Skip to content

Commit 3fb490c

Browse files
[llvm] Proofread Benchmarking.rst (#155792)
1 parent 916bee9 commit 3fb490c

File tree

1 file changed

+10
-10
lines changed

1 file changed

+10
-10
lines changed

llvm/docs/Benchmarking.rst

Lines changed: 10 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -17,24 +17,24 @@ for example.
1717
General
1818
================================
1919

20-
* Use a high resolution timer, e.g. perf under linux.
20+
* Use a high-resolution timer, e.g., perf under Linux.
2121

2222
* Run the benchmark multiple times to be able to recognize noise.
2323

2424
* Disable as many processes or services as possible on the target system.
2525

26-
* Disable frequency scaling, turbo boost and address space
27-
randomization (see OS specific section).
26+
* Disable frequency scaling, Turbo Boost and address space
27+
randomization (see OS-specific section).
2828

29-
* Static link if the OS supports it. That avoids any variation that
29+
* Use static linking if the OS supports it. That avoids any variation that
3030
might be introduced by loading dynamic libraries. This can be done
31-
by passing ``-DLLVM_BUILD_STATIC=ON`` to cmake.
31+
by passing ``-DLLVM_BUILD_STATIC=ON`` to CMake.
3232

33-
* Try to avoid storage. On some systems you can use tmpfs. Putting the
33+
* Try to avoid storage. On some systems, you can use tmpfs. Putting the
3434
program, inputs and outputs on tmpfs avoids touching a real storage
3535
system, which can have a pretty big variability.
3636

37-
To mount it (on linux and freebsd at least)::
37+
To mount it (on Linux and FreeBSD at least)::
3838

3939
mount -t tmpfs -o size=<XX>g none dir_to_mount
4040

@@ -52,7 +52,7 @@ Linux
5252
echo performance > $i
5353
done
5454

55-
* Use https://github.com/lpechacek/cpuset to reserve cpus for just the
55+
* Use https://github.com/lpechacek/cpuset to reserve CPU cores for just the
5656
program you are benchmarking. If using perf, leave at least 2 cores
5757
so that perf runs in one and your program in another::
5858

@@ -73,7 +73,7 @@ Linux
7373

7474
cset shield --exec -- perf stat -r 10 <cmd>
7575

76-
This will run the command after ``--`` in the isolated cpus. The
76+
This will run the command after ``--`` in the isolated CPU cores. The
7777
particular perf command runs the ``<cmd>`` 10 times and reports
7878
statistics.
7979

@@ -82,6 +82,6 @@ With these in place you can expect perf variations of less than 0.1%.
8282
Linux Intel
8383
-----------
8484

85-
* Disable turbo mode::
85+
* Disable Turbo Boost::
8686

8787
echo 1 > /sys/devices/system/cpu/intel_pstate/no_turbo

0 commit comments

Comments
 (0)