igneum/proto-cuda/packs-ca2-mixer/mx8-devnet-epoch0/program.json

131 lines
16 KiB
JSON

{
"format": "igneum-program-pack-3",
"generator": 2,
"attempt": 0,
"program_id": "0xa696c464d9e9649b",
"program_id_derivation": "FNV-1a 64 over 'igneum-program/' || generator_le32 || seed_words as little-endian bytes || attempt_le32",
"dataset_mode": "memory-hard",
"seed": "igneum-epoch/edc4fa844da9dc98d37e965176f6558a31560e40502ab3ae5491b21aaaabfb07/day/69676e65756d2d6461792ffa50000000000000",
"seed_bytes": "edc4fa844da9dc98d37e965176f6558a31560e40502ab3ae5491b21aaaabfb07",
"seed_words": ["0x667d0fbd", "0x7b8e5963", "0x31c67e5e", "0x4529ddc6", "0xef19d6d8", "0xaccf6211", "0xda0aed32", "0xabc6df31"],
"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": "mx8",
"mixer_mult": 8,
"cache_growth": true,
"mixer": "class v3 (Counter ASIC 2.0, 5 October 2026, docs/plans/mixer-x4.md): every mixer application of the item derivation is 8 applications with round keys (r * 8 + j + 1) * 0x9E3779B9, the 8 dependent cache reads per item unchanged; cache growth rule option C: cache words = 2^(26 + doublings(day)), dataset words = 2^(genesis_log2 + doublings(day)), doublings(day) = floor(log2(1 + day / 1460)) for day = days since genesis",
"load_slots": 16,
"load_mix_percent_4_16_64": [100, 0, 0],
"load_width_counts_4_16_64": [16, 0, 0],
"bytes_per_hash": 512,
"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": 16, "add": 13, "mulhi": 9, "shfl": 5, "sub": 5, "mad": 4, "rotl": 4, "xor": 3, "or": 2, "rotr": 2, "mul": 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": "bytes:69676e65756d2d6461792ffa50000000000000",
"day_bytes": "69676e65756d2d6461792ffa50000000000000",
"day_words_from": "seed_words_from_bytes(day_bytes)",
"d0": "0xceed56d7",
"d1": "0x9ba270d2",
"mode": "memory-hard",
"spec": "proto-metal/MEMHARD.md",
"key": ["0xceed56d7", "0x9ba270d2", "0x82caab2d", "0x81ebce0e", "0x12b6ecf1", "0xd0f3fd7c", "0xd872eefe", "0xc158c7bd"],
"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": [17, 12, 20, 23, 7, 3, 27, 16], "mul": ["0xf351d601", "0xa3bb398f", "0xb5a09e35", "0x7509c9c1", "0x6bbf31e9", "0xfc849a79", "0xded91851", "0x8d9113d1", "0x0ff15225", "0x3a5bdd41", "0xab533435", "0xe1c55ad5", "0xe6d3bd0d", "0x9d9ffbbd", "0xbb2a3cf3", "0x50a7c08d"], "rc": ["0xc6892460", "0x25b7228a", "0xcd515004", "0x2846527a", "0xa6324241", "0x36e3ec53", "0x82961bac", "0x0f97ba7d", "0xb6f921a9", "0x3ada24e5", "0xde20ab91", "0x5378eeb2", "0x7d161662", "0x89353cc1", "0xb1aa03a2", "0x788acae6"], "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)"},
"mixer_mult": 8,
"item": "s[0..7] = key; s[8+i] = t * mul[i] + rc[i] for i in 0..7; for r in 0..7: for j in 0..7: s = M(s, rk = (r * 8 + j + 1) * 0x9E3779B9); line = s[0] & 0x003fffff; s[i] ^= cache[line * 16 + i]; then for j in 0..7: s = M(s, rk = (64 + j + 1) * 0x9E3779B9); item(t) = s",
"word": "dataset[w] = item(w >> 4)[w & 15]"
},
"instructions": [
{"i": 0, "op": "add", "dst": 4, "src": 5, "src2": 7, "imm": "0xea86e152", "imm2": "0x5810667a", "rot": 27, "bit": 13, "mask": 2, "width": 1},
{"i": 1, "op": "shfl", "dst": 2, "src": 0, "src2": 7, "imm": "0xe3c2f9cb", "imm2": "0xde0bea4e", "rot": 6, "bit": 9, "mask": 4, "width": 1},
{"i": 2, "op": "add", "dst": 3, "src": 2, "src2": 0, "imm": "0x2cccb6ca", "imm2": "0x642e66db", "rot": 27, "bit": 10, "mask": 2, "width": 1},
{"i": 3, "op": "rotl", "dst": 0, "src": 2, "src2": 1, "imm": "0xb59e83b2", "imm2": "0x19c26fb9", "rot": 19, "bit": 20, "mask": 4, "width": 1},
{"i": 4, "op": "rotr", "dst": 7, "src": 6, "src2": 5, "imm": "0x6f055f55", "imm2": "0x550e4ea1", "rot": 31, "bit": 20, "mask": 4, "width": 1},
{"i": 5, "op": "add", "dst": 7, "src": 4, "src2": 7, "imm": "0xee02465f", "imm2": "0xc1535555", "rot": 31, "bit": 21, "mask": 4, "width": 1},
{"i": 6, "op": "mulhi", "dst": 1, "src": 7, "src2": 5, "imm": "0x7826a6a7", "imm2": "0x946f7818", "rot": 18, "bit": 21, "mask": 8, "width": 1},
{"i": 7, "op": "load", "dst": 4, "src": 2, "src2": 0, "imm": "0x5d080878", "imm2": "0xdf885578", "rot": 5, "bit": 18, "mask": 4, "width": 1},
{"i": 8, "op": "load", "dst": 7, "src": 4, "src2": 1, "imm": "0x875bbb36", "imm2": "0x594a838f", "rot": 24, "bit": 4, "mask": 2, "width": 1},
{"i": 9, "op": "load", "dst": 0, "src": 3, "src2": 1, "imm": "0xe5e607c2", "imm2": "0xa5cd9f75", "rot": 26, "bit": 28, "mask": 4, "width": 1},
{"i": 10, "op": "load", "dst": 5, "src": 1, "src2": 3, "imm": "0xea3f7b43", "imm2": "0x10c8d4e7", "rot": 5, "bit": 29, "mask": 8, "width": 1},
{"i": 11, "op": "load", "dst": 1, "src": 5, "src2": 4, "imm": "0x4454980f", "imm2": "0xebd31581", "rot": 10, "bit": 28, "mask": 16, "width": 1},
{"i": 12, "op": "mulhi", "dst": 3, "src": 5, "src2": 7, "imm": "0xbfd5615c", "imm2": "0xd8224ae2", "rot": 21, "bit": 12, "mask": 2, "width": 1},
{"i": 13, "op": "load", "dst": 1, "src": 3, "src2": 5, "imm": "0x35c07cc5", "imm2": "0xe82db54f", "rot": 7, "bit": 6, "mask": 8, "width": 1},
{"i": 14, "op": "sub", "dst": 0, "src": 3, "src2": 0, "imm": "0x587ee0f1", "imm2": "0xfd23eefd", "rot": 16, "bit": 21, "mask": 16, "width": 1},
{"i": 15, "op": "mad", "dst": 5, "src": 1, "src2": 3, "imm": "0x6974dd29", "imm2": "0xc8148960", "rot": 3, "bit": 11, "mask": 2, "width": 1},
{"i": 16, "op": "mulhi", "dst": 6, "src": 1, "src2": 7, "imm": "0x3072c3c6", "imm2": "0x55ee21f8", "rot": 26, "bit": 1, "mask": 1, "width": 1},
{"i": 17, "op": "add", "dst": 5, "src": 2, "src2": 2, "imm": "0x697b3d00", "imm2": "0x8b965b57", "rot": 9, "bit": 28, "mask": 1, "width": 1},
{"i": 18, "op": "mulhi", "dst": 0, "src": 6, "src2": 3, "imm": "0x2910cacb", "imm2": "0x6ac79431", "rot": 7, "bit": 6, "mask": 4, "width": 1},
{"i": 19, "op": "rotr", "dst": 5, "src": 3, "src2": 0, "imm": "0xed96a94a", "imm2": "0x4c988c10", "rot": 24, "bit": 21, "mask": 8, "width": 1},
{"i": 20, "op": "mulhi", "dst": 5, "src": 2, "src2": 7, "imm": "0x40d2fc76", "imm2": "0x2f7c7eca", "rot": 13, "bit": 8, "mask": 4, "width": 1},
{"i": 21, "op": "add", "dst": 1, "src": 0, "src2": 5, "imm": "0xebcf247a", "imm2": "0x6d7e8d05", "rot": 31, "bit": 1, "mask": 16, "width": 1},
{"i": 22, "op": "add", "dst": 7, "src": 5, "src2": 7, "imm": "0xf66e7017", "imm2": "0xb9e3577e", "rot": 9, "bit": 12, "mask": 16, "width": 1},
{"i": 23, "op": "mulhi", "dst": 1, "src": 5, "src2": 7, "imm": "0xfdfe72fd", "imm2": "0x735eeb8d", "rot": 30, "bit": 25, "mask": 8, "width": 1},
{"i": 24, "op": "sub", "dst": 2, "src": 5, "src2": 0, "imm": "0x32cf1258", "imm2": "0xd813deb6", "rot": 30, "bit": 6, "mask": 16, "width": 1},
{"i": 25, "op": "add", "dst": 7, "src": 4, "src2": 2, "imm": "0x08ffa6c7", "imm2": "0x699ef1bb", "rot": 7, "bit": 2, "mask": 16, "width": 1},
{"i": 26, "op": "shfl", "dst": 3, "src": 4, "src2": 5, "imm": "0x6f53c70d", "imm2": "0x3357513f", "rot": 3, "bit": 26, "mask": 2, "width": 1},
{"i": 27, "op": "add", "dst": 7, "src": 1, "src2": 4, "imm": "0xe60fea84", "imm2": "0xb4ead2fb", "rot": 14, "bit": 14, "mask": 1, "width": 1},
{"i": 28, "op": "add", "dst": 3, "src": 1, "src2": 0, "imm": "0x65c76dab", "imm2": "0x8f30d21d", "rot": 24, "bit": 6, "mask": 1, "width": 1},
{"i": 29, "op": "load", "dst": 2, "src": 1, "src2": 2, "imm": "0x82fad9a6", "imm2": "0x8c6358db", "rot": 7, "bit": 31, "mask": 2, "width": 1},
{"i": 30, "op": "load", "dst": 5, "src": 7, "src2": 3, "imm": "0x6e947ee0", "imm2": "0xaf9a2dda", "rot": 2, "bit": 30, "mask": 4, "width": 1},
{"i": 31, "op": "load", "dst": 2, "src": 5, "src2": 1, "imm": "0x608bb7ce", "imm2": "0x4be663db", "rot": 19, "bit": 1, "mask": 16, "width": 1},
{"i": 32, "op": "shfl", "dst": 1, "src": 7, "src2": 6, "imm": "0x88e52e20", "imm2": "0x77647269", "rot": 20, "bit": 25, "mask": 4, "width": 1},
{"i": 33, "op": "mad", "dst": 4, "src": 5, "src2": 7, "imm": "0xb48420ae", "imm2": "0x3d1f2485", "rot": 14, "bit": 28, "mask": 1, "width": 1},
{"i": 34, "op": "add", "dst": 4, "src": 2, "src2": 3, "imm": "0x0480debe", "imm2": "0xc7ce690c", "rot": 12, "bit": 21, "mask": 16, "width": 1},
{"i": 35, "op": "shfl", "dst": 3, "src": 7, "src2": 5, "imm": "0xa73f59de", "imm2": "0x84b9e329", "rot": 21, "bit": 27, "mask": 8, "width": 1},
{"i": 36, "op": "add", "dst": 7, "src": 1, "src2": 7, "imm": "0xc53b542e", "imm2": "0xe10c2c95", "rot": 21, "bit": 2, "mask": 4, "width": 1},
{"i": 37, "op": "xor", "dst": 5, "src": 7, "src2": 4, "imm": "0x81cd7b0e", "imm2": "0x21a51823", "rot": 12, "bit": 10, "mask": 2, "width": 1},
{"i": 38, "op": "or", "dst": 2, "src": 1, "src2": 3, "imm": "0x7894e657", "imm2": "0xf8e4b972", "rot": 18, "bit": 9, "mask": 4, "width": 1},
{"i": 39, "op": "mulhi", "dst": 1, "src": 0, "src2": 4, "imm": "0xbee8421f", "imm2": "0x070888a8", "rot": 20, "bit": 28, "mask": 4, "width": 1},
{"i": 40, "op": "rotl", "dst": 6, "src": 1, "src2": 4, "imm": "0x4609857a", "imm2": "0xaeecb156", "rot": 19, "bit": 21, "mask": 1, "width": 1},
{"i": 41, "op": "mulhi", "dst": 4, "src": 6, "src2": 0, "imm": "0x1a84e1e9", "imm2": "0x9b26bb72", "rot": 28, "bit": 19, "mask": 1, "width": 1},
{"i": 42, "op": "sub", "dst": 6, "src": 0, "src2": 6, "imm": "0xbf62908e", "imm2": "0xdf03ea88", "rot": 11, "bit": 27, "mask": 16, "width": 1},
{"i": 43, "op": "shfl", "dst": 6, "src": 3, "src2": 4, "imm": "0xa966241c", "imm2": "0x9c639efa", "rot": 12, "bit": 4, "mask": 4, "width": 1},
{"i": 44, "op": "load", "dst": 4, "src": 2, "src2": 3, "imm": "0x7b5b5474", "imm2": "0x45cfc5dd", "rot": 17, "bit": 18, "mask": 8, "width": 1},
{"i": 45, "op": "xor", "dst": 1, "src": 3, "src2": 6, "imm": "0x006193d0", "imm2": "0xfc2acc3f", "rot": 25, "bit": 1, "mask": 1, "width": 1},
{"i": 46, "op": "load", "dst": 7, "src": 0, "src2": 6, "imm": "0x4777c4f8", "imm2": "0x3cf0a02f", "rot": 11, "bit": 14, "mask": 4, "width": 1},
{"i": 47, "op": "load", "dst": 3, "src": 1, "src2": 3, "imm": "0x10692532", "imm2": "0x1a292ea5", "rot": 20, "bit": 23, "mask": 1, "width": 1},
{"i": 48, "op": "mul", "dst": 5, "src": 3, "src2": 7, "imm": "0xadf5bd13", "imm2": "0xb999de2e", "rot": 23, "bit": 10, "mask": 4, "width": 1},
{"i": 49, "op": "sub", "dst": 1, "src": 5, "src2": 4, "imm": "0x68ff101e", "imm2": "0xbdaaf46a", "rot": 25, "bit": 23, "mask": 16, "width": 1},
{"i": 50, "op": "rotl", "dst": 2, "src": 6, "src2": 4, "imm": "0x92d9a412", "imm2": "0x0daf96ea", "rot": 8, "bit": 4, "mask": 4, "width": 1},
{"i": 51, "op": "add", "dst": 1, "src": 5, "src2": 0, "imm": "0xa900fec4", "imm2": "0x77b9bd43", "rot": 6, "bit": 23, "mask": 2, "width": 1},
{"i": 52, "op": "load", "dst": 4, "src": 7, "src2": 1, "imm": "0x51392a72", "imm2": "0x99e8bb36", "rot": 11, "bit": 9, "mask": 1, "width": 1},
{"i": 53, "op": "sub", "dst": 2, "src": 7, "src2": 2, "imm": "0x0ffe2ac7", "imm2": "0x030743df", "rot": 9, "bit": 30, "mask": 16, "width": 1},
{"i": 54, "op": "xor", "dst": 4, "src": 0, "src2": 4, "imm": "0x9123ff15", "imm2": "0x10c329a7", "rot": 28, "bit": 15, "mask": 2, "width": 1},
{"i": 55, "op": "add", "dst": 1, "src": 6, "src2": 5, "imm": "0xe09f54e9", "imm2": "0x83e825bf", "rot": 23, "bit": 14, "mask": 8, "width": 1},
{"i": 56, "op": "load", "dst": 2, "src": 4, "src2": 3, "imm": "0x239de52c", "imm2": "0xf80bae18", "rot": 15, "bit": 24, "mask": 1, "width": 1},
{"i": 57, "op": "mad", "dst": 0, "src": 1, "src2": 4, "imm": "0x31dede8e", "imm2": "0xd3f619e6", "rot": 29, "bit": 7, "mask": 2, "width": 1},
{"i": 58, "op": "load", "dst": 3, "src": 5, "src2": 3, "imm": "0x206437d6", "imm2": "0x28d1c290", "rot": 17, "bit": 28, "mask": 4, "width": 1},
{"i": 59, "op": "or", "dst": 5, "src": 6, "src2": 3, "imm": "0x8fffd674", "imm2": "0x0507903a", "rot": 26, "bit": 27, "mask": 2, "width": 1},
{"i": 60, "op": "mad", "dst": 6, "src": 5, "src2": 7, "imm": "0xf572bdb9", "imm2": "0xeda2af31", "rot": 21, "bit": 8, "mask": 2, "width": 1},
{"i": 61, "op": "rotl", "dst": 4, "src": 2, "src2": 7, "imm": "0x84f12ddf", "imm2": "0x81ef22e1", "rot": 28, "bit": 30, "mask": 1, "width": 1},
{"i": 62, "op": "mulhi", "dst": 5, "src": 0, "src2": 6, "imm": "0xf6bb45ee", "imm2": "0x6bfb632d", "rot": 22, "bit": 0, "mask": 4, "width": 1},
{"i": 63, "op": "load", "dst": 3, "src": 6, "src2": 6, "imm": "0x50ec702a", "imm2": "0xae6ee96e", "rot": 20, "bit": 25, "mask": 2, "width": 1}
]
}