code wiki / (root) / nx_q4k_matmul_bench_test.nx

nx_q4k_matmul_bench_test.nx

buildroot/runtime/nx_q4k_matmul_bench_test.nx

6095 B188 linesdepth 8pulls 14 transitivereach 0 importersview sourcekind gate/prooftopic q4k
docsdependenciesstructsconstsfunctions

about

nx_q4k_matmul_bench_test.nx -- the fused-vs-materialized bench.

dependencies 9 imports · 0 importers

nx_syscalls.nx nx_tier.nx nx_le.nx nx_strconv.nx nx_gguf.nx nx_gguf_load.nx nx_dequant_iter.nx nx_q4k_matmul.nx nx_q4k_matmul_bench.nx nx_q4k_matmul_bench_test.nx

imports: nx_syscalls.nxnx_tier.nxnx_le.nxnx_strconv.nxnx_gguf.nxnx_gguf_load.nxnx_dequant_iter.nxnx_q4k_matmul.nxnx_q4k_matmul_bench.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 _build_blocks nx_le_write_u16 nx_q4k_iter_alloc sys_mmap ↻ nx_gguf_dequant_q4_k nx_le_read_u16 _gguf_f16_to_q24 nx_le_read_u8 nx_q4k_dot_row_col nx_q4k_iter_init nx_le_read_u16 ↻ _gguf_f16_to_q24 ↻ nx_le_read_u8 ↻ nx_q4k_iter_scale _q4k_iter_scale_at nx_q4k_iter_min _q4k_iter_min_at nx_le_read_u8 ↻ sys_clock_gettime_mono sys_openat_wr sys_write _emit sys_mmap ↻ nx_strconv_format_i64 sys_write ↻ sys_close

structs

none

consts

none

functions

13func _emit(fd: i64, label: *u8, label_len: nx_int,
called by 1: main calls 3: sys_mmapnx_strconv_format_i64sys_write
41func _build_blocks(buf: *u8, n: i64) -> nx_int
called by 1: main calls 1: nx_le_write_u16
66func main() -> i64
calls 10: sys_mmap_build_blocksnx_q4k_iter_allocnx_gguf_dequant_q4_knx_q4k_dot_row_colsys_clock_gettime_mono+4