直接上代码就好了，具体的介绍见 ouuan 的介绍 。有什么不会的都可以到这里来了解。

但是由于本题值域是 long long ，和 int 能压 8 位相比只能压 4 位，所以常数优化没有想象中的快。用 __m512i 类型压 8 位也没有速度上的改善。

然后很显然，想在 acwing 这种性能不太行的机子上过，必然是要火车头优化拉满的。

#pragma GCC optimize(3)
#pragma GCC optimize("Ofast")
#pragma GCC optimize("inline")
#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("inline-functions")
#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("inline-small-functions")
#pragma GCC optimize("-finline-small-functions")
#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("inline-functions-called-once")
#pragma GCC optimize("-fdelete-null-pointer-checks")
#include <stdio.h>
#include <immintrin.h>
#define getchar getchar_unlocked
#define putchar putchar_unlocked
#pragma GCC target("sse,sse2,sse3,ssse3,sse4.1,sse4.2,avx,avx2,popcnt,tune=native")
const int N = 100010;
typedef long long i64;
i64 rd()
{
    i64 k = 0, f = 1;
    char s = getchar();
    while (s < '0' || s > '9')
    {
        if (s == '-')
            f = 0;
        s = getchar();
    }
    while (s >= '0' && s <= '9')
    {
        k = (k << 1) + (k << 3) + (s ^ '0');
        s = getchar();
    }
    return f ? k : -k;
}
void wr(i64 x)
{
    if (x < 0)
        putchar('-'), x = -x;
    if (x > 9)
        wr(x / 10);
    putchar((x % 10) ^ '0');
}
int rd_op()
{
    char c = getchar();
    while (c < 'A' || c > 'Z')
        c = getchar();
    return c == 'C';
}
int n, m;
int op, l, r;
// 0-indexed
i64* a;
__m256i A[N >> 2];
// [l, r)
void modify_add(int l, int r, i64 x)
{
    while ((l & 3) && (l < r))
        a[l++] += x;
    if (!(l ^ r))
        return;
    while ((r & 3))
        a[--r] += x;
    if (!(l ^ r))
        return;
    __m256i t = _mm256_set1_epi64x(x);
    for (l >>= 2, r >>= 2; l < r; ++l) 
        A[l] = _mm256_add_epi64(A[l], t);
}
i64 query(int l, int r)
{
    i64 ret = 0;
    while ((l & 3) && (l < r))
        ret += a[l++];
    if (!(l ^ r))
        return ret;
    while ((r & 3))
        ret += a[--r];
    if (!(l ^ r))
        return ret;
    __m256i ans = _mm256_set1_epi32(0);
    for (l >>= 2, r >>= 2; l < r; ++l) 
        ans = _mm256_add_epi64(ans, A[l]);
    for (int i = 0; i < 4; ++i)
        ret += ans[i];
    return ret;
}
int main()
{
    n = rd(), m = rd(), a = (i64*)&A;
    for (int i = 0; i < n; ++i)
        a[i] = rd();
    while (m--)
    {
        op = rd_op(), l = rd() - 1, r = rd();
        if (op & 1)
            modify_add(l, r, rd());
        else
            wr(query(l, r)), putchar('\n');
    }
}