maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[llvm-mca] Increase the default number of iterations to 100. 

llvm-svn: 329694
This commit is contained in:
Andrea Di Biagio 2018-04-10 12:50:03 +00:00
parent 23b8bd1220
commit 074cef3dfb
7 changed files with 146 additions and 57 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llvm/docs/CommandGuide/llvm-mca.rst
View File

@ -95,7 +95,7 @@ option specifies "``-``", then the output will also be sent to standard output.
.. option:: -iterations=<number of iterations> .. option:: -iterations=<number of iterations>
Specify the number of iterations to run. If this flag is set to 0, then the Specify the number of iterations to run. If this flag is set to 0, then the
tool sets the number of iterations to a default value (i.e. 70). tool sets the number of iterations to a default value (i.e. 100).
.. option:: -noalias=<bool> .. option:: -noalias=<bool>

42
llvm/test/tools/llvm-mca/X86/BtVer2/pipes-fpu.s
View File

@ -16,14 +16,12 @@ vsqrtps %xmm0, %xmm2
vaddps %ymm0, %ymm1, %ymm2 vaddps %ymm0, %ymm1, %ymm2
vsqrtps %ymm0, %ymm2 vsqrtps %ymm0, %ymm2
# CHECK: Iterations: 100
# CHECK: Iterations: 70 # CHECK-NEXT: Instructions: 800
# CHECK-NEXT: Instructions: 560 # CHECK-NEXT: Total Cycles: 6306
# CHECK-NEXT: Total Cycles: 4416
# CHECK-NEXT: Dispatch Width: 2 # CHECK-NEXT: Dispatch Width: 2
# CHECK-NEXT: IPC: 0.13 # CHECK-NEXT: IPC: 0.13
# CHECK: Instruction Info: # CHECK: Instruction Info:
# CHECK-NEXT: [1]: #uOps # CHECK-NEXT: [1]: #uOps
# CHECK-NEXT: [2]: Latency # CHECK-NEXT: [2]: Latency
@ -42,7 +40,6 @@ vsqrtps %ymm0, %ymm2
# CHECK-NEXT: 2 3 2.00 vaddps %ymm0, %ymm1, %ymm2 # CHECK-NEXT: 2 3 2.00 vaddps %ymm0, %ymm1, %ymm2
# CHECK-NEXT: 2 42 42.00 vsqrtps %ymm0, %ymm2 # CHECK-NEXT: 2 42 42.00 vsqrtps %ymm0, %ymm2
# CHECK: Resources: # CHECK: Resources:
# CHECK-NEXT: [0] - JALU0 # CHECK-NEXT: [0] - JALU0
# CHECK-NEXT: [1] - JALU1 # CHECK-NEXT: [1] - JALU1
@ -59,14 +56,14 @@ vsqrtps %ymm0, %ymm2
# CHECK-NEXT: [12] - JVALU1 # CHECK-NEXT: [12] - JVALU1
# CHECK-NEXT: [13] - JVIMUL # CHECK-NEXT: [13] - JVIMUL
# CHECK: Resource pressure per iteration: # CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] # CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]
# CHECK-NEXT: - - - 3.00 63.00 6.01 5.99 - - - 1.00 1.00 1.00 3.00 # CHECK-NEXT: - - - 3.00 63.00 6.01 5.99 - - - 1.00 1.00 1.00 3.00
# CHECK: Resource pressure by instruction: # CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions: # CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions:
# CHECK-NEXT: - - - - - 2.00 1.00 - - - - 0.03 0.97 2.00 vpmulld %xmm0, %xmm1, %xmm2 # CHECK-NEXT: - - - - - 2.00 1.00 - - - - 0.02 0.98 2.00 vpmulld %xmm0, %xmm1, %xmm2
# CHECK-NEXT: - - - - - 0.01 0.99 - - - - 0.97 0.03 - vpand %xmm0, %xmm1, %xmm2 # CHECK-NEXT: - - - - - 0.01 0.99 - - - - 0.98 0.02 - vpand %xmm0, %xmm1, %xmm2
# CHECK-NEXT: - - - - - - 1.00 - - - 1.00 - - - vcvttps2dq %xmm0, %xmm2 # CHECK-NEXT: - - - - - - 1.00 - - - 1.00 - - - vcvttps2dq %xmm0, %xmm2
# CHECK-NEXT: - - - - - 1.00 - - - - - - - 1.00 vpclmulqdq $0, %xmm0, %xmm1, %xmm2 # CHECK-NEXT: - - - - - 1.00 - - - - - - - 1.00 vpclmulqdq $0, %xmm0, %xmm1, %xmm2
# CHECK-NEXT: - - - 1.00 - 1.00 - - - - - - - - vaddps %xmm0, %xmm1, %xmm2 # CHECK-NEXT: - - - 1.00 - 1.00 - - - - - - - - vaddps %xmm0, %xmm1, %xmm2
@ -74,11 +71,10 @@ vsqrtps %ymm0, %ymm2
# CHECK-NEXT: - - - 2.00 - 2.00 - - - - - - - - vaddps %ymm0, %ymm1, %ymm2 # CHECK-NEXT: - - - 2.00 - 2.00 - - - - - - - - vaddps %ymm0, %ymm1, %ymm2
# CHECK-NEXT: - - - - 42.00 - 2.00 - - - - - - - vsqrtps %ymm0, %ymm2 # CHECK-NEXT: - - - - 42.00 - 2.00 - - - - - - - vsqrtps %ymm0, %ymm2
# CHECK: Timeline view: # CHECK: Timeline view:
# CHECK-NEXT: 0123456789 0123456789 0123456789 0 # CHECK-NEXT: 0123456789 0123456789 0123456789 0
# CHECK-NEXT: Index 0123456789 0123456789 0123456789 0123456789 # CHECK-NEXT: Index 0123456789 0123456789 0123456789 0123456789
# CHECK: [0,0] DeeeeER . . . . . . . . . . . . . vpmulld %xmm0, %xmm1, %xmm2 # CHECK: [0,0] DeeeeER . . . . . . . . . . . . . vpmulld %xmm0, %xmm1, %xmm2
# CHECK-NEXT: [0,1] .DeE--R . . . . . . . . . . . . . vpand %xmm0, %xmm1, %xmm2 # CHECK-NEXT: [0,1] .DeE--R . . . . . . . . . . . . . vpand %xmm0, %xmm1, %xmm2
# CHECK-NEXT: [0,2] . DeeeER . . . . . . . . . . . . . vcvttps2dq %xmm0, %xmm2 # CHECK-NEXT: [0,2] . DeeeER . . . . . . . . . . . . . vcvttps2dq %xmm0, %xmm2
@ -93,19 +89,19 @@ vsqrtps %ymm0, %ymm2
# CHECK-NEXT: [1,3] . . DeeE----------------------------------------------------------R vpclmulqdq $0, %xmm0, %xmm1, %xmm2 # CHECK-NEXT: [1,3] . . DeeE----------------------------------------------------------R vpclmulqdq $0, %xmm0, %xmm1, %xmm2
# CHECK-NEXT: [1,4] . . DeeeE--------------------------------------------------------R vaddps %xmm0, %xmm1, %xmm2 # CHECK-NEXT: [1,4] . . DeeeE--------------------------------------------------------R vaddps %xmm0, %xmm1, %xmm2
# CHECK: Average Wait times (based on the timeline view): # CHECK: Average Wait times (based on the timeline view):
# CHECK-NEXT: [0]: Executions # CHECK-NEXT: [0]: Executions
# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
# CHECK: [0] [1] [2] [3] # CHECK: [0] [1] [2] [3]
# CHECK-NEXT: 0. 2 1.0 1.0 28.0 vpmulld %xmm0, %xmm1, %xmm2 # CHECK-NEXT: 0. 2 1.0 1.0 28.0 vpmulld %xmm0, %xmm1, %xmm2
# CHECK-NEXT: 1. 2 1.0 1.0 30.5 vpand %xmm0, %xmm1, %xmm2 # CHECK-NEXT: 1. 2 1.0 1.0 30.5 vpand %xmm0, %xmm1, %xmm2
# CHECK-NEXT: 2. 2 1.0 1.0 28.0 vcvttps2dq %xmm0, %xmm2 # CHECK-NEXT: 2. 2 1.0 1.0 28.0 vcvttps2dq %xmm0, %xmm2
# CHECK-NEXT: 3. 2 1.0 1.0 29.5 vpclmulqdq $0, %xmm0, %xmm1, %xmm2 # CHECK-NEXT: 3. 2 1.0 1.0 29.5 vpclmulqdq $0, %xmm0, %xmm1, %xmm2
# CHECK-NEXT: 4. 2 1.0 1.0 28.0 vaddps %xmm0, %xmm1, %xmm2 # CHECK-NEXT: 4. 2 1.0 1.0 28.0 vaddps %xmm0, %xmm1, %xmm2
# CHECK-NEXT: 5. 1 1.0 1.0 0.0 vsqrtps %xmm0, %xmm2 # CHECK-NEXT: 5. 1 1.0 1.0 0.0 vsqrtps %xmm0, %xmm2
# CHECK-NEXT: 6. 1 1.0 1.0 17.0 vaddps %ymm0, %ymm1, %ymm2 # CHECK-NEXT: 6. 1 1.0 1.0 17.0 vaddps %ymm0, %ymm1, %ymm2
# CHECK-NEXT: 7. 1 20.0 20.0 0.0 vsqrtps %ymm0, %ymm2 # CHECK-NEXT: 7. 1 20.0 20.0 0.0 vsqrtps %ymm0, %ymm2

33
llvm/test/tools/llvm-mca/X86/BtVer2/resources-f16c.s
View File

@ -12,6 +12,30 @@ vcvtps2ph $0, %xmm0, (%rax)
vcvtps2ph $0, %ymm0, %xmm2 vcvtps2ph $0, %ymm0, %xmm2
vcvtps2ph $0, %ymm0, (%rax) vcvtps2ph $0, %ymm0, (%rax)
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 800
# CHECK-NEXT: Total Cycles: 1503
# CHECK-NEXT: Dispatch Width: 2
# CHECK-NEXT: IPC: 0.53
# CHECK: Instruction Info:
# CHECK-NEXT: [1]: #uOps
# CHECK-NEXT: [2]: Latency
# CHECK-NEXT: [3]: RThroughput
# CHECK-NEXT: [4]: MayLoad
# CHECK-NEXT: [5]: MayStore
# CHECK-NEXT: [6]: HasSideEffects
# CHECK: [1] [2] [3] [4] [5] [6] Instructions:
# CHECK-NEXT: 1 3 1.00 vcvtph2ps %xmm0, %xmm2
# CHECK-NEXT: 1 8 1.00 * vcvtph2ps (%rax), %xmm2
# CHECK-NEXT: 2 3 2.00 vcvtph2ps %xmm0, %ymm2
# CHECK-NEXT: 2 8 2.00 * vcvtph2ps (%rax), %ymm2
# CHECK-NEXT: 1 3 1.00 vcvtps2ph $0, %xmm0, %xmm2
# CHECK-NEXT: 1 3 1.00 * vcvtps2ph $0, %xmm0, (%rax)
# CHECK-NEXT: 3 6 2.00 vcvtps2ph $0, %ymm0, %xmm2
# CHECK-NEXT: 3 11 2.00 * vcvtps2ph $0, %ymm0, (%rax)
# CHECK: Resources: # CHECK: Resources:
# CHECK-NEXT: [0] - JALU0 # CHECK-NEXT: [0] - JALU0
# CHECK-NEXT: [1] - JALU1 # CHECK-NEXT: [1] - JALU1
@ -28,6 +52,10 @@ vcvtps2ph $0, %ymm0, (%rax)
# CHECK-NEXT: [12] - JVALU1 # CHECK-NEXT: [12] - JVALU1
# CHECK-NEXT: [13] - JVIMUL # CHECK-NEXT: [13] - JVIMUL
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]
# CHECK-NEXT: - - - 2.00 2.00 - 12.00 2.00 - 2.00 12.00 - - -
# CHECK: Resource pressure by instruction: # CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions: # CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions:
# CHECK-NEXT: - - - - - - 1.00 - - - 1.00 - - - vcvtph2ps %xmm0, %xmm2 # CHECK-NEXT: - - - - - - 1.00 - - - 1.00 - - - vcvtph2ps %xmm0, %xmm2
@ -36,5 +64,6 @@ vcvtps2ph $0, %ymm0, (%rax)
# CHECK-NEXT: - - - - - - 2.00 1.00 - - 2.00 - - - vcvtph2ps (%rax), %ymm2 # CHECK-NEXT: - - - - - - 2.00 1.00 - - 2.00 - - - vcvtph2ps (%rax), %ymm2
# CHECK-NEXT: - - - - - - 1.00 - - - 1.00 - - - vcvtps2ph $0, %xmm0, %xmm2 # CHECK-NEXT: - - - - - - 1.00 - - - 1.00 - - - vcvtps2ph $0, %xmm0, %xmm2
# CHECK-NEXT: - - - - - - 1.00 - - 1.00 1.00 - - - vcvtps2ph $0, %xmm0, (%rax) # CHECK-NEXT: - - - - - - 1.00 - - 1.00 1.00 - - - vcvtps2ph $0, %xmm0, (%rax)
# CHECK-NEXT: - - - 1.80 0.20 - 2.00 - - - 2.00 - - - vcvtps2ph $0, %ymm0, %xmm2 # CHECK-NEXT: - - - 1.86 0.14 - 2.00 - - - 2.00 - - - vcvtps2ph $0, %ymm0, %xmm2
# CHECK-NEXT: - - - 0.20 1.80 - 2.00 - - 1.00 2.00 - - - vcvtps2ph $0, %ymm0, (%rax) # CHECK-NEXT: - - - 0.14 1.86 - 2.00 - - 1.00 2.00 - - - vcvtps2ph $0, %ymm0, (%rax)

90
llvm/test/tools/llvm-mca/X86/cpus.s
View File

@ -1,27 +1,73 @@
# RUN: llvm-mca %s -mtriple=x86_64-unknown-unknown -mcpu=btver2 < %s | FileCheck --check-prefix=ALL --check-prefix=BTVER2 %s # RUN: llvm-mca %s -mtriple=x86_64-unknown-unknown -mcpu=btver2 -resource-pressure=false -instruction-info=false < %s | FileCheck --check-prefix=ALL --check-prefix=BTVER2 %s
# RUN: llvm-mca %s -mtriple=x86_64-unknown-unknown -mcpu=znver1 < %s | FileCheck --check-prefix=ALL --check-prefix=ZNVER1 %s # RUN: llvm-mca %s -mtriple=x86_64-unknown-unknown -mcpu=znver1 -resource-pressure=false -instruction-info=false < %s | FileCheck --check-prefix=ALL --check-prefix=ZNVER1 %s
# RUN: llvm-mca %s -mtriple=x86_64-unknown-unknown -mcpu=sandybridge < %s | FileCheck --check-prefix=ALL --check-prefix=SANDYBRIDGE %s # RUN: llvm-mca %s -mtriple=x86_64-unknown-unknown -mcpu=sandybridge -resource-pressure=false -instruction-info=false < %s | FileCheck --check-prefix=ALL --check-prefix=SANDYBRIDGE %s
# RUN: llvm-mca %s -mtriple=x86_64-unknown-unknown -mcpu=ivybridge < %s | FileCheck --check-prefix=ALL --check-prefix=IVYBRIDGE %s # RUN: llvm-mca %s -mtriple=x86_64-unknown-unknown -mcpu=ivybridge -resource-pressure=false -instruction-info=false < %s | FileCheck --check-prefix=ALL --check-prefix=IVYBRIDGE %s
# RUN: llvm-mca %s -mtriple=x86_64-unknown-unknown -mcpu=haswell < %s | FileCheck --check-prefix=ALL --check-prefix=HASWELL %s # RUN: llvm-mca %s -mtriple=x86_64-unknown-unknown -mcpu=haswell -resource-pressure=false -instruction-info=false < %s | FileCheck --check-prefix=ALL --check-prefix=HASWELL %s
# RUN: llvm-mca %s -mtriple=x86_64-unknown-unknown -mcpu=broadwell < %s | FileCheck --check-prefix=ALL --check-prefix=BROADWELL %s # RUN: llvm-mca %s -mtriple=x86_64-unknown-unknown -mcpu=broadwell -resource-pressure=false -instruction-info=false < %s | FileCheck --check-prefix=ALL --check-prefix=BROADWELL %s
# RUN: llvm-mca %s -mtriple=x86_64-unknown-unknown -mcpu=knl < %s | FileCheck --check-prefix=ALL --check-prefix=KNL %s # RUN: llvm-mca %s -mtriple=x86_64-unknown-unknown -mcpu=knl -resource-pressure=false -instruction-info=false < %s | FileCheck --check-prefix=ALL --check-prefix=KNL %s
# RUN: llvm-mca %s -mtriple=x86_64-unknown-unknown -mcpu=skylake < %s | FileCheck --check-prefix=ALL --check-prefix=SKX %s # RUN: llvm-mca %s -mtriple=x86_64-unknown-unknown -mcpu=skylake -resource-pressure=false -instruction-info=false < %s | FileCheck --check-prefix=ALL --check-prefix=SKX %s
# RUN: llvm-mca %s -mtriple=x86_64-unknown-unknown -mcpu=skylake-avx512 < %s | FileCheck --check-prefix=ALL --check-prefix=SKX-AVX512 %s # RUN: llvm-mca %s -mtriple=x86_64-unknown-unknown -mcpu=skylake-avx512 -resource-pressure=false -instruction-info=false < %s | FileCheck --check-prefix=ALL --check-prefix=SKX-AVX512 %s
# RUN: llvm-mca %s -mtriple=x86_64-unknown-unknown -mcpu=slm < %s | FileCheck --check-prefix=ALL --check-prefix=SLM %s # RUN: llvm-mca %s -mtriple=x86_64-unknown-unknown -mcpu=slm -resource-pressure=false -instruction-info=false < %s | FileCheck --check-prefix=ALL --check-prefix=SLM %s
add %edi, %eax add %edi, %eax
# ALL: Iterations: 70 # BTVER2: Iterations: 100
# ALL-NEXT: Instructions: 70 # BTVER2-NEXT: Instructions: 100
# BTVER2-NEXT: Total Cycles: 103
# BTVER2-NEXT: Dispatch Width: 2
# BTVER2-NEXT: IPC: 0.97
# BTVER2: Dispatch Width: 2 # SLM: Iterations: 100
# ZNVER1: Dispatch Width: 4 # SLM-NEXT: Instructions: 100
# SANDYBRIDGE: Dispatch Width: 4 # SLM-NEXT: Total Cycles: 103
# IVYBRIDGE: Dispatch Width: 4 # SLM-NEXT: Dispatch Width: 2
# HASWELL: Dispatch Width: 4 # SLM-NEXT: IPC: 0.97
# BROADWELL: Dispatch Width: 4
# KNL: Dispatch Width: 4 # BROADWELL: Iterations: 100
# SKX: Dispatch Width: 6 # BROADWELL-NEXT: Instructions: 100
# SKX-AVX512: Dispatch Width: 6 # BROADWELL-NEXT: Total Cycles: 103
# SLM: Dispatch Width: 2 # BROADWELL-NEXT: Dispatch Width: 4
# BROADWELL-NEXT: IPC: 0.97
# HASWELL: Iterations: 100
# HASWELL-NEXT: Instructions: 100
# HASWELL-NEXT: Total Cycles: 103
# HASWELL-NEXT: Dispatch Width: 4
# HASWELL-NEXT: IPC: 0.97
# IVYBRIDGE: Iterations: 100
# IVYBRIDGE-NEXT: Instructions: 100
# IVYBRIDGE-NEXT: Total Cycles: 103
# IVYBRIDGE-NEXT: Dispatch Width: 4
# IVYBRIDGE-NEXT: IPC: 0.97
# KNL: Iterations: 100
# KNL-NEXT: Instructions: 100
# KNL-NEXT: Total Cycles: 103
# KNL-NEXT: Dispatch Width: 4
# KNL-NEXT: IPC: 0.97
# SANDYBRIDGE: Iterations: 100
# SANDYBRIDGE-NEXT: Instructions: 100
# SANDYBRIDGE-NEXT: Total Cycles: 103
# SANDYBRIDGE-NEXT: Dispatch Width: 4
# SANDYBRIDGE-NEXT: IPC: 0.97
# ZNVER1: Iterations: 100
# ZNVER1-NEXT: Instructions: 100
# ZNVER1-NEXT: Total Cycles: 103
# ZNVER1-NEXT: Dispatch Width: 4
# ZNVER1-NEXT: IPC: 0.97
# SKX: Iterations: 100
# SKX-NEXT: Instructions: 100
# SKX-NEXT: Total Cycles: 103
# SKX-NEXT: Dispatch Width: 6
# SKX-NEXT: IPC: 0.97
# SKX-AVX512: Iterations: 100
# SKX-AVX512-NEXT: Instructions: 100
# SKX-AVX512-NEXT: Total Cycles: 103
# SKX-AVX512-NEXT: Dispatch Width: 6
# SKX-AVX512-NEXT: IPC: 0.97

32
llvm/test/tools/llvm-mca/X86/default-iterations.s
View File

@ -1,11 +1,29 @@
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 < %s 2>&1 | FileCheck --check-prefix=DEFAULT %s # RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -resource-pressure=false < %s | FileCheck --check-prefix=ALL --check-prefix=DEFAULT %s
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -iterations=0 < %s 2>&1 | FileCheck --check-prefix=DEFAULT %s # RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -iterations=0 -resource-pressure=false < %s | FileCheck --check-prefix=ALL --check-prefix=DEFAULT %s
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -iterations=1 < %s 2>&1 | FileCheck --check-prefix=CUSTOM %s # RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -iterations=1 -resource-pressure=false < %s | FileCheck --check-prefix=ALL --check-prefix=CUSTOM %s
add %eax, %eax add %eax, %eax
# DEFAULT: Iterations: 70 # CUSTOM: Iterations: 1
# DEFAULT-NEXT: Instructions: 70 # CUSTOM-NEXT: Instructions: 1
# CUSTOM-NEXT: Total Cycles: 4
# CUSTOM-NEXT: Dispatch Width: 2
# CUSTOM-NEXT: IPC: 0.25
# DEFAULT: Iterations: 100
# DEFAULT-NEXT: Instructions: 100
# DEFAULT-NEXT: Total Cycles: 103
# DEFAULT-NEXT: Dispatch Width: 2
# DEFAULT-NEXT: IPC: 0.97
# 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
# ALL: [1] [2] [3] [4] [5] [6] Instructions:
# ALL-NEXT: 1 1 0.50 addl %eax, %eax
# CUSTOM: Iterations: 1
# CUSTOM-NEXT: Instructions: 1

2
llvm/tools/llvm-mca/README.txt
View File

@ -59,7 +59,7 @@ sequence of MCInst is then analyzed by a 'Backend' module to generate a
performance report. performance report.
The Backend module internally emulates the execution of the machine code The Backend module internally emulates the execution of the machine code
sequence in a loop of iterations (which by default is 70). At the end of this sequence in a loop of iterations (which by default is 100). At the end of this
process, the backend collects a number of statistics which are then printed out process, the backend collects a number of statistics which are then printed out
in the form of a report. in the form of a report.

2
llvm/tools/llvm-mca/SourceMgr.h
View File

@ -28,7 +28,7 @@ class SourceMgr {
const InstVec &Sequence; const InstVec &Sequence;
unsigned Current; unsigned Current;
unsigned Iterations; unsigned Iterations;
static const unsigned DefaultIterations = 70; static const unsigned DefaultIterations = 100;
public: public:
SourceMgr(const InstVec &MCInstSequence, unsigned NumIterations) SourceMgr(const InstVec &MCInstSequence, unsigned NumIterations)