen, will take yet another look at the LLVM module and demote any by-value SIMD arguments we see. This is a very manual attempt by us to ensure the codegen for a module keeps working, and it unfortunately is likely producing suboptimal code, even in release mode. The saving grace for this, in theory, is that if SIMD types are passed by-value across a boundary in release mode it's pretty unlikely to be performance sensitive (as it's already doing a load/store, and otherwise perf-sensitive bits should be inlined). The implementation here is basically a big wad of C++. It was largely copied from LLVM's own argument promotion pass, only doing the reverse. In local testing this... Closes #50154 Closes #52636 Closes #54583 Closes #55059 [quite a lot]: https://github.com/rust-lang/rust/pull/47743 [discussion]: https://github.com/rust-lang/rust/issues/44367 [wasn't]: https://github.com/rust-lang/rust/issues/50154
This directory currently contains some LLVM support code. This will generally be sent upstream to LLVM in time; for now it lives here. NOTE: the LLVM C++ ABI is subject to between-version breakage and must *never* be exposed to Rust. To allow for easy auditing of that, all Rust-exposed types must be typedef-ed as "LLVMXyz", or "LLVMRustXyz" if they were defined here. Functions that return a failure status and leave the error in the LLVM last error should return an LLVMRustResult rather than an int or anything to avoid confusion. When translating enums, add a single `Other` variant as the first one to allow for new variants to be added. It should abort when used as an input. All other types must not be typedef-ed as such.