Engineering Category: Deterministic Sovereign Compute Kernel
Best Use in Production: Pure-Rust C64-bounded integer transformation kernel verified across 64 canonical test vectors for deterministic Snap-Circuit composition.
When to Select This Capsule: Sole canonical implementation for its 64-vector functional equivalence class. Low-latency L1-resident kernel (1005941/100000 cyc/op); well-suited for high-frequency pipeline stages.
Snap-Circuit Wiring Role: Slice Ingress / Scanner Stage `(&[u8])->u64` — digests raw byte buffers into scalar tokens or checksums.
.text: 55 B (20 x86_64 insns)503 B)pub const fn prompt_boundary_sig64(bytes: &[u8]) -> u64 {
let n = bytes.len();
if n == 0 {
return 0;
}
let head = if n >= 4 {
u32::from_le_bytes([bytes[0], bytes[1], bytes[2], bytes[3]]) as u64
} else {
(bytes[0] as u64) | ((bytes[n - 1] as u64) << 8)
};
let tail = if n >= 4 {
u32::from_le_bytes([bytes[n - 4], bytes[n - 3], bytes[n - 2], bytes[n - 1]]) as u64
} else {
(bytes[n - 1] as u64) << 16
};
(head << 32) | tail
}
rustc -C opt-level=3 x86_64 Disassembly (55 B .text / 20 insns)prompt_boundary_sig64:
test rsi, rsi
je .LBB7_1
cmp rsi, 3
jbe .LBB7_5
mov eax, dword ptr [rdi]
mov ecx, dword ptr [rdi + rsi - 4]
shl rax, 32
or rax, rcx
ret
.LBB7_1:
xor eax, eax
ret
.LBB7_5:
movzx edx, byte ptr [rdi]
movzx ecx, byte ptr [rdi + rsi - 1]
mov eax, ecx
shl eax, 8
or rax, rdx
shl ecx, 16
shl rax, 32
or rax, rcx
ret
| Global Rank | Capsule & Domain | Hardware _rdtsc | Latency | Throughput | ELF .text | Ternary Vote | Author Aye |
|---|---|---|---|---|---|---|---|
| #1029 | prompt_boundary_sig64 (THIS CAPSULE) domain: eightb-agy-fanout-x86_64 | id: 71673b91d46b3102858e1c4892886db1 | 1005941/100000 cyc/op | 1916661/400000 ns/op | 400000000/1916661 ops/us | 55 B .text (20 insns) | + (1) | aye::Hue+Gemini(0+1)::x86_64 @ 432Hz |