code wiki / (root) / nx_nofloat_blockfloat_gemm_gate.nx

nx_nofloat_blockfloat_gemm_gate.nx

buildroot/runtime/nx_nofloat_blockfloat_gemm_gate.nx

7191 B141 linesdepth 3pulls 3 transitivereach 0 importersview sourcekind gate/prooftopic nofloat
docsdependenciesstructsconstsfunctions

about

nx_nofloat_blockfloat_gemm_gate.nx -- BLOCK-FLOAT weights through the no-float GEMM: the format earns its place in the actual compute path (the rung after nx_nofloat_blockfloat_gate proved the format round-trips). The GEMM computes DIRECTLY on the integer mantissas + per-block power-of-2 shifts (no dequant materialisation) -- C[m] = sum_over_K-blocks b ( (sum_{k in b} A[m][k]*q_W[k]) << e_b ). Proves: 1 the direct block-float GEMM == dequant-then-matmul, BYTE-EXACT (the on-mantissa compute is correct) 2 EXCEED (MEASURED): block-float matmul error vs full-precision < per-tensor INT8 matmul error 3 DETERMINISTIC: the block-float GEMM run twice is bit-identical (integer sums + shifts, no float) 4 per-tensor scaling ZEROED the small weight block (lost its whole matmul contribution); block-float kept it expect_exit: 0 license_tier: ORIGINAL

dependencies 2 imports · 0 importers

nx_syscalls.nx nx_gate_verdict.nx nx_nofloat_blockfloat_gemm_gat

imports: nx_syscalls.nxnx_gate_verdict.nx

imported by: nobody (leaf or entry point)

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

main bf_puts sys_write sys_mmap bf_scale bf_bitlen mm bf_gemm bf_absdiff bf_putn sys_mmap ↻ sys_write ↻ bf_chk bf_puts ↻ gv_ctr sys_mmap ↻ gv_verdict gv_puts sys_write ↻ gv_num sys_mmap ↻ sys_write ↻ sys_munmap gv_journal sys_openat_append sys_mmap ↻ gv_catn sys_mmap ↻ sys_munmap ↻ sys_now_realtime_sec sys_mmap ↻ sys_clock_gettime_real gv_cat sys_write ↻ sys_close sys_munmap ↻ sys_exit

structs

none

consts

none

functions

13func bf_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 2: bf_chkmain calls 1: sys_write
14func bf_putn(v: i64) -> i64
called by 1: main calls 2: sys_mmapsys_write
24func bf_chk(name: *u8, ok: i64) -> i64
called by 1: main calls 1: bf_puts
28func bf_bitlen(x: i64) -> i64 { var b: i64 = 0; var m: i64 = x; while m > 0 { m = m >> 1; b = b + 1 } return b }
called by 1: bf_scale
29func bf_absdiff(a: i64, b: i64) -> i64 { if a >= b { return a - b } return b - a }
called by 1: main
30func bf_scale(v: *i64, off: i64, B: i64, M: i64) -> i64
called by 1: main calls 1: bf_bitlen
39func mm(A: *i64, W: *i64, M: i64, K: i64, out: *i64) -> i64
called by 1: main
50func bf_gemm(A: *i64, q_W: *i64, e_bf: *i64, M: i64, K: i64, B: i64, out: *i64) -> i64
called by 1: main
66func main() -> i64