Skip to content

Commit 54dc9f8

Browse files
Updates
1 parent 516a33d commit 54dc9f8

1 file changed

Lines changed: 2 additions & 2 deletions

File tree

  • content/learning-paths/servers-and-cloud-computing/false-sharing-arm-spe

content/learning-paths/servers-and-cloud-computing/false-sharing-arm-spe/how-to-4.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -114,7 +114,7 @@ sudo perf c2c record -g ./false_sharing 1
114114
sudo perf annotate
115115
```
116116

117-
The left screenshot shows the canonical `perf record` command, here the `adrp` instruction falsely reports 52% of the time. However, using `perf c2c` that leverages `arm_spe`, we observe 99% of time associated with the `ldr`, load register command. The standard `perf record` data can be quite misleading!
117+
The left screenshot shows the canonical `perf record` command, here the `adrp` instruction falsely reports 52% of the time. However, using `perf c2c` that leverages `arm_spe`, you can see 99% of time associated with the `ldr`, load register command. The standard `perf record` data can be quite misleading!
118118

119119
![perf-record-annotate](./perf-record-error-skid.png)
120120
![perf-c2c-record-annotate](./perf-c2c-record.png)
@@ -148,7 +148,7 @@ Next, press `d` character to display the cache line details. The last `Source:Li
148148

149149
![perf-c2c-gif](./perf-c2c.gif)
150150

151-
Looking at the corresponding source code, we observe the following.
151+
Looking at the corresponding source code, you can see the following:
152152

153153
```output
154154
...

0 commit comments

Comments
 (0)