Thanks for using Compiler Explorer
Sponsors
Jakt
C++
Ada
Analysis
Android Java
Android Kotlin
Assembly
C
C3
Carbon
C++ (Circle)
CIRCT
Clean
CMake
CMakeScript
COBOL
C++ for OpenCL
MLIR
Cppx
Cppx-Blue
Cppx-Gold
Cpp2-cppfront
Crystal
C#
CUDA C++
D
Dart
Elixir
Erlang
Fortran
F#
Go
Haskell
HLSL
Hook
Hylo
ispc
Java
Julia
Kotlin
LLVM IR
LLVM MIR
Modula-2
Nim
Objective-C
Objective-C++
OCaml
OpenCL C
Pascal
Pony
Python
Racket
Ruby
Rust
Snowball
Scala
Solidity
Spice
Swift
LLVM TableGen
Toit
TypeScript Native
V
Vala
Visual Basic
Zig
Javascript
GIMPLE
rust source #1
Output
Compile to binary object
Link to binary
Execute the code
Intel asm syntax
Demangle identifiers
Verbose demangling
Filters
Unused labels
Library functions
Directives
Comments
Horizontal whitespace
Debug intrinsics
Compiler
BPF gcc (trunk)
mrustc (master)
rustc 1.0.0
rustc 1.1.0
rustc 1.10.0
rustc 1.11.0
rustc 1.12.0
rustc 1.13.0
rustc 1.14.0
rustc 1.15.1
rustc 1.16.0
rustc 1.17.0
rustc 1.18.0
rustc 1.19.0
rustc 1.2.0
rustc 1.20.0
rustc 1.21.0
rustc 1.22.0
rustc 1.23.0
rustc 1.24.0
rustc 1.25.0
rustc 1.26.0
rustc 1.27.0
rustc 1.27.1
rustc 1.28.0
rustc 1.29.0
rustc 1.3.0
rustc 1.30.0
rustc 1.31.0
rustc 1.32.0
rustc 1.33.0
rustc 1.34.0
rustc 1.35.0
rustc 1.36.0
rustc 1.37.0
rustc 1.38.0
rustc 1.39.0
rustc 1.4.0
rustc 1.40.0
rustc 1.41.0
rustc 1.42.0
rustc 1.43.0
rustc 1.44.0
rustc 1.45.0
rustc 1.45.2
rustc 1.46.0
rustc 1.47.0
rustc 1.48.0
rustc 1.49.0
rustc 1.5.0
rustc 1.50.0
rustc 1.51.0
rustc 1.52.0
rustc 1.53.0
rustc 1.54.0
rustc 1.55.0
rustc 1.56.0
rustc 1.57.0
rustc 1.58.0
rustc 1.59.0
rustc 1.6.0
rustc 1.60.0
rustc 1.61.0
rustc 1.62.0
rustc 1.63.0
rustc 1.64.0
rustc 1.65.0
rustc 1.66.0
rustc 1.67.0
rustc 1.68.0
rustc 1.69.0
rustc 1.7.0
rustc 1.70.0
rustc 1.71.0
rustc 1.72.0
rustc 1.73.0
rustc 1.74.0
rustc 1.75.0
rustc 1.76.0
rustc 1.77.0
rustc 1.78.0
rustc 1.8.0
rustc 1.9.0
rustc beta
rustc nightly
rustc-cg-gcc (master)
x86-64 GCCRS (GCC master)
x86-64 GCCRS (GCCRS master)
Options
Source code
#![no_std] #[cfg(target_arch = "x86")] use core::arch::x86::*; #[cfg(target_arch = "x86_64")] use core::arch::x86_64::*; use core::ops::{Add, Mul}; type Block = [u8; 16]; /// Wrapper for `__m128i` - a 128-bit XMM register (SSE2) #[repr(align(16))] #[derive(Copy, Clone)] pub struct M128i(__m128i); impl From<Block> for M128i { // `_mm_loadu_si128` performs an unaligned load #[allow(clippy::cast_ptr_alignment)] fn from(bytes: Block) -> M128i { M128i(unsafe { _mm_loadu_si128(bytes.as_ptr() as *const __m128i) }) } } impl From<M128i> for Block { // `_mm_storeu_si128` performs an unaligned store #[allow(clippy::cast_ptr_alignment)] fn from(xmm: M128i) -> Block { let mut result = Block::default(); unsafe { _mm_storeu_si128(result.as_mut_ptr() as *mut __m128i, xmm.0); } result } } impl Add for M128i { type Output = Self; /// Adds two POLYVAL field elements. fn add(self, rhs: Self) -> Self { M128i(unsafe { xor(self.0, rhs.0) }) } } #[target_feature(enable = "sse2", enable = "sse4.1")] unsafe fn xor(a: __m128i, b: __m128i) -> __m128i { _mm_xor_si128(a, b) } impl Mul for M128i { type Output = Self; /// Computes carryless POLYVAL multiplication over GF(2^128). fn mul(self, rhs: Self) -> Self { unsafe { M128i(clmul(self.0, rhs.0)) } } } #[target_feature(enable = "pclmulqdq", enable = "sse2", enable = "sse4.1")] unsafe fn clmul(lhs: __m128i, rhs: __m128i) -> __m128i { let t1 = _mm_clmulepi64_si128(lhs, rhs, 0x00); let t2 = _mm_clmulepi64_si128(lhs, rhs, 0x01); let t3 = _mm_clmulepi64_si128(lhs, rhs, 0x10); let t4 = _mm_clmulepi64_si128(lhs, rhs, 0x11); let t5 = _mm_xor_si128(t2, t3); let t6 = _mm_xor_si128(t4, _mm_bsrli_si128(t5, 8)); let t7 = _mm_xor_si128(t1, _mm_bslli_si128(t5, 8)); _mm_xor_si128(t6, reduce(t7)) } /// Mask value used when performing Montgomery fast reduction. /// This corresponds to POLYVAL's polynomial with the highest bit unset. const MASK: u128 = 1 << 127 | 1 << 126 | 1 << 121 | 1; /// Fast reduction modulo x^128 + x^127 + x^126 +x^121 + 1 (Gueron 2012) /// Algorithm 4: "Montgomery reduction" /// /// See: <https://crypto.stanford.edu/RealWorldCrypto/slides/gueron.pdf> #[target_feature(enable = "pclmulqdq", enable = "sse2", enable = "sse4.1")] unsafe fn reduce(x: __m128i) -> __m128i { // `_mm_loadu_si128` performs an unaligned load // (`u128` is not necessarily aligned to 16-bytes) #[allow(clippy::cast_ptr_alignment)] let mask = _mm_loadu_si128(&MASK as *const u128 as *const __m128i); let a = _mm_clmulepi64_si128(mask, x, 0x01); let b = _mm_xor_si128(_mm_shuffle_epi32(x, 0x4e), a); let c = _mm_clmulepi64_si128(mask, b, 0x01); _mm_xor_si128(_mm_shuffle_epi32(b, 0x4e), c) }
Become a Patron
Sponsor on GitHub
Donate via PayPal
Source on GitHub
Mailing list
Installed libraries
Wiki
Report an issue
How it works
Contact the author
CE on Mastodon
About the author
Statistics
Changelog
Version tree