nx_dequant_iter_bench_test.nx
buildroot/runtime/nx_dequant_iter_bench_test.nx
about
nx_dequant_iter_bench_test.nx -- iter vs whole-block bench.
Measures elapsed ns for:
path A: nx_gguf_dequant_q4_k (always 256 values)
path B: nx_q4k_iter_init + K * iter_value (K of 256)
for K in {1, 8, 32, 256}.
Writes results to /tmp/nx_dequant_iter_bench.tsv for the smoke
wrapper to cat. Smoke exits 0 if all paths complete without
stale-INF saturation (sanity), regardless of measured numbers.
dependencies 8 imports · 0 importers
imports: nx_syscalls.nxnx_tier.nxnx_le.nxnx_strconv.nxnx_gguf.nxnx_gguf_load.nxnx_dequant_iter.nxnx_dequant_iter_bench.nx
imported by: nobody (leaf or entry point)
call flow from main pre-order; caps 40 nodes / depth 6 declared; ↻ = already shown
structs
| none |
consts
| none |
functions
| 22 | func _emit(fd: i64, label: *u8, label_len: nx_int, |
| 45 | func _build_blocks(buf: *u8, n: i64) -> nx_int |
| 72 | func _time_path_a(buf: *u8, n_blocks: i64, runs: i64, |
| 92 | func _time_path_b(buf: *u8, n_blocks: i64, runs: i64, k: i64) -> i64 called by 1: main calls 5: nx_q4k_iter_allocsys_mmapsys_clock_gettime_mononx_q4k_iter_initnx_q4k_iter_value |
| 125 | func main() -> i64 |