nx_nofloat_attention_gate.nx
buildroot/runtime/nx_nofloat_attention_gate.nx
about
nx_nofloat_attention_gate.nx -- ASSEMBLE the trio into one DETERMINISTIC transformer attention layer.
Composes CAP-NOFLOAT-LAYERNORM + CAP-NOFLOAT-GEMM (matmul) + CAP-NOFLOAT-SOFTMAX, all integer Q16:
LayerNorm(X) -> Q,K,V = Xn*Wq/Wk/Wv -> scores = QK^T * 1/sqrt(D) -> softmax per row -> out = attn*V + X.
Every op integer -> the WHOLE LAYER is bit-exact DETERMINISTIC. Proven by running the full forward with
the score-dot and output-weighted-sum in FORWARD then REVERSE order: the output must be bit-identical
(float attention CANNOT promise this). This is the unit a coding-LLM is stacked from -- now sovereign +
reproducible. No hw writes (Rule 26). expect_exit: 0 license_tier: ORIGINAL
dependencies 2 imports · 0 importers
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
structs
| none |
consts
| 11 | const Q16: i64 = 65536 |
| 12 | const LOG2E: i64 = 94548 |
| 13 | const PC0: i64 = 65536 |
| 14 | const PC1: i64 = 45426 |
| 15 | const PC2: i64 = 15743 |
| 16 | const PC3: i64 = 4367 |
functions
| 18 | func at_puts(s: *u8) -> i64 { var n: i64=0; while s[n]!=(0 as u8){n=n+1} sys_write(1,s,n); return 0 } |
| 19 | func at_num(v: i64) -> i64 { let b: *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 as u8;k=1} while m>0{t[k]=(48+(m%10)) as u8;m=m/10;k=k+1} var i: i64=0; while i<k{b[i]=t[k-1-i];i=i+1} sys_write(1,b,k); return 0 } |
| 20 | func qmul(a: i64, b: i64) -> i64 { return (a*b) >> 16 } |
| 21 | func absd(a: i64, b: i64) -> i64 { if a>b { return a-b } return b-a } called by 1: main |
| 23 | func isqrt(v: i64) -> i64 called by 1: ln_row |
| 32 | func fx_exp(x: i64) -> i64 called by 1: softmax_row |
| 47 | func ln_row(x: *i64, off: i64, D: i64) -> i64 |
| 59 | func proj(src: *i64, W: *i64, dst: *i64, T: i64, D: i64) -> i64 |
| 68 | func softmax_row(sc: *i64, at: *i64, row: i64, T: i64) -> i64 |
| 77 | func attn_fwd(X: *i64, Wq: *i64, Wk: *i64, Wv: *i64, Xn: *i64, Q: *i64, K: *i64, V: *i64, sc: *i64, at: *i64, out: *i64, T: i64, D: i64, scale: i64, rev: i64) -> i64 |
| 106 | func main() -> i64 |