llvm/llvm/test/tools/llvm-mca/X86/Znver4/partially-overlapping-group-resources.s

# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=znver4 -timeline -timeline-max-iterations=1 < %s | FileCheck %s

# This is a test for issue #108157.
#
# llvm-mca was crashing when analyzing the following code snippet. This was due to a bug in the
# instruction issue logic (from class ResourceManager) which was affecting instructions declaring
# consumption of partially overlapping resources.
# This test makes sure that analysis is successful, and that no crash occurs.

.intel_syntax
vpconflictd zmm0, zmm3
kxnorw k1, k1, k1
vpxord zmm1, zmm1, zmm1

# CHECK:      Iterations:        100
# CHECK-NEXT: Instructions:      300
# CHECK-NEXT: Total Cycles:      209
# CHECK-NEXT: Total uOps:        600

# CHECK:      Dispatch Width:    6
# CHECK-NEXT: uOps Per Cycle:    2.87
# CHECK-NEXT: IPC:               1.44
# 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:  4      6     1.50                        vpconflictd	zmm0, zmm3
# CHECK-NEXT:  1      1     0.50                        kxnorw	k1, k1, k1
# CHECK-NEXT:  1      0     0.17                        vpxord	zmm1, zmm1, zmm1

# CHECK:      Resources:
# CHECK-NEXT: [0]   - Zn4AGU0
# CHECK-NEXT: [1]   - Zn4AGU1
# CHECK-NEXT: [2]   - Zn4AGU2
# CHECK-NEXT: [3]   - Zn4ALU0
# CHECK-NEXT: [4]   - Zn4ALU1
# CHECK-NEXT: [5]   - Zn4ALU2
# CHECK-NEXT: [6]   - Zn4ALU3
# CHECK-NEXT: [7]   - Zn4BRU1
# CHECK-NEXT: [8]   - Zn4FP0
# CHECK-NEXT: [9]   - Zn4FP1
# CHECK-NEXT: [10]  - Zn4FP2
# CHECK-NEXT: [11]  - Zn4FP3
# CHECK-NEXT: [12.0] - Zn4FP45
# CHECK-NEXT: [12.1] - Zn4FP45
# CHECK-NEXT: [13]  - Zn4FPSt
# CHECK-NEXT: [14.0] - Zn4LSU
# CHECK-NEXT: [14.1] - Zn4LSU
# CHECK-NEXT: [14.2] - Zn4LSU
# CHECK-NEXT: [15.0] - Zn4Load
# CHECK-NEXT: [15.1] - Zn4Load
# CHECK-NEXT: [15.2] - Zn4Load
# CHECK-NEXT: [16.0] - Zn4Store
# CHECK-NEXT: [16.1] - Zn4Store

# CHECK:      Resource pressure per iteration:
# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12.0] [12.1] [13]   [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1]
# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.76   1.76   1.73   1.75    -      -      -      -      -      -      -      -      -      -      -

# CHECK:      Resource pressure by instruction:
# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12.0] [12.1] [13]   [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1] Instructions:
# CHECK-NEXT:  -      -      -      -      -      -      -      -     1.76   1.76   0.74   1.74    -      -      -      -      -      -      -      -      -      -      -     vpconflictd	zmm0, zmm3
# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -     0.99   0.01    -      -      -      -      -      -      -      -      -      -      -     kxnorw	k1, k1, k1
# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     vpxord	zmm1, zmm1, zmm1

# CHECK:      Timeline view:
# CHECK-NEXT: Index     012345678

# CHECK:      [0,0]     DeeeeeeER   vpconflictd	zmm0, zmm3
# CHECK-NEXT: [0,1]     D==eE---R   kxnorw	k1, k1, k1
# CHECK-NEXT: [0,2]     D-------R   vpxord	zmm1, zmm1, zmm1

# 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       vpconflictd	zmm0, zmm3
# CHECK-NEXT: 1.     1     3.0    3.0    3.0       kxnorw	k1, k1, k1
# CHECK-NEXT: 2.     1     0.0    0.0    7.0       vpxord	zmm1, zmm1, zmm1
# CHECK-NEXT:        1     1.3    1.3    3.3       <total>