Message117069
| Author |
belopolsky |
| Recipients |
alexandre.vassalotti, amaury.forgeotdarc, belopolsky, collinwinter, eli.bendersky, ezio.melotti, flox, georg.brandl, jyasskin, pitrou, rhettinger, teresap989, terry.reedy |
| Date |
2010年09月21日.15:27:56 |
| SpamBayes Score |
3.759719e-07 |
| Marked as misclassified |
No |
| Message-id |
<1285082878.34.0.486344600121.issue9866@psf.upfronthosting.co.za> |
| In-reply-to |
| Content |
I have found the root cause of these differences. The trace function is not called when the opcode is successfully predicted. When computed gotos are enabled, opcode prediction is disabled as explained in the following comment in ceval.c:
Opcode prediction is disabled with threaded code, since the latter allows
the CPU to record separate branch prediction information for each
opcode.
Note that this issue is similar to #884022 which was resolved by disabling opcode prediction in dynamic profile builds.
Given that opcode prediction if off by default, I don't see much of the reason to try to improve tracing of predicted opcodes. |
|
History
|
|---|
| Date |
User |
Action |
Args |
| 2010年09月21日 15:27:58 | belopolsky | set | recipients:
+ belopolsky, georg.brandl, collinwinter, rhettinger, terry.reedy, amaury.forgeotdarc, pitrou, alexandre.vassalotti, jyasskin, ezio.melotti, eli.bendersky, flox, teresap989 |
| 2010年09月21日 15:27:58 | belopolsky | set | messageid: <1285082878.34.0.486344600121.issue9866@psf.upfronthosting.co.za> |
| 2010年09月21日 15:27:57 | belopolsky | link | issue9866 messages |
| 2010年09月21日 15:27:56 | belopolsky | create |
|