reference, declarationdefinition
definition → references, declarations, derived classes, virtual overrides
reference to multiple definitions → definitions
unreferenced
    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
   67
   68
   69
   70
   71
   72
   73
   74
   75
   76
   77
   78
   79
   80
   81
   82
   83
   84
   85
   86
# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -iterations=1500 -timeline -timeline-max-iterations=3 < %s | FileCheck %s

# perf stat reports a throughput of 0.60 IPC for this code snippet.

# The lzcnt cannot execute in parallel with the imul because there is a false
# dependency on %bx.

imul %ax, %bx
lzcnt %ax, %bx
add %cx, %bx

# CHECK:      Iterations:        1500
# CHECK-NEXT: Instructions:      4500
# CHECK-NEXT: Total Cycles:      7503
# CHECK-NEXT: Total uOps:        4500

# CHECK:      Dispatch Width:    2
# CHECK-NEXT: uOps Per Cycle:    0.60
# CHECK-NEXT: IPC:               0.60
# 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      3     1.00                        imulw	%ax, %bx
# CHECK-NEXT:  1      1     0.50                        lzcntw	%ax, %bx
# CHECK-NEXT:  1      1     0.50                        addw	%cx, %bx

# CHECK:      Resources:
# CHECK-NEXT: [0]   - JALU0
# CHECK-NEXT: [1]   - JALU1
# CHECK-NEXT: [2]   - JDiv
# CHECK-NEXT: [3]   - JFPA
# CHECK-NEXT: [4]   - JFPM
# CHECK-NEXT: [5]   - JFPU0
# CHECK-NEXT: [6]   - JFPU1
# CHECK-NEXT: [7]   - JLAGU
# CHECK-NEXT: [8]   - JMul
# CHECK-NEXT: [9]   - JSAGU
# CHECK-NEXT: [10]  - JSTC
# CHECK-NEXT: [11]  - JVALU0
# CHECK-NEXT: [12]  - JVALU1
# CHECK-NEXT: [13]  - JVIMUL

# CHECK:      Resource pressure per iteration:
# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12]   [13]
# CHECK-NEXT: 1.50   1.50    -      -      -      -      -      -     1.00    -      -      -      -      -

# CHECK:      Resource pressure by instruction:
# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12]   [13]   Instructions:
# CHECK-NEXT:  -     1.00    -      -      -      -      -      -     1.00    -      -      -      -      -     imulw	%ax, %bx
# CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -      -     lzcntw	%ax, %bx
# CHECK-NEXT: 0.50   0.50    -      -      -      -      -      -      -      -      -      -      -      -     addw	%cx, %bx

# CHECK:      Timeline view:
# CHECK-NEXT:                     01234567
# CHECK-NEXT: Index     0123456789

# CHECK:      [0,0]     DeeeER    .    . .   imulw	%ax, %bx
# CHECK-NEXT: [0,1]     D===eER   .    . .   lzcntw	%ax, %bx
# CHECK-NEXT: [0,2]     .D===eER  .    . .   addw	%cx, %bx
# CHECK-NEXT: [1,0]     .D====eeeER    . .   imulw	%ax, %bx
# CHECK-NEXT: [1,1]     . D======eER   . .   lzcntw	%ax, %bx
# CHECK-NEXT: [1,2]     . D=======eER  . .   addw	%cx, %bx
# CHECK-NEXT: [2,0]     .  D=======eeeER .   imulw	%ax, %bx
# CHECK-NEXT: [2,1]     .  D==========eER.   lzcntw	%ax, %bx
# CHECK-NEXT: [2,2]     .   D==========eER   addw	%cx, %bx

# 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.     3     4.7    0.3    0.0       imulw	%ax, %bx
# CHECK-NEXT: 1.     3     7.3    0.0    0.0       lzcntw	%ax, %bx
# CHECK-NEXT: 2.     3     7.7    0.0    0.0       addw	%cx, %bx
# CHECK-NEXT:        3     6.6    0.1    0.0       <total>