Debian Codegraph @

llvm/test/tools/llvm-mca/RISCV/MIPS/p8700.s

raw
1 # NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
2 # RUN: llvm-mca -mtriple=riscv64 -mcpu=mips-p8700 -timeline -iterations=1 < %s | FileCheck %s
3
4 # A few instructions to test the pipeline:
5 # - Integer division (IDiv) exercises the p8700GpDiv resource.
6 # - Integer multiplication (IMul) uses p8700GpMul.
7 # - Floating-point multiplication uses the FPUL pipeline.
8 # - Load/Store instructions use the LSU pipeline.
9 # - Simple ALU instructions test the p8700WriteEitherALU and p8700IssueAL2 resources.
10 # - A jump instruction to test the CTI pipeline.
11
12 # Integer division: a0 = a1 / a2
13 # Exercises p8700GpDiv resource.
14 div a0, a1, a2
15
16 # Integer multiplication: a4 = a1 * a2
17 # Exercises p8700GpMul resource.
18 mul a4, a1, a2
19
20 # Floating-point multiply: f1 = f2 * f3 (single precision)
21 # Exercises p8700FpuLong + p8700FpuApu resources.
22 fmul.s f1, f2, f3
23
24 # Load/Store: load word from a0 into a3, then store a3 into a1
25 # Exercises p8700IssueLSU resource.
26 lw a3, 0(a0)
27 sw a3, 0(a1)
28
29 # Simple ALU operations (adding two registers, rotating bits)
30 # Exercises p8700WriteEitherALU.
31 add a5, a1, a2
32 ror a6, a5, a2
33
34 # A jump instruction: a simple forward jump
35 # Exercises p8700IssueCTI resource.
36 jal x0, .Lend
37
38 add a7, a4, a0 # Instruction after jump (won't execute)
39 .Lend:
40 nop
41
42 # CHECK: Iterations: 1
43 # CHECK-NEXT: Instructions: 10
44 # CHECK-NEXT: Total Cycles: 17
45 # CHECK-NEXT: Total uOps: 10
46
47 # CHECK: Dispatch Width: 4
48 # CHECK-NEXT: uOps Per Cycle: 0.59
49 # CHECK-NEXT: IPC: 0.59
50 # CHECK-NEXT: Block RThroughput: 7.0
51
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)
59
60 # CHECK: [1] [2] [3] [4] [5] [6] Instructions:
61 # CHECK-NEXT: 1 7 7.00 div a0, a1, a2
62 # CHECK-NEXT: 1 4 1.00 mul a4, a1, a2
63 # CHECK-NEXT: 1 5 1.00 fmul.s ft1, ft2, ft3
64 # CHECK-NEXT: 1 4 1.00 * lw a3, 0(a0)
65 # CHECK-NEXT: 1 3 1.00 * sw a3, 0(a1)
66 # CHECK-NEXT: 1 1 0.50 add a5, a1, a2
67 # CHECK-NEXT: 1 1 0.50 ror a6, a5, a2
68 # CHECK-NEXT: 1 1 1.00 j .Lend
69 # CHECK-NEXT: 1 1 0.50 add a7, a4, a0
70 # CHECK-NEXT: 1 0 0.50 nop
71
72 # CHECK: Resources:
73 # CHECK-NEXT: [0.0] - p8700AGQ
74 # CHECK-NEXT: [0.1] - p8700AGQ
75 # CHECK-NEXT: [0.2] - p8700AGQ
76 # CHECK-NEXT: [1] - p8700ALQ
77 # CHECK-NEXT: [2.0] - p8700FPQ
78 # CHECK-NEXT: [2.1] - p8700FPQ
79 # CHECK-NEXT: [2.2] - p8700FPQ
80 # CHECK-NEXT: [3] - p8700FpuApu
81 # CHECK-NEXT: [4] - p8700FpuLong
82 # CHECK-NEXT: [5] - p8700GpDiv
83 # CHECK-NEXT: [6] - p8700GpMul
84 # CHECK-NEXT: [7] - p8700IssueAL2
85 # CHECK-NEXT: [8] - p8700IssueCTI
86 # CHECK-NEXT: [9] - p8700IssueFPUL
87 # CHECK-NEXT: [10] - p8700IssueFPUS
88 # CHECK-NEXT: [11] - p8700IssueLSU
89
90 # CHECK: Resource pressure per iteration:
91 # CHECK-NEXT: [0.0] [0.1] [0.2] [1] [2.0] [2.1] [2.2] [3] [4] [5] [6] [7] [8] [9] [10] [11]
92 # CHECK-NEXT: 1.00 1.00 1.00 2.00 - - - 1.00 1.00 7.00 1.00 2.00 1.00 - - 2.00
93
94 # CHECK: Resource pressure by instruction:
95 # CHECK-NEXT: [0.0] [0.1] [0.2] [1] [2.0] [2.1] [2.2] [3] [4] [5] [6] [7] [8] [9] [10] [11] Instructions:
96 # CHECK-NEXT: - - - - - - - - - 7.00 - - - - - - div a0, a1, a2
97 # CHECK-NEXT: - - - - - - - - - - 1.00 - - - - - mul a4, a1, a2
98 # CHECK-NEXT: - - - - - - - 1.00 1.00 - - - - - - - fmul.s ft1, ft2, ft3
99 # CHECK-NEXT: - 1.00 - - - - - - - - - - - - - 1.00 lw a3, 0(a0)
100 # CHECK-NEXT: 1.00 - - - - - - - - - - - - - - 1.00 sw a3, 0(a1)
101 # CHECK-NEXT: - - - - - - - - - - - 1.00 - - - - add a5, a1, a2
102 # CHECK-NEXT: - - - 1.00 - - - - - - - - - - - - ror a6, a5, a2
103 # CHECK-NEXT: - - 1.00 - - - - - - - - - 1.00 - - - j .Lend
104 # CHECK-NEXT: - - - 1.00 - - - - - - - - - - - - add a7, a4, a0
105 # CHECK-NEXT: - - - - - - - - - - - 1.00 - - - - nop
106
107 # CHECK: Timeline view:
108 # CHECK-NEXT: 0123456
109 # CHECK-NEXT: Index 0123456789
110
111 # CHECK: [0,0] DeeeeeeeER. .. div a0, a1, a2
112 # CHECK-NEXT: [0,1] DeeeeE---R. .. mul a4, a1, a2
113 # CHECK-NEXT: [0,2] DeeeeeE--R. .. fmul.s ft1, ft2, ft3
114 # CHECK-NEXT: [0,3] D=======eeeeER .. lw a3, 0(a0)
115 # CHECK-NEXT: [0,4] .D==========eeeER sw a3, 0(a1)
116 # CHECK-NEXT: [0,5] .DeE------------R add a5, a1, a2
117 # CHECK-NEXT: [0,6] .D=eE-----------R ror a6, a5, a2
118 # CHECK-NEXT: [0,7] .DeE------------R j .Lend
119 # CHECK-NEXT: [0,8] . D=====eE------R add a7, a4, a0
120 # CHECK-NEXT: [0,9] . DE------------R nop
121
122 # CHECK: Average Wait times (based on the timeline view):
123 # CHECK-NEXT: [0]: Executions
124 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
125 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
126 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
127
128 # CHECK: [0] [1] [2] [3]
129 # CHECK-NEXT: 0. 1 1.0 1.0 0.0 div a0, a1, a2
130 # CHECK-NEXT: 1. 1 1.0 1.0 3.0 mul a4, a1, a2
131 # CHECK-NEXT: 2. 1 1.0 1.0 2.0 fmul.s ft1, ft2, ft3
132 # CHECK-NEXT: 3. 1 8.0 0.0 0.0 lw a3, 0(a0)
133 # CHECK-NEXT: 4. 1 11.0 0.0 0.0 sw a3, 0(a1)
134 # CHECK-NEXT: 5. 1 1.0 1.0 12.0 add a5, a1, a2
135 # CHECK-NEXT: 6. 1 2.0 0.0 11.0 ror a6, a5, a2
136 # CHECK-NEXT: 7. 1 1.0 1.0 12.0 j .Lend
137 # CHECK-NEXT: 8. 1 6.0 0.0 6.0 add a7, a4, a0
138 # CHECK-NEXT: 9. 1 1.0 1.0 12.0 nop
139 # CHECK-NEXT: 1 3.3 0.6 5.8 <total>