Thanks for using Compiler Explorer
Sponsors
Jakt
C++
Ada
Algol68
Analysis
Android Java
Android Kotlin
Assembly
C
C3
Carbon
C with Coccinelle
C++ with Coccinelle
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#
GLSL
Go
Haskell
HLSL
Hook
Hylo
IL
ispc
Java
Julia
Kotlin
LLVM IR
LLVM MIR
Modula-2
Mojo
Nim
Numba
Nix
Objective-C
Objective-C++
OCaml
Odin
OpenCL C
Pascal
Pony
PTX
Python
Racket
Raku
Ruby
Rust
Sail
Snowball
Scala
Slang
Solidity
Spice
SPIR-V
Swift
LLVM TableGen
Toit
Triton
TypeScript Native
V
Vala
Visual Basic
Vyper
WASM
Zig
Javascript
GIMPLE
Ygen
sway
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
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 1.79.0
rustc 1.8.0
rustc 1.80.0
rustc 1.81.0
rustc 1.82.0
rustc 1.83.0
rustc 1.84.0
rustc 1.85.0
rustc 1.86.0
rustc 1.87.0
rustc 1.88.0
rustc 1.89.0
rustc 1.9.0
rustc beta
rustc nightly
rustc-cg-gcc (master)
x86-64 GCCRS (GCC master)
x86-64 GCCRS (GCCRS master)
x86-64 GCCRS 14.1 (GCC assertions)
x86-64 GCCRS 14.1 (GCC)
x86-64 GCCRS 14.2 (GCC assertions)
x86-64 GCCRS 14.2 (GCC)
x86-64 GCCRS 14.3 (GCC assertions)
x86-64 GCCRS 14.3 (GCC)
x86-64 GCCRS 15.1 (GCC assertions)
x86-64 GCCRS 15.1 (GCC)
x86-64 GCCRS 15.2 (GCC assertions)
x86-64 GCCRS 15.2 (GCC)
Options
Source code
extern crate core; use core::arch::x86_64::{__m256i, _mm256_set1_epi8, _mm256_loadu_si256, _mm256_cmpgt_epi8, _mm256_cmpeq_epi8, _mm256_movemask_epi8, _popcnt32, _mm256_extract_epi8}; use std::ptr::{addr_of}; const AVX2WIDTH: usize = 32; pub fn count_group_by(a: &[u8]) -> [i64; 256] { let mut result = [0; 256]; for &x in a { result[x as usize] += 1; } result } pub fn sum(a: &[i64]) -> i64 { let mut result = 0; for x in a { result += x; } result } pub fn count_group_by_avx2(a: &[u8]) -> [i64; 256] { unsafe { count_group_by_avx2_unsafe(a) } } pub unsafe fn count_group_by_avx2_unsafe(a: &[u8]) -> [i64; 256] { let mut result: [i64; 256] = [0; 256]; let mask0 = _mm256_set1_epi8(0); let mask1 = _mm256_set1_epi8(1); let mask2 = _mm256_set1_epi8(2); let mask3 = _mm256_set1_epi8(3); let mut i = 0; while i < a.len() - AVX2WIDTH { let addr = &a[i]; let ymm = _mm256_loadu_si256(addr_of!(addr) as *const __m256i); result[0] += _popcnt32(_mm256_movemask_epi8(_mm256_cmpeq_epi8(ymm, mask0))) as i64; result[1] += _popcnt32(_mm256_movemask_epi8(_mm256_cmpeq_epi8(ymm, mask1))) as i64; result[2] += _popcnt32(_mm256_movemask_epi8(_mm256_cmpeq_epi8(ymm, mask2))) as i64; result[3] += _popcnt32(_mm256_movemask_epi8(_mm256_cmpeq_epi8(ymm, mask3))) as i64; i += AVX2WIDTH; } while i < a.len() { result[a[i] as usize] += 1; i += 1; } result }
nim source #2
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
nim (trunk)
nim 1.0.4
nim 1.0.6
nim 1.2.0
nim 1.4.2
nim 1.4.4
nim 1.4.6
nim 1.4.8
nim 1.6.0
nim 1.6.16
nim 2.0.0
Options
Source code
{.passC: "-mavx2".} {.passL: "-mavx2".} import os type m256i* {.importc: "__m256i", header: "immintrin.h".} = object type m256* {.importc: "__m256", header: "immintrin.h".} = object const avx2width* = 32 proc set1_epi8*(b: int8 | uint8): m256i {.importc: "_mm256_set1_epi8", header: "immintrin.h".} proc loadu_byte*(p: ptr byte): m256i {.importc: "_mm256_loadu_si256", header: "immintrin.h".} proc popcnt_u32*(a: int32): int32 {.importc: "_mm_popcnt_u32", header: "immintrin.h".} proc cmpeq_epi8*(a, b: m256i): m256i {.importc: "_mm256_cmpeq_epi8", header: "immintrin.h".} proc cmpgt_epi8*(a, b: m256i): m256i {.importc: "_mm256_cmpgt_epi8", header: "immintrin.h".} proc movemask_epi8*(a: m256i): int32 {.importc: "_mm256_movemask_epi8", header: "immintrin.h".} proc extract_epi8*(a: m256i, off: int): byte {.importc: "_mm256_extract_epi8", header: "immintrin.h".} proc countGroupByAVX2*(a: openArray[uint8]): array[256, int] = let mask0 = set1_epi8(0) let mask1 = set1_epi8(1) let mask2 = set1_epi8(2) let mask3 = set1_epi8(3) var i = 0 while i < a.len-avx2width: let ymm = loadu_byte(unsafeAddr a[i]) result[0] += popcnt_u32 movemask_epi8 cmpeq_epi8(ymm, mask0) result[1] += popcnt_u32 movemask_epi8 cmpeq_epi8(ymm, mask1) result[2] += popcnt_u32 movemask_epi8 cmpeq_epi8(ymm, mask2) result[3] += popcnt_u32 movemask_epi8 cmpeq_epi8(ymm, mask3) i += avx2width while i < a.len: result[a[i]].inc inc i proc main() = let p3 = paramStr(1) echo countGroupByAVX2([1'u8,2,uint8(p3[0])]) main()
Become a Patron
Sponsor on GitHub
Donate via PayPal
Compiler Explorer Shop
Source on GitHub
Mailing list
Installed libraries
Wiki
Report an issue
How it works
Contact the author
CE on Mastodon
CE on Bluesky
Statistics
Changelog
Version tree