From 5291012ef93d2f64bf749866c19ad6e5b65997ba Mon Sep 17 00:00:00 2001
From: Nan Xiao <nan@chinadtrace.org>
Date: Thu, 21 Nov 2019 17:20:42 +0800
Subject: [PATCH] Add record-events-per-thread.md

---
 SUMMARY.md                              |  3 +-
 posts/record-event-counts-per-thread.md | 57 +++++++++++++++++++++++++
 2 files changed, 59 insertions(+), 1 deletion(-)
 create mode 100644 posts/record-event-counts-per-thread.md

diff --git a/SUMMARY.md b/SUMMARY.md
index 6a91042..db79b0e 100644
--- a/SUMMARY.md
+++ b/SUMMARY.md
@@ -5,6 +5,7 @@
 * [How to specify monitoring events](posts/how-to-specify-monitoring-events.md)
 * [What is skid](posts/what-is-skid.md)
 * [Count events](posts/count-events.md)
+* [Record event counts per thread](posts/record-event-counts-per-thread.md)
 * [Profile memory access](posts/profile-memory-access.md)
 * [Check cache false sharing](posts/check-cache-false-sharing.md)
 * [Profile system in real time](posts/profile-system-in-real-time.md)
@@ -12,4 +13,4 @@
 * [Measure scheduler latency](posts/measure-scheduler-latency.md)
 * [Use ftrace](posts/use-ftrace.md)
 * [Show performance difference](posts/show-performance-difference.md)
-* [The end](posts/the-end.md)
\ No newline at end of file
+* [The end](posts/the-end.md)
diff --git a/posts/record-event-counts-per-thread.md b/posts/record-event-counts-per-thread.md
new file mode 100644
index 0000000..ade0f25
--- /dev/null
+++ b/posts/record-event-counts-per-thread.md
@@ -0,0 +1,57 @@
+# Record event counts per thread
+
+`perf record` can be used to record event counts for every thread when using `-s` option. Check following multi-thread program:  
+
+```
+$ cat sum.c
+#include <omp.h>
+
+#define N 100000000
+#define THRAED_NUM 8
+
+int values[N];
+
+int main(void)
+{
+    int sum[THRAED_NUM];
+
+    #pragma omp parallel for
+    for (int i = 0; i < THRAED_NUM; i++)
+    {
+        int local_sum;
+        for (int j = 0; j < N; j++)
+        {
+            local_sum += values[j] >> i;
+        }
+        sum[i] = local_sum;
+    }
+
+    return 0;
+}
+```
+
+Build and use `perf record` to note down event counts for every thread:  
+
+```
+# gcc -fopenmp -g sum.c -o sum
+# perf record -s ./sum
+[ perf record: Woken up 1 times to write data ]
+[ perf record: Captured and wrote 0.404 MB perf.data (8757 samples) ]
+```
+
+Use `perf report` to analyze it (`-T` option means displaying per-thread event counts):  
+
+```
+# perf report -T
+......
+#  PID   TID      cycles:uppp
+  9960  9963        751824252
+  9960  9961        750625307
+  9960  9965        749742594
+  9960  9967        749228142
+  9960  9968                0
+  9960  9970          9857914
+  9960  9974          9150516
+  9960  9977          8928628
+......
+```