gen_autofdo_event.py was stumbling on models with stepping so
I updated the script to handle this case similar to the code in
https://github.com/andikleen/pmu-tools/blob/c6a5f63aede19def8886d6a8b74d7a55c38ca947/event_download.py
The second change was to tolerate cases when the CPU supports PEBS but the
perf command with /p fails. This can happen in, e.g., a virtual machine.
I regenerated gcc-auto-profile using the updated script.
contrib/ChangeLog:
* gen_autofdo_event.py: handle stepping, non-working PEBS
gcc/ChangeLog:
* config/i386/gcc-auto-profile: regenerate
---
contrib/gen_autofdo_event.py | 54 ++++++++++++++++++++++----------
gcc/config/i386/gcc-auto-profile | 41 +++++++++++++++++++-----
2 files changed, 71 insertions(+), 24 deletions(-)
diff --git a/contrib/gen_autofdo_event.py b/contrib/gen_autofdo_event.py
index c97460c61c6..1eb6f1d6d85 100755
--- a/contrib/gen_autofdo_event.py
+++ b/contrib/gen_autofdo_event.py
@@ -46,20 +46,29 @@ args = ap.parse_args()
eventmap = collections.defaultdict(list)
-def get_cpu_str():
- with open('/proc/cpuinfo', 'r') as c:
- vendor, fam, model = None, None, None
- for j in c:
- n = j.split()
- if n[0] == 'vendor_id':
- vendor = n[2]
- elif n[0] == 'model' and n[1] == ':':
- model = int(n[2])
- elif n[0] == 'cpu' and n[1] == 'family':
- fam = int(n[3])
- if vendor and fam and model:
- return "%s-%d-%X" % (vendor, fam, model), model
- return None, None
+def get_cpustr():
+ cpuinfo = os.getenv("CPUINFO")
+ if cpuinfo is None:
+ cpuinfo = '/proc/cpuinfo'
+ f = open(cpuinfo, 'r')
+ cpu = [None, None, None, None]
+ for j in f:
+ n = j.split()
+ if n[0] == 'vendor_id':
+ cpu[0] = n[2]
+ elif n[0] == 'model' and n[1] == ':':
+ cpu[2] = int(n[2])
+ elif n[0] == 'cpu' and n[1] == 'family':
+ cpu[1] = int(n[3])
+ elif n[0] == 'stepping' and n[1] == ':':
+ cpu[3] = int(n[2])
+ if all(v is not None for v in cpu):
+ break
+ # stepping for SKX only
+ stepping = cpu[0] == "GenuineIntel" and cpu[1] == 6 and cpu[2] == 0x55
+ if stepping:
+ return "%s-%d-%X-%X" % tuple(cpu)
+ return "%s-%d-%X" % tuple(cpu)[:3]
def find_event(eventurl, model):
print >>sys.stderr, "Downloading", eventurl
@@ -81,7 +90,7 @@ def find_event(eventurl, model):
return found
if not args.all:
- cpu, model = get_cpu_str()
+ cpu = get_cpu_str()
if not cpu:
sys.exit("Unknown CPU type")
@@ -94,7 +103,8 @@ for j in u:
n = j.rstrip().split(',')
if len(n) >= 4 and (args.all or n[0] == cpu) and n[3] == "core":
if args.all:
- vendor, fam, model = n[0].split("-")
+ components = n[0].split("-")
+ model = components[2]
model = int(model, 16)
cpufound += 1
found += find_event(baseurl + n[2], model)
@@ -146,7 +156,17 @@ case `egrep -q "^cpu family\s*: 6" /proc/cpuinfo &&
echo >&2 "Unknown CPU. Run contrib/gen_autofdo_event.py --all --script to
update script."
exit 1 ;;'''
print "esac"
- print 'exec perf record -e $E -b "$@"'
+ print "set -x"
+ print 'if ! perf record -e $E -b "$@" ; then'
+ print ' # PEBS may not actually be working even if the processor supports
it'
+ print ' # (e.g., in a virtual machine). Trying to run without /p.'
+ print ' set +x'
+ print ' echo >&2 "Retrying without /p."'
+ print ' E="$(echo "${E}" | sed -e \'s/\/p/\//\')"'
+ print ' set -x'
+ print ' exec perf record -e $E -b "$@"'
+ print ' set +x'
+ print 'fi'
if cpufound == 0 and not args.all:
sys.exit('CPU %s not found' % cpu)
diff --git a/gcc/config/i386/gcc-auto-profile b/gcc/config/i386/gcc-auto-profile
index 5da5c63cd84..56f64cbff1f 100755
--- a/gcc/config/i386/gcc-auto-profile
+++ b/gcc/config/i386/gcc-auto-profile
@@ -1,7 +1,7 @@
#!/bin/sh
-# profile workload for gcc profile feedback (autofdo) using Linux perf
-# auto generated. to regenerate for new CPUs run
-# contrib/gen_autofdo_event.py --shell --all in gcc source
+# Profile workload for gcc profile feedback (autofdo) using Linux perf.
+# Auto generated. To regenerate for new CPUs run
+# contrib/gen_autofdo_event.py --script --all in gcc source
# usages:
# gcc-auto-profile program (profile program and children)
@@ -10,7 +10,7 @@
# gcc-auto-profile --kernel -a sleep X (profile kernel)
# gcc-auto-profile --all -a sleep X (profile kernel and user space)
-# identify branches taken event for CPU
+# Identify branches taken event for CPU.
#
FLAGS=u
@@ -37,7 +37,12 @@ case `egrep -q "^cpu family\s*: 6" /proc/cpuinfo &&
egrep "^model\s*:" /proc/cpuinfo | head -n1` in
model*:\ 55|\
model*:\ 77|\
-model*:\ 76) E="cpu/event=0xC4,umask=0xFE/p$FLAGS" ;;
+model*:\ 76|\
+model*:\ 92|\
+model*:\ 95|\
+model*:\ 87|\
+model*:\ 133|\
+model*:\ 122) E="cpu/event=0xC4,umask=0xFE/p$FLAGS" ;;
model*:\ 42|\
model*:\ 45|\
model*:\ 58|\
@@ -48,9 +53,16 @@ model*:\ 70|\
model*:\ 63|\
model*:\ 61|\
model*:\ 71|\
+model*:\ 79|\
model*:\ 86|\
model*:\ 78|\
-model*:\ 94) E="cpu/event=0xC4,umask=0x20/p$FLAGS" ;;
+model*:\ 94|\
+model*:\ 142|\
+model*:\ 158|\
+model*:\ 165|\
+model*:\ 166|\
+model*:\ 85|\
+model*:\ 85) E="cpu/event=0xC4,umask=0x20/p$FLAGS" ;;
model*:\ 46|\
model*:\ 30|\
model*:\ 31|\
@@ -63,8 +75,23 @@ model*:\ 38|\
model*:\ 39|\
model*:\ 54|\
model*:\ 53) E="cpu/event=0x88,umask=0x41/p$FLAGS" ;;
+model*:\ 126|\
+model*:\ 140|\
+model*:\ 141|\
+model*:\ 106|\
+model*:\ 108) E="cpu/event=0xc4,umask=0x20/p$FLAGS" ;;
*)
echo >&2 "Unknown CPU. Run contrib/gen_autofdo_event.py --all --script to
update script."
exit 1 ;;
esac
-exec perf record -e $E -b "$@"
+set -x
+if ! perf record -e $E -b "$@" ; then
+ # PEBS may not actually be working even if the processor supports it
+ # (e.g., in a virtual machine). Trying to run without /p.
+ set +x
+ echo >&2 "Retrying without /p."
+ E="$(echo "${E}" | sed -e 's/\/p/\//')"
+ set -x
+ exec perf record -e $E -b "$@"
+ set +x
+fi
--
2.25.1
