code wiki / _hdl_build / nx_qlayer_test.nx

nx_qlayer_test.nx

buildroot/runtime/_hdl_build/nx_qlayer_test.nx

5680 B90 linesdepth 5pulls 8 transitivereach 0 importersview sourcekind gate/proof
docsdependenciesstructsconstsfunctions

about

nx_qlayer_test.nx -- the TEAM does a decode layer END TO END, every organ in its lane: ENGINEER diagnoses the layer's bottleneck (roofline) -> MEMORY-bound (matvec has no reuse). BUILDER picks the quality-balanced format under the Council floor -> Q4_K_M class (4-bit). BUILDER builds the kernel: pre-quantize the matrix, run the hot streamed matvec. ENGINEER verifies the WHOLE layer output 1:1 vs exact, max per-row error vs the floor. Exit 0 only if: memory-bound diagnosed, Builder picks 4-bit, layer error within floor, >=3x less data moved. This is the full session's stack (governor + roofline + quality balance + kernel) composed into one autonomous decode layer. license_tier: ORIGINAL

dependencies 3 imports · 0 importers

nx_qlayer.nx nx_builder_quant.nx nx_syscalls.nx nx_qlayer_test.nx

imports: nx_qlayer.nxnx_builder_quant.nxnx_syscalls.nx

imported by: nobody (leaf or entry point)

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

main lt_puts sys_write sys_mmap qlayer_bytes_ref16 eng_diagnose_kernel rf_bound eng_recommend_lever lt_num sys_mmap ↻ sys_write ↻ bld_select_operating_point eng_diagnose_kernel ↻ eng_recommend_lever ↻ qb_select council_quality_admit qb_combined qb_quality_score qb_speed_score ql_blocks_per_row qlayer_matvec_exact qlayer_quantize ql_blocks_per_row ↻ qmv_block_scale qmv_abs qmv_code qlayer_matvec ql_blocks_per_row ↻ qlayer_l2_relerr_permil qlayer_isqrt qlayer_bytes_q ql_blocks_per_row ↻ sys_exit

structs

none

consts

none

functions

14func lt_puts(s: *u8) -> i64 { var n: i64 = 0; while s[n] != (0 as u8) { n = n + 1 } sys_write(1, s, n); return 0 }
called by 1: main calls 1: sys_write
15func lt_num(v: i64) -> i64 { let bb: *u8 = sys_mmap(28); var m: i64=v; if m<0 {m=0-m; sys_write(1,"-" as *u8,1)}; let t: *u8 = sys_mmap(28); var k: i64=0; if m==0 {t[0]=48;k=1}; while m>0 {t[k]=48+(m%10); m=m/10; k=k+1}; var i: i64=0; while i<k {bb[i]=t[k-1-i]; i=i+1}; sys_write(1, bb, k); return 0 }
called by 1: main calls 2: sys_mmapsys_write
17func main() -> i64