Re: [PATCH v2 0/7] perf diff: diff cycles at basic block level

On 6/5/2019 7:44 PM, Jiri Olsa wrote: On Mon, Jun 03, 2019 at 10:36:10PM +0800, Jin Yao wrote: In some cases small changes in hot loops can show big differences. But it's difficult to identify these differences. perf diff currently can only diff symbols (functions). We can also expand it to

Re: [PATCH v2 0/7] perf diff: diff cycles at basic block level

On Mon, Jun 03, 2019 at 10:36:10PM +0800, Jin Yao wrote: > In some cases small changes in hot loops can show big differences. > But it's difficult to identify these differences. > > perf diff currently can only diff symbols (functions). We can also expand > it to diff cycles of individual programs

Re: [PATCH v2 0/7] perf diff: diff cycles at basic block level

On 6/3/2019 10:36 PM, Jin Yao wrote: In some cases small changes in hot loops can show big differences. But it's difficult to identify these differences. perf diff currently can only diff symbols (functions). We can also expand it to diff cycles of individual programs blocks as reported by ti

[PATCH v2 0/7] perf diff: diff cycles at basic block level

In some cases small changes in hot loops can show big differences. But it's difficult to identify these differences. perf diff currently can only diff symbols (functions). We can also expand it to diff cycles of individual programs blocks as reported by timed LBR. This would allow to identify chan