dc84789e34
Nothing changes for the default class: the pinned packs are byte-identical (tests/packs.rs), the v2 draw stream is untouched.
LoadClass {mix, load_slots, scratch}: fixed widths w16, w64, w64x4 (4 loads of 64 B), era mixes 50/35/15 and 25/50/25 drawn per load with one extra below(100) roll, and the scratch variant scr0/2/4/8 (persistent warps, 1 MiB per warp, tagged lazy fill, measurement only). A wide load reads the W-aligned address and folds every word: x = dst ^ w0; x = (rotl(x, 11) * 0x9e3779b1) ^ w[j]. Program ids carry the class. proto-opencl/host.c taken from opencl-rdna4 23810df (--memprobe, select read-back).
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
111 lines
11 KiB
Metal
111 lines
11 KiB
Metal
#include <metal_stdlib>
|
|
using namespace metal;
|
|
|
|
#define MASK 0x0fffffffu
|
|
constant uint SEEDW[8] = { 0x30b957f0u, 0x374e2a95u, 0xf416345eu, 0x7af15ccbu, 0xf0bcabc5u, 0xb5b36f35u, 0xf99641c7u, 0xd0312afeu };
|
|
|
|
inline uint splitmix32(uint x) {
|
|
x ^= x >> 16; x *= 0x7feb352du;
|
|
x ^= x >> 15; x *= 0x846ca68bu;
|
|
x ^= x >> 16;
|
|
return x;
|
|
}
|
|
inline uint rotl_imm(uint x, uint n) { return (x << n) | (x >> (32u - n)); } // n in 1..31
|
|
inline uint rotr_var(uint x, uint n) { n &= 31u; return (x >> n) | (x << ((32u - n) & 31u)); }
|
|
inline uint ds_elem(uint i, uint d0, uint d1) {
|
|
uint x = i ^ d0;
|
|
x *= 0x9E3779B1u; x ^= x >> 15;
|
|
x += d1;
|
|
x *= 0x85EBCA77u; x ^= x >> 13;
|
|
x *= 0xC2B2AE3Du; x ^= x >> 16;
|
|
return x;
|
|
}
|
|
|
|
// Header-bound variant: the init words come from buffer 3 (bind.rs), not from SEEDW.
|
|
kernel void igneum_hash_bound(device const uint* dataset [[buffer(0)]],
|
|
device ulong* out [[buffer(1)]],
|
|
constant uint& baseNonce [[buffer(2)]],
|
|
constant uint* initw [[buffer(3)]],
|
|
uint gid [[thread_position_in_grid]]) {
|
|
uint nonce = baseNonce + gid;
|
|
uint r0, r1, r2, r3, r4, r5, r6, r7;
|
|
{ uint x = nonce ^ initw[0]; x += 0x9e3779b9u * 1u; x = splitmix32(x); r0 = x ^ initw[1]; }
|
|
{ uint x = nonce ^ initw[1]; x += 0x9e3779b9u * 2u; x = splitmix32(x); r1 = x ^ initw[2]; }
|
|
{ uint x = nonce ^ initw[2]; x += 0x9e3779b9u * 3u; x = splitmix32(x); r2 = x ^ initw[3]; }
|
|
{ uint x = nonce ^ initw[3]; x += 0x9e3779b9u * 4u; x = splitmix32(x); r3 = x ^ initw[4]; }
|
|
{ uint x = nonce ^ initw[4]; x += 0x9e3779b9u * 5u; x = splitmix32(x); r4 = x ^ initw[5]; }
|
|
{ uint x = nonce ^ initw[5]; x += 0x9e3779b9u * 6u; x = splitmix32(x); r5 = x ^ initw[6]; }
|
|
{ uint x = nonce ^ initw[6]; x += 0x9e3779b9u * 7u; x = splitmix32(x); r6 = x ^ initw[7]; }
|
|
{ uint x = nonce ^ initw[7]; x += 0x9e3779b9u * 8u; x = splitmix32(x); r7 = x ^ initw[0]; }
|
|
|
|
for (uint it = 0u; it < 8u; ++it) {
|
|
uint sel = r0;
|
|
r3 = rotr_var(r3, r4); // 0
|
|
r0 = r0 ^ r7; // 1
|
|
{ uint b_ = (r0 & MASK) & ~15u; device const uint4* l_ = (device const uint4*)(dataset + b_); uint4 v0_ = l_[0]; uint4 v1_ = l_[1]; uint4 v2_ = l_[2]; uint4 v3_ = l_[3]; uint x_ = r1 ^ v0_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.w; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.w; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.w; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.w; r1 = x_; } // 2
|
|
r5 = rotl_imm(r5, 15u); // 3
|
|
r2 = r2 + r3 + select(0xd7a264d9u, 0xd35e575cu, ((sel >> 6u) & 1u) != 0u); // 4
|
|
r5 = r5 ^ simd_shuffle_xor(r2, (ushort)1); // 5
|
|
r1 = r2 * r5 + r1; // 6
|
|
r2 = r2 | r3; // 7
|
|
r3 = r3 ^ r5; // 8
|
|
r0 = r0 + r3 + select(0x4e543e70u, 0xd98be6edu, ((sel >> 29u) & 1u) != 0u); // 9
|
|
r5 = rotr_var(r5, r1); // 10
|
|
r3 = r3 * r5; // 11
|
|
r2 = r2 ^ r7; // 12
|
|
r1 = r1 + r6 + select(0xe36f3c9fu, 0x97a9219cu, ((sel >> 30u) & 1u) != 0u); // 13
|
|
r2 = r2 | r1; // 14
|
|
r1 = r1 | r3; // 15
|
|
r7 = r3 * r7 + r7; // 16
|
|
r3 = r3 + r2 + select(0x0c0a7b49u, 0xf799b153u, ((sel >> 13u) & 1u) != 0u); // 17
|
|
r7 = r7 ^ dataset[r5 & MASK]; // 18
|
|
r7 = r7 ^ dataset[r2 & MASK]; // 19
|
|
r5 = r5 ^ simd_shuffle_xor(r0, (ushort)8); // 20
|
|
r4 = r4 ^ dataset[r1 & MASK]; // 21
|
|
r5 = r5 ^ dataset[r7 & MASK]; // 22
|
|
r4 = r4 ^ r2; // 23
|
|
r5 = r5 + r3 + select(0x011f9670u, 0x26eb8325u, ((sel >> 14u) & 1u) != 0u); // 24
|
|
r0 = r0 * r1; // 25
|
|
r4 = r4 ^ r7; // 26
|
|
r7 = r7 + r5 + select(0x42177757u, 0xf12a4057u, ((sel >> 26u) & 1u) != 0u); // 27
|
|
r5 = r0 * r7 + r5; // 28
|
|
r3 = r3 * r6; // 29
|
|
r6 = rotl_imm(r6, 24u); // 30
|
|
r4 = rotr_var(r4, r0); // 31
|
|
r6 = r6 ^ dataset[r4 & MASK]; // 32
|
|
r0 = r0 ^ simd_shuffle_xor(r1, (ushort)1); // 33
|
|
r4 = r4 * r5; // 34
|
|
r2 = rotl_imm(r2, 15u); // 35
|
|
r7 = r7 + r3 + select(0xe0ebc725u, 0xc1b9573fu, ((sel >> 5u) & 1u) != 0u); // 36
|
|
{ uint b_ = (r2 & MASK) & ~3u; device const uint4* l_ = (device const uint4*)(dataset + b_); uint4 v0_ = l_[0]; uint x_ = r0 ^ v0_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.w; r0 = x_; } // 37
|
|
r7 = r0 * r2 + r7; // 38
|
|
r0 = r0 + r7 + select(0xd0b844deu, 0xde4cd365u, ((sel >> 16u) & 1u) != 0u); // 39
|
|
{ uint b_ = (r6 & MASK) & ~15u; device const uint4* l_ = (device const uint4*)(dataset + b_); uint4 v0_ = l_[0]; uint4 v1_ = l_[1]; uint4 v2_ = l_[2]; uint4 v3_ = l_[3]; uint x_ = r7 ^ v0_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.w; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.w; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.w; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.w; r7 = x_; } // 40
|
|
r0 = r0 ^ r1; // 41
|
|
r1 = rotl_imm(r1, 19u); // 42
|
|
r7 = r7 ^ r1; // 43
|
|
r2 = r2 * r4; // 44
|
|
{ uint b_ = (r4 & MASK) & ~15u; device const uint4* l_ = (device const uint4*)(dataset + b_); uint4 v0_ = l_[0]; uint4 v1_ = l_[1]; uint4 v2_ = l_[2]; uint4 v3_ = l_[3]; uint x_ = r6 ^ v0_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.w; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.w; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.w; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.w; r6 = x_; } // 45
|
|
r7 = r7 + r3 + select(0x7633c48cu, 0x5d12f1a2u, ((sel >> 28u) & 1u) != 0u); // 46
|
|
r3 = r3 ^ dataset[r2 & MASK]; // 47
|
|
{ uint b_ = (r5 & MASK) & ~15u; device const uint4* l_ = (device const uint4*)(dataset + b_); uint4 v0_ = l_[0]; uint4 v1_ = l_[1]; uint4 v2_ = l_[2]; uint4 v3_ = l_[3]; uint x_ = r2 ^ v0_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.w; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.w; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.w; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.w; r2 = x_; } // 48
|
|
r7 = r7 * r5; // 49
|
|
r3 = r7 * r0 + r3; // 50
|
|
{ uint b_ = (r2 & MASK) & ~3u; device const uint4* l_ = (device const uint4*)(dataset + b_); uint4 v0_ = l_[0]; uint x_ = r3 ^ v0_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.w; r3 = x_; } // 51
|
|
{ uint b_ = (r7 & MASK) & ~3u; device const uint4* l_ = (device const uint4*)(dataset + b_); uint4 v0_ = l_[0]; uint x_ = r4 ^ v0_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.w; r4 = x_; } // 52
|
|
r4 = mulhi(r4, r1); // 53
|
|
r7 = r7 + r4 + select(0xf64a6e41u, 0xd8ed09bau, ((sel >> 24u) & 1u) != 0u); // 54
|
|
r5 = mulhi(r5, r3); // 55
|
|
r5 = r5 * r7; // 56
|
|
{ uint b_ = (r0 & MASK) & ~15u; device const uint4* l_ = (device const uint4*)(dataset + b_); uint4 v0_ = l_[0]; uint4 v1_ = l_[1]; uint4 v2_ = l_[2]; uint4 v3_ = l_[3]; uint x_ = r3 ^ v0_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.w; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.w; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.w; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.w; r3 = x_; } // 57
|
|
r5 = mulhi(r5, r2); // 58
|
|
r7 = r7 * r5; // 59
|
|
{ uint b_ = (r3 & MASK) & ~15u; device const uint4* l_ = (device const uint4*)(dataset + b_); uint4 v0_ = l_[0]; uint4 v1_ = l_[1]; uint4 v2_ = l_[2]; uint4 v3_ = l_[3]; uint x_ = r6 ^ v0_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v0_.w; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v1_.w; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v2_.w; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.x; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.y; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.z; x_ = (rotl_imm(x_, 11u) * 0x9e3779b1u) ^ v3_.w; r6 = x_; } // 60
|
|
r7 = r1 * r1 + r7; // 61
|
|
r0 = r0 ^ dataset[r7 & MASK]; // 62
|
|
r5 = r5 * r3; // 63
|
|
}
|
|
uint lo = r0 ^ rotl_imm(r1, 7u) ^ rotl_imm(r2, 14u) ^ rotl_imm(r3, 21u);
|
|
uint hi = r4 ^ rotl_imm(r5, 9u) ^ rotl_imm(r6, 18u) ^ rotl_imm(r7, 27u);
|
|
out[gid] = ((ulong)hi << 32) | (ulong)lo;
|
|
}
|