Re: RFR: 8266054: VectorAPI rotate operation optimization [v10]

2021-07-27 Thread Jatin Bhateja
On Tue, 27 Jul 2021 02:52:13 GMT, Eric Liu wrote: >> @sviswa7, SLP flow will either have a constant 8bit shift value or a >> variable shift present in vector, this also include broadcasted non-constant >> shift value or a shift value beyond 8 bit. > > It would be better comment here, since the

Re: RFR: 8266054: VectorAPI rotate operation optimization [v10]

2021-07-26 Thread Eric Liu
On Mon, 26 Jul 2021 18:56:01 GMT, Jatin Bhateja wrote: >> @jatin-bhateja This question is still pending. > > @sviswa7, SLP flow will either have a constant 8bit shift value or a variable > shift present in vector. So non constant scalar case will not be hit through > this route. It would be

Re: RFR: 8266054: VectorAPI rotate operation optimization [v10]

2021-07-26 Thread Jatin Bhateja
On Mon, 26 Jul 2021 17:19:07 GMT, Sandhya Viswanathan wrote: >> And'ing with shift_mask is already done on Java API side implementation >> before making a call to intrinsic rountine. > > @jatin-bhateja This question is still pending. @sviswa7, SLP flow will either have a constant 8bit shift

Re: RFR: 8266054: VectorAPI rotate operation optimization [v10]

2021-07-26 Thread Jatin Bhateja
On Mon, 26 Jul 2021 17:19:07 GMT, Sandhya Viswanathan wrote: >> And'ing with shift_mask is already done on Java API side implementation >> before making a call to intrinsic rountine. > > @jatin-bhateja This question is still pending. Other than VectorAPI , SLP also infers vector rotates

Re: RFR: 8266054: VectorAPI rotate operation optimization [v10]

2021-07-26 Thread Sandhya Viswanathan
On Sun, 18 Jul 2021 20:22:18 GMT, Jatin Bhateja wrote: >> src/hotspot/share/opto/vectornode.cpp line 1180: >> >>> 1178: cnt = cnt->in(1); >>> 1179: } >>> 1180: shiftRCnt = cnt; >> >> Why do we remove the And with mask here? > > And'ing with shift_mask is already done on Java API

Re: RFR: 8266054: VectorAPI rotate operation optimization [v10]

2021-07-18 Thread Jatin Bhateja
On Fri, 16 Jul 2021 00:52:21 GMT, Sandhya Viswanathan wrote: >> Jatin Bhateja has updated the pull request with a new target base due to a >> merge or a rebase. The pull request now contains 15 commits: >> >> - 8266054: Incorporating styling changes based on reviews. >> - Merge branch

Re: RFR: 8266054: VectorAPI rotate operation optimization [v10]

2021-07-15 Thread Sandhya Viswanathan
On Thu, 15 Jul 2021 08:34:42 GMT, Jatin Bhateja wrote: >> Current VectorAPI Java side implementation expresses rotateLeft and >> rotateRight operation using following operations:- >> >> vec1 = lanewise(VectorOperators.LSHL, n) >> vec2 = lanewise(VectorOperators.LSHR, n) >> res =

Re: RFR: 8266054: VectorAPI rotate operation optimization [v10]

2021-07-15 Thread Jatin Bhateja
> Current VectorAPI Java side implementation expresses rotateLeft and > rotateRight operation using following operations:- > > vec1 = lanewise(VectorOperators.LSHL, n) > vec2 = lanewise(VectorOperators.LSHR, n) > res = lanewise(VectorOperations.OR, vec1 , vec2) > > This patch moves