RFR: 8300208: Optimize Adler32 stub for AVX-512 targets.

2023-01-17 Thread Jatin Bhateja
Patch optimizes Adler32 stub for AVX512 target. Main computation loop now uses zero extended lane widening load vector operation. New sequence also honors AVX3Thresholds so that implementation uses existing AVX2 instruction sequence on relevant targets if input size is smaller than threshold li

Re: RFR: 8300208: Optimize Adler32 stub for AVX-512 targets.

2023-01-17 Thread Vladimir Kozlov
On Tue, 17 Jan 2023 17:24:20 GMT, Jatin Bhateja wrote: > Patch optimizes Adler32 stub for AVX512 target. > > Main computation loop now uses zero extended lane widening load vector > operation. > > New sequence also honors AVX3Thresholds so that implementation uses existing > AVX2 instruction

Re: RFR: 8300208: Optimize Adler32 stub for AVX-512 targets.

2023-01-18 Thread Vladimir Kozlov
On Tue, 17 Jan 2023 17:24:20 GMT, Jatin Bhateja wrote: > Patch optimizes Adler32 stub for AVX512 target. > > Main computation loop now uses zero extended lane widening load vector > operation. > > New sequence also honors AVX3Thresholds so that implementation uses existing > AVX2 instruction

Re: RFR: 8300208: Optimize Adler32 stub for AVX-512 targets.

2023-01-21 Thread Andrey Turbanov
On Tue, 17 Jan 2023 17:24:20 GMT, Jatin Bhateja wrote: > Patch optimizes Adler32 stub for AVX512 target. > > Main computation loop now uses zero extended lane widening load vector > operation. > > New sequence also honors AVX3Thresholds so that implementation uses existing > AVX2 instruction