660f0eb16c
Exporter writes kernel.cl next to kernel.cu (same instruction list; memory-hard core emitted in a third, OpenCL C dialect with the same literals as memhard.h). Pack headers are now C99-safe so a plain C host can include them. proto-opencl/host.c: C99 + OpenCL 1.2 API, device list, runtime build, cache fill and FNV check, dataset build and self-test, 3 vector warps standalone and in batch, bench and sweep as host.cu, whole-batch fingerprint. The 32-lane exchange is sub_group_shuffle_xor only when the queried sub-group size for a 32-item work-group is exactly 32; otherwise a local-memory exchange with one barrier per exchange, so wave64 hardware cannot change the hash (WAVEFRONT.md). build.sh (macOS, Linux), build.bat (MSVC), README with the exact AMD-rig commands. Proven without AMD silicon: Apple OpenCL 1.2 on the M5 Max 96/96 on all three packs (45.0 Mhash/s at 1 GiB, Apple number, not AMD); pocl 7.2 CPU device 96/96 on both exchange paths including the real sub_group_shuffle_xor text; CPU emulator 7 configurations incl. 64-wide sub-groups, identical fingerprint f99fb375b3abeaf5 everywhere. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
47 lines
5 KiB
C++
47 lines
5 KiB
C++
// Generated by proto-metal/igneum-bench --export-pack for seed "igneum-genesis". Do not edit by hand.
|
|
// Expected outputs: proto-metal CPU interpreter (cpuWarp, closed-form dataset) on Apple M5 Max; Metal GPU cross-check PASS 3/3 warps
|
|
#pragma once
|
|
#ifdef __cplusplus
|
|
#include <cstdint>
|
|
#else
|
|
#include <stdint.h>
|
|
#endif
|
|
|
|
#define IGNEUM_VEC_WARPS 3
|
|
static const uint32_t IGNEUM_VEC_BASE[IGNEUM_VEC_WARPS] = { 0u, 4096u, 1000000u };
|
|
static const uint64_t IGNEUM_VEC_OUT[IGNEUM_VEC_WARPS][32] = {
|
|
{ // base nonce 0
|
|
0x2941e93c76cb1910ull, 0xc0099c34df8280aeull, 0xe61da8a237797181ull, 0xfb944794eaa8ea1dull, 0x0093934e41befb07ull, 0xd4ba2031c0385915ull, 0x75a8a43902cee166ull, 0xb4ce2d6829aaa27cull,
|
|
0x478095c2e9911e5dull, 0x595c8107b2792a66ull, 0x21b1b582752cc1d2ull, 0x16e746aa4d9532b8ull, 0x35129dbb17efe2e4ull, 0x926e0b679bf37640ull, 0xb2701dd71a189e19ull, 0x100e94f487022795ull,
|
|
0x2b9bc5aa1452be87ull, 0x8dabbbe8b909130bull, 0x93a2cd4cba088297ull, 0x662c3e253432099eull, 0xf489da4c9c770867ull, 0xe37864f932e97adfull, 0x3ddf029de9b3c1edull, 0x9059da45130736acull,
|
|
0x1a667325a17e0016ull, 0x74723d71ab69828aull, 0x121026c2f14795c1ull, 0x4989e1480c662cc8ull, 0xac3b8fd5307c0ab4ull, 0xdc3fc0bb843e84e8ull, 0xfa86df690d119639ull, 0x453388e1be04e25full
|
|
},
|
|
{ // base nonce 4096
|
|
0x198f269c663acaf6ull, 0x6c125dcda3cade45ull, 0x0ae4eba3f2a0cdecull, 0xc112952633d9477cull, 0x2dfc52ebb7281f9eull, 0x70b0e04375823959ull, 0x699e78e051dfaa76ull, 0xd91ae88bc2eba03full,
|
|
0x928b2939d0b23e68ull, 0x0e5feb811f4dd40bull, 0xd0e4ce74e6693b53ull, 0xbd8ac2d12ea0ea1bull, 0xa39bcd116eec4f88ull, 0xdd07f4f6a5a07514ull, 0xdc1cf8b4615b8842ull, 0xde0fb1599057c2ddull,
|
|
0x56edb1995f7c341eull, 0x02782ce22dd25939ull, 0x150b52d7b4b87319ull, 0xd5c89a9a6c2786c3ull, 0x8aef759270e00bbaull, 0xf9f26409968ea1eaull, 0x2013ae93398863f0ull, 0x863877ca875900deull,
|
|
0x6e05e03111bf02a3ull, 0x21ec57017818f221ull, 0x62b33a3456032a3bull, 0x5bc24dc2bf442511ull, 0xb97041874e099be7ull, 0x2d9f09fb5d11fa13ull, 0x43f3f83f764ea247ull, 0xa3ec25a3072b734cull
|
|
},
|
|
{ // base nonce 1000000
|
|
0xa63f6d32a9dc2bacull, 0x3263d16a85274409ull, 0xca7b34b1061437c7ull, 0xaf24083fbe9a33acull, 0x68c42544f8798a73ull, 0x5ba44c42278e0d0aull, 0x12b31f0da8ea79e3ull, 0xa4a6186f5f5b7280ull,
|
|
0x1534d7e10b3f87aeull, 0xb04618c9238e7436ull, 0x28be2d38f9db17d7ull, 0xebed3a6006a491d1ull, 0x23d50e8d3518ee39ull, 0xd75fac65bc8d1975ull, 0x3fd5c0a165c0669bull, 0x882720cae6122082ull,
|
|
0xc107a8305a1f009dull, 0xa58cc24784025f2cull, 0x7ee69d59a87a92ebull, 0x46009435f6f19482ull, 0xf50c2623a7f856acull, 0x1cc0ddf7b3dc20faull, 0xcbc7f0bb8cd2ec14ull, 0x119c2409ce2462baull,
|
|
0x1b544f117b80334cull, 0xdb47d6cdd3cf93fcull, 0xdb8c149c9914ddaeull, 0xc6c5e4b5ea412748ull, 0x4437723f548837ffull, 0x1fc1eb1bda8e067cull, 0x786dfa4dc7a84237ull, 0x1fc0ac22d46fb45dull
|
|
}
|
|
};
|
|
|
|
// Dataset self-test: dataset[0..15] and dataset[IGNEUM_MASK] (268435455).
|
|
static const uint32_t IGNEUM_DS_HEAD[16] = {
|
|
0x82174c0fu, 0x577bdb9cu, 0x111053bfu, 0x2bb85514u, 0xd83e190fu, 0x8ccd9427u, 0x3f69d5e4u, 0xf3bbe1dcu,
|
|
0xb3aa7e90u, 0xc33f5f73u, 0xb83a2b10u, 0xc4d7c8ffu, 0xefa6d1a8u, 0x7029b116u, 0x5e48fab0u, 0x0ef66e40u
|
|
};
|
|
static const uint32_t IGNEUM_DS_LAST_INDEX = 268435455u;
|
|
static const uint32_t IGNEUM_DS_LAST = 0xf78c84a4u;
|
|
// 64 sampled dataset words (index, value) computed on the Mac.
|
|
#define IGNEUM_DS_SAMPLES 64
|
|
static const uint32_t IGNEUM_DS_SAMPLE_INDEX[IGNEUM_DS_SAMPLES] = {
|
|
59471966u, 217795994u, 208353206u, 42483309u, 172547758u, 148076330u, 183853158u, 214389424u, 267488061u, 169781097u, 184093494u, 153880993u, 84977930u, 46426879u, 3093825u, 225364072u, 44593546u, 260713159u, 168250303u, 52384140u, 223401610u, 45554030u, 95410555u, 175039924u, 79171087u, 267580473u, 24168642u, 37981670u, 171551130u, 195559979u, 204611762u, 140997658u, 138925853u, 86637313u, 20736778u, 219665210u, 160430336u, 264654675u, 8013395u, 228945585u, 213884386u, 104419827u, 44185464u, 142737231u, 99284897u, 132475900u, 61861762u, 132056166u, 262388043u, 91878046u, 117353561u, 124768597u, 71352993u, 190698941u, 46055428u, 55281366u, 165145231u, 106810753u, 171985651u, 232085256u, 159510492u, 40072060u, 209107596u, 39023794u
|
|
};
|
|
static const uint32_t IGNEUM_DS_SAMPLE_VALUE[IGNEUM_DS_SAMPLES] = {
|
|
0x3ef2f18du, 0xed632a6bu, 0x2daad897u, 0x1201639fu, 0x8e79ca54u, 0x488d4f3du, 0x5206fa5cu, 0xf60c5f15u, 0x5af790f7u, 0xdb48b2cau, 0x2b55a0e4u, 0xc8c5100fu, 0xe4afb4a4u, 0x35a42586u, 0xff4cb6d1u, 0x1d6cac9fu, 0x889230c1u, 0x95316e2au, 0x61b099e9u, 0x97b89bb2u, 0x05171be5u, 0x7f0157abu, 0x13825368u, 0x562ab1bfu, 0x6e3b06b8u, 0xc9b51434u, 0xc994b628u, 0x26643aa8u, 0x56ae558cu, 0xdc8fdaaau, 0x2ed21c3fu, 0x3a29b91bu, 0xfd98ca1eu, 0x44c7dd8au, 0xaab155c8u, 0x0db02165u, 0x637c813au, 0x5648617eu, 0x3e163337u, 0x64bf0ad7u, 0x43381384u, 0x824dca58u, 0xab7bf62eu, 0x10880075u, 0x292498dau, 0x925fea4du, 0x606466a0u, 0x37923fc4u, 0x3544915bu, 0x742b205du, 0x3228e7adu, 0x1ce5ec92u, 0xd7857a5cu, 0x200a560bu, 0xc29076c7u, 0x886a1a06u, 0x1f415038u, 0x60fa6028u, 0x1fb1d0f9u, 0xee203b87u, 0xa12f7ea5u, 0x6ecd91dcu, 0x260e00b4u, 0xef4a4067u
|
|
};
|