#include "candies.h"
#include <bits/stdc++.h>
#pragma GCC optimize("O3,unroll-loops")
#pragma GCC target("avx2")
using namespace std;
typedef long long ll;
typedef pair<int,int> pii;
typedef pair<ll,ll> pll;
void debug_out(){cerr << endl;}
template<typename Head, typename... Tail>
void debug_out(Head H, Tail... T){
cerr << H << ' ';
debug_out(T...);
}
#define debug(...) cerr << "(" << #__VA_ARGS__ << "): ", debug_out(__VA_ARGS__)
#define F first
#define S second
#define all(x) x.begin(), x.end()
#define MP(x, y) make_pair(x, y)
const int maxn = 2e5 + 10;
const int S = 2048;
int n, q, a[maxn], c[maxn], l[maxn], r[maxn], v[maxn];
void add1(int l, int r, int x);
void add2(int l, int r, int x);
void add3(int l, int r, int x, int y);
void add4(int l, int r, int x, int y);
asm(R"dard(
.p2align 4
.globl _Z4add1iii
.type _Z4add1iii, @function
_Z4add1iii:
.myLFB9900:
.cfi_startproc
endbr64
pushq %rbp
.cfi_def_cfa_offset 16
.cfi_offset 6, -16
vmovd %edx, %xmm1
movslq %edi, %rcx
movq %rsp, %rbp
.cfi_def_cfa_register 6
pushq %r12
pushq %rbx
andq $-32, %rsp
.cfi_offset 12, -24
.cfi_offset 3, -32
vmovd %xmm1, -4(%rsp)
cmpl %esi, %ecx
jg .myL57
movl %esi, %r11d
movl %esi, %r9d
subl %ecx, %r11d
leal 1(%r11), %ebx
cmpl $6, %r11d
jbe .myL18
movl %ebx, %r12d
movslq %ecx, %rsi
leaq a(%rip), %r8
xorl %eax, %eax
shrl $3, %r12d
salq $2, %rsi
vpbroadcastd %xmm1, %ymm2
leaq c(%rip), %r10
salq $5, %r12
leaq (%r8,%rsi), %rdx
addq %r10, %rsi
leaq -32(%r12), %rdi
shrq $5, %rdi
addq $1, %rdi
andl $7, %edi
je .myL14
cmpq $1, %rdi
je .myL41
cmpq $2, %rdi
je .myL42
cmpq $3, %rdi
je .myL43
cmpq $4, %rdi
je .myL44
cmpq $5, %rdi
je .myL45
cmpq $6, %rdi
jne .myL59
.myL46:
vpaddd (%rdx,%rax), %ymm2, %ymm0
vpminsd (%rsi,%rax), %ymm0, %ymm0
vmovdqu %ymm0, (%rdx,%rax)
addq $32, %rax
.myL45:
vpaddd (%rdx,%rax), %ymm2, %ymm0
vpminsd (%rsi,%rax), %ymm0, %ymm0
vmovdqu %ymm0, (%rdx,%rax)
addq $32, %rax
.myL44:
vpaddd (%rdx,%rax), %ymm2, %ymm0
vpminsd (%rsi,%rax), %ymm0, %ymm0
vmovdqu %ymm0, (%rdx,%rax)
addq $32, %rax
.myL43:
vpaddd (%rdx,%rax), %ymm2, %ymm0
vpminsd (%rsi,%rax), %ymm0, %ymm0
vmovdqu %ymm0, (%rdx,%rax)
addq $32, %rax
.myL42:
vpaddd (%rdx,%rax), %ymm2, %ymm0
vpminsd (%rsi,%rax), %ymm0, %ymm0
vmovdqu %ymm0, (%rdx,%rax)
addq $32, %rax
.myL41:
vpaddd (%rdx,%rax), %ymm2, %ymm0
vpminsd (%rsi,%rax), %ymm0, %ymm0
vmovdqu %ymm0, (%rdx,%rax)
addq $32, %rax
cmpq %r12, %rax
je .myL55
.myL14:
vpaddd (%rdx,%rax), %ymm2, %ymm0
vpminsd (%rsi,%rax), %ymm0, %ymm0
leaq 32(%rax), %rdi
vmovdqu %ymm0, (%rdx,%rax)
vpaddd 32(%rdx,%rax), %ymm2, %ymm0
vpminsd 32(%rsi,%rax), %ymm0, %ymm0
vmovdqu %ymm0, 32(%rdx,%rax)
vpaddd 64(%rdx,%rax), %ymm2, %ymm0
vpminsd 64(%rsi,%rax), %ymm0, %ymm0
vmovdqu %ymm0, 64(%rdx,%rax)
vpaddd 64(%rdx,%rdi), %ymm2, %ymm0
vpminsd 64(%rsi,%rdi), %ymm0, %ymm0
leaq 224(%rdi), %rax
vmovdqu %ymm0, 64(%rdx,%rdi)
vpaddd 96(%rdx,%rdi), %ymm2, %ymm0
vpminsd 96(%rsi,%rdi), %ymm0, %ymm0
vmovdqu %ymm0, 96(%rdx,%rdi)
vpaddd 128(%rdx,%rdi), %ymm2, %ymm0
vpminsd 128(%rsi,%rdi), %ymm0, %ymm0
vmovdqu %ymm0, 128(%rdx,%rdi)
vpaddd 160(%rdx,%rdi), %ymm2, %ymm0
vpminsd 160(%rsi,%rdi), %ymm0, %ymm0
vmovdqu %ymm0, 160(%rdx,%rdi)
vpaddd 192(%rdx,%rdi), %ymm2, %ymm0
vpminsd 192(%rsi,%rdi), %ymm0, %ymm0
vmovdqu %ymm0, 192(%rdx,%rdi)
cmpq %r12, %rax
jne .myL14
.myL55:
movl %ebx, %edx
andl $-8, %edx
leal (%rdx,%rcx), %eax
cmpl %edx, %ebx
je .myL60
vzeroupper
.myL13:
subl %edx, %r11d
leal 1(%r11), %esi
cmpl $2, %r11d
jbe .myL16
addq %rdx, %rcx
vbroadcastss -4(%rsp), %xmm0
leaq (%r8,%rcx,4), %rdx
vpaddd (%rdx), %xmm0, %xmm0
vpminsd (%r10,%rcx,4), %xmm0, %xmm0
vmovdqu %xmm0, (%rdx)
movl %esi, %edx
andl $-4, %edx
addl %edx, %eax
cmpl %edx, %esi
je .myL57
.myL16:
movslq %eax, %rdx
vmovd (%r8,%rdx,4), %xmm0
vmovd (%r10,%rdx,4), %xmm2
vpaddd %xmm0, %xmm1, %xmm0
vpminsd %xmm2, %xmm0, %xmm0
vmovd %xmm0, (%r8,%rdx,4)
leal 1(%rax), %edx
cmpl %r9d, %edx
jg .myL57
movslq %edx, %rdx
addl $2, %eax
vmovd (%r8,%rdx,4), %xmm0
vmovd (%r10,%rdx,4), %xmm2
vpaddd %xmm0, %xmm1, %xmm0
vpminsd %xmm2, %xmm0, %xmm0
vmovd %xmm0, (%r8,%rdx,4)
cmpl %eax, %r9d
jl .myL57
cltq
vmovd (%r8,%rax,4), %xmm0
vpaddd %xmm0, %xmm1, %xmm1
vmovd (%r10,%rax,4), %xmm0
vpminsd %xmm0, %xmm1, %xmm1
vmovd %xmm1, (%r8,%rax,4)
.myL57:
leaq -16(%rbp), %rsp
popq %rbx
popq %r12
popq %rbp
.cfi_remember_state
.cfi_def_cfa 7, 8
ret
.p2align 4,,10
.p2align 3
.myL59:
.cfi_restore_state
vpaddd (%rdx), %ymm2, %ymm0
vpminsd (%rsi), %ymm0, %ymm0
movl $32, %eax
vmovdqu %ymm0, (%rdx)
jmp .myL46
.p2align 4,,10
.p2align 3
.myL60:
vzeroupper
leaq -16(%rbp), %rsp
popq %rbx
popq %r12
popq %rbp
.cfi_remember_state
.cfi_def_cfa 7, 8
ret
.myL18:
.cfi_restore_state
movl %ecx, %eax
xorl %edx, %edx
leaq a(%rip), %r8
leaq c(%rip), %r10
jmp .myL13
.cfi_endproc
.myLFE9900:
.size _Z4add1iii, .-_Z4add1iii
.p2align 4
.globl _Z4add2iii
.type _Z4add2iii, @function
_Z4add2iii:
.myLFB9901:
.cfi_startproc
endbr64
pushq %rbp
.cfi_def_cfa_offset 16
.cfi_offset 6, -16
vmovd %edx, %xmm1
movslq %edi, %rcx
movq %rsp, %rbp
.cfi_def_cfa_register 6
andq $-32, %rsp
vmovd %xmm1, -4(%rsp)
cmpl %esi, %ecx
jg .myL106
movl %esi, %r9d
movl %esi, %edi
subl %ecx, %r9d
leal 1(%r9), %r10d
cmpl $6, %r9d
jbe .myL68
movl %r10d, %edx
vpbroadcastd %xmm1, %ymm3
vpxor %xmm2, %xmm2, %xmm2
movslq %ecx, %rax
shrl $3, %edx
leaq a(%rip), %r8
leal -1(%rdx), %esi
leaq (%r8,%rax,4), %rax
salq $5, %rsi
leaq 32(%rax), %rdx
leaq (%rsi,%rdx), %r11
shrq $5, %rsi
andl $7, %esi
je .myL64
vpaddd (%rax), %ymm3, %ymm0
vpmaxsd %ymm2, %ymm0, %ymm0
vmovdqu %ymm0, (%rax)
movq %rdx, %rax
addq $32, %rdx
cmpq $1, %rsi
je .myL64
cmpq $2, %rsi
je .myL91
cmpq $3, %rsi
je .myL92
cmpq $4, %rsi
je .myL93
cmpq $5, %rsi
je .myL94
cmpq $6, %rsi
jne .myL108
.myL95:
vpaddd (%rax), %ymm3, %ymm0
vpmaxsd %ymm2, %ymm0, %ymm0
vmovdqu %ymm0, (%rax)
movq %rdx, %rax
addq $32, %rdx
.myL94:
vpaddd (%rax), %ymm3, %ymm0
vpmaxsd %ymm2, %ymm0, %ymm0
vmovdqu %ymm0, (%rax)
movq %rdx, %rax
addq $32, %rdx
.myL93:
vpaddd (%rax), %ymm3, %ymm0
vpmaxsd %ymm2, %ymm0, %ymm0
vmovdqu %ymm0, (%rax)
movq %rdx, %rax
addq $32, %rdx
.myL92:
vpaddd (%rax), %ymm3, %ymm0
vpmaxsd %ymm2, %ymm0, %ymm0
vmovdqu %ymm0, (%rax)
movq %rdx, %rax
addq $32, %rdx
.myL91:
vpaddd (%rax), %ymm3, %ymm0
vpmaxsd %ymm2, %ymm0, %ymm0
vmovdqu %ymm0, (%rax)
movq %rdx, %rax
addq $32, %rdx
jmp .myL64
.p2align 4,,10
.p2align 3
.myL109:
vpaddd (%rdx), %ymm3, %ymm0
leaq 224(%rdx), %rax
addq $256, %rdx
vpmaxsd %ymm2, %ymm0, %ymm0
vmovdqu %ymm0, -256(%rdx)
vpaddd -224(%rdx), %ymm3, %ymm0
vpmaxsd %ymm2, %ymm0, %ymm0
vmovdqu %ymm0, -224(%rdx)
vpaddd -192(%rdx), %ymm3, %ymm0
vpmaxsd %ymm2, %ymm0, %ymm0
vmovdqu %ymm0, -192(%rdx)
vpaddd -160(%rdx), %ymm3, %ymm0
vpmaxsd %ymm2, %ymm0, %ymm0
vmovdqu %ymm0, -160(%rdx)
vpaddd -128(%rdx), %ymm3, %ymm0
vpmaxsd %ymm2, %ymm0, %ymm0
vmovdqu %ymm0, -128(%rdx)
vpaddd -96(%rdx), %ymm3, %ymm0
vpmaxsd %ymm2, %ymm0, %ymm0
vmovdqu %ymm0, -96(%rdx)
vpaddd -64(%rdx), %ymm3, %ymm0
vpmaxsd %ymm2, %ymm0, %ymm0
vmovdqu %ymm0, -64(%rdx)
.myL64:
vpaddd (%rax), %ymm3, %ymm0
vpmaxsd %ymm2, %ymm0, %ymm0
vmovdqu %ymm0, (%rax)
cmpq %r11, %rdx
jne .myL109
movl %r10d, %edx
andl $-8, %edx
leal (%rdx,%rcx), %eax
cmpl %edx, %r10d
je .myL110
vzeroupper
.myL63:
subl %edx, %r9d
leal 1(%r9), %esi
cmpl $2, %r9d
jbe .myL66
addq %rdx, %rcx
vbroadcastss -4(%rsp), %xmm0
vpxor %xmm2, %xmm2, %xmm2
leaq (%r8,%rcx,4), %rdx
vpaddd (%rdx), %xmm0, %xmm0
vpmaxsd %xmm2, %xmm0, %xmm0
vmovdqu %xmm0, (%rdx)
movl %esi, %edx
andl $-4, %edx
addl %edx, %eax
cmpl %edx, %esi
je .myL106
.myL66:
movslq %eax, %rdx
vpxor %xmm2, %xmm2, %xmm2
vmovd (%r8,%rdx,4), %xmm0
vpaddd %xmm0, %xmm1, %xmm0
vpmaxsd %xmm2, %xmm0, %xmm0
vmovd %xmm0, (%r8,%rdx,4)
leal 1(%rax), %edx
cmpl %edx, %edi
jl .myL106
movslq %edx, %rdx
addl $2, %eax
vpinsrd $0, (%r8,%rdx,4), %xmm2, %xmm0
vpaddd %xmm0, %xmm1, %xmm0
vpmaxsd %xmm2, %xmm0, %xmm0
vmovd %xmm0, (%r8,%rdx,4)
cmpl %eax, %edi
jl .myL106
cltq
vpinsrd $0, (%r8,%rax,4), %xmm2, %xmm0
vpaddd %xmm0, %xmm1, %xmm1
vpmaxsd %xmm2, %xmm1, %xmm1
vmovd %xmm1, (%r8,%rax,4)
.myL106:
leave
.cfi_remember_state
.cfi_def_cfa 7, 8
ret
.p2align 4,,10
.p2align 3
.myL108:
.cfi_restore_state
vpaddd (%rax), %ymm3, %ymm0
vpmaxsd %ymm2, %ymm0, %ymm0
vmovdqu %ymm0, (%rax)
movq %rdx, %rax
addq $32, %rdx
jmp .myL95
.p2align 4,,10
.p2align 3
.myL110:
vzeroupper
leave
.cfi_remember_state
.cfi_def_cfa 7, 8
ret
.myL68:
.cfi_restore_state
movl %ecx, %eax
xorl %edx, %edx
leaq a(%rip), %r8
jmp .myL63
.cfi_endproc
.myLFE9901:
.size _Z4add2iii, .-_Z4add2iii
.p2align 4
.globl _Z4add3iiii
.type _Z4add3iiii, @function
_Z4add3iiii:
.myLFB9902:
.cfi_startproc
endbr64
pushq %rbp
.cfi_def_cfa_offset 16
.cfi_offset 6, -16
vmovd %edx, %xmm1
vmovd %ecx, %xmm2
movq %rsp, %rbp
.cfi_def_cfa_register 6
pushq %r12
pushq %rbx
andq $-32, %rsp
.cfi_offset 12, -24
.cfi_offset 3, -32
vmovd %xmm1, -4(%rsp)
vmovd %xmm2, -8(%rsp)
cmpl %esi, %edi
jg .myL157
movl %esi, %r11d
movl %esi, %r9d
subl %edi, %r11d
leal 1(%r11), %ebx
cmpl $6, %r11d
jbe .myL118
movl %ebx, %r12d
movslq %edi, %rcx
leaq a(%rip), %r8
xorl %eax, %eax
shrl $3, %r12d
salq $2, %rcx
vpbroadcastd %xmm1, %ymm5
leaq c(%rip), %r10
salq $5, %r12
leaq (%r8,%rcx), %rdx
vpbroadcastd %xmm2, %ymm4
addq %r10, %rcx
leaq -32(%r12), %rsi
vpxor %xmm3, %xmm3, %xmm3
shrq $5, %rsi
addq $1, %rsi
andl $7, %esi
je .myL114
cmpq $1, %rsi
je .myL141
cmpq $2, %rsi
je .myL142
cmpq $3, %rsi
je .myL143
cmpq $4, %rsi
je .myL144
cmpq $5, %rsi
je .myL145
cmpq $6, %rsi
jne .myL159
.myL146:
vpaddd (%rdx,%rax), %ymm5, %ymm0
vpminsd (%rcx,%rax), %ymm0, %ymm0
vpaddd %ymm4, %ymm0, %ymm0
vpmaxsd %ymm3, %ymm0, %ymm0
vmovdqu %ymm0, (%rdx,%rax)
addq $32, %rax
.myL145:
vpaddd (%rdx,%rax), %ymm5, %ymm0
vpminsd (%rcx,%rax), %ymm0, %ymm0
vpaddd %ymm4, %ymm0, %ymm0
vpmaxsd %ymm3, %ymm0, %ymm0
vmovdqu %ymm0, (%rdx,%rax)
addq $32, %rax
.myL144:
vpaddd (%rdx,%rax), %ymm5, %ymm0
vpminsd (%rcx,%rax), %ymm0, %ymm0
vpaddd %ymm4, %ymm0, %ymm0
vpmaxsd %ymm3, %ymm0, %ymm0
vmovdqu %ymm0, (%rdx,%rax)
addq $32, %rax
.myL143:
vpaddd (%rdx,%rax), %ymm5, %ymm0
vpminsd (%rcx,%rax), %ymm0, %ymm0
vpaddd %ymm4, %ymm0, %ymm0
vpmaxsd %ymm3, %ymm0, %ymm0
vmovdqu %ymm0, (%rdx,%rax)
addq $32, %rax
.myL142:
vpaddd (%rdx,%rax), %ymm5, %ymm0
vpminsd (%rcx,%rax), %ymm0, %ymm0
vpaddd %ymm4, %ymm0, %ymm0
vpmaxsd %ymm3, %ymm0, %ymm0
vmovdqu %ymm0, (%rdx,%rax)
addq $32, %rax
.myL141:
vpaddd (%rdx,%rax), %ymm5, %ymm0
vpminsd (%rcx,%rax), %ymm0, %ymm0
vpaddd %ymm4, %ymm0, %ymm0
vpmaxsd %ymm3, %ymm0, %ymm0
vmovdqu %ymm0, (%rdx,%rax)
addq $32, %rax
cmpq %r12, %rax
je .myL155
.myL114:
vpaddd (%rdx,%rax), %ymm5, %ymm0
vpminsd (%rcx,%rax), %ymm0, %ymm0
leaq 32(%rax), %rsi
vpaddd %ymm4, %ymm0, %ymm0
vpmaxsd %ymm3, %ymm0, %ymm0
vmovdqu %ymm0, (%rdx,%rax)
vpaddd 32(%rdx,%rax), %ymm5, %ymm0
vpminsd 32(%rcx,%rax), %ymm0, %ymm0
vpaddd %ymm4, %ymm0, %ymm0
vpmaxsd %ymm3, %ymm0, %ymm0
vmovdqu %ymm0, 32(%rdx,%rax)
vpaddd 64(%rdx,%rax), %ymm5, %ymm0
vpminsd 64(%rcx,%rax), %ymm0, %ymm0
vpaddd %ymm4, %ymm0, %ymm0
vpmaxsd %ymm3, %ymm0, %ymm0
vmovdqu %ymm0, 64(%rdx,%rax)
vpaddd 64(%rdx,%rsi), %ymm5, %ymm0
vpminsd 64(%rcx,%rsi), %ymm0, %ymm0
leaq 224(%rsi), %rax
vpaddd %ymm4, %ymm0, %ymm0
vpmaxsd %ymm3, %ymm0, %ymm0
vmovdqu %ymm0, 64(%rdx,%rsi)
vpaddd 96(%rdx,%rsi), %ymm5, %ymm0
vpminsd 96(%rcx,%rsi), %ymm0, %ymm0
vpaddd %ymm4, %ymm0, %ymm0
vpmaxsd %ymm3, %ymm0, %ymm0
vmovdqu %ymm0, 96(%rdx,%rsi)
vpaddd 128(%rdx,%rsi), %ymm5, %ymm0
vpminsd 128(%rcx,%rsi), %ymm0, %ymm0
vpaddd %ymm4, %ymm0, %ymm0
vpmaxsd %ymm3, %ymm0, %ymm0
vmovdqu %ymm0, 128(%rdx,%rsi)
vpaddd 160(%rdx,%rsi), %ymm5, %ymm0
vpminsd 160(%rcx,%rsi), %ymm0, %ymm0
vpaddd %ymm4, %ymm0, %ymm0
vpmaxsd %ymm3, %ymm0, %ymm0
vmovdqu %ymm0, 160(%rdx,%rsi)
vpaddd 192(%rdx,%rsi), %ymm5, %ymm0
vpminsd 192(%rcx,%rsi), %ymm0, %ymm0
vpaddd %ymm4, %ymm0, %ymm0
vpmaxsd %ymm3, %ymm0, %ymm0
vmovdqu %ymm0, 192(%rdx,%rsi)
cmpq %r12, %rax
jne .myL114
.myL155:
movl %ebx, %edx
andl $-8, %edx
leal (%rdx,%rdi), %eax
cmpl %edx, %ebx
je .myL160
vzeroupper
.myL113:
subl %edx, %r11d
leal 1(%r11), %ecx
cmpl $2, %r11d
jbe .myL116
movslq %edi, %rdi
vbroadcastss -8(%rsp), %xmm3
vbroadcastss -4(%rsp), %xmm0
addq %rdx, %rdi
leaq (%r8,%rdi,4), %rdx
vpaddd (%rdx), %xmm0, %xmm0
vpminsd (%r10,%rdi,4), %xmm0, %xmm0
vpaddd %xmm3, %xmm0, %xmm0
vpxor %xmm3, %xmm3, %xmm3
vpmaxsd %xmm3, %xmm0, %xmm0
vmovdqu %xmm0, (%rdx)
movl %ecx, %edx
andl $-4, %edx
addl %edx, %eax
cmpl %edx, %ecx
je .myL157
.myL116:
movslq %eax, %rdx
vmovd (%r8,%rdx,4), %xmm0
vmovd (%r10,%rdx,4), %xmm3
vpaddd %xmm0, %xmm1, %xmm0
vpminsd %xmm3, %xmm0, %xmm0
vpxor %xmm3, %xmm3, %xmm3
vpaddd %xmm2, %xmm0, %xmm0
vpmaxsd %xmm3, %xmm0, %xmm0
vmovd %xmm0, (%r8,%rdx,4)
leal 1(%rax), %edx
cmpl %edx, %r9d
jl .myL157
movslq %edx, %rdx
addl $2, %eax
vpinsrd $0, (%r8,%rdx,4), %xmm3, %xmm0
vpinsrd $0, (%r10,%rdx,4), %xmm3, %xmm3
vpaddd %xmm0, %xmm1, %xmm0
vpminsd %xmm3, %xmm0, %xmm0
vpxor %xmm3, %xmm3, %xmm3
vpaddd %xmm2, %xmm0, %xmm0
vpmaxsd %xmm3, %xmm0, %xmm0
vmovd %xmm0, (%r8,%rdx,4)
cmpl %eax, %r9d
jl .myL157
cltq
vpinsrd $0, (%r8,%rax,4), %xmm3, %xmm0
vpaddd %xmm0, %xmm1, %xmm0
vpinsrd $0, (%r10,%rax,4), %xmm3, %xmm1
vpminsd %xmm1, %xmm0, %xmm0
vpaddd %xmm2, %xmm0, %xmm0
vpmaxsd %xmm3, %xmm0, %xmm0
vmovd %xmm0, (%r8,%rax,4)
.myL157:
leaq -16(%rbp), %rsp
popq %rbx
popq %r12
popq %rbp
.cfi_remember_state
.cfi_def_cfa 7, 8
ret
.p2align 4,,10
.p2align 3
.myL159:
.cfi_restore_state
vpaddd (%rdx), %ymm5, %ymm0
vpminsd (%rcx), %ymm0, %ymm0
movl $32, %eax
vpaddd %ymm4, %ymm0, %ymm0
vpmaxsd %ymm3, %ymm0, %ymm0
vmovdqu %ymm0, (%rdx)
jmp .myL146
.p2align 4,,10
.p2align 3
.myL160:
vzeroupper
leaq -16(%rbp), %rsp
popq %rbx
popq %r12
popq %rbp
.cfi_remember_state
.cfi_def_cfa 7, 8
ret
.myL118:
.cfi_restore_state
movl %edi, %eax
xorl %edx, %edx
leaq a(%rip), %r8
leaq c(%rip), %r10
jmp .myL113
.cfi_endproc
.myLFE9902:
.size _Z4add3iiii, .-_Z4add3iiii
.p2align 4
.globl _Z4add4iiii
.type _Z4add4iiii, @function
_Z4add4iiii:
.myLFB9903:
.cfi_startproc
endbr64
pushq %rbp
.cfi_def_cfa_offset 16
.cfi_offset 6, -16
vmovd %edx, %xmm1
vmovd %ecx, %xmm2
movq %rsp, %rbp
.cfi_def_cfa_register 6
pushq %r12
pushq %rbx
andq $-32, %rsp
.cfi_offset 12, -24
.cfi_offset 3, -32
vmovd %xmm1, -4(%rsp)
vmovd %xmm2, -8(%rsp)
cmpl %esi, %edi
jg .myL207
movl %esi, %r11d
movl %esi, %r9d
subl %edi, %r11d
leal 1(%r11), %ebx
cmpl $6, %r11d
jbe .myL168
movl %ebx, %r12d
movslq %edi, %rcx
leaq a(%rip), %r8
xorl %eax, %eax
shrl $3, %r12d
salq $2, %rcx
vpbroadcastd %xmm1, %ymm5
leaq c(%rip), %r10
salq $5, %r12
leaq (%r8,%rcx), %rdx
vpbroadcastd %xmm2, %ymm3
addq %r10, %rcx
leaq -32(%r12), %rsi
vpxor %xmm4, %xmm4, %xmm4
shrq $5, %rsi
addq $1, %rsi
andl $7, %esi
je .myL164
cmpq $1, %rsi
je .myL191
cmpq $2, %rsi
je .myL192
cmpq $3, %rsi
je .myL193
cmpq $4, %rsi
je .myL194
cmpq $5, %rsi
je .myL195
cmpq $6, %rsi
jne .myL209
.myL196:
vpaddd (%rdx,%rax), %ymm5, %ymm0
vpmaxsd %ymm4, %ymm0, %ymm0
vpaddd %ymm3, %ymm0, %ymm0
vpminsd (%rcx,%rax), %ymm0, %ymm0
vmovdqu %ymm0, (%rdx,%rax)
addq $32, %rax
.myL195:
vpaddd (%rdx,%rax), %ymm5, %ymm0
vpmaxsd %ymm4, %ymm0, %ymm0
vpaddd %ymm3, %ymm0, %ymm0
vpminsd (%rcx,%rax), %ymm0, %ymm0
vmovdqu %ymm0, (%rdx,%rax)
addq $32, %rax
.myL194:
vpaddd (%rdx,%rax), %ymm5, %ymm0
vpmaxsd %ymm4, %ymm0, %ymm0
vpaddd %ymm3, %ymm0, %ymm0
vpminsd (%rcx,%rax), %ymm0, %ymm0
vmovdqu %ymm0, (%rdx,%rax)
addq $32, %rax
.myL193:
vpaddd (%rdx,%rax), %ymm5, %ymm0
vpmaxsd %ymm4, %ymm0, %ymm0
vpaddd %ymm3, %ymm0, %ymm0
vpminsd (%rcx,%rax), %ymm0, %ymm0
vmovdqu %ymm0, (%rdx,%rax)
addq $32, %rax
.myL192:
vpaddd (%rdx,%rax), %ymm5, %ymm0
vpmaxsd %ymm4, %ymm0, %ymm0
vpaddd %ymm3, %ymm0, %ymm0
vpminsd (%rcx,%rax), %ymm0, %ymm0
vmovdqu %ymm0, (%rdx,%rax)
addq $32, %rax
.myL191:
vpaddd (%rdx,%rax), %ymm5, %ymm0
vpmaxsd %ymm4, %ymm0, %ymm0
vpaddd %ymm3, %ymm0, %ymm0
vpminsd (%rcx,%rax), %ymm0, %ymm0
vmovdqu %ymm0, (%rdx,%rax)
addq $32, %rax
cmpq %r12, %rax
je .myL205
.myL164:
vpaddd (%rdx,%rax), %ymm5, %ymm0
leaq 32(%rax), %rsi
vpmaxsd %ymm4, %ymm0, %ymm0
vpaddd %ymm3, %ymm0, %ymm0
vpminsd (%rcx,%rax), %ymm0, %ymm0
vmovdqu %ymm0, (%rdx,%rax)
vpaddd 32(%rdx,%rax), %ymm5, %ymm0
vpmaxsd %ymm4, %ymm0, %ymm0
vpaddd %ymm3, %ymm0, %ymm0
vpminsd 32(%rcx,%rax), %ymm0, %ymm0
vmovdqu %ymm0, 32(%rdx,%rax)
vpaddd 64(%rdx,%rax), %ymm5, %ymm0
vpmaxsd %ymm4, %ymm0, %ymm0
vpaddd %ymm3, %ymm0, %ymm0
vpminsd 64(%rcx,%rax), %ymm0, %ymm0
vmovdqu %ymm0, 64(%rdx,%rax)
vpaddd 64(%rdx,%rsi), %ymm5, %ymm0
leaq 224(%rsi), %rax
vpmaxsd %ymm4, %ymm0, %ymm0
vpaddd %ymm3, %ymm0, %ymm0
vpminsd 64(%rcx,%rsi), %ymm0, %ymm0
vmovdqu %ymm0, 64(%rdx,%rsi)
vpaddd 96(%rdx,%rsi), %ymm5, %ymm0
vpmaxsd %ymm4, %ymm0, %ymm0
vpaddd %ymm3, %ymm0, %ymm0
vpminsd 96(%rcx,%rsi), %ymm0, %ymm0
vmovdqu %ymm0, 96(%rdx,%rsi)
vpaddd 128(%rdx,%rsi), %ymm5, %ymm0
vpmaxsd %ymm4, %ymm0, %ymm0
vpaddd %ymm3, %ymm0, %ymm0
vpminsd 128(%rcx,%rsi), %ymm0, %ymm0
vmovdqu %ymm0, 128(%rdx,%rsi)
vpaddd 160(%rdx,%rsi), %ymm5, %ymm0
vpmaxsd %ymm4, %ymm0, %ymm0
vpaddd %ymm3, %ymm0, %ymm0
vpminsd 160(%rcx,%rsi), %ymm0, %ymm0
vmovdqu %ymm0, 160(%rdx,%rsi)
vpaddd 192(%rdx,%rsi), %ymm5, %ymm0
vpmaxsd %ymm4, %ymm0, %ymm0
vpaddd %ymm3, %ymm0, %ymm0
vpminsd 192(%rcx,%rsi), %ymm0, %ymm0
vmovdqu %ymm0, 192(%rdx,%rsi)
cmpq %r12, %rax
jne .myL164
.myL205:
movl %ebx, %edx
andl $-8, %edx
leal (%rdx,%rdi), %eax
cmpl %edx, %ebx
je .myL210
vzeroupper
.myL163:
subl %edx, %r11d
leal 1(%r11), %ecx
cmpl $2, %r11d
jbe .myL166
movslq %edi, %rdi
vbroadcastss -4(%rsp), %xmm0
vpxor %xmm3, %xmm3, %xmm3
addq %rdx, %rdi
leaq (%r8,%rdi,4), %rdx
vpaddd (%rdx), %xmm0, %xmm0
vpmaxsd %xmm3, %xmm0, %xmm0
vbroadcastss -8(%rsp), %xmm3
vpaddd %xmm3, %xmm0, %xmm0
vpminsd (%r10,%rdi,4), %xmm0, %xmm0
vmovdqu %xmm0, (%rdx)
movl %ecx, %edx
andl $-4, %edx
addl %edx, %eax
cmpl %edx, %ecx
je .myL207
.myL166:
movslq %eax, %rdx
vpxor %xmm3, %xmm3, %xmm3
vmovd (%r8,%rdx,4), %xmm0
vpaddd %xmm0, %xmm1, %xmm0
vpmaxsd %xmm3, %xmm0, %xmm0
vpinsrd $0, (%r10,%rdx,4), %xmm3, %xmm3
vpaddd %xmm2, %xmm0, %xmm0
vpminsd %xmm3, %xmm0, %xmm0
vmovd %xmm0, (%r8,%rdx,4)
leal 1(%rax), %edx
cmpl %edx, %r9d
jl .myL207
movslq %edx, %rdx
vpxor %xmm3, %xmm3, %xmm3
addl $2, %eax
vmovd (%r8,%rdx,4), %xmm0
vpaddd %xmm0, %xmm1, %xmm0
vpmaxsd %xmm3, %xmm0, %xmm0
vpinsrd $0, (%r10,%rdx,4), %xmm3, %xmm3
vpaddd %xmm2, %xmm0, %xmm0
vpminsd %xmm3, %xmm0, %xmm0
vmovd %xmm0, (%r8,%rdx,4)
cmpl %eax, %r9d
jl .myL207
cltq
vmovd (%r8,%rax,4), %xmm0
vpaddd %xmm0, %xmm1, %xmm0
vpxor %xmm1, %xmm1, %xmm1
vpmaxsd %xmm1, %xmm0, %xmm0
vpinsrd $0, (%r10,%rax,4), %xmm1, %xmm1
vpaddd %xmm2, %xmm0, %xmm0
vpminsd %xmm1, %xmm0, %xmm0
vmovd %xmm0, (%r8,%rax,4)
.myL207:
leaq -16(%rbp), %rsp
popq %rbx
popq %r12
popq %rbp
.cfi_remember_state
.cfi_def_cfa 7, 8
ret
.p2align 4,,10
.p2align 3
.myL209:
.cfi_restore_state
vpaddd (%rdx), %ymm5, %ymm0
movl $32, %eax
vpmaxsd %ymm4, %ymm0, %ymm0
vpaddd %ymm3, %ymm0, %ymm0
vpminsd (%rcx), %ymm0, %ymm0
vmovdqu %ymm0, (%rdx)
jmp .myL196
.p2align 4,,10
.p2align 3
.myL210:
vzeroupper
leaq -16(%rbp), %rsp
popq %rbx
popq %r12
popq %rbp
.cfi_remember_state
.cfi_def_cfa 7, 8
ret
.myL168:
.cfi_restore_state
movl %edi, %eax
xorl %edx, %edx
leaq a(%rip), %r8
leaq c(%rip), %r10
jmp .myL163
.cfi_endproc
.myLFE9903:
.size _Z4add4iiii, .-_Z4add4iiii
)dard");
/*
void add1(int l, int r, int x){
// debug(1, l, r, x);
for (int i = l; i <= r; i++){
a[i] = (a[i]+x > c[i]? c[i]: a[i]+x);
}
}
void add2(int l, int r, int x){
// debug(2, l, r, x);
for (int i = l; i <= r; i++){
a[i] = (a[i]+x < 0? 0: a[i]+x);
}
}
void add3(int l, int r, int x, int y){
// debug(3, l, r, x, y);
for (int i = l; i <= r; i++){
a[i] = (a[i]+x > c[i]? c[i]: a[i]+x);
// debug(i, a[i]);
a[i] = (a[i]+y < 0? 0: a[i]+y);
// debug(i, a[i]);
}
}
void add4(int l, int r, int x, int y){
//debug(4, l, r, x, y);
for (int i = l; i <= r; i++){
a[i] = (a[i]+x < 0? 0: a[i]+x);
a[i] = (a[i]+y > c[i]? c[i]: a[i]+y);
}
}*/
vector<int> distribute_candies(vector<int> C, vector<int> L, vector<int> R, vector<int> V) {
n = C.size();
q = L.size();
for (int i = 0; i < n; i++){
c[i] = C[i];
}
for (int i = 0; i < q; i++){
l[i] = L[i];
r[i] = R[i];
v[i] = V[i];
}
for (int st = 0; st < n; st += S){
for (int i = 0; i < q; i += 2){
if (i + 1 == q){
int L = max(st, l[i]);
int R = min(st+S-1, r[i]);
if (v[i] > 0) add1(L, R, v[i]);
if (v[i] < 0) add2(L, R, v[i]);
break;
}
int L1 = max(st, l[i]);
int R1 = min(st+S-1, r[i]);
int L2 = max(st, l[i+1]);
int R2 = min(st+S-1, r[i+1]);
if (v[i] == 0 && v[i+1] == 0) continue;
if (v[i] >= 0 && v[i+1] >= 0){
add1(L1, min(R1, L2-1), v[i]);
add1(L2, min(R2, L1-1), v[i+1]);
add1(max(L1, L2), min(R1, R2), min(v[i]+v[i+1],(int)1e9));
add1(max(L1, R2+1), R1, v[i]);
add1(max(L2, R1+1), R2, v[i+1]);
}
else if (v[i] <= 0 && v[i+1] <= 0){
add2(L1, min(R1, L2-1), v[i]);
add2(L2, min(R2, L1-1), v[i+1]);
add2(max(L1, L2), min(R1, R2), max(v[i]+v[i+1],(int)-1e9));
add2(max(L1, R2+1), R1, v[i]);
add2(max(L2, R1+1), R2, v[i+1]);
}
else if (v[i] >= 0 && v[i+1] <= 0){
add1(L1, min(R1, L2-1), v[i]);
add2(L2, min(R2, L1-1), v[i+1]);
add3(max(L1, L2), min(R1, R2), v[i], v[i+1]);
add1(max(L1, R2+1), R1, v[i]);
add2(max(L2, R1+1), R2, v[i+1]);
}
else{
add2(L1, min(R1, L2-1), v[i]);
add1(L2, min(R2, L1-1), v[i+1]);
add4(max(L1, L2), min(R1, R2), v[i], v[i+1]);
add2(max(L1, R2+1), R1, v[i]);
add1(max(L2, R1+1), R2, v[i+1]);
}
}
}
vector<int> ans;
for (int i = 0; i < n; i++){
ans.push_back(a[i]);
}
return ans;
}
| # |
결과 |
실행 시간 |
메모리 |
Grader output |
| 1 |
Correct |
0 ms |
212 KB |
Output is correct |
| 2 |
Correct |
0 ms |
212 KB |
Output is correct |
| 3 |
Correct |
1 ms |
340 KB |
Output is correct |
| 4 |
Correct |
1 ms |
340 KB |
Output is correct |
| 5 |
Correct |
1 ms |
340 KB |
Output is correct |
| # |
결과 |
실행 시간 |
메모리 |
Grader output |
| 1 |
Correct |
939 ms |
11560 KB |
Output is correct |
| 2 |
Correct |
910 ms |
11708 KB |
Output is correct |
| 3 |
Correct |
917 ms |
11620 KB |
Output is correct |
| # |
결과 |
실행 시간 |
메모리 |
Grader output |
| 1 |
Correct |
1 ms |
340 KB |
Output is correct |
| 2 |
Correct |
56 ms |
7404 KB |
Output is correct |
| 3 |
Correct |
47 ms |
5544 KB |
Output is correct |
| 4 |
Correct |
862 ms |
11616 KB |
Output is correct |
| 5 |
Correct |
867 ms |
11584 KB |
Output is correct |
| 6 |
Correct |
862 ms |
11532 KB |
Output is correct |
| 7 |
Correct |
812 ms |
11712 KB |
Output is correct |
| # |
결과 |
실행 시간 |
메모리 |
Grader output |
| 1 |
Correct |
1 ms |
212 KB |
Output is correct |
| 2 |
Correct |
0 ms |
340 KB |
Output is correct |
| 3 |
Correct |
54 ms |
7408 KB |
Output is correct |
| 4 |
Correct |
49 ms |
4664 KB |
Output is correct |
| 5 |
Correct |
1333 ms |
11624 KB |
Output is correct |
| 6 |
Correct |
1329 ms |
11552 KB |
Output is correct |
| 7 |
Correct |
1333 ms |
11632 KB |
Output is correct |
| 8 |
Correct |
1386 ms |
11596 KB |
Output is correct |
| 9 |
Correct |
1383 ms |
11712 KB |
Output is correct |
| # |
결과 |
실행 시간 |
메모리 |
Grader output |
| 1 |
Correct |
0 ms |
212 KB |
Output is correct |
| 2 |
Correct |
0 ms |
212 KB |
Output is correct |
| 3 |
Correct |
1 ms |
340 KB |
Output is correct |
| 4 |
Correct |
1 ms |
340 KB |
Output is correct |
| 5 |
Correct |
1 ms |
340 KB |
Output is correct |
| 6 |
Correct |
939 ms |
11560 KB |
Output is correct |
| 7 |
Correct |
910 ms |
11708 KB |
Output is correct |
| 8 |
Correct |
917 ms |
11620 KB |
Output is correct |
| 9 |
Correct |
1 ms |
340 KB |
Output is correct |
| 10 |
Correct |
56 ms |
7404 KB |
Output is correct |
| 11 |
Correct |
47 ms |
5544 KB |
Output is correct |
| 12 |
Correct |
862 ms |
11616 KB |
Output is correct |
| 13 |
Correct |
867 ms |
11584 KB |
Output is correct |
| 14 |
Correct |
862 ms |
11532 KB |
Output is correct |
| 15 |
Correct |
812 ms |
11712 KB |
Output is correct |
| 16 |
Correct |
1 ms |
212 KB |
Output is correct |
| 17 |
Correct |
0 ms |
340 KB |
Output is correct |
| 18 |
Correct |
54 ms |
7408 KB |
Output is correct |
| 19 |
Correct |
49 ms |
4664 KB |
Output is correct |
| 20 |
Correct |
1333 ms |
11624 KB |
Output is correct |
| 21 |
Correct |
1329 ms |
11552 KB |
Output is correct |
| 22 |
Correct |
1333 ms |
11632 KB |
Output is correct |
| 23 |
Correct |
1386 ms |
11596 KB |
Output is correct |
| 24 |
Correct |
1383 ms |
11712 KB |
Output is correct |
| 25 |
Correct |
0 ms |
212 KB |
Output is correct |
| 26 |
Correct |
44 ms |
4560 KB |
Output is correct |
| 27 |
Correct |
56 ms |
7412 KB |
Output is correct |
| 28 |
Correct |
874 ms |
11628 KB |
Output is correct |
| 29 |
Correct |
902 ms |
11668 KB |
Output is correct |
| 30 |
Correct |
886 ms |
11632 KB |
Output is correct |
| 31 |
Correct |
937 ms |
11608 KB |
Output is correct |
| 32 |
Correct |
901 ms |
11628 KB |
Output is correct |
