xref: /linux/rust/zerocopy/benches/insert_vec_zeroed.x86-64.mca (revision c37398010a05055e78cf0c75defb90df06c4e999)
1Iterations:        100
2Instructions:      7200
3Total Cycles:      7648
4Total uOps:        9300
5
6Dispatch Width:    4
7uOps Per Cycle:    1.22
8IPC:               0.94
9Block RThroughput: 23.3
10
11
12Instruction Info:
13[1]: #uOps
14[2]: Latency
15[3]: RThroughput
16[4]: MayLoad
17[5]: MayStore
18[6]: HasSideEffects (U)
19
20[1]    [2]    [3]    [4]    [5]    [6]    Instructions:
21 2      5     1.00           *            push	rbp
22 2      5     1.00           *            push	r15
23 2      5     1.00           *            push	r14
24 2      5     1.00           *            push	r13
25 2      5     1.00           *            push	r12
26 2      5     1.00           *            push	rbx
27 1      1     0.33                        sub	rsp, 24
28 1      5     0.50    *                   mov	r12, qword ptr [rdi + 16]
29 1      1     0.33                        mov	r13, r12
30 1      1     0.33                        sub	r13, rsi
31 1      1     1.00                        jb	.LBB6_10
32 1      1     0.33                        mov	rbx, rdi
33 1      5     0.50    *                   mov	rax, qword ptr [rdi]
34 1      1     0.33                        mov	rcx, rax
35 1      1     0.33                        sub	rcx, r12
36 1      1     0.33                        cmp	rdx, rcx
37 1      1     1.00                        jbe	.LBB6_4
38 1      1     0.33                        add	r12, rdx
39 1      1     1.00                        jae	.LBB6_7
40 1      0     0.25                        xor	eax, eax
41 1      1     1.00                        jmp	.LBB6_6
42 1      5     0.50    *                   mov	rax, qword ptr [rbx + 8]
43 1      1     0.33                        add	r12, rdx
44 1      1     0.50                        lea	rcx, [rsi + 2*rsi]
45 1      1     0.50                        lea	r14, [rax + 2*rcx]
46 1      1     0.33                        add	rdx, rdx
47 1      1     0.50                        lea	r15, [rdx + 2*rdx]
48 1      1     0.50                        lea	rdi, [r14 + r15]
49 1      1     0.33                        add	r13, r13
50 1      1     0.50                        lea	rdx, [2*r13]
51 1      1     0.33                        add	rdx, r13
52 1      1     0.33                        mov	rsi, r14
53 4      7     1.00    *                   call	qword ptr [rip + memmove@GOTPCREL]
54 1      1     0.33                        mov	rdi, r14
55 1      0     0.25                        xor	esi, esi
56 1      1     0.33                        mov	rdx, r15
57 4      7     1.00    *                   call	qword ptr [rip + memset@GOTPCREL]
58 1      1     1.00           *            mov	qword ptr [rbx + 16], r12
59 1      1     0.33                        mov	al, 1
60 1      1     0.33                        add	rsp, 24
61 1      6     0.50    *                   pop	rbx
62 1      6     0.50    *                   pop	r12
63 1      6     0.50    *                   pop	r13
64 1      6     0.50    *                   pop	r14
65 1      6     0.50    *                   pop	r15
66 1      6     0.50    *                   pop	rbp
67 1      1     1.00                  U     ret
68 1      1     0.33                        mov	r15, rsi
69 1      1     0.33                        mov	rbp, rdx
70 1      1     0.50                        lea	rcx, [rax + rax]
71 1      1     0.33                        cmp	r12, rcx
72 3      3     1.00                        cmova	rcx, r12
73 1      1     0.33                        cmp	rcx, 5
74 1      1     0.33                        mov	r14d, 4
75 2      2     0.67                        cmovae	r14, rcx
76 1      5     0.50    *                   mov	rdx, qword ptr [rbx + 8]
77 1      1     0.33                        mov	rdi, rsp
78 1      1     0.33                        mov	rsi, rax
79 1      1     0.33                        mov	rcx, r14
80 3      5     1.00                        call	<alloc::raw_vec::RawVecInner>::finish_grow
81 2      6     0.50    *                   cmp	dword ptr [rsp], 1
82 1      1     1.00                        je	.LBB6_3
83 1      5     0.50    *                   mov	rax, qword ptr [rsp + 8]
84 1      1     1.00           *            mov	qword ptr [rbx + 8], rax
85 1      1     1.00           *            mov	qword ptr [rbx], r14
86 1      1     0.33                        mov	rdx, rbp
87 1      1     0.33                        mov	rsi, r15
88 1      1     1.00                        jmp	.LBB6_5
89 1      1     0.50                        lea	rdi, [rip + .Lanon.HASH.1]
90 1      1     0.50                        lea	rdx, [rip + .Lanon.HASH.3]
91 1      1     0.33                        mov	esi, 37
92 4      7     1.00    *                   call	qword ptr [rip + core::panicking::panic@GOTPCREL]
93
94
95Resources:
96[0]   - SBDivider
97[1]   - SBFPDivider
98[2]   - SBPort0
99[3]   - SBPort1
100[4]   - SBPort4
101[5]   - SBPort5
102[6.0] - SBPort23
103[6.1] - SBPort23
104
105
106Resource pressure per iteration:
107[0]    [1]    [2]    [3]    [4]    [5]    [6.0]  [6.1]
108 -      -     17.02  16.50  13.00  19.48  14.00  14.00
109
110Resource pressure by instruction:
111[0]    [1]    [2]    [3]    [4]    [5]    [6.0]  [6.1]  Instructions:
112 -      -      -      -     1.00    -     0.98   0.02   push	rbp
113 -      -      -      -     1.00    -     0.02   0.98   push	r15
114 -      -      -      -     1.00    -     0.99   0.01   push	r14
115 -      -      -      -     1.00    -     0.01   0.99   push	r13
116 -      -      -      -     1.00    -     0.99   0.01   push	r12
117 -      -      -      -     1.00    -     0.01   0.99   push	rbx
118 -      -     0.49   0.51    -      -      -      -     sub	rsp, 24
119 -      -      -      -      -      -     0.04   0.96   mov	r12, qword ptr [rdi + 16]
120 -      -     0.49   0.50    -     0.01    -      -     mov	r13, r12
121 -      -     0.48   0.51    -     0.01    -      -     sub	r13, rsi
122 -      -      -      -      -     1.00    -      -     jb	.LBB6_10
123 -      -     0.49   0.49    -     0.02    -      -     mov	rbx, rdi
124 -      -      -      -      -      -     0.97   0.03   mov	rax, qword ptr [rdi]
125 -      -     0.51   0.49    -      -      -      -     mov	rcx, rax
126 -      -     0.49   0.02    -     0.49    -      -     sub	rcx, r12
127 -      -     0.49   0.50    -     0.01    -      -     cmp	rdx, rcx
128 -      -      -      -      -     1.00    -      -     jbe	.LBB6_4
129 -      -     0.02   0.49    -     0.49    -      -     add	r12, rdx
130 -      -      -      -      -     1.00    -      -     jae	.LBB6_7
131 -      -      -      -      -      -      -      -     xor	eax, eax
132 -      -      -      -      -     1.00    -      -     jmp	.LBB6_6
133 -      -      -      -      -      -     0.97   0.03   mov	rax, qword ptr [rbx + 8]
134 -      -     0.51   0.49    -      -      -      -     add	r12, rdx
135 -      -     0.49   0.51    -      -      -      -     lea	rcx, [rsi + 2*rsi]
136 -      -     0.50   0.50    -      -      -      -     lea	r14, [rax + 2*rcx]
137 -      -     0.51   0.49    -      -      -      -     add	rdx, rdx
138 -      -     0.50   0.50    -      -      -      -     lea	r15, [rdx + 2*rdx]
139 -      -     0.49   0.51    -      -      -      -     lea	rdi, [r14 + r15]
140 -      -     0.50   0.49    -     0.01    -      -     add	r13, r13
141 -      -     0.51   0.49    -      -      -      -     lea	rdx, [2*r13]
142 -      -     0.01   0.01    -     0.98    -      -     add	rdx, r13
143 -      -     0.01    -      -     0.99    -      -     mov	rsi, r14
144 -      -      -      -     1.00   1.00   1.98   0.02   call	qword ptr [rip + memmove@GOTPCREL]
145 -      -     0.49   0.50    -     0.01    -      -     mov	rdi, r14
146 -      -      -      -      -      -      -      -     xor	esi, esi
147 -      -     0.50   0.50    -      -      -      -     mov	rdx, r15
148 -      -      -      -     1.00   1.00   1.96   0.04   call	qword ptr [rip + memset@GOTPCREL]
149 -      -      -      -     1.00    -     0.01   0.99   mov	qword ptr [rbx + 16], r12
150 -      -     0.50    -      -     0.50    -      -     mov	al, 1
151 -      -     0.51   0.49    -      -      -      -     add	rsp, 24
152 -      -      -      -      -      -     0.02   0.98   pop	rbx
153 -      -      -      -      -      -     0.03   0.97   pop	r12
154 -      -      -      -      -      -     0.03   0.97   pop	r13
155 -      -      -      -      -      -     0.97   0.03   pop	r14
156 -      -      -      -      -      -     0.03   0.97   pop	r15
157 -      -      -      -      -      -     0.01   0.99   pop	rbp
158 -      -      -      -      -     1.00    -      -     ret
159 -      -     0.49   0.51    -      -      -      -     mov	r15, rsi
160 -      -     0.51   0.49    -      -      -      -     mov	rbp, rdx
161 -      -     0.49   0.51    -      -      -      -     lea	rcx, [rax + rax]
162 -      -     0.49   0.50    -     0.01    -      -     cmp	r12, rcx
163 -      -     1.04   0.50    -     1.46    -      -     cmova	rcx, r12
164 -      -     0.49   0.49    -     0.02    -      -     cmp	rcx, 5
165 -      -     0.50    -      -     0.50    -      -     mov	r14d, 4
166 -      -     0.50   0.51    -     0.99    -      -     cmovae	r14, rcx
167 -      -      -      -      -      -     0.97   0.03   mov	rdx, qword ptr [rbx + 8]
168 -      -      -     0.51    -     0.49    -      -     mov	rdi, rsp
169 -      -     0.01   0.50    -     0.49    -      -     mov	rsi, rax
170 -      -     0.49   0.50    -     0.01    -      -     mov	rcx, r14
171 -      -      -      -     1.00   1.00   0.99   0.01   call	<alloc::raw_vec::RawVecInner>::finish_grow
172 -      -     0.51   0.49    -      -     0.50   0.50   cmp	dword ptr [rsp], 1
173 -      -      -      -      -     1.00    -      -     je	.LBB6_3
174 -      -      -      -      -      -     0.50   0.50   mov	rax, qword ptr [rsp + 8]
175 -      -      -      -     1.00    -     0.99   0.01   mov	qword ptr [rbx + 8], rax
176 -      -      -      -     1.00    -     0.01   0.99   mov	qword ptr [rbx], r14
177 -      -     0.49   0.50    -     0.01    -      -     mov	rdx, rbp
178 -      -     0.50   0.01    -     0.49    -      -     mov	rsi, r15
179 -      -      -      -      -     1.00    -      -     jmp	.LBB6_5
180 -      -     0.01   0.99    -      -      -      -     lea	rdi, [rip + .Lanon.HASH.1]
181 -      -     0.99   0.01    -      -      -      -     lea	rdx, [rip + .Lanon.HASH.3]
182 -      -     0.02   0.49    -     0.49    -      -     mov	esi, 37
183 -      -      -      -     1.00   1.00   0.02   1.98   call	qword ptr [rip + core::panicking::panic@GOTPCREL]
184