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
| # NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=znver1 -iterations=1 -resource-pressure=false -timeline < %s | FileCheck %s
# An instruction that writes to a 32-bit register will not have any false
# dependence on the corresponding 64-bit register because the upper part of
# the 64-bit register is set to zero
imulq %rax, %rcx
addl %edx, %ecx
addq %rcx, %rdx
# CHECK: Iterations: 1
# CHECK-NEXT: Instructions: 3
# CHECK-NEXT: Total Cycles: 9
# CHECK-NEXT: Total uOps: 4
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 0.44
# CHECK-NEXT: IPC: 0.33
# CHECK-NEXT: Block RThroughput: 1.0
# CHECK: Instruction Info:
# CHECK-NEXT: [1]: #uOps
# CHECK-NEXT: [2]: Latency
# CHECK-NEXT: [3]: RThroughput
# CHECK-NEXT: [4]: MayLoad
# CHECK-NEXT: [5]: MayStore
# CHECK-NEXT: [6]: HasSideEffects (U)
# CHECK: [1] [2] [3] [4] [5] [6] Instructions:
# CHECK-NEXT: 2 4 1.00 imulq %rax, %rcx
# CHECK-NEXT: 1 1 0.25 addl %edx, %ecx
# CHECK-NEXT: 1 1 0.25 addq %rcx, %rdx
# CHECK: Timeline view:
# CHECK-NEXT: Index 012345678
# CHECK: [0,0] DeeeeER . imulq %rax, %rcx
# CHECK-NEXT: [0,1] D====eER. addl %edx, %ecx
# CHECK-NEXT: [0,2] D=====eER addq %rcx, %rdx
# CHECK: Average Wait times (based on the timeline view):
# CHECK-NEXT: [0]: Executions
# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
# CHECK: [0] [1] [2] [3]
# CHECK-NEXT: 0. 1 1.0 1.0 0.0 imulq %rax, %rcx
# CHECK-NEXT: 1. 1 5.0 0.0 0.0 addl %edx, %ecx
# CHECK-NEXT: 2. 1 6.0 0.0 0.0 addq %rcx, %rdx
# CHECK-NEXT: 1 4.0 0.3 0.0 <total>
|