1		i	synthesize instructions events
2		b	synthesize branches events
3		c	synthesize branches events (calls only)
4		r	synthesize branches events (returns only)
5		x	synthesize transactions events
6		w	synthesize ptwrite events
7		p	synthesize power events
8		o	synthesize other events recorded due to the use
9			of aux-output (refer to perf record)
10		e	synthesize error events
11		d	create a debug log
12		g	synthesize a call chain (use with i or x)
13		G	synthesize a call chain on existing event records
14		l	synthesize last branch entries (use with i or x)
15		L	synthesize last branch entries on existing event records
16		s       skip initial number of events
17
18	The default is all events i.e. the same as --itrace=ibxwpe,
19	except for perf script where it is --itrace=ce
20
21	In addition, the period (default 100000, except for perf script where it is 1)
22	for instructions events can be specified in units of:
23
24		i	instructions
25		t	ticks
26		ms	milliseconds
27		us	microseconds
28		ns	nanoseconds (default)
29
30	Also the call chain size (default 16, max. 1024) for instructions or
31	transactions events can be specified.
32
33	Also the number of last branch entries (default 64, max. 1024) for
34	instructions or transactions events can be specified.
35
36	Similar to options g and l, size may also be specified for options G and L.
37	On x86, note that G and L work poorly when data has been recorded with
38	large PEBS. Refer linkperf:perf-intel-pt[1] man page for details.
39
40	It is also possible to skip events generated (instructions, branches, transactions,
41	ptwrite, power) at the beginning. This is useful to ignore initialization code.
42
43	--itrace=i0nss1000000
44
45	skips the first million instructions.
46