igneum/proto-cuda/packs-readwidth/scr2k128/program.json

130 lines
16 KiB
JSON

{
"format": "igneum-program-pack-3",
"generator": 2,
"attempt": 0,
"program_id": "0xe0afe0d155bc25d9",
"program_id_derivation": "FNV-1a 64 over 'igneum-program-rw/' || generator_le32 || seed_words as little-endian bytes || attempt_le32 || mix[3] || load_slots_u8 || 'scratch/' || scratch_k_u8 || scratch_kb_u8",
"dataset_mode": "memory-hard",
"seed": "igneum-genesis",
"seed_bytes": "69676e65756d2d67656e65736973",
"seed_words": ["0x67a9a7be", "0x1a155b25", "0xfddfb732", "0x4b5af2e8", "0xc55caf33", "0xa27c13b7", "0x06628a48", "0x03852469"],
"seed_derivation": "seed_words = FNV-1a 64 over seed_bytes (attempt 0) or seed_bytes || attempt_le32 (attempt k >= 1), basis ^ (salt * 0x9E3779B97F4A7C15) for salt 0..3, then h ^= h>>33; h *= 0xff51afd7ed558ccd; h ^= h>>33; words[2*salt] = low 32, words[2*salt+1] = high 32",
"generator_rule": "version 2: exactly 16 load slots drawn first from instructions 1..63 (partial Fisher-Yates), the other 48 ops from the ten non-load weights (sum 75); a load's source is drawn from the registers other than dst written by an earlier instruction and not read by a load since; the candidate must pass the acceptance rule of spec 01 section 1.4.6 (static: no cyclically stale load source, every register has an injecting write; dynamic: 64 units on the seed-keyed closed-form dataset with no constant register bit, no lane-constant load site, under 164 saturated final values, every output bit within 136 of 1024, distinct addresses above 245760), else the next attempt of the seed is tried",
"lanes": 32,
"registers": 8,
"iterations": 8,
"instruction_count": 64,
"loads_per_hash": 128,
"load_class": "scr2k128",
"load_slots": 16,
"load_mix_percent_4_16_64": [100, 0, 0],
"load_width_counts_4_16_64": [14, 0, 0],
"bytes_per_hash": 448,
"scratch_ops_per_hash": 16,
"scratch_kib_per_warp": 128,
"scratch": "variant 5 (measurement only): persistent warps; a 128 KiB scratch per warp of 256 16-byte slots per lane (lane-major); slot = src & 0xff; a slot reads as its fill (scratch_fill(seed words, unit base nonce, lane, slot, j) = splitmix32(((base + lane) ^ seed[j]) + slot * 0x9e3779b1 + (j + 1) * 0x85ebca77), j in 0..2) until the unit writes it; read w0 w1 w2 (behind a per-unit tag on the GPU), x = fold(dst, w0, w1, w2), dst = x, rewrite (x ^ w1, rotl(x, 7) ^ w2, x + w0)",
"wide_load": "read-width experiment (5 October 2026, docs/plans/read-width.md), NOT the lottery hash: a load of W words (width field, 4 or 16) reads dataset[b .. b + W) with b = (src & mask) & ~(W - 1) and folds every word into dst: x = dst ^ w[0]; for j in 1..W: x = (rotl(x, 11) * 0x9e3779b1) ^ w[j]; dst = x; width 1 is the plain load; the width is drawn per instruction from the class mix with one extra below(100) draw after the nine of version 2, and the program id is FNV-1a 64 over 'igneum-program-rw/' || generator_le32 || seed words || attempt_le32 || mix[3] || load_slots",
"op_mix": {"load": 14, "add": 9, "mad": 7, "xor": 7, "mul": 5, "sub": 5, "mulhi": 4, "or": 4, "shfl": 4, "rotr": 2, "scratch": 2, "rotl": 1},
"register_init": "for i in 0..7: x = nonce ^ seed_words[i]; x += 0x9e3779b9 * (i+1) (mod 2^32); x = splitmix32(x); r[i] = x ^ seed_words[(i+1) & 7]",
"splitmix32": "x ^= x>>16; x *= 0x7feb352d; x ^= x>>15; x *= 0x846ca68b; x ^= x>>16",
"iteration": "sel = r0 sampled once at the top of each iteration, then all instructions in order",
"output": "lo = r0 ^ rotl(r1,7) ^ rotl(r2,14) ^ rotl(r3,21); hi = r4 ^ rotl(r5,9) ^ rotl(r6,18) ^ rotl(r7,27); out = (hi << 32) | lo",
"op_semantics": {
"add": "dst = dst + src + (bit `bit` of sel ? imm2 : imm)",
"sub": "dst = dst - src",
"mul": "dst = dst * src (low 32)",
"mulhi": "dst = high 32 bits of dst * src",
"xor": "dst = dst ^ src",
"or": "dst = dst | src",
"rotl": "dst = rotl(dst, rot), rot in 1..31",
"rotr": "dst = rotr(dst, src & 31)",
"mad": "dst = src * src2 + dst",
"shfl": "dst = dst ^ (src of lane (lane ^ mask)), mask in {1,2,4,8,16}, within the 32-lane warp",
"load": "dst = dst ^ dataset[src & dataset.mask]",
"wload": "base = (src of lane 0 & dataset.mask) & ~31; dst = dst ^ dataset[base + lane] (warp-coalesced 128-byte load, lever b, only when --wide-frac > 0)"
},
"dataset": {
"log2_words": 28,
"bytes": 1073741824,
"mask": "0x0fffffff",
"day": "2026-10-03",
"day_bytes": "6461792f323032362d31302d3033",
"day_words_from": "seed_words_from_bytes(day_bytes)",
"d0": "0x3067619f",
"d1": "0x3c269176",
"mode": "memory-hard",
"spec": "proto-metal/MEMHARD.md",
"key": ["0x3067619f", "0x3c269176", "0x84a03b03", "0xf8c63294", "0xff977c5b", "0xe60def3e", "0x63630141", "0xb8fbcb58"],
"key_derivation": "the 8 words of seed_words_from_bytes(day_bytes); d0, d1 are key[0], key[1]",
"cache": {"log2_words": 26, "bytes": 268435456, "line_words": 16, "segment_lines": 64, "segments": 65536, "block": "ChaCha12 core + feed-forward, rotations 16 12 8 7", "sigma": ["0x61707865", "0x3320646e", "0x79622d32", "0x6b206574"], "tag": ["0x49676e65", "0x756d4d48"], "chain": "in_j = prev_line ^ (sigma[0..3] || key[0..7] || seg || j || tag[0..1]); line_j = block(in_j); prev_0 = 0"},
"mixer": {"draw": "SplitMix64 seeded with key[0] | key[1] << 32: rot[0..7] = 1 + next() % 31, mul[0..15] = low32(next()) | 1, rc[0..15] = low32(next())", "rot": [20, 20, 19, 4, 26, 3, 3, 27], "mul": ["0x42146205", "0x52cbe0fb", "0x7ecf4a03", "0x6728907f", "0xd81d9751", "0x132952c3", "0xf60de277", "0x05358035", "0xbaf6499d", "0xe4db9667", "0x3e98f45d", "0xd0004edd", "0x2691630d", "0x9beb3bcf", "0xab310379", "0x99cfb423"], "rc": ["0xbab68293", "0xcc162340", "0x6ce151cc", "0xe62b8997", "0xc9c80297", "0xf74a1654", "0x3d704af5", "0x3cf522b7", "0x2b9cac04", "0xa880ac10", "0x13e5dd1d", "0x6fc3e233", "0x2d83eeac", "0x9006e8bf", "0x2c4b5362", "0x31b49ee2"], "round": "for i in 0..15: s[i] = (s[i] ^ (rc[i] + (r+1) * 0x9E3779B9)) * mul[i]; then quarter rounds on columns (0,4,8,12) (1,5,9,13) (2,6,10,14) (3,7,11,15) with rot[0..3] and diagonals (0,5,10,15) (1,6,11,12) (2,7,8,13) (3,4,9,14) with rot[4..7]", "quarter_round": "a += b; d ^= a; d = rotl(d, r1); c += d; b ^= c; b = rotl(b, r2); a += b; d ^= a; d = rotl(d, r3); c += d; b ^= c; b = rotl(b, r4)"},
"item": "s[0..7] = key; s[8+i] = t * mul[i] + rc[i] for i in 0..7; for r in 0..7: s = M_r(s); line = s[0] & 0x003fffff; s[i] ^= cache[line * 16 + i]; then s = M_8(s); item(t) = s",
"word": "dataset[w] = item(w >> 4)[w & 15]"
},
"instructions": [
{"i": 0, "op": "mad", "dst": 2, "src": 3, "src2": 4, "imm": "0xbf7b174d", "imm2": "0x337b762e", "rot": 17, "bit": 2, "mask": 2, "width": 1},
{"i": 1, "op": "add", "dst": 1, "src": 7, "src2": 2, "imm": "0x42da7657", "imm2": "0xc3bd2355", "rot": 25, "bit": 4, "mask": 16, "width": 1},
{"i": 2, "op": "add", "dst": 2, "src": 3, "src2": 0, "imm": "0x61f0b51c", "imm2": "0x2735a174", "rot": 4, "bit": 26, "mask": 2, "width": 1},
{"i": 3, "op": "mad", "dst": 4, "src": 0, "src2": 6, "imm": "0x679648a8", "imm2": "0x3044ba32", "rot": 31, "bit": 31, "mask": 4, "width": 1},
{"i": 4, "op": "load", "dst": 7, "src": 2, "src2": 6, "imm": "0x5d1ca2a2", "imm2": "0xe2481807", "rot": 24, "bit": 3, "mask": 1, "width": 1},
{"i": 5, "op": "load", "dst": 4, "src": 1, "src2": 2, "imm": "0x987c017a", "imm2": "0xf4d60559", "rot": 2, "bit": 0, "mask": 4, "width": 1},
{"i": 6, "op": "shfl", "dst": 6, "src": 3, "src2": 7, "imm": "0x6ea7b2df", "imm2": "0x9fce5071", "rot": 7, "bit": 15, "mask": 4, "width": 1},
{"i": 7, "op": "shfl", "dst": 1, "src": 5, "src2": 1, "imm": "0x26a2ecde", "imm2": "0xfec6ad22", "rot": 15, "bit": 11, "mask": 8, "width": 1},
{"i": 8, "op": "xor", "dst": 7, "src": 5, "src2": 2, "imm": "0xbe4b445c", "imm2": "0x17a5a9c7", "rot": 8, "bit": 8, "mask": 1, "width": 1},
{"i": 9, "op": "or", "dst": 3, "src": 4, "src2": 1, "imm": "0xccb7d785", "imm2": "0xc335364c", "rot": 14, "bit": 12, "mask": 4, "width": 1},
{"i": 10, "op": "or", "dst": 1, "src": 2, "src2": 3, "imm": "0x4e7dc10d", "imm2": "0x196d165c", "rot": 14, "bit": 27, "mask": 16, "width": 1},
{"i": 11, "op": "load", "dst": 4, "src": 3, "src2": 1, "imm": "0xc5c3b55d", "imm2": "0xec061424", "rot": 26, "bit": 27, "mask": 8, "width": 1},
{"i": 12, "op": "or", "dst": 6, "src": 2, "src2": 3, "imm": "0x306542fe", "imm2": "0x1bb1b429", "rot": 31, "bit": 0, "mask": 2, "width": 1},
{"i": 13, "op": "mul", "dst": 2, "src": 5, "src2": 6, "imm": "0xa672cdd3", "imm2": "0x59a4829c", "rot": 22, "bit": 13, "mask": 16, "width": 1},
{"i": 14, "op": "load", "dst": 1, "src": 2, "src2": 5, "imm": "0x028b4d37", "imm2": "0x7bbd78ea", "rot": 15, "bit": 2, "mask": 8, "width": 1},
{"i": 15, "op": "rotl", "dst": 7, "src": 6, "src2": 6, "imm": "0x5c88a1a7", "imm2": "0x5c628769", "rot": 1, "bit": 3, "mask": 8, "width": 1},
{"i": 16, "op": "scratch", "dst": 3, "src": 6, "src2": 7, "imm": "0xbac2ae81", "imm2": "0xcbbc7bdb", "rot": 18, "bit": 8, "mask": 8, "width": 1},
{"i": 17, "op": "load", "dst": 7, "src": 4, "src2": 2, "imm": "0xe8ab93e9", "imm2": "0xa00de107", "rot": 2, "bit": 1, "mask": 16, "width": 1},
{"i": 18, "op": "shfl", "dst": 3, "src": 4, "src2": 7, "imm": "0x1d2b8cab", "imm2": "0x80b4f9a2", "rot": 14, "bit": 25, "mask": 2, "width": 1},
{"i": 19, "op": "mad", "dst": 4, "src": 0, "src2": 2, "imm": "0x5fba7bc2", "imm2": "0xdf099cfb", "rot": 4, "bit": 15, "mask": 16, "width": 1},
{"i": 20, "op": "shfl", "dst": 0, "src": 6, "src2": 3, "imm": "0x0a3056de", "imm2": "0x7f0c25c3", "rot": 27, "bit": 13, "mask": 8, "width": 1},
{"i": 21, "op": "xor", "dst": 5, "src": 7, "src2": 4, "imm": "0xbd066e1d", "imm2": "0x6d3ddc5a", "rot": 2, "bit": 29, "mask": 1, "width": 1},
{"i": 22, "op": "mulhi", "dst": 2, "src": 5, "src2": 0, "imm": "0xc7e9887a", "imm2": "0x19ec898f", "rot": 14, "bit": 9, "mask": 1, "width": 1},
{"i": 23, "op": "load", "dst": 3, "src": 7, "src2": 2, "imm": "0xc7fcfc8f", "imm2": "0x8528b94f", "rot": 17, "bit": 13, "mask": 4, "width": 1},
{"i": 24, "op": "mulhi", "dst": 7, "src": 3, "src2": 5, "imm": "0xd91641e8", "imm2": "0xaf77faf2", "rot": 22, "bit": 21, "mask": 1, "width": 1},
{"i": 25, "op": "or", "dst": 5, "src": 4, "src2": 0, "imm": "0x84c03868", "imm2": "0xf6c691b7", "rot": 29, "bit": 14, "mask": 8, "width": 1},
{"i": 26, "op": "mad", "dst": 4, "src": 5, "src2": 2, "imm": "0x3bb2b6ba", "imm2": "0x49d95fd5", "rot": 1, "bit": 5, "mask": 8, "width": 1},
{"i": 27, "op": "mul", "dst": 5, "src": 1, "src2": 7, "imm": "0x0a816217", "imm2": "0x405c4f73", "rot": 13, "bit": 27, "mask": 4, "width": 1},
{"i": 28, "op": "mulhi", "dst": 6, "src": 7, "src2": 6, "imm": "0xd69c4715", "imm2": "0xe0ebc4ce", "rot": 29, "bit": 2, "mask": 8, "width": 1},
{"i": 29, "op": "add", "dst": 6, "src": 1, "src2": 2, "imm": "0x3b2d2124", "imm2": "0x187a9128", "rot": 1, "bit": 9, "mask": 16, "width": 1},
{"i": 30, "op": "rotr", "dst": 6, "src": 7, "src2": 0, "imm": "0x5c64a589", "imm2": "0x61c9a38d", "rot": 17, "bit": 21, "mask": 16, "width": 1},
{"i": 31, "op": "load", "dst": 3, "src": 1, "src2": 7, "imm": "0xc37723fa", "imm2": "0xf3b024da", "rot": 16, "bit": 27, "mask": 16, "width": 1},
{"i": 32, "op": "load", "dst": 1, "src": 0, "src2": 7, "imm": "0xcc7972c4", "imm2": "0xad098d15", "rot": 30, "bit": 21, "mask": 8, "width": 1},
{"i": 33, "op": "add", "dst": 0, "src": 4, "src2": 4, "imm": "0x2c35699f", "imm2": "0x351dde38", "rot": 21, "bit": 18, "mask": 4, "width": 1},
{"i": 34, "op": "scratch", "dst": 0, "src": 2, "src2": 3, "imm": "0xfae8902b", "imm2": "0x5cd8306f", "rot": 5, "bit": 28, "mask": 16, "width": 1},
{"i": 35, "op": "mul", "dst": 0, "src": 3, "src2": 1, "imm": "0x4fa3f3db", "imm2": "0xdbf37e75", "rot": 7, "bit": 18, "mask": 4, "width": 1},
{"i": 36, "op": "xor", "dst": 2, "src": 5, "src2": 5, "imm": "0x47f136c5", "imm2": "0x06ce9153", "rot": 19, "bit": 10, "mask": 2, "width": 1},
{"i": 37, "op": "load", "dst": 4, "src": 0, "src2": 0, "imm": "0x04cc1d55", "imm2": "0x35c52d04", "rot": 11, "bit": 14, "mask": 2, "width": 1},
{"i": 38, "op": "mad", "dst": 1, "src": 3, "src2": 5, "imm": "0x3958f280", "imm2": "0x8713c7e1", "rot": 5, "bit": 23, "mask": 16, "width": 1},
{"i": 39, "op": "add", "dst": 0, "src": 3, "src2": 3, "imm": "0xa907b90b", "imm2": "0x1b053acf", "rot": 30, "bit": 25, "mask": 16, "width": 1},
{"i": 40, "op": "rotr", "dst": 2, "src": 5, "src2": 4, "imm": "0xf8662282", "imm2": "0x10bb9e30", "rot": 8, "bit": 6, "mask": 2, "width": 1},
{"i": 41, "op": "mul", "dst": 3, "src": 2, "src2": 4, "imm": "0x49087d74", "imm2": "0x6348b489", "rot": 17, "bit": 9, "mask": 16, "width": 1},
{"i": 42, "op": "add", "dst": 1, "src": 5, "src2": 1, "imm": "0xa32e000c", "imm2": "0x6058c2e3", "rot": 25, "bit": 20, "mask": 8, "width": 1},
{"i": 43, "op": "xor", "dst": 3, "src": 4, "src2": 2, "imm": "0x3dad0eb6", "imm2": "0xb97578cb", "rot": 3, "bit": 27, "mask": 1, "width": 1},
{"i": 44, "op": "load", "dst": 3, "src": 5, "src2": 7, "imm": "0x374aec92", "imm2": "0x626f11df", "rot": 20, "bit": 18, "mask": 8, "width": 1},
{"i": 45, "op": "add", "dst": 1, "src": 5, "src2": 6, "imm": "0x81b8bc2c", "imm2": "0x1907970c", "rot": 28, "bit": 7, "mask": 4, "width": 1},
{"i": 46, "op": "xor", "dst": 7, "src": 1, "src2": 0, "imm": "0xef6ac348", "imm2": "0x963bb7e6", "rot": 26, "bit": 3, "mask": 8, "width": 1},
{"i": 47, "op": "add", "dst": 0, "src": 3, "src2": 0, "imm": "0x838b5065", "imm2": "0x36360066", "rot": 3, "bit": 31, "mask": 4, "width": 1},
{"i": 48, "op": "mulhi", "dst": 7, "src": 5, "src2": 0, "imm": "0x8458f7ac", "imm2": "0xc1c15026", "rot": 27, "bit": 15, "mask": 8, "width": 1},
{"i": 49, "op": "load", "dst": 0, "src": 2, "src2": 4, "imm": "0x636a9dc4", "imm2": "0xac023d9b", "rot": 22, "bit": 29, "mask": 1, "width": 1},
{"i": 50, "op": "sub", "dst": 2, "src": 6, "src2": 0, "imm": "0x2baec8c9", "imm2": "0x4390f156", "rot": 3, "bit": 12, "mask": 8, "width": 1},
{"i": 51, "op": "sub", "dst": 7, "src": 5, "src2": 7, "imm": "0x19234061", "imm2": "0xe84dfade", "rot": 4, "bit": 19, "mask": 1, "width": 1},
{"i": 52, "op": "xor", "dst": 2, "src": 3, "src2": 5, "imm": "0xdc2cd71e", "imm2": "0x1b5d334b", "rot": 9, "bit": 8, "mask": 8, "width": 1},
{"i": 53, "op": "sub", "dst": 7, "src": 0, "src2": 4, "imm": "0x605c31ec", "imm2": "0x9923ff88", "rot": 28, "bit": 25, "mask": 4, "width": 1},
{"i": 54, "op": "mad", "dst": 3, "src": 5, "src2": 0, "imm": "0xc0cc51a6", "imm2": "0x3fd7701b", "rot": 20, "bit": 1, "mask": 4, "width": 1},
{"i": 55, "op": "xor", "dst": 7, "src": 5, "src2": 5, "imm": "0xad7493e7", "imm2": "0x3e400372", "rot": 13, "bit": 8, "mask": 1, "width": 1},
{"i": 56, "op": "load", "dst": 2, "src": 7, "src2": 1, "imm": "0x87e933c9", "imm2": "0x8c854c1b", "rot": 17, "bit": 3, "mask": 8, "width": 1},
{"i": 57, "op": "sub", "dst": 5, "src": 6, "src2": 5, "imm": "0x11be3bc9", "imm2": "0xbbaa8e24", "rot": 6, "bit": 5, "mask": 16, "width": 1},
{"i": 58, "op": "load", "dst": 1, "src": 3, "src2": 2, "imm": "0xa732351a", "imm2": "0xc01349cd", "rot": 14, "bit": 17, "mask": 16, "width": 1},
{"i": 59, "op": "load", "dst": 1, "src": 4, "src2": 0, "imm": "0xb20547b2", "imm2": "0xc94655de", "rot": 27, "bit": 30, "mask": 1, "width": 1},
{"i": 60, "op": "sub", "dst": 4, "src": 6, "src2": 7, "imm": "0x67cf904c", "imm2": "0x6873b216", "rot": 27, "bit": 7, "mask": 16, "width": 1},
{"i": 61, "op": "mul", "dst": 1, "src": 2, "src2": 7, "imm": "0x93ab0bf4", "imm2": "0x96158375", "rot": 14, "bit": 0, "mask": 16, "width": 1},
{"i": 62, "op": "mad", "dst": 3, "src": 6, "src2": 0, "imm": "0x41a443a3", "imm2": "0xe69d7919", "rot": 9, "bit": 0, "mask": 16, "width": 1},
{"i": 63, "op": "add", "dst": 0, "src": 1, "src2": 3, "imm": "0x2fe0e98b", "imm2": "0xc88e2942", "rot": 5, "bit": 16, "mask": 16, "width": 1}
]
}