xref: /linux/rust/zerocopy/benches/extend_vec_zeroed.x86-64.mca (revision 056a5087d87ead77dedbe9cf5bde53b7cd4b4651)
1Iterations:        100
2Instructions:      5400
3Total Cycles:      6595
4Total uOps:        6800
5
6Dispatch Width:    4
7uOps Per Cycle:    1.03
8IPC:               0.82
9Block RThroughput: 17.0
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	r15
22 2      5     1.00           *            push	r14
23 2      5     1.00           *            push	r13
24 2      5     1.00           *            push	r12
25 2      5     1.00           *            push	rbx
26 1      1     0.33                        sub	rsp, 32
27 1      1     0.33                        mov	rbx, rdi
28 1      5     0.50    *                   mov	rax, qword ptr [rdi]
29 1      5     0.50    *                   mov	r12, qword ptr [rdi + 16]
30 1      1     0.33                        mov	rcx, rax
31 1      1     0.33                        sub	rcx, r12
32 1      1     0.33                        cmp	rsi, rcx
33 1      1     1.00                        jbe	.LBB6_3
34 1      1     0.33                        mov	r15, r12
35 1      1     0.33                        add	r15, rsi
36 1      1     1.00                        jae	.LBB6_6
37 1      0     0.25                        xor	eax, eax
38 1      1     1.00                        jmp	.LBB6_5
39 1      5     0.50    *                   mov	rax, qword ptr [rbx + 8]
40 1      1     0.50                        lea	r15, [r12 + rsi]
41 1      1     0.50                        lea	rcx, [r12 + 2*r12]
42 1      1     0.50                        lea	rdi, [rax + 2*rcx]
43 1      1     0.33                        add	rsi, rsi
44 1      1     0.50                        lea	rdx, [rsi + 2*rsi]
45 1      0     0.25                        xor	esi, esi
46 4      7     1.00    *                   call	qword ptr [rip + memset@GOTPCREL]
47 1      1     1.00           *            mov	qword ptr [rbx + 16], r15
48 1      1     0.33                        mov	al, 1
49 1      1     0.33                        add	rsp, 32
50 1      6     0.50    *                   pop	rbx
51 1      6     0.50    *                   pop	r12
52 1      6     0.50    *                   pop	r13
53 1      6     0.50    *                   pop	r14
54 1      6     0.50    *                   pop	r15
55 1      1     1.00                  U     ret
56 1      1     0.33                        mov	r13, rsi
57 1      1     0.50                        lea	rcx, [rax + rax]
58 1      1     0.33                        cmp	r15, rcx
59 3      3     1.00                        cmova	rcx, r15
60 1      1     0.33                        cmp	rcx, 5
61 1      1     0.33                        mov	r14d, 4
62 2      2     0.67                        cmovae	r14, rcx
63 1      5     0.50    *                   mov	rdx, qword ptr [rbx + 8]
64 1      1     0.50                        lea	rdi, [rsp + 8]
65 1      1     0.33                        mov	rsi, rax
66 1      1     0.33                        mov	rcx, r14
67 3      5     1.00                        call	<alloc::raw_vec::RawVecInner>::finish_grow
68 2      6     0.50    *                   cmp	dword ptr [rsp + 8], 1
69 1      1     1.00                        je	.LBB6_2
70 1      5     0.50    *                   mov	rax, qword ptr [rsp + 16]
71 1      1     1.00           *            mov	qword ptr [rbx + 8], rax
72 1      1     1.00           *            mov	qword ptr [rbx], r14
73 1      1     0.33                        mov	rsi, r13
74 1      1     1.00                        jmp	.LBB6_4
75
76
77Resources:
78[0]   - SBDivider
79[1]   - SBFPDivider
80[2]   - SBPort0
81[3]   - SBPort1
82[4]   - SBPort4
83[5]   - SBPort5
84[6.0] - SBPort23
85[6.1] - SBPort23
86
87
88Resource pressure per iteration:
89[0]    [1]    [2]    [3]    [4]    [5]    [6.0]  [6.1]
90 -      -     12.00  12.00  10.00  13.00  11.00  11.00
91
92Resource pressure by instruction:
93[0]    [1]    [2]    [3]    [4]    [5]    [6.0]  [6.1]  Instructions:
94 -      -      -      -     1.00    -     0.49   0.51   push	r15
95 -      -      -      -     1.00    -     0.51   0.49   push	r14
96 -      -      -      -     1.00    -     0.50   0.50   push	r13
97 -      -      -      -     1.00    -     0.50   0.50   push	r12
98 -      -      -      -     1.00    -     0.50   0.50   push	rbx
99 -      -     0.01   0.99    -      -      -      -     sub	rsp, 32
100 -      -      -      -      -     1.00    -      -     mov	rbx, rdi
101 -      -      -      -      -      -     0.50   0.50   mov	rax, qword ptr [rdi]
102 -      -      -      -      -      -     0.50   0.50   mov	r12, qword ptr [rdi + 16]
103 -      -      -     1.00    -      -      -      -     mov	rcx, rax
104 -      -      -     0.99    -     0.01    -      -     sub	rcx, r12
105 -      -      -      -      -     1.00    -      -     cmp	rsi, rcx
106 -      -      -      -      -     1.00    -      -     jbe	.LBB6_3
107 -      -     0.01   0.98    -     0.01    -      -     mov	r15, r12
108 -      -     0.99   0.01    -      -      -      -     add	r15, rsi
109 -      -      -      -      -     1.00    -      -     jae	.LBB6_6
110 -      -      -      -      -      -      -      -     xor	eax, eax
111 -      -      -      -      -     1.00    -      -     jmp	.LBB6_5
112 -      -      -      -      -      -     0.50   0.50   mov	rax, qword ptr [rbx + 8]
113 -      -     1.00    -      -      -      -      -     lea	r15, [r12 + rsi]
114 -      -     0.98   0.02    -      -      -      -     lea	rcx, [r12 + 2*r12]
115 -      -     0.99   0.01    -      -      -      -     lea	rdi, [rax + 2*rcx]
116 -      -      -     1.00    -      -      -      -     add	rsi, rsi
117 -      -     0.99   0.01    -      -      -      -     lea	rdx, [rsi + 2*rsi]
118 -      -      -      -      -      -      -      -     xor	esi, esi
119 -      -      -      -     1.00   1.00   1.00   1.00   call	qword ptr [rip + memset@GOTPCREL]
120 -      -      -      -     1.00    -     0.50   0.50   mov	qword ptr [rbx + 16], r15
121 -      -     0.01   0.99    -      -      -      -     mov	al, 1
122 -      -     1.00    -      -      -      -      -     add	rsp, 32
123 -      -      -      -      -      -     0.50   0.50   pop	rbx
124 -      -      -      -      -      -     0.50   0.50   pop	r12
125 -      -      -      -      -      -     0.50   0.50   pop	r13
126 -      -      -      -      -      -     0.50   0.50   pop	r14
127 -      -      -      -      -      -     0.50   0.50   pop	r15
128 -      -      -      -      -     1.00    -      -     ret
129 -      -     1.00    -      -      -      -      -     mov	r13, rsi
130 -      -     0.01   0.99    -      -      -      -     lea	rcx, [rax + rax]
131 -      -     0.99   0.01    -      -      -      -     cmp	r15, rcx
132 -      -     2.00   0.01    -     0.99    -      -     cmova	rcx, r15
133 -      -     0.01   0.99    -      -      -      -     cmp	rcx, 5
134 -      -     0.01   0.99    -      -      -      -     mov	r14d, 4
135 -      -     1.00   0.01    -     0.99    -      -     cmovae	r14, rcx
136 -      -      -      -      -      -     0.50   0.50   mov	rdx, qword ptr [rbx + 8]
137 -      -     0.01   0.99    -      -      -      -     lea	rdi, [rsp + 8]
138 -      -      -     1.00    -      -      -      -     mov	rsi, rax
139 -      -      -     0.01    -     0.99    -      -     mov	rcx, r14
140 -      -      -      -     1.00   1.00   0.50   0.50   call	<alloc::raw_vec::RawVecInner>::finish_grow
141 -      -      -     0.99    -     0.01   0.50   0.50   cmp	dword ptr [rsp + 8], 1
142 -      -      -      -      -     1.00    -      -     je	.LBB6_2
143 -      -      -      -      -      -     0.50   0.50   mov	rax, qword ptr [rsp + 16]
144 -      -      -      -     1.00    -     0.49   0.51   mov	qword ptr [rbx + 8], rax
145 -      -      -      -     1.00    -     0.51   0.49   mov	qword ptr [rbx], r14
146 -      -     0.99   0.01    -      -      -      -     mov	rsi, r13
147 -      -      -      -      -     1.00    -      -     jmp	.LBB6_4
148