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
| # NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=bdver2 -iterations=1 -timeline -resource-pressure=false < %s | FileCheck %s
# The vmul can start executing 3cy in advance. That is beause the first use
# operand (i.e. %xmm1) is a ReadAfterLd. That means, the memory operand is
# evaluated before %xmm1.
vaddps %xmm0, %xmm0, %xmm1
vmulps (%rdi), %xmm1, %xmm2
# CHECK: Iterations: 1
# CHECK-NEXT: Instructions: 2
# CHECK-NEXT: Total Cycles: 13
# CHECK-NEXT: Total uOps: 2
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 0.15
# CHECK-NEXT: IPC: 0.15
# CHECK-NEXT: Block RThroughput: 1.5
# 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: 1 5 1.00 vaddps %xmm0, %xmm0, %xmm1
# CHECK-NEXT: 1 10 1.50 * vmulps (%rdi), %xmm1, %xmm2
# CHECK: Timeline view:
# CHECK-NEXT: 012
# CHECK-NEXT: Index 0123456789
# CHECK: [0,0] DeeeeeER . . vaddps %xmm0, %xmm0, %xmm1
# CHECK-NEXT: [0,1] DeeeeeeeeeeER vmulps (%rdi), %xmm1, %xmm2
# 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 vaddps %xmm0, %xmm0, %xmm1
# CHECK-NEXT: 1. 1 1.0 0.0 0.0 vmulps (%rdi), %xmm1, %xmm2
# CHECK-NEXT: 1 1.0 0.5 0.0 <total>
|