llvm-for-llvmta/test/tools/llvm-mca/X86/BdVer2/dependency-breaking-sbb-2.s

97 lines
4.4 KiB
ArmAsm

# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=bdver2 -timeline -timeline-max-iterations=3 -iterations=1500 < %s | FileCheck %s
# perf stat reports a throughput of 1.51 IPC for this block of code.
# The SBB does not depend on the value of register EAX. That means, it doesn't
# have to wait for the IMUL to write-back on EAX. However, it still depends on
# the ADD for EFLAGS.
imul %edx, %eax
add %edx, %edx
sbb %eax, %eax
# CHECK: Iterations: 1500
# CHECK-NEXT: Instructions: 4500
# CHECK-NEXT: Total Cycles: 4014
# CHECK-NEXT: Total uOps: 4500
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 1.12
# CHECK-NEXT: IPC: 1.12
# CHECK-NEXT: Block RThroughput: 2.0
# 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: 1 4 2.00 imull %edx, %eax
# CHECK-NEXT: 1 1 1.00 addl %edx, %edx
# CHECK-NEXT: 1 1 1.00 sbbl %eax, %eax
# CHECK: Resources:
# CHECK-NEXT: [0.0] - PdAGLU01
# CHECK-NEXT: [0.1] - PdAGLU01
# CHECK-NEXT: [1] - PdBranch
# CHECK-NEXT: [2] - PdCount
# CHECK-NEXT: [3] - PdDiv
# CHECK-NEXT: [4] - PdEX0
# CHECK-NEXT: [5] - PdEX1
# CHECK-NEXT: [6] - PdFPCVT
# CHECK-NEXT: [7.0] - PdFPFMA
# CHECK-NEXT: [7.1] - PdFPFMA
# CHECK-NEXT: [8.0] - PdFPMAL
# CHECK-NEXT: [8.1] - PdFPMAL
# CHECK-NEXT: [9] - PdFPMMA
# CHECK-NEXT: [10] - PdFPSTO
# CHECK-NEXT: [11] - PdFPU0
# CHECK-NEXT: [12] - PdFPU1
# CHECK-NEXT: [13] - PdFPU2
# CHECK-NEXT: [14] - PdFPU3
# CHECK-NEXT: [15] - PdFPXBR
# CHECK-NEXT: [16.0] - PdLoad
# CHECK-NEXT: [16.1] - PdLoad
# CHECK-NEXT: [17] - PdMul
# CHECK-NEXT: [18] - PdStore
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0.0] [0.1] [1] [2] [3] [4] [5] [6] [7.0] [7.1] [8.0] [8.1] [9] [10] [11] [12] [13] [14] [15] [16.0] [16.1] [17] [18]
# CHECK-NEXT: - - - - - 2.66 2.34 - - - - - - - - - - - - - - 2.00 -
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0.0] [0.1] [1] [2] [3] [4] [5] [6] [7.0] [7.1] [8.0] [8.1] [9] [10] [11] [12] [13] [14] [15] [16.0] [16.1] [17] [18] Instructions:
# CHECK-NEXT: - - - - - - 1.00 - - - - - - - - - - - - - - 2.00 - imull %edx, %eax
# CHECK-NEXT: - - - - - 1.33 0.67 - - - - - - - - - - - - - - - - addl %edx, %edx
# CHECK-NEXT: - - - - - 1.33 0.67 - - - - - - - - - - - - - - - - sbbl %eax, %eax
# CHECK: Timeline view:
# CHECK-NEXT: 01234
# CHECK-NEXT: Index 0123456789
# CHECK: [0,0] D==eeeeER . . imull %edx, %eax
# CHECK-NEXT: [0,1] DeE-----R . . addl %edx, %edx
# CHECK-NEXT: [0,2] D===eE--R . . sbbl %eax, %eax
# CHECK-NEXT: [1,0] D=====eeeeER . imull %edx, %eax
# CHECK-NEXT: [1,1] .DeE-------R . addl %edx, %edx
# CHECK-NEXT: [1,2] .D====eE---R . sbbl %eax, %eax
# CHECK-NEXT: [2,0] .D=======eeeeER imull %edx, %eax
# CHECK-NEXT: [2,1] .D==eE--------R addl %edx, %edx
# CHECK-NEXT: [2,2] . D=====eE----R sbbl %eax, %eax
# 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 5.7 2.0 0.0 imull %edx, %eax
# CHECK-NEXT: 1. 3 1.7 0.7 6.7 addl %edx, %edx
# CHECK-NEXT: 2. 3 5.0 2.7 3.0 sbbl %eax, %eax
# CHECK-NEXT: 3 4.1 1.8 3.2 <total>