// what is matter? never mind. 
#pragma GCC optimize("Ofast")
#pragma GCC optimize("unroll-loops")
//#pragma GCC target("sse,sse2,sse3,sse4,popcnt,abm,mmx,avx,avx2") 
#include<bits/stdc++.h>
#define For(i,a,b) for(int i=(a);i<=(b);++i)
#define Rep(i,a,b) for(int i=(a);i>=(b);--i)
#define ll long long
//#define int long long
#define ull unsigned long long
using namespace std;
inline int read()
{
    char c=getchar();int x=0;bool f=0;
    for(;!isdigit(c);c=getchar())f^=!(c^45);
    for(;isdigit(c);c=getchar())x=(x<<1)+(x<<3)+(c^48);
    if(f)x=-x;return x;
}

#define fi first
#define se second
#define pb push_back
#define mkp make_pair
typedef pair<int,int>pii;
typedef vector<int>vi;

#define maxn 300005
#define inf 0x3f3f3f3f

#define N 505

mt19937_64 rnd(time(0));
int n,n1,n2,cnt[N],a[N][N],id[N];
bool vis[N*N];

vector<vi>res;

vector<pii>g[N*2];
int tol[N],tor[N],st[N*30],tp;

vi cir;
void euler(int u){
	while(g[u].size()){
		auto [v,w]=g[u].back(); g[u].pop_back();
		if(vis[w])continue;
		vis[w]=1,euler(v),cir.pb(w);
	}
}
vector<vector<vector<int>>>divide(vector<vi>e){
	int n=e.size(),d=e[0].size();
	For(i,0,n-1)For(j,0,d-1){
		int v=e[i][j]+n,w=i*d+j;
		g[i].pb(mkp(v,w));
		g[v].pb(mkp(i,w));
		vis[w]=0;
	}
	cir.clear();
	For(i,0,n*2-1)if(g[i].size())euler(i);
	assert(cir.size()==n*d);
	vector<vector<vector<int>>>es(2,vector<vi>(n));
	For(i,0,n*d-1){
		int u=cir[i]/d,j=cir[i]%d;
		es[i%2][u].pb(e[u][j]);
	}
	return es;
}
void color(vector<vi>e){
	int n=e.size(),d=e[0].size();
//	cout<<"color "<<n<<" "<<d<<"\n";
//	For(i,0,n-1){
//		for(int x:e[i])cout<<x<<" ";
//		cout<<"\n";
//	}puts("----");
	if(d==1){
		vi o;
		For(i,0,n-1)o.pb(e[i][0]);
		res.pb(o);
		return;
	}
	if(d%2==0){
		auto t=divide(e);
		color(t[0]),color(t[1]);
		return;
	}
	For(i,0,n-1)id[i]=i,tol[i]=tor[i]=-1,vis[i]=0;
	shuffle(id,id+n,rnd);
	For(_,0,n-1){
		int u=id[_];
		tp=0;
		int j=u;
		while(j!=-1){
			int t=e[j][rnd()%d];
			while(t==tor[j])t=e[j][rnd()%d];
			while(vis[t]) vis[st[tp--]]=0;
			vis[t]=1;
			st[++tp]=t;
			j=tol[t];
		}
		while(tp){
			int u=st[tp],lst=st[tp-1]; --tp;
			tor[tol[lst]]=u;
			tol[u]=tol[lst];
			vis[u]=0;
		}
		tor[u]=st[1];
		tol[st[1]]=u;
	}
	For(i,0,n-1)tor[tol[i]]=i;
	vi o;
	For(i,0,n-1)o.pb(tor[i]);
	res.pb(o);
	For(i,0,n-1)e[i].erase(find(e[i].begin(),e[i].end(),tor[i]));
	color(e);
}

void work()
{
	n=read(),n1=read(),n2=read();
	For(i,1,n)cnt[i]=0;
	For(i,1,n1)For(j,1,n2)a[i][j]=read(),cnt[a[i][j]]++;
	vector<vi>es(n);
	For(i,1,n1){
		For(j,1,n)vis[j]=0;
		For(j,1,n2)vis[a[i][j]]=1;
		For(j,1,n)if(!vis[j])es[i-1].pb(j-1);
	}
	For(i,1,n)
		if(cnt[i]<n1+n2-n){
			puts("No");
			return;
		}
	if(n2<n){
		For(i,1,n)id[i]=i;
		For(i,n1+1,n){
			sort(id+1,id+n+1,[&](int x,int y){
				return cnt[x]>cnt[y];
			});
			For(j,1,n-n2) --cnt[id[j]],es[i-1].pb(id[j]-1);
		}
		color(es);
	//	For(i,1,n-n2)For(j,1,n)cout<<res[i-1][j-1]+1<<" \n"[j==n];puts("res1");
		For(i,1,n-n2)For(j,1,n1)a[j][i+n2]=res[i-1][j-1]+1;
		res.clear();
	}
	if(n1<n){
		For(i,0,n-1)es[i].clear();
		For(i,1,n){
			For(j,1,n)vis[j]=0;
			For(j,1,n1)vis[a[j][i]]=1;
			For(j,1,n)if(!vis[j])es[i-1].pb(j-1);
		}
		color(es);
	//	For(i,1,n1)For(j,1,n)cout<<res[i-1][j-1]+1<<" \n"[j==n];puts("res2");
		For(i,1,n-n1)For(j,1,n)a[i+n1][j]=res[i-1][j-1]+1;
		res.clear();
	}
	puts("Yes");
	For(i,1,n){
		For(j,1,n)printf("%d ",a[i][j]);
		puts("");
	}
}

signed main()
{
	int T=read();
	while(T--)work();
	return 0;
}
/*

*/