Re: RFR: 8188046: java.lang.Math.mutliplyHigh does not run in constant time

2021-07-02 Thread Joe Darcy
On Thu, 1 Jul 2021 23:46:00 GMT, Brian Burkhalter wrote: > Please consider this proposal to remove the fast path in > `java.lang.Math.multiplyHigh()` the small performance improvement of which is > eclipsed by the branch penalty. Marked as reviewed by darcy (Reviewer). - PR:

Re: RFR: 8188046: java.lang.Math.mutliplyHigh does not run in constant time

2021-07-02 Thread Roger Riggs
On Thu, 1 Jul 2021 23:46:00 GMT, Brian Burkhalter wrote: > Please consider this proposal to remove the fast path in > `java.lang.Math.multiplyHigh()` the small performance improvement of which is > eclipsed by the branch penalty. Marked as reviewed by rriggs (Reviewer). - PR:

Re: RFR: 8188046: java.lang.Math.mutliplyHigh does not run in constant time

2021-07-01 Thread Brian Burkhalter
On Thu, 1 Jul 2021 23:46:00 GMT, Brian Burkhalter wrote: > Please consider this proposal to remove the fast path in > `java.lang.Math.multiplyHigh()` the small performance improvement of which is > eclipsed by the branch penalty. Please refer to the issue for a benchmark and sample output

RFR: 8188046: java.lang.Math.mutliplyHigh does not run in constant time

2021-07-01 Thread Brian Burkhalter
Please consider this proposal to remove the fast path in `java.lang.Math.multiplyHigh()` the small performance improvement of which is eclipsed by the branch penalty. - Commit messages: - 8188046: java.lang.Math.mutliplyHigh does not run in constant time Changes: