Snektron

streams: 1
threads per block: 32
blocks: 4096
warp size: 64
number of multiprocessors (CUs or WGPs): 120
total threads: 131072
max warps active: 4096
max blocks active: 4096
max threads per multiprocessor: 2560
est. max warps per CU/WGP: 34.1333

Snektron

#include <stdio.h>
#include <stdlib.h>
#include <sys/mman.h>

const char start[] = {1,3,4,1,1,1,1,1,1,1,1,2,2,1,4,2,4,1,1,1,1,1,5,4,1,1,2,1,1,1,1,4,1,1,1,4,4,1,1,1,1,1,1,1,2,4,1,3,1,1,2,1,2,1,1,4,1,1,1,4,3,1,3,1,5,1,1,3,4,1,1,1,3,1,1,1,1,1,1,1,1,1,1,1,1,1,5,2,5,5,3,2,1,5,1,1,1,1,1,1,1,1,1,1,1,1,2,1,1,1,1,5,1,1,1,1,5,1,1,1,1,1,4,1,1,1,1,1,3,1,1,1,1,1,1,1,1,1,1,1,3,1,2,4,1,5,5,1,1,5,3,4,4,4,1,1,1,2,1,1,1,1,1,1,2,1,1,1,1,1,1,5,3,1,4,1,1,2,2,1,2,2,5,1,1,1,2,1,1,1,1,3,4,5,1,2,1,1,1,1,1,5,2,1,1,1,1,1,1,5,1,1,1,1,1,1,1,5,1,4,1,5,1,1,1,1,1,1,1,1,1,1,1,1,1,2,1,1,1,1,5,4,5,1,1,1,1,1,1,1,5,1,1,3,1,1,1,3,1,4,2,1,5,1,3,5,5,2,1,3,1,1,1,1,1,3,1,3,1,1,2,4,3,1,4,2,2,1,1,1,1,1,1,1,5,2,1,1,1,2};

size_t num_for(size_t x) {
    char* mem = mmap(NULL, 1000000000000, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
    if (mem == MAP_FAILED) {
        puts(":(");

Snektron

const std = @import("std");

const Vec3 = struct {
    x: f32,
    y: f32,
    z: f32,

    const up = Vec3{.x = 0, .y = 1, .z = 0};

    fn add(a: Vec3, b: Vec3) Vec3 {

Snektron

const std = @import("std");
const Allocator = std.mem.Allocator;

const workload_size = 1 << 20;
const n_workloads = 4;
const repetition = 4;
const use_async = true;
const use_manual_prefetch = true;

const Cell = extern struct {

Snektron

const std = @import("std");
const mem = std.mem;
const testing = std.testing;
const Allocator = mem.Allocator;
const ArenaAllocator = std.heap.ArenaAllocator;
const SegmentedList = std.SegmentedList;

pub const Attribute = struct {
    name: []const u8,
    value: []const u8

Snektron

const std = @import("std");
const Log2Int = std.math.Log2Int;
const IntType = std.meta.IntType;

fn radix(comptime T: type, comptime bits: Log2Int(T), shift: Log2Int(T), value: T) IntType(false, bits) {
    const RadixType = IntType(false, bits);
    return @intCast(RadixType, (value >> shift) & std.math.maxInt(RadixType));
}

fn partialRadixSort(comptime T: type, comptime bits: Log2Int(T), shift: Log2Int(T), src: []const T, dst: []T) void {

Snektron

// Finds factors of 1 + 11! + (11!)! using CUDA
// Primes to check whether they are a factor of above numbers
// are to be supplied one-per-line to the program.
// See https://cr.yp.to/primegen.html for generating primes.
// Compile with `nvcc -o fact fact.cu`.
// Run with `./fact ./primes.txt`

#include <vector>
#include <fstream>
#include <iostream>

Snektron

#include <iterator>
#include <array>
#include <cstddef>

template <typename T>
using remove_cvref = std::remove_cv_t<std::remove_reference_t<T>>;

template <typename T, T... values>
struct Seq {

Snektron

GPU: RX 580 (8 GB)
vulkan: 1.1.107
total rays: 311040000
total render time: 18540.1
total mray/s: 16.7766
average fps: 8.07517
frames: 150
# Frame number: total rays, outputs, total render time, max render time, min render time, mray/s
frame 0: 2073600 rays, 1, 77.8995 ms, 77.8995 ms, 77.8995 ms, 26.6189 mray/s
frame 1: 2073600 rays, 1, 77.8482 ms, 77.8482 ms, 77.8482 ms, 26.6365 mray/s