1 # NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
2 # RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=znver4 -instruction-tables < %s | FileCheck %s
6 vpopcntd
(%rdi
){1to4
}, %xmm0
8 vpopcntd
%xmm1
, %xmm0
{%k1
}
9 vpopcntd
(%rdi
), %xmm0
{%k1
}
10 vpopcntd
(%rdi
){1to4
}, %xmm0
{%k1
}
12 vpopcntd
%xmm1
, %xmm0
{%k1
} {z
}
13 vpopcntd
(%rdi
), %xmm0
{%k1
} {z
}
14 vpopcntd
(%rdi
){1to4
}, %xmm0
{%k1
} {z
}
17 vpopcntd
(%rdi
), %ymm0
18 vpopcntd
(%rdi
){1to8
}, %ymm0
20 vpopcntd
%ymm1
, %ymm0
{%k1
}
21 vpopcntd
(%rdi
), %ymm0
{%k1
}
22 vpopcntd
(%rdi
){1to8
}, %ymm0
{%k1
}
24 vpopcntd
%ymm1
, %ymm0
{%k1
} {z
}
25 vpopcntd
(%rdi
), %ymm0
{%k1
} {z
}
26 vpopcntd
(%rdi
){1to8
}, %ymm0
{%k1
} {z
}
29 vpopcntq
(%rdi
), %xmm0
30 vpopcntq
(%rdi
){1to2
}, %xmm0
32 vpopcntq
%xmm1
, %xmm0
{%k1
}
33 vpopcntq
(%rdi
), %xmm0
{%k1
}
34 vpopcntq
(%rdi
){1to2
}, %xmm0
{%k1
}
36 vpopcntq
%xmm1
, %xmm0
{%k1
} {z
}
37 vpopcntq
(%rdi
), %xmm0
{%k1
} {z
}
38 vpopcntq
(%rdi
){1to2
}, %xmm0
{%k1
} {z
}
41 vpopcntq
(%rdi
), %ymm0
42 vpopcntq
(%rdi
){1to4
}, %ymm0
44 vpopcntq
%ymm1
, %ymm0
{%k1
}
45 vpopcntq
(%rdi
), %ymm0
{%k1
}
46 vpopcntq
(%rdi
){1to4
}, %ymm0
{%k1
}
48 vpopcntq
%ymm1
, %ymm0
{%k1
} {z
}
49 vpopcntq
(%rdi
), %ymm0
{%k1
} {z
}
50 vpopcntq
(%rdi
){1to4
}, %ymm0
{%k1
} {z
}
52 # CHECK: Instruction Info:
53 # CHECK-NEXT: [1]: #uOps
54 # CHECK-NEXT: [2]: Latency
55 # CHECK-NEXT: [3]: RThroughput
56 # CHECK-NEXT: [4]: MayLoad
57 # CHECK-NEXT: [5]: MayStore
58 # CHECK-NEXT: [6]: HasSideEffects (U)
60 # CHECK: [1] [2] [3] [4] [5] [6] Instructions:
61 # CHECK-NEXT: 1 2 1.00 vpopcntd %xmm1, %xmm0
62 # CHECK-NEXT: 1 8 0.50 * vpopcntd (%rdi), %xmm0
63 # CHECK-NEXT: 1 8 0.50 * vpopcntd (%rdi){1to4}, %xmm0
64 # CHECK-NEXT: 1 2 1.00 vpopcntd %xmm1, %xmm0 {%k1}
65 # CHECK-NEXT: 1 8 0.50 * vpopcntd (%rdi), %xmm0 {%k1}
66 # CHECK-NEXT: 1 8 0.50 * vpopcntd (%rdi){1to4}, %xmm0 {%k1}
67 # CHECK-NEXT: 1 2 1.00 vpopcntd %xmm1, %xmm0 {%k1} {z}
68 # CHECK-NEXT: 1 8 0.50 * vpopcntd (%rdi), %xmm0 {%k1} {z}
69 # CHECK-NEXT: 1 8 0.50 * vpopcntd (%rdi){1to4}, %xmm0 {%k1} {z}
70 # CHECK-NEXT: 1 1 0.25 vpopcntd %ymm1, %ymm0
71 # CHECK-NEXT: 1 8 0.50 * vpopcntd (%rdi), %ymm0
72 # CHECK-NEXT: 1 8 0.50 * vpopcntd (%rdi){1to8}, %ymm0
73 # CHECK-NEXT: 1 1 0.25 vpopcntd %ymm1, %ymm0 {%k1}
74 # CHECK-NEXT: 1 8 0.50 * vpopcntd (%rdi), %ymm0 {%k1}
75 # CHECK-NEXT: 1 8 0.50 * vpopcntd (%rdi){1to8}, %ymm0 {%k1}
76 # CHECK-NEXT: 1 1 0.25 vpopcntd %ymm1, %ymm0 {%k1} {z}
77 # CHECK-NEXT: 1 8 0.50 * vpopcntd (%rdi), %ymm0 {%k1} {z}
78 # CHECK-NEXT: 1 8 0.50 * vpopcntd (%rdi){1to8}, %ymm0 {%k1} {z}
79 # CHECK-NEXT: 1 2 1.00 vpopcntq %xmm1, %xmm0
80 # CHECK-NEXT: 1 8 0.50 * vpopcntq (%rdi), %xmm0
81 # CHECK-NEXT: 1 8 0.50 * vpopcntq (%rdi){1to2}, %xmm0
82 # CHECK-NEXT: 1 2 1.00 vpopcntq %xmm1, %xmm0 {%k1}
83 # CHECK-NEXT: 1 8 0.50 * vpopcntq (%rdi), %xmm0 {%k1}
84 # CHECK-NEXT: 1 8 0.50 * vpopcntq (%rdi){1to2}, %xmm0 {%k1}
85 # CHECK-NEXT: 1 2 1.00 vpopcntq %xmm1, %xmm0 {%k1} {z}
86 # CHECK-NEXT: 1 8 0.50 * vpopcntq (%rdi), %xmm0 {%k1} {z}
87 # CHECK-NEXT: 1 8 0.50 * vpopcntq (%rdi){1to2}, %xmm0 {%k1} {z}
88 # CHECK-NEXT: 1 1 0.25 vpopcntq %ymm1, %ymm0
89 # CHECK-NEXT: 1 8 0.50 * vpopcntq (%rdi), %ymm0
90 # CHECK-NEXT: 1 8 0.50 * vpopcntq (%rdi){1to4}, %ymm0
91 # CHECK-NEXT: 1 1 0.25 vpopcntq %ymm1, %ymm0 {%k1}
92 # CHECK-NEXT: 1 8 0.50 * vpopcntq (%rdi), %ymm0 {%k1}
93 # CHECK-NEXT: 1 8 0.50 * vpopcntq (%rdi){1to4}, %ymm0 {%k1}
94 # CHECK-NEXT: 1 1 0.25 vpopcntq %ymm1, %ymm0 {%k1} {z}
95 # CHECK-NEXT: 1 8 0.50 * vpopcntq (%rdi), %ymm0 {%k1} {z}
96 # CHECK-NEXT: 1 8 0.50 * vpopcntq (%rdi){1to4}, %ymm0 {%k1} {z}
99 # CHECK-NEXT: [0] - Zn4AGU0
100 # CHECK-NEXT: [1] - Zn4AGU1
101 # CHECK-NEXT: [2] - Zn4AGU2
102 # CHECK-NEXT: [3] - Zn4ALU0
103 # CHECK-NEXT: [4] - Zn4ALU1
104 # CHECK-NEXT: [5] - Zn4ALU2
105 # CHECK-NEXT: [6] - Zn4ALU3
106 # CHECK-NEXT: [7] - Zn4BRU1
107 # CHECK-NEXT: [8] - Zn4FP0
108 # CHECK-NEXT: [9] - Zn4FP1
109 # CHECK-NEXT: [10] - Zn4FP2
110 # CHECK-NEXT: [11] - Zn4FP3
111 # CHECK-NEXT: [12.0] - Zn4FP45
112 # CHECK-NEXT: [12.1] - Zn4FP45
113 # CHECK-NEXT: [13] - Zn4FPSt
114 # CHECK-NEXT: [14.0] - Zn4LSU
115 # CHECK-NEXT: [14.1] - Zn4LSU
116 # CHECK-NEXT: [14.2] - Zn4LSU
117 # CHECK-NEXT: [15.0] - Zn4Load
118 # CHECK-NEXT: [15.1] - Zn4Load
119 # CHECK-NEXT: [15.2] - Zn4Load
120 # CHECK-NEXT: [16.0] - Zn4Store
121 # CHECK-NEXT: [16.1] - Zn4Store
123 # CHECK: Resource pressure per iteration:
124 # CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12.0] [12.1] [13] [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1]
125 # CHECK-NEXT: - - - - - - - - 13.50 13.50 7.50 7.50 12.00 12.00 - 8.00 8.00 8.00 8.00 8.00 8.00 - -
127 # CHECK: Resource pressure by instruction:
128 # CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12.0] [12.1] [13] [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1] Instructions:
129 # CHECK-NEXT: - - - - - - - - 1.00 1.00 - - - - - - - - - - - - - vpopcntd %xmm1, %xmm0
130 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntd (%rdi), %xmm0
131 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntd (%rdi){1to4}, %xmm0
132 # CHECK-NEXT: - - - - - - - - 1.00 1.00 - - - - - - - - - - - - - vpopcntd %xmm1, %xmm0 {%k1}
133 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntd (%rdi), %xmm0 {%k1}
134 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntd (%rdi){1to4}, %xmm0 {%k1}
135 # CHECK-NEXT: - - - - - - - - 1.00 1.00 - - - - - - - - - - - - - vpopcntd %xmm1, %xmm0 {%k1} {z}
136 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntd (%rdi), %xmm0 {%k1} {z}
137 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntd (%rdi){1to4}, %xmm0 {%k1} {z}
138 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 - - - - - - - - - - - vpopcntd %ymm1, %ymm0
139 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntd (%rdi), %ymm0
140 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntd (%rdi){1to8}, %ymm0
141 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 - - - - - - - - - - - vpopcntd %ymm1, %ymm0 {%k1}
142 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntd (%rdi), %ymm0 {%k1}
143 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntd (%rdi){1to8}, %ymm0 {%k1}
144 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 - - - - - - - - - - - vpopcntd %ymm1, %ymm0 {%k1} {z}
145 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntd (%rdi), %ymm0 {%k1} {z}
146 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntd (%rdi){1to8}, %ymm0 {%k1} {z}
147 # CHECK-NEXT: - - - - - - - - 1.00 1.00 - - - - - - - - - - - - - vpopcntq %xmm1, %xmm0
148 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntq (%rdi), %xmm0
149 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntq (%rdi){1to2}, %xmm0
150 # CHECK-NEXT: - - - - - - - - 1.00 1.00 - - - - - - - - - - - - - vpopcntq %xmm1, %xmm0 {%k1}
151 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntq (%rdi), %xmm0 {%k1}
152 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntq (%rdi){1to2}, %xmm0 {%k1}
153 # CHECK-NEXT: - - - - - - - - 1.00 1.00 - - - - - - - - - - - - - vpopcntq %xmm1, %xmm0 {%k1} {z}
154 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntq (%rdi), %xmm0 {%k1} {z}
155 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntq (%rdi){1to2}, %xmm0 {%k1} {z}
156 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 - - - - - - - - - - - vpopcntq %ymm1, %ymm0
157 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntq (%rdi), %ymm0
158 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntq (%rdi){1to4}, %ymm0
159 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 - - - - - - - - - - - vpopcntq %ymm1, %ymm0 {%k1}
160 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntq (%rdi), %ymm0 {%k1}
161 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntq (%rdi){1to4}, %ymm0 {%k1}
162 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 - - - - - - - - - - - vpopcntq %ymm1, %ymm0 {%k1} {z}
163 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntq (%rdi), %ymm0 {%k1} {z}
164 # CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 0.50 0.50 - 0.33 0.33 0.33 0.33 0.33 0.33 - - vpopcntq (%rdi){1to4}, %ymm0 {%k1} {z}