# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=haswell -timeline -iterations=2 < %s | FileCheck %s
# PR51494: A read-advance on the implicit read of EDX/RDX was missing.
# LLVM-MCA-BEGIN
mulxl (%rdi), %eax, %edx
# LLVM-MCA-END
# LLVM-MCA-BEGIN
mulxq (%rdi), %rax, %rdx
# LLVM-MCA-END
# CHECK: [0] Code Region
# CHECK: Iterations: 2
# CHECK-NEXT: Instructions: 2
# CHECK-NEXT: Total Cycles: 16
# CHECK-NEXT: Total uOps: 10
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 0.63
# CHECK-NEXT: IPC: 0.13
# CHECK-NEXT: Block RThroughput: 1.3
# 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: 5 9 1.00 * mulxl (%rdi), %eax, %edx
# CHECK: Resources:
# CHECK-NEXT: [0] - HWDivider
# CHECK-NEXT: [1] - HWFPDivider
# CHECK-NEXT: [2] - HWPort0
# CHECK-NEXT: [3] - HWPort1
# CHECK-NEXT: [4] - HWPort2
# CHECK-NEXT: [5] - HWPort3
# CHECK-NEXT: [6] - HWPort4
# CHECK-NEXT: [7] - HWPort5
# CHECK-NEXT: [8] - HWPort6
# CHECK-NEXT: [9] - HWPort7
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9]
# CHECK-NEXT: - - 0.50 1.00 0.50 0.50 - 0.50 1.00 -
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] Instructions:
# CHECK-NEXT: - - 0.50 1.00 0.50 0.50 - 0.50 1.00 - mulxl (%rdi), %eax, %edx
# CHECK: Timeline view:
# CHECK-NEXT: 012345
# CHECK-NEXT: Index 0123456789
# CHECK: [0,0] DeeeeeeeeeER . mulxl (%rdi), %eax, %edx
# CHECK-NEXT: [1,0] . D==eeeeeeeeeER mulxl (%rdi), %eax, %edx
# 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. 2 2.0 0.5 0.0 mulxl (%rdi), %eax, %edx
# CHECK: [1] Code Region
# CHECK: Iterations: 2
# CHECK-NEXT: Instructions: 2
# CHECK-NEXT: Total Cycles: 16
# CHECK-NEXT: Total uOps: 8
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 0.50
# CHECK-NEXT: IPC: 0.13
# 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: 4 9 1.00 * mulxq (%rdi), %rax, %rdx
# CHECK: Resources:
# CHECK-NEXT: [0] - HWDivider
# CHECK-NEXT: [1] - HWFPDivider
# CHECK-NEXT: [2] - HWPort0
# CHECK-NEXT: [3] - HWPort1
# CHECK-NEXT: [4] - HWPort2
# CHECK-NEXT: [5] - HWPort3
# CHECK-NEXT: [6] - HWPort4
# CHECK-NEXT: [7] - HWPort5
# CHECK-NEXT: [8] - HWPort6
# CHECK-NEXT: [9] - HWPort7
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9]
# CHECK-NEXT: - - - 1.00 0.50 0.50 - - 1.00 -
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] Instructions:
# CHECK-NEXT: - - - 1.00 0.50 0.50 - - 1.00 - mulxq (%rdi), %rax, %rdx
# CHECK: Timeline view:
# CHECK-NEXT: 012345
# CHECK-NEXT: Index 0123456789
# CHECK: [0,0] DeeeeeeeeeER . mulxq (%rdi), %rax, %rdx
# CHECK-NEXT: [1,0] .D===eeeeeeeeeER mulxq (%rdi), %rax, %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. 2 2.5 0.5 0.0 mulxq (%rdi), %rax, %rdx
Codebase Browser
llvm