代码

// TEST
#pragma GCC optimize(3)
#pragma GCC target("avx")
#pragma GCC optimize("Ofast")

#pragma GCC optimize("-fgcse")
#pragma GCC optimize("-fgcse-lm")
#pragma GCC optimize("-fipa-sra")
#pragma GCC optimize("-ftree-pre")
#pragma GCC optimize("-ftree-vrp")
#pragma GCC optimize("-fpeephole2")
#pragma GCC optimize("-ffast-math")
#pragma GCC optimize("-fsched-spec")
#pragma GCC optimize("unroll-loops")
#pragma GCC optimize("-falign-jumps")
#pragma GCC optimize("-falign-loops")
#pragma GCC optimize("-falign-labels")
#pragma GCC optimize("-fdevirtualize")
#pragma GCC optimize("-fcaller-saves")
#pragma GCC optimize("-fcrossjumping")
#pragma GCC optimize("-fthread-jumps")
#pragma GCC optimize("-funroll-loops")
#pragma GCC optimize("-fwhole-program")
#pragma GCC optimize("-freorder-blocks")
#pragma GCC optimize("-fschedule-insns")

#pragma GCC optimize("-ftree-tail-merge")
#pragma GCC optimize("-fschedule-insns2")
#pragma GCC optimize("-fstrict-aliasing")
#pragma GCC optimize("-fstrict-overflow")
#pragma GCC optimize("-falign-functions")
#pragma GCC optimize("-fcse-skip-blocks")
#pragma GCC optimize("-fcse-follow-jumps")
#pragma GCC optimize("-fsched-interblock")
#pragma GCC optimize("-fpartial-inlining")
#pragma GCC optimize("no-stack-protector")
#pragma GCC optimize("-freorder-functions")
#pragma GCC optimize("-findirect-inlining")
#pragma GCC optimize("-fhoist-adjacent-loads")
#pragma GCC optimize("-frerun-cse-after-loop")


#pragma GCC optimize("-ftree-switch-conversion")
#pragma GCC optimize("-foptimize-sibling-calls")
#pragma GCC optimize("-fexpensive-optimizations")
#pragma GCC optimize("-funsafe-loop-optimizations")

#pragma GCC optimize("-fdelete-null-pointer-checks")
 void sort(unsigned *a, int n)  {
#define N 100000000
#define D 256
#define D1 255
#define cal(w,w2,tw,op) p=w2-1;for(i=0;i<D;++i)rs[i]=p,p+=tw[i];for(i=0;i<N;i+=8){	p=w+i;	*++rs[p[0]op]=p[0],	*++rs[p[1]op]=p[1],	*++rs[p[2]op]=p[2],	*++rs[p[3]op]=p[3],	*++rs[p[4]op]=p[4],	*++rs[p[5]op]=p[5],	*++rs[p[6]op]=p[6],	*++rs[p[7]op]=p[7];}
unsigned b[N],*rs[D],t0[D],t1[D],t2[D],t3[D];
unsigned*p,i,x;
for(i=0;i<D;++i){
	t0[i]=0;
	t1[i]=0;
	t2[i]=0;
	t3[i]=0;
}
for(i=0;i<N;){
#define A x=a[i],++t0[x&D1],++t1[x>>8&D1],++t2[x>>16&D1],++t3[x>>24],++i;
A A A A
#undef A
}
cal(a,b,t0,&D1);
cal(b,a,t1,>>8&D1);
cal(a,b,t2,>>16&D1);
cal(b,a,t3,>>24);
}

评测结果