llvm/llvm/test/tools/llvm-mca/AArch64/Cortex/IPC/A55-6-mul.s

# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
# RUN: llvm-mca -mtriple=aarch64 -mcpu=cortex-a55 --all-views=false --summary-view --iterations=1000 < %s | FileCheck %s

# It appears that ADD and MUL fuse together, if both can be issued in
# one cycle:
#
#     add  w12, w8, #1
#     mul  w10, w12, w10
#
# FIXME: MCA (and LLVM scheduling model) do not support this. The test
# case uses different registers to break the pattern.

add	w8, w8, #1
add	w13, w8, #1
mul	w10, w12, w10

# CHECK:      Iterations:        1000
# CHECK-NEXT: Instructions:      3000
# CHECK-NEXT: Total Cycles:      3003
# CHECK-NEXT: Total uOps:        3000

# CHECK:      Dispatch Width:    2
# CHECK-NEXT: uOps Per Cycle:    1.00
# CHECK-NEXT: IPC:               1.00
# CHECK-NEXT: Block RThroughput: 1.5