


Modular arithmetics and NTT (finite field DFT) optimizations
Original question:
I wanted to use NTT for fast squaring (see Fast bignum square computation), but the result is slow even for really big numbers .. more than 12000 bits.
My question is:
- Is there a way to optimize my NTT transform?
I did not mean to speed it by parallelism (threads); this is low-level layer only. - Is there a way to speed up my modular arithmetics?
Code:
//--------------------------------------------------------------------------- class fourier_NTT // Number theoretic transform { public: DWORD r,L,p,N; DWORD W,iW,rN; fourier_NTT(){ r=0; L=0; p=0; W=0; iW=0; rN=0; } // main interface void NTT(DWORD *dst,DWORD *src,DWORD n=0); // DWORD dst[n] = fast NTT(DWORD src[n]) void iNTT(DWORD *dst,DWORD *src,DWORD n=0); // DWORD dst[n] = fast INTT(DWORD src[n]) // Helper functions bool init(DWORD n); // init r,L,p,W,iW,rN void NTT_fast(DWORD *dst,DWORD *src,DWORD n,DWORD w); // DWORD dst[n] = fast NTT(DWORD src[n]) // Only for testing void NTT_slow(DWORD *dst,DWORD *src,DWORD n,DWORD w); // DWORD dst[n] = slow NTT(DWORD src[n]) void iNTT_slow(DWORD *dst,DWORD *src,DWORD n,DWORD w); // DWORD dst[n] = slow INTT(DWORD src[n]) // DWORD arithmetics DWORD shl(DWORD a); DWORD shr(DWORD a); // Modular arithmetics DWORD mod(DWORD a); DWORD modadd(DWORD a,DWORD b); DWORD modsub(DWORD a,DWORD b); DWORD modmul(DWORD a,DWORD b); DWORD modpow(DWORD a,DWORD b); }; //--------------------------------------------------------------------------- void fourier_NTT:: NTT(DWORD *dst,DWORD *src,DWORD n) { if (n>0) init(n); NTT_fast(dst,src,N,W); // NTT_slow(dst,src,N,W); } //--------------------------------------------------------------------------- void fourier_NTT::INTT(DWORD *dst,DWORD *src,DWORD n) { if (n>0) init(n); NTT_fast(dst,src,N,iW); for (DWORD i=0;i<n dst intt_slow bool fourier_ntt::init n p else ntt overflow can ocur r="2;" if>0x10000000)) { r=0; L=0; p=0; W=0; iW=0; rN=0; N=0; return false; } L=0x30000000/n; // 32:30 bit best for unsigned 32 bit // r=2; p=0x78000001; if ((n0x04000000)) { r=0; L=0; p=0; W=0; iW=0; rN=0; N=0; return false; } L=0x3c000000/n; // 31:27 bit best for signed 32 bit // r=2; p=0x00010001; if ((n0x00000020)) { r=0; L=0; p=0; W=0; iW=0; rN=0; N=0; return false; } L=0x00000020/n; // 17:16 bit best for 16 bit // r=2; p=0x0a000001; if ((n0x01000000)) { r=0; L=0; p=0; W=0; iW=0; rN=0; N=0; return false; } L=0x01000000/n; // 28:25 bit N=n; // size of vectors [DWORDs] W=modpow(r, L); // Wn for NTT iW=modpow(r,p-1-L); // Wn for INTT rN=modpow(n,p-2 ); // scale for INTT return true; } //--------------------------------------------------------------------------- void fourier_NTT:: NTT_fast(DWORD *dst,DWORD *src,DWORD n,DWORD w) { if (n>1,w2=modmul(w,w); // reorder even,odd for (i=0,j=0;i<n2 dst for j="1;i<n" recursion ntt_fast even odd restore results a0="src[i];" a1="modmul(src[j],w2);" void fourier_ntt:: ntt_slow n w dword i a="0;" wi="modmul(wi,wj);" wj="modmul(wj,w);" fourier_ntt::intt_slow fourier_ntt::shl return fourier_ntt::shr>>1)&0x7FFFFFFF; } //--------------------------------------------------------------------------- DWORD fourier_NTT::mod(DWORD a) { DWORD bb;</n2></n>
The above is the detailed content of How Can I Optimize My Number Theoretic Transform (NTT) and Modular Arithmetic for Faster Big Number Squaring?. For more information, please follow other related articles on the PHP Chinese website!

This article details C function return types, encompassing basic (int, float, char, etc.), derived (arrays, pointers, structs), and void types. The compiler determines the return type via the function declaration and the return statement, enforcing

Gulc is a high-performance C library prioritizing minimal overhead, aggressive inlining, and compiler optimization. Ideal for performance-critical applications like high-frequency trading and embedded systems, its design emphasizes simplicity, modul

This article explains C function declaration vs. definition, argument passing (by value and by pointer), return values, and common pitfalls like memory leaks and type mismatches. It emphasizes the importance of declarations for modularity and provi

This article details C functions for string case conversion. It explains using toupper() and tolower() from ctype.h, iterating through strings, and handling null terminators. Common pitfalls like forgetting ctype.h and modifying string literals are

This article examines C function return value storage. Small return values are typically stored in registers for speed; larger values may use pointers to memory (stack or heap), impacting lifetime and requiring manual memory management. Directly acc

This article analyzes the multifaceted uses of the adjective "distinct," exploring its grammatical functions, common phrases (e.g., "distinct from," "distinctly different"), and nuanced application in formal vs. informal

This article explains the C Standard Template Library (STL), focusing on its core components: containers, iterators, algorithms, and functors. It details how these interact to enable generic programming, improving code efficiency and readability t

This article details efficient STL algorithm usage in C . It emphasizes data structure choice (vectors vs. lists), algorithm complexity analysis (e.g., std::sort vs. std::partial_sort), iterator usage, and parallel execution. Common pitfalls like


Hot AI Tools

Undresser.AI Undress
AI-powered app for creating realistic nude photos

AI Clothes Remover
Online AI tool for removing clothes from photos.

Undress AI Tool
Undress images for free

Clothoff.io
AI clothes remover

AI Hentai Generator
Generate AI Hentai for free.

Hot Article

Hot Tools

mPDF
mPDF is a PHP library that can generate PDF files from UTF-8 encoded HTML. The original author, Ian Back, wrote mPDF to output PDF files "on the fly" from his website and handle different languages. It is slower than original scripts like HTML2FPDF and produces larger files when using Unicode fonts, but supports CSS styles etc. and has a lot of enhancements. Supports almost all languages, including RTL (Arabic and Hebrew) and CJK (Chinese, Japanese and Korean). Supports nested block-level elements (such as P, DIV),

SublimeText3 Linux new version
SublimeText3 Linux latest version

Notepad++7.3.1
Easy-to-use and free code editor

PhpStorm Mac version
The latest (2018.2.1) professional PHP integrated development tool

Dreamweaver CS6
Visual web development tools
