1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
Iterations: 100
Instructions: 7200
Total Cycles: 7648
Total uOps: 9300
Dispatch Width: 4
uOps Per Cycle: 1.22
IPC: 0.94
Block RThroughput: 23.3
Instruction Info:
[1]: #uOps
[2]: Latency
[3]: RThroughput
[4]: MayLoad
[5]: MayStore
[6]: HasSideEffects (U)
[1] [2] [3] [4] [5] [6] Instructions:
2 5 1.00 * push rbp
2 5 1.00 * push r15
2 5 1.00 * push r14
2 5 1.00 * push r13
2 5 1.00 * push r12
2 5 1.00 * push rbx
1 1 0.33 sub rsp, 24
1 5 0.50 * mov r12, qword ptr [rdi + 16]
1 1 0.33 mov r13, r12
1 1 0.33 sub r13, rsi
1 1 1.00 jb .LBB6_10
1 1 0.33 mov rbx, rdi
1 5 0.50 * mov rax, qword ptr [rdi]
1 1 0.33 mov rcx, rax
1 1 0.33 sub rcx, r12
1 1 0.33 cmp rdx, rcx
1 1 1.00 jbe .LBB6_4
1 1 0.33 add r12, rdx
1 1 1.00 jae .LBB6_7
1 0 0.25 xor eax, eax
1 1 1.00 jmp .LBB6_6
1 5 0.50 * mov rax, qword ptr [rbx + 8]
1 1 0.33 add r12, rdx
1 1 0.50 lea rcx, [rsi + 2*rsi]
1 1 0.50 lea r14, [rax + 2*rcx]
1 1 0.33 add rdx, rdx
1 1 0.50 lea r15, [rdx + 2*rdx]
1 1 0.50 lea rdi, [r14 + r15]
1 1 0.33 add r13, r13
1 1 0.50 lea rdx, [2*r13]
1 1 0.33 add rdx, r13
1 1 0.33 mov rsi, r14
4 7 1.00 * call qword ptr [rip + memmove@GOTPCREL]
1 1 0.33 mov rdi, r14
1 0 0.25 xor esi, esi
1 1 0.33 mov rdx, r15
4 7 1.00 * call qword ptr [rip + memset@GOTPCREL]
1 1 1.00 * mov qword ptr [rbx + 16], r12
1 1 0.33 mov al, 1
1 1 0.33 add rsp, 24
1 6 0.50 * pop rbx
1 6 0.50 * pop r12
1 6 0.50 * pop r13
1 6 0.50 * pop r14
1 6 0.50 * pop r15
1 6 0.50 * pop rbp
1 1 1.00 U ret
1 1 0.33 mov r15, rsi
1 1 0.33 mov rbp, rdx
1 1 0.50 lea rcx, [rax + rax]
1 1 0.33 cmp r12, rcx
3 3 1.00 cmova rcx, r12
1 1 0.33 cmp rcx, 5
1 1 0.33 mov r14d, 4
2 2 0.67 cmovae r14, rcx
1 5 0.50 * mov rdx, qword ptr [rbx + 8]
1 1 0.33 mov rdi, rsp
1 1 0.33 mov rsi, rax
1 1 0.33 mov rcx, r14
3 5 1.00 call <alloc::raw_vec::RawVecInner>::finish_grow
2 6 0.50 * cmp dword ptr [rsp], 1
1 1 1.00 je .LBB6_3
1 5 0.50 * mov rax, qword ptr [rsp + 8]
1 1 1.00 * mov qword ptr [rbx + 8], rax
1 1 1.00 * mov qword ptr [rbx], r14
1 1 0.33 mov rdx, rbp
1 1 0.33 mov rsi, r15
1 1 1.00 jmp .LBB6_5
1 1 0.50 lea rdi, [rip + .Lanon.HASH.1]
1 1 0.50 lea rdx, [rip + .Lanon.HASH.3]
1 1 0.33 mov esi, 37
4 7 1.00 * call qword ptr [rip + core::panicking::panic@GOTPCREL]
Resources:
[0] - SBDivider
[1] - SBFPDivider
[2] - SBPort0
[3] - SBPort1
[4] - SBPort4
[5] - SBPort5
[6.0] - SBPort23
[6.1] - SBPort23
Resource pressure per iteration:
[0] [1] [2] [3] [4] [5] [6.0] [6.1]
- - 17.02 16.50 13.00 19.48 14.00 14.00
Resource pressure by instruction:
[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
- - - - 1.00 - 0.98 0.02 push rbp
- - - - 1.00 - 0.02 0.98 push r15
- - - - 1.00 - 0.99 0.01 push r14
- - - - 1.00 - 0.01 0.99 push r13
- - - - 1.00 - 0.99 0.01 push r12
- - - - 1.00 - 0.01 0.99 push rbx
- - 0.49 0.51 - - - - sub rsp, 24
- - - - - - 0.04 0.96 mov r12, qword ptr [rdi + 16]
- - 0.49 0.50 - 0.01 - - mov r13, r12
- - 0.48 0.51 - 0.01 - - sub r13, rsi
- - - - - 1.00 - - jb .LBB6_10
- - 0.49 0.49 - 0.02 - - mov rbx, rdi
- - - - - - 0.97 0.03 mov rax, qword ptr [rdi]
- - 0.51 0.49 - - - - mov rcx, rax
- - 0.49 0.02 - 0.49 - - sub rcx, r12
- - 0.49 0.50 - 0.01 - - cmp rdx, rcx
- - - - - 1.00 - - jbe .LBB6_4
- - 0.02 0.49 - 0.49 - - add r12, rdx
- - - - - 1.00 - - jae .LBB6_7
- - - - - - - - xor eax, eax
- - - - - 1.00 - - jmp .LBB6_6
- - - - - - 0.97 0.03 mov rax, qword ptr [rbx + 8]
- - 0.51 0.49 - - - - add r12, rdx
- - 0.49 0.51 - - - - lea rcx, [rsi + 2*rsi]
- - 0.50 0.50 - - - - lea r14, [rax + 2*rcx]
- - 0.51 0.49 - - - - add rdx, rdx
- - 0.50 0.50 - - - - lea r15, [rdx + 2*rdx]
- - 0.49 0.51 - - - - lea rdi, [r14 + r15]
- - 0.50 0.49 - 0.01 - - add r13, r13
- - 0.51 0.49 - - - - lea rdx, [2*r13]
- - 0.01 0.01 - 0.98 - - add rdx, r13
- - 0.01 - - 0.99 - - mov rsi, r14
- - - - 1.00 1.00 1.98 0.02 call qword ptr [rip + memmove@GOTPCREL]
- - 0.49 0.50 - 0.01 - - mov rdi, r14
- - - - - - - - xor esi, esi
- - 0.50 0.50 - - - - mov rdx, r15
- - - - 1.00 1.00 1.96 0.04 call qword ptr [rip + memset@GOTPCREL]
- - - - 1.00 - 0.01 0.99 mov qword ptr [rbx + 16], r12
- - 0.50 - - 0.50 - - mov al, 1
- - 0.51 0.49 - - - - add rsp, 24
- - - - - - 0.02 0.98 pop rbx
- - - - - - 0.03 0.97 pop r12
- - - - - - 0.03 0.97 pop r13
- - - - - - 0.97 0.03 pop r14
- - - - - - 0.03 0.97 pop r15
- - - - - - 0.01 0.99 pop rbp
- - - - - 1.00 - - ret
- - 0.49 0.51 - - - - mov r15, rsi
- - 0.51 0.49 - - - - mov rbp, rdx
- - 0.49 0.51 - - - - lea rcx, [rax + rax]
- - 0.49 0.50 - 0.01 - - cmp r12, rcx
- - 1.04 0.50 - 1.46 - - cmova rcx, r12
- - 0.49 0.49 - 0.02 - - cmp rcx, 5
- - 0.50 - - 0.50 - - mov r14d, 4
- - 0.50 0.51 - 0.99 - - cmovae r14, rcx
- - - - - - 0.97 0.03 mov rdx, qword ptr [rbx + 8]
- - - 0.51 - 0.49 - - mov rdi, rsp
- - 0.01 0.50 - 0.49 - - mov rsi, rax
- - 0.49 0.50 - 0.01 - - mov rcx, r14
- - - - 1.00 1.00 0.99 0.01 call <alloc::raw_vec::RawVecInner>::finish_grow
- - 0.51 0.49 - - 0.50 0.50 cmp dword ptr [rsp], 1
- - - - - 1.00 - - je .LBB6_3
- - - - - - 0.50 0.50 mov rax, qword ptr [rsp + 8]
- - - - 1.00 - 0.99 0.01 mov qword ptr [rbx + 8], rax
- - - - 1.00 - 0.01 0.99 mov qword ptr [rbx], r14
- - 0.49 0.50 - 0.01 - - mov rdx, rbp
- - 0.50 0.01 - 0.49 - - mov rsi, r15
- - - - - 1.00 - - jmp .LBB6_5
- - 0.01 0.99 - - - - lea rdi, [rip + .Lanon.HASH.1]
- - 0.99 0.01 - - - - lea rdx, [rip + .Lanon.HASH.3]
- - 0.02 0.49 - 0.49 - - mov esi, 37
- - - - 1.00 1.00 0.02 1.98 call qword ptr [rip + core::panicking::panic@GOTPCREL]