98 lines
4.7 KiB
ArmAsm
98 lines
4.7 KiB
ArmAsm
# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
|
|
# RUN: llvm-mca -mtriple=aarch64-linux-gnu -mcpu=exynos-m3 -resource-pressure=false -noalias=false < %s | FileCheck %s -check-prefixes=ALL,M3
|
|
# RUN: llvm-mca -mtriple=aarch64-linux-gnu -mcpu=exynos-m4 -resource-pressure=false -noalias=false < %s | FileCheck %s -check-prefixes=ALL,M4
|
|
# RUN: llvm-mca -mtriple=aarch64-linux-gnu -mcpu=exynos-m5 -resource-pressure=false -noalias=false < %s | FileCheck %s -check-prefixes=ALL,M5
|
|
|
|
st2 {v0.s, v1.s}[0], [sp]
|
|
st2 {v0.2s, v1.2s}, [sp]
|
|
|
|
st2 {v0.d, v1.d}[0], [sp]
|
|
st2 {v0.2d, v1.2d}, [sp]
|
|
|
|
st2 {v0.s, v1.s}[0], [sp], #8
|
|
st2 {v0.2s, v1.2s}, [sp], #16
|
|
|
|
st2 {v0.d, v1.d}[0], [sp], #16
|
|
st2 {v0.2d, v1.2d}, [sp], #32
|
|
|
|
st2 {v0.s, v1.s}[0], [sp], x0
|
|
st2 {v0.2s, v1.2s}, [sp], x0
|
|
|
|
st2 {v0.d, v1.d}[0], [sp], x0
|
|
st2 {v0.2d, v1.2d}, [sp], x0
|
|
|
|
# ALL: Iterations: 100
|
|
# ALL-NEXT: Instructions: 1200
|
|
|
|
# M3-NEXT: Total Cycles: 8703
|
|
# M3-NEXT: Total uOps: 5400
|
|
|
|
# M4-NEXT: Total Cycles: 2403
|
|
# M4-NEXT: Total uOps: 2300
|
|
|
|
# M5-NEXT: Total Cycles: 2403
|
|
# M5-NEXT: Total uOps: 2000
|
|
|
|
# ALL: Dispatch Width: 6
|
|
|
|
# M3-NEXT: uOps Per Cycle: 0.62
|
|
# M3-NEXT: IPC: 0.14
|
|
# M3-NEXT: Block RThroughput: 40.5
|
|
|
|
# M4-NEXT: uOps Per Cycle: 0.96
|
|
# M4-NEXT: IPC: 0.50
|
|
# M4-NEXT: Block RThroughput: 7.5
|
|
|
|
# M5-NEXT: uOps Per Cycle: 0.83
|
|
# M5-NEXT: IPC: 0.50
|
|
# M5-NEXT: Block RThroughput: 7.5
|
|
|
|
# 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: 4 7 3.00 * st2 { v0.s, v1.s }[0], [sp]
|
|
# M3-NEXT: 4 7 3.00 * st2 { v0.2s, v1.2s }, [sp]
|
|
# M3-NEXT: 4 7 3.00 * st2 { v0.d, v1.d }[0], [sp]
|
|
# M3-NEXT: 6 8 4.50 * st2 { v0.2d, v1.2d }, [sp]
|
|
# M3-NEXT: 4 7 3.00 * st2 { v0.s, v1.s }[0], [sp], #8
|
|
# M3-NEXT: 4 7 3.00 * st2 { v0.2s, v1.2s }, [sp], #16
|
|
# M3-NEXT: 4 7 3.00 * st2 { v0.d, v1.d }[0], [sp], #16
|
|
# M3-NEXT: 6 8 4.50 * st2 { v0.2d, v1.2d }, [sp], #32
|
|
# M3-NEXT: 4 7 3.00 * st2 { v0.s, v1.s }[0], [sp], x0
|
|
# M3-NEXT: 4 7 3.00 * st2 { v0.2s, v1.2s }, [sp], x0
|
|
# M3-NEXT: 4 7 3.00 * st2 { v0.d, v1.d }[0], [sp], x0
|
|
# M3-NEXT: 6 8 4.50 * st2 { v0.2d, v1.2d }, [sp], x0
|
|
|
|
# M4-NEXT: 1 2 0.50 * st2 { v0.s, v1.s }[0], [sp]
|
|
# M4-NEXT: 1 2 0.50 * st2 { v0.2s, v1.2s }, [sp]
|
|
# M4-NEXT: 1 2 0.50 * st2 { v0.d, v1.d }[0], [sp]
|
|
# M4-NEXT: 2 2 1.00 * st2 { v0.2d, v1.2d }, [sp]
|
|
# M4-NEXT: 2 2 0.50 * st2 { v0.s, v1.s }[0], [sp], #8
|
|
# M4-NEXT: 2 2 0.50 * st2 { v0.2s, v1.2s }, [sp], #16
|
|
# M4-NEXT: 2 2 0.50 * st2 { v0.d, v1.d }[0], [sp], #16
|
|
# M4-NEXT: 3 2 1.00 * st2 { v0.2d, v1.2d }, [sp], #32
|
|
# M4-NEXT: 2 2 0.50 * st2 { v0.s, v1.s }[0], [sp], x0
|
|
# M4-NEXT: 2 2 0.50 * st2 { v0.2s, v1.2s }, [sp], x0
|
|
# M4-NEXT: 2 2 0.50 * st2 { v0.d, v1.d }[0], [sp], x0
|
|
# M4-NEXT: 3 2 1.00 * st2 { v0.2d, v1.2d }, [sp], x0
|
|
|
|
# M5-NEXT: 1 2 0.50 * st2 { v0.s, v1.s }[0], [sp]
|
|
# M5-NEXT: 1 2 0.50 * st2 { v0.2s, v1.2s }, [sp]
|
|
# M5-NEXT: 1 2 0.50 * st2 { v0.d, v1.d }[0], [sp]
|
|
# M5-NEXT: 1 2 1.00 * st2 { v0.2d, v1.2d }, [sp]
|
|
# M5-NEXT: 2 2 0.50 * st2 { v0.s, v1.s }[0], [sp], #8
|
|
# M5-NEXT: 2 2 0.50 * st2 { v0.2s, v1.2s }, [sp], #16
|
|
# M5-NEXT: 2 2 0.50 * st2 { v0.d, v1.d }[0], [sp], #16
|
|
# M5-NEXT: 2 2 1.00 * st2 { v0.2d, v1.2d }, [sp], #32
|
|
# M5-NEXT: 2 2 0.50 * st2 { v0.s, v1.s }[0], [sp], x0
|
|
# M5-NEXT: 2 2 0.50 * st2 { v0.2s, v1.2s }, [sp], x0
|
|
# M5-NEXT: 2 2 0.50 * st2 { v0.d, v1.d }[0], [sp], x0
|
|
# M5-NEXT: 2 2 1.00 * st2 { v0.2d, v1.2d }, [sp], x0
|