Compiler projects using llvm
# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -iterations=100 -timeline -timeline-max-iterations=1 -bottleneck-analysis < %s | FileCheck %s

vhaddps %xmm0, %xmm0, %xmm1

# CHECK:      Iterations:        100
# CHECK-NEXT: Instructions:      100
# CHECK-NEXT: Total Cycles:      106
# CHECK-NEXT: Total uOps:        100

# CHECK:      Dispatch Width:    2
# CHECK-NEXT: uOps Per Cycle:    0.94
# CHECK-NEXT: IPC:               0.94
# CHECK-NEXT: Block RThroughput: 1.0

# CHECK:      Cycles with backend pressure increase [ 76.42% ]
# CHECK-NEXT: Throughput Bottlenecks:
# CHECK-NEXT:   Resource Pressure       [ 76.42% ]
# CHECK-NEXT:   - JFPA  [ 76.42% ]
# CHECK-NEXT:   - JFPU0  [ 76.42% ]
# CHECK-NEXT:   Data Dependencies:      [ 0.00% ]
# CHECK-NEXT:   - Register Dependencies [ 0.00% ]
# CHECK-NEXT:   - Memory Dependencies   [ 0.00% ]

# CHECK:      Critical sequence based on the simulation:

# CHECK:                    Instruction                                 Dependency Information
# CHECK-NEXT:  +----< 0.    vhaddps	%xmm0, %xmm0, %xmm1
# CHECK-NEXT:  |
# CHECK-NEXT:  |    < loop carried >
# CHECK-NEXT:  |
# CHECK-NEXT:  +----> 0.    vhaddps	%xmm0, %xmm0, %xmm1               ## RESOURCE interference:  JFPA [ probability: 99% ]
# CHECK-NEXT:  |
# CHECK-NEXT:  |    < loop carried >
# CHECK-NEXT:  |
# CHECK-NEXT:  +----> 0.    vhaddps	%xmm0, %xmm0, %xmm1               ## RESOURCE interference:  JFPA [ probability: 99% ]

# 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      4     1.00                        vhaddps	%xmm0, %xmm0, %xmm1

# 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:  -      -      -     1.00    -     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    -      -      -      -      -      -      -      -     vhaddps	%xmm0, %xmm0, %xmm1

# CHECK:      Timeline view:
# CHECK-NEXT: Index     0123456

# CHECK:      [0,0]     DeeeeER   vhaddps	%xmm0, %xmm0, %xmm1

# 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       vhaddps	%xmm0, %xmm0, %xmm1