ZipAndSkipTries/msw_8cuh_source.html

#pragma once


#include <cstddef> // size_t

#include <cstdint> // uintmax_t


size_t seq_find_mismatch(const uintmax_t * const a, const uintmax_t * const b, size_t n);


size_t par_find_mismatch(const uintmax_t * const a, const uintmax_t * const b, size_t n);


size_t par_find_mismatch(const uintmax_t * const d_a, const uintmax_t * const b, uintmax_t *d_large_block, size_t n);


uintmax_t* alloc_large_block_to_device(size_t max_n);

alloc_to_device
T * alloc_to_device(size_t size)
Allocates memory on the CUDA device.
Definition cuda_utils.cuh:190

seq_find_mismatch
size_t seq_find_mismatch(const uintmax_t *const a, const uintmax_t *const b, size_t n)
Sequential implementation of finding the first mismatching word between two arrays.
Definition msw.cu:141

alloc_large_block_to_device
uintmax_t * alloc_large_block_to_device(size_t max_n)
Allocates a large block of device memory for parallel mismatch operations.
Definition msw.cu:256

par_find_mismatch
size_t par_find_mismatch(const uintmax_t *const a, const uintmax_t *const b, size_t n)
GPU-accelerated implementation of finding the first mismatching word.
Definition msw.cu:280