llvm-for-llvmta/test/tools/llvm-mca/AArch64/Exynos/double-recp.s

67 lines
2.3 KiB
ArmAsm

# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
# RUN: llvm-mca -march=aarch64 -mcpu=exynos-m3 -resource-pressure=false < %s | FileCheck %s -check-prefixes=ALL,M3
# RUN: llvm-mca -march=aarch64 -mcpu=exynos-m4 -resource-pressure=false < %s | FileCheck %s -check-prefixes=ALL,M4
# RUN: llvm-mca -march=aarch64 -mcpu=exynos-m5 -resource-pressure=false < %s | FileCheck %s -check-prefixes=ALL,M5
fmov d31, #1.00000000
fdiv d30, d31, d30
# Newton series for 1 / x.
frecpe d1, d0
frecps d2, d0, d1
fmul d1, d1, d2
frecps d2, d0, d1
fmul d1, d1, d2
frecps d0, d0, d1
fmul d0, d1, d0
# ALL: Iterations: 100
# ALL-NEXT: Instructions: 900
# M3-NEXT: Total Cycles: 2503
# M4-NEXT: Total Cycles: 2403
# M5-NEXT: Total Cycles: 2403
# ALL-NEXT: Total uOps: 900
# ALL: Dispatch Width: 6
# M3-NEXT: uOps Per Cycle: 0.36
# M3-NEXT: IPC: 0.36
# M3-NEXT: Block RThroughput: 3.3
# M4-NEXT: uOps Per Cycle: 0.37
# M4-NEXT: IPC: 0.37
# M4-NEXT: Block RThroughput: 2.3
# M5-NEXT: uOps Per Cycle: 0.37
# M5-NEXT: IPC: 0.37
# M5-NEXT: Block RThroughput: 2.3
# ALL: Instruction Info:
# ALL-NEXT: [1]: #uOps
# ALL-NEXT: [2]: Latency
# ALL-NEXT: [3]: RThroughput
# ALL-NEXT: [4]: MayLoad
# ALL-NEXT: [5]: MayStore
# ALL-NEXT: [6]: HasSideEffects (U)
# ALL: [1] [2] [3] [4] [5] [6] Instructions:
# ALL-NEXT: 1 1 0.33 fmov d31, #1.00000000
# M3-NEXT: 1 12 3.25 fdiv d30, d31, d30
# M3-NEXT: 1 4 0.50 frecpe d1, d0
# M4-NEXT: 1 12 2.25 fdiv d30, d31, d30
# M4-NEXT: 1 3 0.50 frecpe d1, d0
# M5-NEXT: 1 12 2.25 fdiv d30, d31, d30
# M5-NEXT: 1 3 0.50 frecpe d1, d0
# ALL-NEXT: 1 4 0.33 frecps d2, d0, d1
# ALL-NEXT: 1 3 0.33 fmul d1, d1, d2
# ALL-NEXT: 1 4 0.33 frecps d2, d0, d1
# ALL-NEXT: 1 3 0.33 fmul d1, d1, d2
# ALL-NEXT: 1 4 0.33 frecps d0, d0, d1
# ALL-NEXT: 1 3 0.33 fmul d0, d1, d0