load.s
2.54 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
# RUN: llvm-mca -march=aarch64 -mcpu=exynos-m3 -resource-pressure=false < %s | FileCheck %s -check-prefixes=ALL,M3
# RUN: llvm-mca -march=aarch64 -mcpu=exynos-m4 -resource-pressure=false < %s | FileCheck %s -check-prefixes=ALL,M4
# RUN: llvm-mca -march=aarch64 -mcpu=exynos-m5 -resource-pressure=false < %s | FileCheck %s -check-prefixes=ALL,M5
ldr w0, 1f
ldur x0, [sp, #8]
ldrb w0, [sp], #1
ldrsh w0, [sp, #2]!
ldr x0, [sp, #8]
ldrb w0, [sp, x31]
ldrsh w0, [sp, x31, lsl #1]
ldr w0, [sp, w31, sxtw]
ldr x0, [sp, w31, uxtw #3]
ldnp w0, w1, [sp, #8]
ldp x0, x1, [sp], #16
ldpsw x0, x1, [sp, #8]!
1:
# ALL: Iterations: 100
# ALL-NEXT: Instructions: 1200
# ALL-NEXT: Total Cycles: 1904
# M3-NEXT: Total uOps: 1600
# M4-NEXT: Total uOps: 1400
# M5-NEXT: Total uOps: 1400
# ALL: Dispatch Width: 6
# M3-NEXT: uOps Per Cycle: 0.84
# M4-NEXT: uOps Per Cycle: 0.74
# M5-NEXT: uOps Per Cycle: 0.74
# ALL-NEXT: IPC: 0.63
# ALL-NEXT: Block RThroughput: 6.0
# ALL: Instruction Info:
# ALL-NEXT: [1]: #uOps
# ALL-NEXT: [2]: Latency
# ALL-NEXT: [3]: RThroughput
# ALL-NEXT: [4]: MayLoad
# ALL-NEXT: [5]: MayStore
# ALL-NEXT: [6]: HasSideEffects (U)
# ALL: [1] [2] [3] [4] [5] [6] Instructions:
# ALL-NEXT: 1 4 0.50 * ldr w0, {{\.?}}Ltmp0
# ALL-NEXT: 1 4 0.50 * ldur x0, [sp, #8]
# ALL-NEXT: 1 4 0.50 * ldrb w0, [sp], #1
# ALL-NEXT: 1 4 0.50 * ldrsh w0, [sp, #2]!
# ALL-NEXT: 1 4 0.50 * ldr x0, [sp, #8]
# ALL-NEXT: 1 4 0.50 * ldrb w0, [sp, xzr]
# ALL-NEXT: 1 5 0.50 * ldrsh w0, [sp, xzr, lsl #1]
# M3-NEXT: 2 5 0.50 * ldr w0, [sp, wzr, sxtw]
# M3-NEXT: 2 5 0.50 * ldr x0, [sp, wzr, uxtw #3]
# M4-NEXT: 1 5 0.50 * ldr w0, [sp, wzr, sxtw]
# M4-NEXT: 1 5 0.50 * ldr x0, [sp, wzr, uxtw #3]
# M5-NEXT: 1 5 0.50 * ldr w0, [sp, wzr, sxtw]
# M5-NEXT: 1 5 0.50 * ldr x0, [sp, wzr, uxtw #3]
# ALL-NEXT: 1 4 0.50 * ldnp w0, w1, [sp, #8]
# ALL-NEXT: 2 4 0.50 * ldp x0, x1, [sp], #16
# ALL-NEXT: 2 4 0.50 * ldpsw x0, x1, [sp, #8]!