Bulat-Ziganshin

---------------------------------------------------------------------------------------------------
---- "Взаимодействующие последовательные процессы", как описано в книге Хоара.                 ----
---------------------------------------------------------------------------------------------------
-- |
-- Module      :  Process
-- Copyright   :  (c) Bulat Ziganshin <Bulat.Ziganshin@gmail.com>
-- License     :  Public domain
--
-- Maintainer  :  Bulat.Ziganshin@gmail.com
-- Stability   :  experimental

Bulat-Ziganshin

/* GHC_PACKAGES base rts
*/
#include "Stg.h"
#include "HsBase.h"
START_MOD_INIT(__stginit_Main,__stginit_Main_)
EF_(__stginit_SystemziEnvironment_);
EF_(__stginit_SystemziIOziUnsafe_);
EF_(__stginit_DataziChar_);
EF_(__stginit_Prelude_);
REGISTER_IMPORT(__stginit_SystemziEnvironment_);

Bulat-Ziganshin

#include <stdio.h>
#include <math.h>
#include <algorithm>

int main (int argc, char **argv)
{
  if(argc!=2)  {printf("Usage: prime N\n  Prints prime number higher or equal to N\n"); return 0;}
  unsigned long long N, N0;
  sscanf (argv[1], "%llu", &N);  N0=N;
  unsigned m = std::min((unsigned long long)(sqrt(N))+10, N);

Bulat-Ziganshin

C:\!FreeArc\public\FARSH\SMHasher>a xxh64
-------------------------------------------------------------------------------
--- Testing XXH64 (xxHash, 64-bit result)                             --- Testing XXH64 (xxHash, 64-bit result)

[[[ Speed Tests ]]]                                                   [[[ Speed Tests ]]]

Bulk speed test - 262144-byte keys                                    Bulk speed test - 262144-byte keys
Alignment  0 -  4.441 bytes/cycle - 12706.75 MiB/sec @ 3 ghz          Alignment  0 -  3.516 bytes/cycle - 10058.15 MiB/sec @ 3 ghz
Alignment  1 -  4.408 bytes/cycle - 12610.07 MiB/sec @ 3 ghz          Alignment  1 -  4.390 bytes/cycle - 12559.72 MiB/sec @ 3 ghz

Bulat-Ziganshin

template< int Mode=0 >
struct MTF {

  enum{ CNUM=256 };
  typedef short ranktypeF;
  typedef byte  ranktypeB;

  ranktypeF RankF[CNUM]; 
  ranktypeB RankB[CNUM]; 

Bulat-Ziganshin

/*
 * srcoder.c for the OpenBWT project
 * Copyright (c) 2008-2010 Yuta Mori. All Rights Reserved.
 *
 * Permission is hereby granted, free of charge, to any person
 * obtaining a copy of this software and associated documentation
 * files (the "Software"), to deal in the Software without
 * restriction, including without limitation the rights to use,
 * copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the

Bulat-Ziganshin

#include<stdio.h>
#include<stdlib.h>
#include <cuda.h>
#include<omp.h>
#include <helper_functions.h>
#include <helper_cuda.h>
#include <cuda_runtime.h>

void fill_matrix(int *A, int fac, int m, int n)
{

Bulat-Ziganshin

#include<stdio.h>
#include<stdlib.h>
#include <cuda.h>
#include<omp.h>
#include <helper_functions.h>
#include <helper_cuda.h>
#include <cuda_runtime.h>

void fill_matrix(int *A, int fac, int m, int n)
{

Bulat-Ziganshin

#include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include <stdio.h>

#define DATA_SIZE	(1 << 29)
#define DATA_ACCESSES (1 << 8)
#define BLOCK_SIZE 128
#define BLOCKS_COUNT 1024

template<int COUNT, int PAGE_SIZE, typename T>

Bulat-Ziganshin

https://devtalk.nvidia.com/default/topic/933827/cuda-programming-and-performance/fast-256-bin-histogram/
http://www.cse.uconn.edu/~zshi/course/cse5302/ref/chhugani08sorting.pdf
http://link.springer.com/chapter/10.1007/978-3-642-23397-5_16
http://arxiv.org/abs/1008.2849 Faster Radix Sort via Virtual Memory and Write-Combining Jan Wassenberg, Peter Sanders

https://devtalk.nvidia.com/default/topic/378826/cuda-programming-and-performance/my-speedy-sgemm/post/2703033/#2703033
https://devtalk.nvidia.com/default/topic/390366/cuda-programming-and-performance/instruction-latency/post/2768197/#2768197
https://devtalk.nvidia.com/default/topic/913832/cuda-programming-and-performance/sum-reduction-working-in-fermi-kepler-and-maxwell/
https://devtalk.nvidia.com/default/topic/776043/cuda-programming-and-performance/whats-new-in-maxwell-sm_52-gtx-9xx-/1
https://devtalk.nvidia.com/default/topic/690631/cuda-programming-and-performance/so-whats-new-about-maxwell-/post/4305310/#4305310