3

我尝试编译使用 SSE2 的英特尔提供的随机数生成器函数。如果我尝试编译以下代码：

/////////////////////////////////////////////////////////////////////////////
// The Software is provided "AS IS" and possibly with faults. 
// Intel disclaims any and all warranties and guarantees, express, implied or
// otherwise, arising, with respect to the software delivered hereunder,
// including but not limited to the warranty of merchantability, the warranty
// of fitness for a particular purpose, and any warranty of non-infringement
// of the intellectual property rights of any third party.
// Intel neither assumes nor authorizes any person to assume for it any other
// liability. Customer will use the software at its own risk. Intel will not
// be liable to customer for any direct or indirect damages incurred in using
// the software. In no event will Intel be liable for loss of profits, loss of
// use, loss of data, business interruption, nor for punitive, incidental,
// consequential, or special damages of any kind, even if advised of
// the possibility of such damages.
//
// Copyright (c) 2003 Intel Corporation
//
// Third-party brands and names are the property of their respective owners
//
///////////////////////////////////////////////////////////////////////////
// Random Number Generation for SSE / SSE2
// Source File
// Version 0.1
// Author Kipp Owens, Rajiv Parikh
////////////////////////////////////////////////////////////////////////



#ifndef RAND_SSE_H
#define RAND_SSE_H
#include "emmintrin.h"
#include <time.h>

//#define COMPATABILITY
//define this if you wish to return values similar to the standard rand();


void srand_sse( unsigned int seed );
void rand_sse( unsigned int* );

__declspec( align(16) ) static __m128i cur_seed;

void srand_sse( unsigned int seed ) {
    cur_seed = _mm_set_epi32( seed, seed+1, seed, seed+1 );
}

inline void rand_sse( unsigned int* result ) {
    __declspec( align(16) ) __m128i cur_seed_split;
    __declspec( align(16) ) __m128i multiplier;
    __declspec( align(16) ) __m128i adder;
    __declspec( align(16) ) __m128i mod_mask;
    __declspec( align(16) ) __m128i sra_mask;
    __declspec( align(16) ) __m128i sseresult;
    __declspec( align(16) ) static const unsigned int mult[4] = { 214013, 17405, 214013, 69069 };
    __declspec( align(16) ) static const unsigned int gadd[4] = { 2531011, 10395331, 13737667, 1 };
    __declspec( align(16) ) static const unsigned int mask[4] = { 0xFFFFFFFF, 0, 0xFFFFFFFF, 0 };
    __declspec( align(16) ) static const unsigned int masklo[4] = { 0x00007FFF, 0x00007FFF, 0x00007FFF, 0x00007FFF };

    adder = _mm_load_si128( (__m128i*) gadd);
    multiplier = _mm_load_si128( (__m128i*) mult);
    mod_mask = _mm_load_si128( (__m128i*) mask);
    sra_mask = _mm_load_si128( (__m128i*) masklo);
    cur_seed_split = _mm_shuffle_epi32( cur_seed, _MM_SHUFFLE( 2, 3, 0, 1 ) );

    cur_seed = _mm_mul_epu32( cur_seed, multiplier );
    multiplier = _mm_shuffle_epi32( multiplier, _MM_SHUFFLE( 2, 3, 0, 1 ) );
    cur_seed_split = _mm_mul_epu32( cur_seed_split, multiplier );

    cur_seed = _mm_and_si128( cur_seed, mod_mask);
    cur_seed_split = _mm_and_si128( cur_seed_split, mod_mask );
    cur_seed_split = _mm_shuffle_epi32( cur_seed_split, _MM_SHUFFLE( 2, 3, 0, 1 ) );
    cur_seed = _mm_or_si128( cur_seed, cur_seed_split );
    cur_seed = _mm_add_epi32( cur_seed, adder);

    #ifdef COMPATABILITY

    // Add the lines below if you wish to reduce your results to 16-bit vals...
    sseresult = _mm_srai_epi32( cur_seed, 16);
    sseresult = _mm_and_si128( sseresult, sra_mask );
    _mm_storeu_si128( (__m128i*) result, sseresult );
    return;

    #endif

    _mm_storeu_si128( (__m128i*) result, cur_seed);
    return;
}

#endif

int main() {
    srand_see(time(0));

    return 0;
}

我得到错误：

rand_sse.cpp:40:11: error: expected constructor, destructor, or type conversion before ‘(’ token
rand_sse.cpp: In function ‘void srand_sse(unsigned int)’:
rand_sse.cpp:43:5: error: ‘cur_seed’ was not declared in this scope
rand_sse.cpp: In function ‘void rand_sse(unsigned int*)’:
rand_sse.cpp:47:25: error: ‘align’ was not declared in this scope
rand_sse.cpp:47:27: error: ‘__declspec’ was not declared in this scope
rand_sse.cpp:47:29: error: expected ‘;’ before ‘__m128i’
rand_sse.cpp:48:29: error: expected ‘;’ before ‘__m128i’
rand_sse.cpp:49:29: error: expected ‘;’ before ‘__m128i’
rand_sse.cpp:50:29: error: expected ‘;’ before ‘__m128i’
rand_sse.cpp:51:29: error: expected ‘;’ before ‘__m128i’
rand_sse.cpp:52:29: error: expected ‘;’ before ‘__m128i’
rand_sse.cpp:53:29: error: expected ‘;’ before ‘static’
rand_sse.cpp:54:29: error: expected ‘;’ before ‘static’
rand_sse.cpp:55:29: error: expected ‘;’ before ‘static’
rand_sse.cpp:56:29: error: expected ‘;’ before ‘static’
rand_sse.cpp:58:5: error: ‘adder’ was not declared in this scope
rand_sse.cpp:58:40: error: ‘gadd’ was not declared in this scope
rand_sse.cpp:59:5: error: ‘multiplier’ was not declared in this scope
rand_sse.cpp:59:45: error: ‘mult’ was not declared in this scope
rand_sse.cpp:60:5: error: ‘mod_mask’ was not declared in this scope
rand_sse.cpp:60:43: error: ‘mask’ was not declared in this scope
rand_sse.cpp:61:5: error: ‘sra_mask’ was not declared in this scope
rand_sse.cpp:61:43: error: ‘masklo’ was not declared in this scope
rand_sse.cpp:62:5: error: ‘cur_seed_split’ was not declared in this scope
rand_sse.cpp:62:41: error: ‘cur_seed’ was not declared in this scope

代码取自：Intel 它是在 Ubuntu 64bit 和 GCC 4.6.3 上编译的，使用以下命令：

g++ rand_sse.cpp -O2 -march=core2 -msse2 -o rand_sse

我错过了什么？关于我做错了什么的任何建议都会非常有帮助。谢谢！

4

1 回答 1

10

只需卸下__declspec (align(16))零件。类型__m128等已经以正确的对齐方式声明。

PS。好的，还有一些数组，GCC 的方法是__attribute__ ((aligned(16))).

如果没有该对齐属性，它会正常工作，但效率会降低。

于 2012-11-29T14:47:14.363 回答