AVX 512 doc

Author: hkratz

README.md

@@ -13,11 +13,12 @@ This library has been thoroughly tested with sample data as well as fuzzing and
 ## Features
 * `basic` API for the fastest validation, optimized for valid UTF-8
 * `compat` API as a fully compatible replacement for `std::str::from_utf8()`
+* 🆕 AVX 512 support on modern x86/x86-64 CPUs since Rust 1.89
 * Supports AVX 2 and SSE 4.2 implementations on x86 and x86-64
 * ARM64 (aarch64) SIMD is supported since Rust 1.61
 * WASM (wasm32) SIMD is supported
 * 🆕 armv7 NEON support with the `armv7_neon` feature on nightly Rust
-* x86-64: Up to 23 times faster than the std library on valid non-ASCII, up to four times faster on ASCI
+* x86-64: Up to 23 times faster than the std library on valid non-ASCII, up to four times faster on ASCII
 * aarch64: Up to eleven times faster than the std library on valid non-ASCII, up to four times faster on ASCII (Apple Silicon)
 * Faster than the original simdjson implementation
 * Selects the fastest implementation at runtime based on CPU support (on x86)
@@ -71,14 +72,17 @@ This comes at a slight performance penalty compared to the `basic` API even if t
 ## Implementation selection
 
 ### X86
-The fastest implementation is selected at runtime using the `std::is_x86_feature_detected!` macro, unless the CPU
-targeted by the compiler supports the fastest available implementation.
-So if you compile with `RUSTFLAGS="-C target-cpu=native"` on a recent x86-64 machine, the AVX 2 implementation is selected at
-compile-time and runtime selection is disabled.
+The fastest implementation is usually selected at runtime using the `std::is_x86_feature_detected!` macro. The AVX 512 
+implementation is however only selected if the CPU support the VBMI2 features to avoid throttling happening with CPUs before 
+Intels Ice Lake microarchitecture.
+
+If you compile with `RUSTFLAGS="-C target-cpu=native"` on a recent x86-64 machine whichs support AVX 512 with Rust 1.89 or later,
+the AVX 512 implementation is selected at compile-time and runtime selection is disabled.
 
 For no-std support (compiled with `--no-default-features`) the implementation is always selected at compile time based on
 the targeted CPU. Use `RUSTFLAGS="-C target-feature=+avx2"` for the AVX 2 implementation or `RUSTFLAGS="-C target-feature=+sse4.2"`
-for the SSE 4.2 implementation.
+for the SSE 4.2 implementation. For AVX 512 use `RUSTFLAGS="-C target-feature=+avx512f,+avx512bw,+avx512vbmi,+avx512vbmi2"` with 
+Rust 1.89 or later.
 
 ### ARM64
 The SIMD implementation is used automatically since Rust 1.61.