CCCL (CUDA C++ Core Libraries) provides: - CUB: device/block/warp-level GPU primitives (reduce, scan, sort, topk) - Thrust: high-level parallel algorithms (transform_reduce, sort, scan) - libcudacxx: CUDA C++ standard library (atomics, barriers, memory) - cudax: experimental features (memory resources, allocators) - Tuning policies: per-SM hardware-specific algorithm parameters Competition optimization vectors mapped to CCCL: - Output TPS (83% weight): warp_reduce, block_reduce, device_topk - Input TPS (14% weight): device_scan, block_load, prefetch - Cache TPS (3% weight): prefix caching strategy patterns - Memory (0.9 util): pooled/cached/buddy allocators Source: https://github.com/NVIDIA/cccl (shallow clone, HEAD only) License: Apache-2.0
162 lines
5.0 KiB
C++
162 lines
5.0 KiB
C++
/*
|
|
A C-program for MT19937, with initialization improved 2002/1/26.
|
|
Coded by Takuji Nishimura and Makoto Matsumoto.
|
|
|
|
Before using, initialize the state by using init_genrand(seed)
|
|
or init_by_array(init_key, key_length).
|
|
|
|
Copyright (C) 1997 - 2002, Makoto Matsumoto and Takuji Nishimura,
|
|
All rights reserved.
|
|
|
|
Redistribution and use in source and binary forms, with or without
|
|
modification, are permitted provided that the following conditions
|
|
are met:
|
|
|
|
1. Redistributions of source code must retain the above copyright
|
|
notice, this list of conditions and the following disclaimer.
|
|
|
|
2. Redistributions in binary form must reproduce the above copyright
|
|
notice, this list of conditions and the following disclaimer in the
|
|
documentation and/or other materials provided with the distribution.
|
|
|
|
3. The names of its contributors may not be used to endorse or promote
|
|
products derived from this software without specific prior written
|
|
permission.
|
|
|
|
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
|
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
|
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
|
A PARTICAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
|
|
CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
|
|
EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
|
|
PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
|
PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
|
|
LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
|
|
NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
|
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
|
|
|
|
Any feedback is very welcome.
|
|
http://www.math.sci.hiroshima-u.ac.jp/~m-mat/MT/emt.html
|
|
email: m-mat @ math.sci.hiroshima-u.ac.jp (remove space)
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
namespace mersenne
|
|
{
|
|
/* Period parameters */
|
|
constexpr unsigned int N = 624;
|
|
constexpr unsigned int M = 397;
|
|
constexpr unsigned int MATRIX_A = 0x9908b0df; /* constant vector a */
|
|
constexpr unsigned int UPPER_MASK = 0x80000000; /* most significant w-r bits */
|
|
constexpr unsigned int LOWER_MASK = 0x7fffffff; /* least significant r bits */
|
|
|
|
static unsigned int mt[N]; /* the array for the state vector */
|
|
static int mti = N + 1; /* mti==N+1 means mt[N] is not initialized */
|
|
|
|
/* initializes mt[N] with a seed */
|
|
inline void init_genrand(unsigned int s)
|
|
{
|
|
mt[0] = s & 0xffffffff;
|
|
for (mti = 1; mti < static_cast<int>(N); mti++)
|
|
{
|
|
mt[mti] = (1812433253 * (mt[mti - 1] ^ (mt[mti - 1] >> 30)) + mti);
|
|
|
|
/* See Knuth TAOCP Vol2. 3rd Ed. P.106 for mtiplier. */
|
|
/* In the previous versions, MSBs of the seed affect */
|
|
/* only MSBs of the array mt[]. */
|
|
/* 2002/01/09 modified by Makoto Matsumoto */
|
|
|
|
mt[mti] &= 0xffffffff;
|
|
/* for >32 bit machines */
|
|
}
|
|
}
|
|
|
|
/* initialize by an array with array-length */
|
|
/* init_key is the array for initializing keys */
|
|
/* key_length is its length */
|
|
/* slight change for C++, 2004/2/26 */
|
|
inline void init_by_array(unsigned int init_key[], int key_length)
|
|
{
|
|
int i, j, k;
|
|
init_genrand(19650218);
|
|
i = 1;
|
|
j = 0;
|
|
k = (static_cast<int>(N) > key_length ? static_cast<int>(N) : key_length);
|
|
for (; k; k--)
|
|
{
|
|
mt[i] = (mt[i] ^ ((mt[i - 1] ^ (mt[i - 1] >> 30)) * 1664525)) + init_key[j] + j; /* non linear */
|
|
mt[i] &= 0xffffffff; /* for WORDSIZE > 32 machines */
|
|
i++;
|
|
j++;
|
|
if (i >= static_cast<int>(N))
|
|
{
|
|
mt[0] = mt[N - 1];
|
|
i = 1;
|
|
}
|
|
if (j >= key_length)
|
|
{
|
|
j = 0;
|
|
}
|
|
}
|
|
for (k = N - 1; k; k--)
|
|
{
|
|
mt[i] = (mt[i] ^ ((mt[i - 1] ^ (mt[i - 1] >> 30)) * 1566083941)) - i; /* non linear */
|
|
mt[i] &= 0xffffffff; /* for WORDSIZE > 32 machines */
|
|
i++;
|
|
if (i >= static_cast<int>(N))
|
|
{
|
|
mt[0] = mt[N - 1];
|
|
i = 1;
|
|
}
|
|
}
|
|
|
|
mt[0] = 0x80000000; /* MSB is 1; assuring non-zero initial array */
|
|
}
|
|
|
|
/* generates a random number on [0,0xffffffff]-interval */
|
|
inline unsigned int genrand_int32()
|
|
{
|
|
unsigned int y;
|
|
static unsigned int mag01[2] = {0x0, MATRIX_A};
|
|
|
|
/* mag01[x] = x * MATRIX_A for x=0,1 */
|
|
|
|
if (mti >= static_cast<int>(N))
|
|
{ /* generate N words at one time */
|
|
int kk;
|
|
|
|
if (mti == N + 1) /* if init_genrand() has not been called, */
|
|
{
|
|
init_genrand(5489); /* a defat initial seed is used */
|
|
}
|
|
|
|
for (kk = 0; kk < static_cast<int>(N - M); kk++)
|
|
{
|
|
y = (mt[kk] & UPPER_MASK) | (mt[kk + 1] & LOWER_MASK);
|
|
mt[kk] = mt[kk + M] ^ (y >> 1) ^ mag01[y & 0x1];
|
|
}
|
|
for (; kk < static_cast<int>(N - 1); kk++)
|
|
{
|
|
y = (mt[kk] & UPPER_MASK) | (mt[kk + 1] & LOWER_MASK);
|
|
mt[kk] = mt[kk + (M - N)] ^ (y >> 1) ^ mag01[y & 0x1];
|
|
}
|
|
y = (mt[N - 1] & UPPER_MASK) | (mt[0] & LOWER_MASK);
|
|
mt[N - 1] = mt[M - 1] ^ (y >> 1) ^ mag01[y & 0x1];
|
|
|
|
mti = 0;
|
|
}
|
|
|
|
y = mt[mti++];
|
|
|
|
/* Tempering */
|
|
y ^= (y >> 11);
|
|
y ^= (y << 7) & 0x9d2c5680;
|
|
y ^= (y << 15) & 0xefc60000;
|
|
y ^= (y >> 18);
|
|
|
|
return y;
|
|
}
|
|
} // namespace mersenne
|