Re: RFR: 8333396: Performance regression of DecimalFormat.format [v10]

2024-06-24 Thread Chen Liang
On Fri, 21 Jun 2024 07:25:27 GMT, lingjun-cg wrote: >> ### Performance regression of DecimalFormat.format >> From the output of perf, we can see the hottest regions contain atomic >> instructions. But when run with JDK 11, there is no such problem. The >> reason is the removed biased locking.

Re: RFR: 8333396: Performance regression of DecimalFormat.format [v10]

2024-06-21 Thread lingjun-cg
On Fri, 21 Jun 2024 07:25:27 GMT, lingjun-cg wrote: >> ### Performance regression of DecimalFormat.format >> From the output of perf, we can see the hottest regions contain atomic >> instructions. But when run with JDK 11, there is no such problem. The >> reason is the removed biased locking.

Re: RFR: 8333396: Performance regression of DecimalFormat.format [v10]

2024-06-21 Thread lingjun-cg
> ### Performance regression of DecimalFormat.format > From the output of perf, we can see the hottest regions contain atomic > instructions. But when run with JDK 11, there is no such problem. The reason > is the removed biased locking. > The DecimalFormat uses StringBuffer everywhere, and St