# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=haswell -timeline -timeline-max-iterations=3 < %s | FileCheck %s
# Code snippet taken from PR48024.
stmxcsr -4(%rsp)
movl $-24577, %eax # imm = 0x9FFF
andl -4(%rsp), %eax
movl %eax, -8(%rsp)
ldmxcsr -8(%rsp)
retq
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 600
# CHECK-NEXT: Total Cycles: 809
# CHECK-NEXT: Total uOps: 1300
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 1.61
# CHECK-NEXT: IPC: 0.74
# CHECK-NEXT: Block RThroughput: 3.3
# 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: 3 2 1.00 * U stmxcsr -4(%rsp)
# CHECK-NEXT: 1 1 0.25 movl $-24577, %eax
# CHECK-NEXT: 2 6 0.50 * andl -4(%rsp), %eax
# CHECK-NEXT: 1 1 1.00 * movl %eax, -8(%rsp)
# CHECK-NEXT: 3 7 1.00 * * U ldmxcsr -8(%rsp)
# CHECK-NEXT: 3 7 1.00 U retq
# 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: - - 1.77 1.71 1.75 1.75 2.00 1.81 1.71 1.50
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] Instructions:
# CHECK-NEXT: - - - - - - 1.00 1.00 - 1.00 stmxcsr -4(%rsp)
# CHECK-NEXT: - - 0.26 0.46 - - - 0.27 0.01 - movl $-24577, %eax
# CHECK-NEXT: - - 0.28 0.28 0.49 0.51 - 0.07 0.37 - andl -4(%rsp), %eax
# CHECK-NEXT: - - - - 0.18 0.32 1.00 - - 0.50 movl %eax, -8(%rsp)
# CHECK-NEXT: - - 1.00 0.67 0.58 0.42 - - 0.33 - ldmxcsr -8(%rsp)
# CHECK-NEXT: - - 0.23 0.30 0.50 0.50 - 0.47 1.00 - retq
# CHECK: Timeline view:
# CHECK-NEXT: 0123456789 012
# CHECK-NEXT: Index 0123456789 0123456789
# CHECK: [0,0] DeeER. . . . . . . stmxcsr -4(%rsp)
# CHECK-NEXT: [0,1] DeE-R. . . . . . . movl $-24577, %eax
# CHECK-NEXT: [0,2] .DeeeeeeER. . . . . . andl -4(%rsp), %eax
# CHECK-NEXT: [0,3] .D======eER . . . . . movl %eax, -8(%rsp)
# CHECK-NEXT: [0,4] . D=====eeeeeeeER . . . . ldmxcsr -8(%rsp)
# CHECK-NEXT: [0,5] . DeeeeeeeE----R . . . . retq
# CHECK-NEXT: [1,0] . D==========eeER . . . . stmxcsr -4(%rsp)
# CHECK-NEXT: [1,1] . DeE-----------R . . . . movl $-24577, %eax
# CHECK-NEXT: [1,2] . DeeeeeeE-----R . . . . andl -4(%rsp), %eax
# CHECK-NEXT: [1,3] . D==========eER . . . . movl %eax, -8(%rsp)
# CHECK-NEXT: [1,4] . .D=========eeeeeeeER. . . ldmxcsr -8(%rsp)
# CHECK-NEXT: [1,5] . . D=eeeeeeeE-------R. . . retq
# CHECK-NEXT: [2,0] . . D==============eeER . . stmxcsr -4(%rsp)
# CHECK-NEXT: [2,1] . . DeE---------------R . . movl $-24577, %eax
# CHECK-NEXT: [2,2] . . DeeeeeeE---------R . . andl -4(%rsp), %eax
# CHECK-NEXT: [2,3] . . D==============eER . . movl %eax, -8(%rsp)
# CHECK-NEXT: [2,4] . . D=============eeeeeeeER ldmxcsr -8(%rsp)
# CHECK-NEXT: [2,5] . . .DeeeeeeeE------------R retq
# 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 9.0 0.3 0.0 stmxcsr -4(%rsp)
# CHECK-NEXT: 1. 3 1.0 1.0 9.0 movl $-24577, %eax
# CHECK-NEXT: 2. 3 1.0 1.0 4.7 andl -4(%rsp), %eax
# CHECK-NEXT: 3. 3 11.0 0.7 0.0 movl %eax, -8(%rsp)
# CHECK-NEXT: 4. 3 10.0 0.0 0.0 ldmxcsr -8(%rsp)
# CHECK-NEXT: 5. 3 1.3 1.3 7.7 retq
# CHECK-NEXT: 3 5.6 0.7 3.6 <total>
Codebase Browser
llvm