344 lines
15 KiB
ArmAsm
344 lines
15 KiB
ArmAsm
# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
|
|
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -iterations=1 -all-views=false -timeline < %s | FileCheck %s -check-prefixes=ALL,BARCELONA
|
|
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=bdver2 -iterations=1 -all-views=false -timeline < %s | FileCheck %s -check-prefixes=ALL,BDVER2
|
|
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -iterations=1 -all-views=false -timeline < %s | FileCheck %s -check-prefixes=ALL,BTVER2
|
|
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=znver1 -iterations=1 -all-views=false -timeline < %s | FileCheck %s -check-prefixes=ALL,ZNVER1
|
|
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=znver2 -iterations=1 -all-views=false -timeline < %s | FileCheck %s -check-prefixes=ALL,ZNVER2
|
|
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=haswell -iterations=1 -all-views=false -timeline < %s | FileCheck %s -check-prefixes=ALL,HASWELL
|
|
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=broadwell -iterations=1 -all-views=false -timeline < %s | FileCheck %s -check-prefixes=ALL,BROADWELL
|
|
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=skylake -iterations=1 -all-views=false -timeline < %s | FileCheck %s -check-prefixes=ALL,SKYLAKE
|
|
|
|
#LLVM-MCA-BEGIN test_sqrtss
|
|
leaq 8(%rsp, %rdi, 2), %rax
|
|
sqrtss (%rax), %xmm1
|
|
#LLVM-MCA-END
|
|
|
|
#LLVM-MCA-BEGIN test_sqrtsd
|
|
leaq 8(%rsp, %rdi, 2), %rax
|
|
sqrtsd (%rax), %xmm1
|
|
#LLVM-MCA-END
|
|
|
|
#LLVM-MCA-BEGIN test_rsqrtss
|
|
leaq 8(%rsp, %rdi, 2), %rax
|
|
rsqrtss (%rax), %xmm1
|
|
#LLVM-MCA-END
|
|
|
|
#LLVM-MCA-BEGIN test_rcp
|
|
leaq 8(%rsp, %rdi, 2), %rax
|
|
rcpss (%rax), %xmm1
|
|
#LLVM-MCA-END
|
|
|
|
# ALL: [0] Code Region - test_sqrtss
|
|
|
|
# ALL: Timeline view:
|
|
|
|
# BARCELONA-NEXT: 0123456789
|
|
# BARCELONA-NEXT: Index 0123456789 0123
|
|
|
|
# BDVER2-NEXT: 012345678
|
|
# BDVER2-NEXT: Index 0123456789
|
|
|
|
# BROADWELL-NEXT: 0123456789
|
|
# BROADWELL-NEXT: Index 0123456789
|
|
|
|
# BTVER2-NEXT: 0123456789 0
|
|
# BTVER2-NEXT: Index 0123456789 0123456789
|
|
|
|
# HASWELL-NEXT: 0123456789
|
|
# HASWELL-NEXT: Index 0123456789
|
|
|
|
# SKYLAKE-NEXT: 0123456789
|
|
# SKYLAKE-NEXT: Index 0123456789 0
|
|
|
|
# ZNVER1-NEXT: 0123456789 0
|
|
# ZNVER1-NEXT: Index 0123456789 0123456789
|
|
|
|
# ZNVER2-NEXT: 0123456789 0
|
|
# ZNVER2-NEXT: Index 0123456789 0123456789
|
|
|
|
# BARCELONA: [0,0] DeER . . . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# BARCELONA-NEXT: [0,1] D=eeeeeeeeeeeeeeeeeeeeER sqrtss (%rax), %xmm1
|
|
|
|
# BDVER2: [0,0] DeeER. . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# BDVER2-NEXT: [0,1] D==eeeeeeeeeeeeeeER sqrtss (%rax), %xmm1
|
|
|
|
# BROADWELL: [0,0] DeER . . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# BROADWELL-NEXT: [0,1] D=eeeeeeeeeeeeeeeeER sqrtss (%rax), %xmm1
|
|
|
|
# BTVER2: [0,0] DeeER. . . . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# BTVER2-NEXT: [0,1] D==eeeeeeeeeeeeeeeeeeeeeeeeeeER sqrtss (%rax), %xmm1
|
|
|
|
# HASWELL: [0,0] DeER . . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# HASWELL-NEXT: [0,1] D=eeeeeeeeeeeeeeeeER sqrtss (%rax), %xmm1
|
|
|
|
# SKYLAKE: [0,0] DeER . . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# SKYLAKE-NEXT: [0,1] D=eeeeeeeeeeeeeeeeeER sqrtss (%rax), %xmm1
|
|
|
|
# ZNVER1: [0,0] DeER . . . . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# ZNVER1-NEXT: [0,1] D=eeeeeeeeeeeeeeeeeeeeeeeeeeeER sqrtss (%rax), %xmm1
|
|
|
|
# ZNVER2: [0,0] DeER . . . . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# ZNVER2-NEXT: [0,1] D=eeeeeeeeeeeeeeeeeeeeeeeeeeeER sqrtss (%rax), %xmm1
|
|
|
|
# ALL: Average Wait times (based on the timeline view):
|
|
# ALL-NEXT: [0]: Executions
|
|
# ALL-NEXT: [1]: Average time spent waiting in a scheduler's queue
|
|
# ALL-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
|
|
# ALL-NEXT: [3]: Average time elapsed from WB until retire stage
|
|
|
|
# ALL: [0] [1] [2] [3]
|
|
# ALL-NEXT: 0. 1 1.0 1.0 0.0 leaq 8(%rsp,%rdi,2), %rax
|
|
|
|
# BARCELONA-NEXT: 1. 1 2.0 0.0 0.0 sqrtss (%rax), %xmm1
|
|
# BARCELONA-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# BDVER2-NEXT: 1. 1 3.0 0.0 0.0 sqrtss (%rax), %xmm1
|
|
# BDVER2-NEXT: 1 2.0 0.5 0.0 <total>
|
|
|
|
# BROADWELL-NEXT: 1. 1 2.0 0.0 0.0 sqrtss (%rax), %xmm1
|
|
# BROADWELL-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# BTVER2-NEXT: 1. 1 3.0 0.0 0.0 sqrtss (%rax), %xmm1
|
|
# BTVER2-NEXT: 1 2.0 0.5 0.0 <total>
|
|
|
|
# HASWELL-NEXT: 1. 1 2.0 0.0 0.0 sqrtss (%rax), %xmm1
|
|
# HASWELL-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# SKYLAKE-NEXT: 1. 1 2.0 0.0 0.0 sqrtss (%rax), %xmm1
|
|
# SKYLAKE-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# ZNVER1-NEXT: 1. 1 2.0 0.0 0.0 sqrtss (%rax), %xmm1
|
|
# ZNVER1-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# ZNVER2-NEXT: 1. 1 2.0 0.0 0.0 sqrtss (%rax), %xmm1
|
|
# ZNVER2-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# ALL: [1] Code Region - test_sqrtsd
|
|
|
|
# ALL: Timeline view:
|
|
|
|
# BARCELONA-NEXT: 0123456789 0
|
|
# BARCELONA-NEXT: Index 0123456789 0123456789
|
|
|
|
# BDVER2-NEXT: 012345678
|
|
# BDVER2-NEXT: Index 0123456789
|
|
|
|
# BROADWELL-NEXT: 0123456789
|
|
# BROADWELL-NEXT: Index 0123456789 01234
|
|
|
|
# BTVER2-NEXT: 0123456789 0123456
|
|
# BTVER2-NEXT: Index 0123456789 0123456789
|
|
|
|
# HASWELL-NEXT: 0123456789
|
|
# HASWELL-NEXT: Index 0123456789 01234
|
|
|
|
# SKYLAKE-NEXT: 0123456789
|
|
# SKYLAKE-NEXT: Index 0123456789 0123456
|
|
|
|
# ZNVER1-NEXT: 0123456789 0
|
|
# ZNVER1-NEXT: Index 0123456789 0123456789
|
|
|
|
# ZNVER2-NEXT: 0123456789 0
|
|
# ZNVER2-NEXT: Index 0123456789 0123456789
|
|
|
|
# BARCELONA: [0,0] DeER . . . . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# BARCELONA-NEXT: [0,1] D=eeeeeeeeeeeeeeeeeeeeeeeeeeeER sqrtsd (%rax), %xmm1
|
|
|
|
# BDVER2: [0,0] DeeER. . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# BDVER2-NEXT: [0,1] D==eeeeeeeeeeeeeeER sqrtsd (%rax), %xmm1
|
|
|
|
# BROADWELL: [0,0] DeER . . . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# BROADWELL-NEXT: [0,1] D=eeeeeeeeeeeeeeeeeeeeeER sqrtsd (%rax), %xmm1
|
|
|
|
# BTVER2: [0,0] DeeER. . . . . . .. leaq 8(%rsp,%rdi,2), %rax
|
|
# BTVER2-NEXT: [0,1] D==eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeER sqrtsd (%rax), %xmm1
|
|
|
|
# HASWELL: [0,0] DeER . . . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# HASWELL-NEXT: [0,1] D=eeeeeeeeeeeeeeeeeeeeeER sqrtsd (%rax), %xmm1
|
|
|
|
# SKYLAKE: [0,0] DeER . . . . .. leaq 8(%rsp,%rdi,2), %rax
|
|
# SKYLAKE-NEXT: [0,1] D=eeeeeeeeeeeeeeeeeeeeeeeER sqrtsd (%rax), %xmm1
|
|
|
|
# ZNVER1: [0,0] DeER . . . . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# ZNVER1-NEXT: [0,1] D=eeeeeeeeeeeeeeeeeeeeeeeeeeeER sqrtsd (%rax), %xmm1
|
|
|
|
# ZNVER2: [0,0] DeER . . . . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# ZNVER2-NEXT: [0,1] D=eeeeeeeeeeeeeeeeeeeeeeeeeeeER sqrtsd (%rax), %xmm1
|
|
|
|
# ALL: Average Wait times (based on the timeline view):
|
|
# ALL-NEXT: [0]: Executions
|
|
# ALL-NEXT: [1]: Average time spent waiting in a scheduler's queue
|
|
# ALL-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
|
|
# ALL-NEXT: [3]: Average time elapsed from WB until retire stage
|
|
|
|
# ALL: [0] [1] [2] [3]
|
|
# ALL-NEXT: 0. 1 1.0 1.0 0.0 leaq 8(%rsp,%rdi,2), %rax
|
|
|
|
# BARCELONA-NEXT: 1. 1 2.0 0.0 0.0 sqrtsd (%rax), %xmm1
|
|
# BARCELONA-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# BDVER2-NEXT: 1. 1 3.0 0.0 0.0 sqrtsd (%rax), %xmm1
|
|
# BDVER2-NEXT: 1 2.0 0.5 0.0 <total>
|
|
|
|
# BROADWELL-NEXT: 1. 1 2.0 0.0 0.0 sqrtsd (%rax), %xmm1
|
|
# BROADWELL-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# BTVER2-NEXT: 1. 1 3.0 0.0 0.0 sqrtsd (%rax), %xmm1
|
|
# BTVER2-NEXT: 1 2.0 0.5 0.0 <total>
|
|
|
|
# HASWELL-NEXT: 1. 1 2.0 0.0 0.0 sqrtsd (%rax), %xmm1
|
|
# HASWELL-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# SKYLAKE-NEXT: 1. 1 2.0 0.0 0.0 sqrtsd (%rax), %xmm1
|
|
# SKYLAKE-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# ZNVER1-NEXT: 1. 1 2.0 0.0 0.0 sqrtsd (%rax), %xmm1
|
|
# ZNVER1-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# ZNVER2-NEXT: 1. 1 2.0 0.0 0.0 sqrtsd (%rax), %xmm1
|
|
# ZNVER2-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# ALL: [2] Code Region - test_rsqrtss
|
|
|
|
# ALL: Timeline view:
|
|
|
|
# BARCELONA-NEXT: 01234
|
|
# BDVER2-NEXT: 01234
|
|
# BROADWELL-NEXT: 0123
|
|
# BTVER2-NEXT: 01
|
|
# HASWELL-NEXT: 0123
|
|
# SKYLAKE-NEXT: 012
|
|
# ZNVER1-NEXT: 012345
|
|
# ZNVER2-NEXT: 012345
|
|
|
|
# ALL-NEXT: Index 0123456789
|
|
|
|
# BARCELONA: [0,0] DeER . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# BARCELONA-NEXT: [0,1] D=eeeeeeeeeeeER rsqrtss (%rax), %xmm1
|
|
|
|
# BDVER2: [0,0] DeeER. . . leaq 8(%rsp,%rdi,2), %rax
|
|
# BDVER2-NEXT: [0,1] D==eeeeeeeeeeER rsqrtss (%rax), %xmm1
|
|
|
|
# BROADWELL: [0,0] DeER . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# BROADWELL-NEXT: [0,1] D=eeeeeeeeeeER rsqrtss (%rax), %xmm1
|
|
|
|
# BTVER2: [0,0] DeeER. .. leaq 8(%rsp,%rdi,2), %rax
|
|
# BTVER2-NEXT: [0,1] D==eeeeeeeER rsqrtss (%rax), %xmm1
|
|
|
|
# HASWELL: [0,0] DeER . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# HASWELL-NEXT: [0,1] D=eeeeeeeeeeER rsqrtss (%rax), %xmm1
|
|
|
|
# SKYLAKE: [0,0] DeER . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# SKYLAKE-NEXT: [0,1] D=eeeeeeeeeER rsqrtss (%rax), %xmm1
|
|
|
|
# ZNVER1: [0,0] DeER . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# ZNVER1-NEXT: [0,1] D=eeeeeeeeeeeeER rsqrtss (%rax), %xmm1
|
|
|
|
# ZNVER2: [0,0] DeER . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# ZNVER2-NEXT: [0,1] D=eeeeeeeeeeeeER rsqrtss (%rax), %xmm1
|
|
|
|
# ALL: Average Wait times (based on the timeline view):
|
|
# ALL-NEXT: [0]: Executions
|
|
# ALL-NEXT: [1]: Average time spent waiting in a scheduler's queue
|
|
# ALL-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
|
|
# ALL-NEXT: [3]: Average time elapsed from WB until retire stage
|
|
|
|
# ALL: [0] [1] [2] [3]
|
|
# ALL-NEXT: 0. 1 1.0 1.0 0.0 leaq 8(%rsp,%rdi,2), %rax
|
|
|
|
# BARCELONA-NEXT: 1. 1 2.0 0.0 0.0 rsqrtss (%rax), %xmm1
|
|
# BARCELONA-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# BDVER2-NEXT: 1. 1 3.0 0.0 0.0 rsqrtss (%rax), %xmm1
|
|
# BDVER2-NEXT: 1 2.0 0.5 0.0 <total>
|
|
|
|
# BROADWELL-NEXT: 1. 1 2.0 0.0 0.0 rsqrtss (%rax), %xmm1
|
|
# BROADWELL-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# BTVER2-NEXT: 1. 1 3.0 0.0 0.0 rsqrtss (%rax), %xmm1
|
|
# BTVER2-NEXT: 1 2.0 0.5 0.0 <total>
|
|
|
|
# HASWELL-NEXT: 1. 1 2.0 0.0 0.0 rsqrtss (%rax), %xmm1
|
|
# HASWELL-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# SKYLAKE-NEXT: 1. 1 2.0 0.0 0.0 rsqrtss (%rax), %xmm1
|
|
# SKYLAKE-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# ZNVER1-NEXT: 1. 1 2.0 0.0 0.0 rsqrtss (%rax), %xmm1
|
|
# ZNVER1-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# ZNVER2-NEXT: 1. 1 2.0 0.0 0.0 rsqrtss (%rax), %xmm1
|
|
# ZNVER2-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# ALL: [3] Code Region - test_rcp
|
|
|
|
# ALL: Timeline view:
|
|
|
|
# BARCELONA-NEXT: 01234
|
|
# BDVER2-NEXT: 01234
|
|
# BROADWELL-NEXT: 0123
|
|
# BTVER2-NEXT: 01
|
|
# HASWELL-NEXT: 0123
|
|
# SKYLAKE-NEXT: 012
|
|
# ZNVER1-NEXT: 012345
|
|
# ZNVER2-NEXT: 012345
|
|
|
|
# ALL-NEXT: Index 0123456789
|
|
|
|
# BARCELONA: [0,0] DeER . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# BARCELONA-NEXT: [0,1] D=eeeeeeeeeeeER rcpss (%rax), %xmm1
|
|
|
|
# BDVER2: [0,0] DeeER. . . leaq 8(%rsp,%rdi,2), %rax
|
|
# BDVER2-NEXT: [0,1] D==eeeeeeeeeeER rcpss (%rax), %xmm1
|
|
|
|
# BROADWELL: [0,0] DeER . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# BROADWELL-NEXT: [0,1] D=eeeeeeeeeeER rcpss (%rax), %xmm1
|
|
|
|
# BTVER2: [0,0] DeeER. .. leaq 8(%rsp,%rdi,2), %rax
|
|
# BTVER2-NEXT: [0,1] D==eeeeeeeER rcpss (%rax), %xmm1
|
|
|
|
# HASWELL: [0,0] DeER . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# HASWELL-NEXT: [0,1] D=eeeeeeeeeeER rcpss (%rax), %xmm1
|
|
|
|
# SKYLAKE: [0,0] DeER . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# SKYLAKE-NEXT: [0,1] D=eeeeeeeeeER rcpss (%rax), %xmm1
|
|
|
|
# ZNVER1: [0,0] DeER . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# ZNVER1-NEXT: [0,1] D=eeeeeeeeeeeeER rcpss (%rax), %xmm1
|
|
|
|
# ZNVER2: [0,0] DeER . . . leaq 8(%rsp,%rdi,2), %rax
|
|
# ZNVER2-NEXT: [0,1] D=eeeeeeeeeeeeER rcpss (%rax), %xmm1
|
|
|
|
# ALL: Average Wait times (based on the timeline view):
|
|
# ALL-NEXT: [0]: Executions
|
|
# ALL-NEXT: [1]: Average time spent waiting in a scheduler's queue
|
|
# ALL-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
|
|
# ALL-NEXT: [3]: Average time elapsed from WB until retire stage
|
|
|
|
# ALL: [0] [1] [2] [3]
|
|
# ALL-NEXT: 0. 1 1.0 1.0 0.0 leaq 8(%rsp,%rdi,2), %rax
|
|
|
|
# BARCELONA-NEXT: 1. 1 2.0 0.0 0.0 rcpss (%rax), %xmm1
|
|
# BARCELONA-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# BDVER2-NEXT: 1. 1 3.0 0.0 0.0 rcpss (%rax), %xmm1
|
|
# BDVER2-NEXT: 1 2.0 0.5 0.0 <total>
|
|
|
|
# BROADWELL-NEXT: 1. 1 2.0 0.0 0.0 rcpss (%rax), %xmm1
|
|
# BROADWELL-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# BTVER2-NEXT: 1. 1 3.0 0.0 0.0 rcpss (%rax), %xmm1
|
|
# BTVER2-NEXT: 1 2.0 0.5 0.0 <total>
|
|
|
|
# HASWELL-NEXT: 1. 1 2.0 0.0 0.0 rcpss (%rax), %xmm1
|
|
# HASWELL-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# SKYLAKE-NEXT: 1. 1 2.0 0.0 0.0 rcpss (%rax), %xmm1
|
|
# SKYLAKE-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# ZNVER1-NEXT: 1. 1 2.0 0.0 0.0 rcpss (%rax), %xmm1
|
|
# ZNVER1-NEXT: 1 1.5 0.5 0.0 <total>
|
|
|
|
# ZNVER2-NEXT: 1. 1 2.0 0.0 0.0 rcpss (%rax), %xmm1
|
|
# ZNVER2-NEXT: 1 1.5 0.5 0.0 <total>
|