Debian Codegraph @

llvm/test/tools/llvm-mca/AArch64/Exynos/asimd-st2.s

raw
1 # NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
2 # RUN: llvm-mca -mtriple=aarch64-linux-gnu -mcpu=exynos-m3 -resource-pressure=false -noalias=false < %s | FileCheck %s -check-prefixes=ALL,M3
3 # RUN: llvm-mca -mtriple=aarch64-linux-gnu -mcpu=exynos-m4 -resource-pressure=false -noalias=false < %s | FileCheck %s -check-prefixes=ALL,M4
4 # RUN: llvm-mca -mtriple=aarch64-linux-gnu -mcpu=exynos-m5 -resource-pressure=false -noalias=false < %s | FileCheck %s -check-prefixes=ALL,M5
5
6 st2 {v0.s, v1.s}[0], [sp]
7 st2 {v0.2s, v1.2s}, [sp]
8
9 st2 {v0.d, v1.d}[0], [sp]
10 st2 {v0.2d, v1.2d}, [sp]
11
12 st2 {v0.s, v1.s}[0], [sp], #8
13 st2 {v0.2s, v1.2s}, [sp], #16
14
15 st2 {v0.d, v1.d}[0], [sp], #16
16 st2 {v0.2d, v1.2d}, [sp], #32
17
18 st2 {v0.s, v1.s}[0], [sp], x0
19 st2 {v0.2s, v1.2s}, [sp], x0
20
21 st2 {v0.d, v1.d}[0], [sp], x0
22 st2 {v0.2d, v1.2d}, [sp], x0
23
24 # ALL: Iterations: 100
25 # ALL-NEXT: Instructions: 1200
26
27 # M3-NEXT: Total Cycles: 8703
28 # M3-NEXT: Total uOps: 5400
29
30 # M4-NEXT: Total Cycles: 2403
31 # M4-NEXT: Total uOps: 2300
32
33 # M5-NEXT: Total Cycles: 2403
34 # M5-NEXT: Total uOps: 2000
35
36 # ALL: Dispatch Width: 6
37
38 # M3-NEXT: uOps Per Cycle: 0.62
39 # M3-NEXT: IPC: 0.14
40 # M3-NEXT: Block RThroughput: 40.5
41
42 # M4-NEXT: uOps Per Cycle: 0.96
43 # M4-NEXT: IPC: 0.50
44 # M4-NEXT: Block RThroughput: 7.5
45
46 # M5-NEXT: uOps Per Cycle: 0.83
47 # M5-NEXT: IPC: 0.50
48 # M5-NEXT: Block RThroughput: 7.5
49
50 # ALL: Instruction Info:
51 # ALL-NEXT: [1]: #uOps
52 # ALL-NEXT: [2]: Latency
53 # ALL-NEXT: [3]: RThroughput
54 # ALL-NEXT: [4]: MayLoad
55 # ALL-NEXT: [5]: MayStore
56 # ALL-NEXT: [6]: HasSideEffects (U)
57
58 # ALL: [1] [2] [3] [4] [5] [6] Instructions:
59
60 # M3-NEXT: 4 7 3.00 * st2 { v0.s, v1.s }[0], [sp]
61 # M3-NEXT: 4 7 3.00 * st2 { v0.2s, v1.2s }, [sp]
62 # M3-NEXT: 4 7 3.00 * st2 { v0.d, v1.d }[0], [sp]
63 # M3-NEXT: 6 8 4.50 * st2 { v0.2d, v1.2d }, [sp]
64 # M3-NEXT: 4 7 3.00 * st2 { v0.s, v1.s }[0], [sp], #8
65 # M3-NEXT: 4 7 3.00 * st2 { v0.2s, v1.2s }, [sp], #16
66 # M3-NEXT: 4 7 3.00 * st2 { v0.d, v1.d }[0], [sp], #16
67 # M3-NEXT: 6 8 4.50 * st2 { v0.2d, v1.2d }, [sp], #32
68 # M3-NEXT: 4 7 3.00 * st2 { v0.s, v1.s }[0], [sp], x0
69 # M3-NEXT: 4 7 3.00 * st2 { v0.2s, v1.2s }, [sp], x0
70 # M3-NEXT: 4 7 3.00 * st2 { v0.d, v1.d }[0], [sp], x0
71 # M3-NEXT: 6 8 4.50 * st2 { v0.2d, v1.2d }, [sp], x0
72
73 # M4-NEXT: 1 2 0.50 * st2 { v0.s, v1.s }[0], [sp]
74 # M4-NEXT: 1 2 0.50 * st2 { v0.2s, v1.2s }, [sp]
75 # M4-NEXT: 1 2 0.50 * st2 { v0.d, v1.d }[0], [sp]
76 # M4-NEXT: 2 2 1.00 * st2 { v0.2d, v1.2d }, [sp]
77 # M4-NEXT: 2 2 0.50 * st2 { v0.s, v1.s }[0], [sp], #8
78 # M4-NEXT: 2 2 0.50 * st2 { v0.2s, v1.2s }, [sp], #16
79 # M4-NEXT: 2 2 0.50 * st2 { v0.d, v1.d }[0], [sp], #16
80 # M4-NEXT: 3 2 1.00 * st2 { v0.2d, v1.2d }, [sp], #32
81 # M4-NEXT: 2 2 0.50 * st2 { v0.s, v1.s }[0], [sp], x0
82 # M4-NEXT: 2 2 0.50 * st2 { v0.2s, v1.2s }, [sp], x0
83 # M4-NEXT: 2 2 0.50 * st2 { v0.d, v1.d }[0], [sp], x0
84 # M4-NEXT: 3 2 1.00 * st2 { v0.2d, v1.2d }, [sp], x0
85
86 # M5-NEXT: 1 2 0.50 * st2 { v0.s, v1.s }[0], [sp]
87 # M5-NEXT: 1 2 0.50 * st2 { v0.2s, v1.2s }, [sp]
88 # M5-NEXT: 1 2 0.50 * st2 { v0.d, v1.d }[0], [sp]
89 # M5-NEXT: 1 2 1.00 * st2 { v0.2d, v1.2d }, [sp]
90 # M5-NEXT: 2 2 0.50 * st2 { v0.s, v1.s }[0], [sp], #8
91 # M5-NEXT: 2 2 0.50 * st2 { v0.2s, v1.2s }, [sp], #16
92 # M5-NEXT: 2 2 0.50 * st2 { v0.d, v1.d }[0], [sp], #16
93 # M5-NEXT: 2 2 1.00 * st2 { v0.2d, v1.2d }, [sp], #32
94 # M5-NEXT: 2 2 0.50 * st2 { v0.s, v1.s }[0], [sp], x0
95 # M5-NEXT: 2 2 0.50 * st2 { v0.2s, v1.2s }, [sp], x0
96 # M5-NEXT: 2 2 0.50 * st2 { v0.d, v1.d }[0], [sp], x0
97 # M5-NEXT: 2 2 1.00 * st2 { v0.2d, v1.2d }, [sp], x0