73 lines
2.6 KiB
ArmAsm
73 lines
2.6 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
|
||
|
|
|
||
|
|
fsqrt s30, s30
|
||
|
|
fmov s31, #1.00000000
|
||
|
|
fdiv s30, s31, s30
|
||
|
|
|
||
|
|
# Newton series for 1 / sqrtf().
|
||
|
|
frsqrte s1, s0
|
||
|
|
fmul s2, s1, s1
|
||
|
|
frsqrts s2, s0, s2
|
||
|
|
fmul s1, s1, s2
|
||
|
|
fmul s2, s1, s1
|
||
|
|
frsqrts s0, s0, s2
|
||
|
|
fmul s0, s1, s0
|
||
|
|
|
||
|
|
# ALL: Iterations: 100
|
||
|
|
# ALL-NEXT: Instructions: 1000
|
||
|
|
|
||
|
|
# M3-NEXT: Total Cycles: 2503
|
||
|
|
# M4-NEXT: Total Cycles: 2303
|
||
|
|
# M5-NEXT: Total Cycles: 2303
|
||
|
|
|
||
|
|
# ALL-NEXT: Total uOps: 1000
|
||
|
|
|
||
|
|
# ALL: Dispatch Width: 6
|
||
|
|
|
||
|
|
# M3-NEXT: uOps Per Cycle: 0.40
|
||
|
|
# M3-NEXT: IPC: 0.40
|
||
|
|
# M3-NEXT: Block RThroughput: 19.0
|
||
|
|
|
||
|
|
# M4-NEXT: uOps Per Cycle: 0.43
|
||
|
|
# M4-NEXT: IPC: 0.43
|
||
|
|
# M4-NEXT: Block RThroughput: 2.0
|
||
|
|
|
||
|
|
# M5-NEXT: uOps Per Cycle: 0.43
|
||
|
|
# M5-NEXT: IPC: 0.43
|
||
|
|
# M5-NEXT: Block RThroughput: 2.0
|
||
|
|
|
||
|
|
# 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:
|
||
|
|
|
||
|
|
# M3-NEXT: 1 18 19.00 fsqrt s30, s30
|
||
|
|
# M4-NEXT: 1 8 1.75 fsqrt s30, s30
|
||
|
|
# M5-NEXT: 1 8 1.25 fsqrt s30, s30
|
||
|
|
|
||
|
|
# ALL-NEXT: 1 1 0.33 fmov s31, #1.00000000
|
||
|
|
|
||
|
|
# M3-NEXT: 1 7 2.00 fdiv s30, s31, s30
|
||
|
|
# M3-NEXT: 1 4 0.50 frsqrte s1, s0
|
||
|
|
|
||
|
|
# M4-NEXT: 1 7 1.50 fdiv s30, s31, s30
|
||
|
|
# M4-NEXT: 1 3 0.50 frsqrte s1, s0
|
||
|
|
|
||
|
|
# M5-NEXT: 1 7 1.00 fdiv s30, s31, s30
|
||
|
|
# M5-NEXT: 1 3 0.50 frsqrte s1, s0
|
||
|
|
|
||
|
|
# ALL-NEXT: 1 3 0.33 fmul s2, s1, s1
|
||
|
|
# ALL-NEXT: 1 4 0.33 frsqrts s2, s0, s2
|
||
|
|
# ALL-NEXT: 1 3 0.33 fmul s1, s1, s2
|
||
|
|
# ALL-NEXT: 1 3 0.33 fmul s2, s1, s1
|
||
|
|
# ALL-NEXT: 1 4 0.33 frsqrts s0, s0, s2
|
||
|
|
# ALL-NEXT: 1 3 0.33 fmul s0, s1, s0
|