code wiki / _hdl_build / nx_chacha_scalar_bench.nx

nx_chacha_scalar_bench.nx

buildroot/runtime/_hdl_build/nx_chacha_scalar_bench.nx

2085 B44 linesdepth 2pulls 2 transitivereach 0 importersview sourcekind bench
docsdependenciesstructsconstsfunctions

about

nx_chacha_scalar_bench.nx -- matched scalar baseline for the SIMD ChaCha bench. Same block function (scalar qr, RFC 8439 input), looped M=4,000,000 times (256 MB keystream), no print. Time it the same way (`time ./elf`) so SIMD-vs-scalar is apples-to-apples on the same hardware/toolchain. license_tier: ORIGINAL

dependencies 1 imports · 0 importers

nx_syscalls.nx nx_chacha_scalar_bench.nx

imports: nx_syscalls.nx

imported by: nobody (leaf or entry point)

call flow from main pre-order; caps 40 nodes / depth 6 declared; ↻ = already shown

main sys_mmap qr u32 rotl32 u32 ↻

structs

none

consts

5const K_MAGIC_4000000: i64 = 4000000

functions

7func u32(x: i64) -> i64 { return x & 0xFFFFFFFF }
called by 2: qrmain
8func rotl32(x: i64, r: i64) -> i64 { let a: i64 = (x << r) & 0xFFFFFFFF; let b: i64 = (x & 0xFFFFFFFF) >> (32 - r); return a | b }
called by 1: qr
9func qr(s: *i64, a: i64, b: i64, c: i64, d: i64) -> i64
called by 1: main calls 2: u32rotl32
17func main() -> i64
calls 3: sys_mmapqru32