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>
109 lines
8.8 KiB
Metal
109 lines
8.8 KiB
Metal
#include <metal_stdlib>
|
|
using namespace metal;
|
|
|
|
#define MASK 0x0fffffffu
|
|
constant uint SEEDW[8] = { 0xc255b2bfu, 0xdba9d396u, 0x6ea527e4u, 0x05f1866au, 0x2947e02eu, 0x0ecc5c6fu, 0xc3b7068du, 0x282d1c2eu };
|
|
|
|
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;
|
|
}
|
|
|
|
kernel void igneum_hash(device const uint* dataset [[buffer(0)]],
|
|
device ulong* out [[buffer(1)]],
|
|
constant uint& baseNonce [[buffer(2)]],
|
|
uint gid [[thread_position_in_grid]]) {
|
|
uint nonce = baseNonce + gid;
|
|
uint r0, r1, r2, r3, r4, r5, r6, r7;
|
|
{ uint x = nonce ^ SEEDW[0]; x += 0x9e3779b9u * 1u; x = splitmix32(x); r0 = x ^ SEEDW[1]; }
|
|
{ uint x = nonce ^ SEEDW[1]; x += 0x9e3779b9u * 2u; x = splitmix32(x); r1 = x ^ SEEDW[2]; }
|
|
{ uint x = nonce ^ SEEDW[2]; x += 0x9e3779b9u * 3u; x = splitmix32(x); r2 = x ^ SEEDW[3]; }
|
|
{ uint x = nonce ^ SEEDW[3]; x += 0x9e3779b9u * 4u; x = splitmix32(x); r3 = x ^ SEEDW[4]; }
|
|
{ uint x = nonce ^ SEEDW[4]; x += 0x9e3779b9u * 5u; x = splitmix32(x); r4 = x ^ SEEDW[5]; }
|
|
{ uint x = nonce ^ SEEDW[5]; x += 0x9e3779b9u * 6u; x = splitmix32(x); r5 = x ^ SEEDW[6]; }
|
|
{ uint x = nonce ^ SEEDW[6]; x += 0x9e3779b9u * 7u; x = splitmix32(x); r6 = x ^ SEEDW[7]; }
|
|
{ uint x = nonce ^ SEEDW[7]; x += 0x9e3779b9u * 8u; x = splitmix32(x); r7 = x ^ SEEDW[0]; }
|
|
|
|
for (uint it = 0u; it < 8u; ++it) {
|
|
uint sel = r0;
|
|
r3 = rotl_imm(r3, 26u); // 0
|
|
r2 = rotr_var(r2, r0); // 1
|
|
r0 = r0 ^ r7; // 2
|
|
r4 = r4 ^ r7; // 3
|
|
r2 = r2 ^ dataset[r4 & MASK]; // 4
|
|
{ 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_; } // 5
|
|
r0 = r0 ^ simd_shuffle_xor(r7, (ushort)4); // 6
|
|
r6 = rotl_imm(r6, 31u); // 7
|
|
r1 = r4 * r2 + r1; // 8
|
|
r1 = r7 * r0 + r1; // 9
|
|
r4 = r4 ^ dataset[r1 & MASK]; // 10
|
|
r6 = r7 * r0 + r6; // 11
|
|
r2 = r2 * r6; // 12
|
|
{ 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_; } // 13
|
|
r2 = r2 + r7 + select(0x5df3957du, 0x4a3db5a5u, ((sel >> 22u) & 1u) != 0u); // 14
|
|
r5 = r5 ^ simd_shuffle_xor(r7, (ushort)1); // 15
|
|
r3 = r5 * r6 + r3; // 16
|
|
r2 = r2 * r5; // 17
|
|
r1 = r1 ^ simd_shuffle_xor(r5, (ushort)1); // 18
|
|
r0 = r0 - r1; // 19
|
|
r4 = r6 * r4 + r4; // 20
|
|
r3 = r3 ^ simd_shuffle_xor(r0, (ushort)16); // 21
|
|
r1 = rotl_imm(r1, 24u); // 22
|
|
r1 = r1 + r0 + select(0x5c141117u, 0xfc07c54cu, ((sel >> 22u) & 1u) != 0u); // 23
|
|
r2 = r2 ^ dataset[r0 & MASK]; // 24
|
|
r0 = r0 ^ r1; // 25
|
|
r3 = r3 ^ r7; // 26
|
|
{ uint b_ = (r3 & MASK) & ~3u; device const uint4* l_ = (device const uint4*)(dataset + b_); uint4 v0_ = l_[0]; 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; r2 = x_; } // 27
|
|
r0 = r0 ^ r6; // 28
|
|
r4 = r4 ^ r1; // 29
|
|
r6 = r6 * r3; // 30
|
|
r3 = rotl_imm(r3, 23u); // 31
|
|
r7 = rotr_var(r7, r1); // 32
|
|
r6 = r6 ^ simd_shuffle_xor(r2, (ushort)2); // 33
|
|
{ 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_ = r5 ^ 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; r5 = x_; } // 34
|
|
r6 = r6 + r3 + select(0xfb55c58du, 0x0b74657bu, ((sel >> 29u) & 1u) != 0u); // 35
|
|
{ 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_ = 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_; } // 36
|
|
r1 = r1 ^ dataset[r4 & MASK]; // 37
|
|
{ uint b_ = (r3 & MASK) & ~3u; device const uint4* l_ = (device const uint4*)(dataset + b_); uint4 v0_ = l_[0]; 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; r6 = x_; } // 38
|
|
r4 = r4 ^ dataset[r7 & MASK]; // 39
|
|
r7 = mulhi(r7, r3); // 40
|
|
r0 = r0 | r6; // 41
|
|
r0 = r3 * r0 + r0; // 42
|
|
{ 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_ = 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; 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; r4 = x_; } // 43
|
|
r2 = r4 * r0 + r2; // 44
|
|
r2 = r4 * r2 + r2; // 45
|
|
r7 = r7 ^ simd_shuffle_xor(r5, (ushort)16); // 46
|
|
r6 = r1 * r4 + r6; // 47
|
|
r7 = r7 ^ dataset[r1 & MASK]; // 48
|
|
r6 = mulhi(r6, r5); // 49
|
|
r5 = mulhi(r5, r0); // 50
|
|
{ uint b_ = (r6 & MASK) & ~3u; device const uint4* l_ = (device const uint4*)(dataset + b_); uint4 v0_ = l_[0]; 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; r1 = x_; } // 51
|
|
r7 = r7 ^ simd_shuffle_xor(r3, (ushort)1); // 52
|
|
r2 = r2 ^ r5; // 53
|
|
r0 = r0 ^ simd_shuffle_xor(r6, (ushort)4); // 54
|
|
r2 = r2 * r5; // 55
|
|
r5 = r5 * r6; // 56
|
|
{ uint b_ = (r4 & MASK) & ~3u; device const uint4* l_ = (device const uint4*)(dataset + b_); uint4 v0_ = l_[0]; 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; r6 = x_; } // 57
|
|
r4 = r7 * r7 + r4; // 58
|
|
r2 = r2 ^ dataset[r1 & MASK]; // 59
|
|
r1 = r1 * r4; // 60
|
|
r3 = r3 * r4; // 61
|
|
r6 = r6 ^ r4; // 62
|
|
r3 = rotr_var(r3, r1); // 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;
|
|
}
|