Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v15]

2024-03-25 Thread Scott Gibbons
> Re-write the IndexOf code without the use of the pcmpestri instruction, only > using AVX2 instructions. This change accelerates String.IndexOf on average > 1.3x for AVX2. The benchmark numbers: > > > BenchmarkScore > Latest

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v14]

2024-03-23 Thread Francesco Nigro
On Sat, 23 Mar 2024 02:16:57 GMT, Scott Gibbons wrote: >> Re-write the IndexOf code without the use of the pcmpestri instruction, only >> using AVX2 instructions. This change accelerates String.IndexOf on average >> 1.3x for AVX2. The benchmark numbers: >> >> >> Benchmark

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v14]

2024-03-23 Thread Scott Gibbons
On Sat, 23 Mar 2024 09:57:49 GMT, Francesco Nigro wrote: >> Scott Gibbons has updated the pull request with a new target base due to a >> merge or a rebase. The pull request now contains 46 commits: >> >> - Merge branch 'openjdk:master' into indexof >> - Cleaned up, ready for review >> - Pre

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v14]

2024-03-23 Thread Francesco Nigro
On Sat, 23 Mar 2024 02:16:57 GMT, Scott Gibbons wrote: >> Re-write the IndexOf code without the use of the pcmpestri instruction, only >> using AVX2 instructions. This change accelerates String.IndexOf on average >> 1.3x for AVX2. The benchmark numbers: >> >> >> Benchmark

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v14]

2024-03-22 Thread Scott Gibbons
> Re-write the IndexOf code without the use of the pcmpestri instruction, only > using AVX2 instructions. This change accelerates String.IndexOf on average > 1.3x for AVX2. The benchmark numbers: > > > BenchmarkScore > Latest

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v13]

2024-03-22 Thread Scott Gibbons
On Thu, 22 Feb 2024 03:15:10 GMT, Scott Gibbons wrote: >> Re-write the IndexOf code without the use of the pcmpestri instruction, only >> using AVX2 instructions. This change accelerates String.IndexOf on average >> 1.3x for AVX2. The benchmark numbers: >> >> >> Benchmark

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v8]

2024-02-26 Thread Jatin Bhateja
On Wed, 21 Feb 2024 15:51:21 GMT, Scott Gibbons wrote: >> Hi @asgibbons , >> >> I am getting following error with slowdebug build on Meteor Lake system. >> >> >> ERROR: Build failed for target 'images' in configuration >> 'linux-x86_64-server-slowdebug' (exit code 2) >> >> === Output from f

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v13]

2024-02-26 Thread Jatin Bhateja
On Thu, 22 Feb 2024 03:15:10 GMT, Scott Gibbons wrote: >> Re-write the IndexOf code without the use of the pcmpestri instruction, only >> using AVX2 instructions. This change accelerates String.IndexOf on average >> 1.3x for AVX2. The benchmark numbers: >> >> >> Benchmark

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v13]

2024-02-21 Thread Scott Gibbons
> Re-write the IndexOf code without the use of the pcmpestri instruction, only > using AVX2 instructions. This change accelerates String.IndexOf on average > 1.3x for AVX2. The benchmark numbers: > > > BenchmarkScore > Latest

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v12]

2024-02-21 Thread Scott Gibbons
> Re-write the IndexOf code without the use of the pcmpestri instruction, only > using AVX2 instructions. This change accelerates String.IndexOf on average > 1.3x for AVX2. The benchmark numbers: > > > BenchmarkScore > Latest

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v8]

2024-02-21 Thread Scott Gibbons
On Tue, 20 Feb 2024 09:49:23 GMT, Jatin Bhateja wrote: >> Thank you all for the reviews. I have been asked to simplify this code to >> facilitate easier review, and to remove the gcc library code I used for >> memcmp. We also discovered that special-casing up to 31 bytes of needle was >> not

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v8]

2024-02-20 Thread Jatin Bhateja
On Wed, 14 Feb 2024 14:31:03 GMT, Scott Gibbons wrote: >> Scott Gibbons has updated the pull request incrementally with one additional >> commit since the last revision: >> >> Remove gcc lib fn; reduce spacial cases to 10 from 32 > > Thank you all for the reviews. I have been asked to simpli

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v11]

2024-02-14 Thread Scott Gibbons
> Re-write the IndexOf code without the use of the pcmpestri instruction, only > using AVX2 instructions. This change accelerates String.IndexOf on average > 1.3x for AVX2. The benchmark numbers: > > > BenchmarkScore > Latest

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v10]

2024-02-14 Thread Scott Gibbons
> Re-write the IndexOf code without the use of the pcmpestri instruction, only > using AVX2 instructions. This change accelerates String.IndexOf on average > 1.3x for AVX2. The benchmark numbers: > > > BenchmarkScore > Latest

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v9]

2024-02-14 Thread Scott Gibbons
> Re-write the IndexOf code without the use of the pcmpestri instruction, only > using AVX2 instructions. This change accelerates String.IndexOf on average > 1.3x for AVX2. The benchmark numbers: > > > BenchmarkScore > Latest

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v8]

2024-02-14 Thread Scott Gibbons
On Wed, 14 Feb 2024 00:48:18 GMT, Scott Gibbons wrote: >> Re-write the IndexOf code without the use of the pcmpestri instruction, only >> using AVX2 instructions. This change accelerates String.IndexOf on average >> 1.3x for AVX2. The benchmark numbers: >> >> >> Benchmark

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v8]

2024-02-13 Thread Scott Gibbons
> Re-write the IndexOf code without the use of the pcmpestri instruction, only > using AVX2 instructions. This change accelerates String.IndexOf on average > 1.3x for AVX2. The benchmark numbers: > > > BenchmarkScore > Latest

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v7]

2024-01-21 Thread Jatin Bhateja
On Mon, 22 Jan 2024 07:05:56 GMT, Jatin Bhateja wrote: >> Scott Gibbons has updated the pull request with a new target base due to a >> merge or a rebase. The pull request now contains 22 commits: >> >> - Merge branch 'openjdk:master' into indexof >> - Merge branch 'openjdk:master' into index

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v7]

2024-01-21 Thread Jatin Bhateja
On Thu, 11 Jan 2024 23:06:32 GMT, Scott Gibbons wrote: >> Re-write the IndexOf code without the use of the pcmpestri instruction, only >> using AVX2 instructions. This change accelerates String.IndexOf on average >> 1.3x for AVX2. The benchmark numbers: >> >> >> Benchmark

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v7]

2024-01-16 Thread Vladimir Kozlov
On Tue, 16 Jan 2024 23:51:15 GMT, Scott Gibbons wrote: >> src/hotspot/cpu/x86/stubGenerator_x86_64.cpp line 4111: >> >>> 4109: if ((UseAVX == 2) && EnableX86ECoreOpts && >>> VM_Version::supports_avx2()) { >>> 4110: StubRoutines::_string_indexof = generate_string_indexof(); >>> 4111: } >

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v7]

2024-01-16 Thread Scott Gibbons
On Tue, 16 Jan 2024 22:27:52 GMT, Vladimir Kozlov wrote: >> Scott Gibbons has updated the pull request with a new target base due to a >> merge or a rebase. The pull request now contains 22 commits: >> >> - Merge branch 'openjdk:master' into indexof >> - Merge branch 'openjdk:master' into ind

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v7]

2024-01-16 Thread Vladimir Kozlov
On Thu, 11 Jan 2024 23:06:32 GMT, Scott Gibbons wrote: >> Re-write the IndexOf code without the use of the pcmpestri instruction, only >> using AVX2 instructions. This change accelerates String.IndexOf on average >> 1.3x for AVX2. The benchmark numbers: >> >> >> Benchmark

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v7]

2024-01-16 Thread Jatin Bhateja
On Thu, 11 Jan 2024 23:06:32 GMT, Scott Gibbons wrote: >> Re-write the IndexOf code without the use of the pcmpestri instruction, only >> using AVX2 instructions. This change accelerates String.IndexOf on average >> 1.3x for AVX2. The benchmark numbers: >> >> >> Benchmark

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v7]

2024-01-16 Thread Jatin Bhateja
On Thu, 11 Jan 2024 23:06:32 GMT, Scott Gibbons wrote: >> Re-write the IndexOf code without the use of the pcmpestri instruction, only >> using AVX2 instructions. This change accelerates String.IndexOf on average >> 1.3x for AVX2. The benchmark numbers: >> >> >> Benchmark

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v7]

2024-01-16 Thread Jatin Bhateja
On Thu, 11 Jan 2024 23:06:32 GMT, Scott Gibbons wrote: >> Re-write the IndexOf code without the use of the pcmpestri instruction, only >> using AVX2 instructions. This change accelerates String.IndexOf on average >> 1.3x for AVX2. The benchmark numbers: >> >> >> Benchmark

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v7]

2024-01-16 Thread Jatin Bhateja
On Thu, 11 Jan 2024 23:06:32 GMT, Scott Gibbons wrote: >> Re-write the IndexOf code without the use of the pcmpestri instruction, only >> using AVX2 instructions. This change accelerates String.IndexOf on average >> 1.3x for AVX2. The benchmark numbers: >> >> >> Benchmark

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v7]

2024-01-16 Thread Jatin Bhateja
On Thu, 11 Jan 2024 23:06:32 GMT, Scott Gibbons wrote: >> Re-write the IndexOf code without the use of the pcmpestri instruction, only >> using AVX2 instructions. This change accelerates String.IndexOf on average >> 1.3x for AVX2. The benchmark numbers: >> >> >> Benchmark

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v7]

2024-01-16 Thread Jatin Bhateja
On Thu, 11 Jan 2024 23:06:32 GMT, Scott Gibbons wrote: >> Re-write the IndexOf code without the use of the pcmpestri instruction, only >> using AVX2 instructions. This change accelerates String.IndexOf on average >> 1.3x for AVX2. The benchmark numbers: >> >> >> Benchmark

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v7]

2024-01-15 Thread Jatin Bhateja
On Thu, 11 Jan 2024 23:06:32 GMT, Scott Gibbons wrote: >> Re-write the IndexOf code without the use of the pcmpestri instruction, only >> using AVX2 instructions. This change accelerates String.IndexOf on average >> 1.3x for AVX2. The benchmark numbers: >> >> >> Benchmark

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v7]

2024-01-15 Thread Andrey Turbanov
On Thu, 11 Jan 2024 23:06:32 GMT, Scott Gibbons wrote: >> Re-write the IndexOf code without the use of the pcmpestri instruction, only >> using AVX2 instructions. This change accelerates String.IndexOf on average >> 1.3x for AVX2. The benchmark numbers: >> >> >> Benchmark

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v7]

2024-01-11 Thread Scott Gibbons
> Re-write the IndexOf code without the use of the pcmpestri instruction, only > using AVX2 instructions. This change accelerates String.IndexOf on average > 1.3x for AVX2. The benchmark numbers: > > > BenchmarkScore > Latest

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v5]

2024-01-09 Thread Jatin Bhateja
On Thu, 21 Dec 2023 15:21:08 GMT, Scott Gibbons wrote: >> Re-write the IndexOf code without the use of the pcmpestri instruction, only >> using AVX2 instructions. This change accelerates String.IndexOf on average >> 1.3x for AVX2. The benchmark numbers: >> >> >> Benchmark

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v6]

2024-01-09 Thread Emanuel Peter
On Mon, 8 Jan 2024 20:48:39 GMT, Scott Gibbons wrote: >> Re-write the IndexOf code without the use of the pcmpestri instruction, only >> using AVX2 instructions. This change accelerates String.IndexOf on average >> 1.3x for AVX2. The benchmark numbers: >> >> >> Benchmark

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v6]

2024-01-08 Thread Scott Gibbons
> Re-write the IndexOf code without the use of the pcmpestri instruction, only > using AVX2 instructions. This change accelerates String.IndexOf on average > 1.3x for AVX2. The benchmark numbers: > > > BenchmarkScore > Latest

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v5]

2023-12-21 Thread Scott Gibbons
> Re-write the IndexOf code without the use of the pcmpestri instruction, only > using AVX2 instructions. This change accelerates String.IndexOf on average > 1.3x for AVX2. The benchmark numbers: > > > BenchmarkScore > Latest

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v2]

2023-12-20 Thread Sandhya Viswanathan
On Wed, 29 Nov 2023 15:01:32 GMT, Scott Gibbons wrote: >> Re-write the IndexOf code without the use of the pcmpestri instruction, only >> using AVX2 instructions. This change accelerates String.IndexOf on average >> 1.3x for AVX2. The benchmark numbers: >> >> >> Benchmark

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v4]

2023-12-20 Thread Sandhya Viswanathan
On Tue, 19 Dec 2023 18:42:19 GMT, Scott Gibbons wrote: >> Re-write the IndexOf code without the use of the pcmpestri instruction, only >> using AVX2 instructions. This change accelerates String.IndexOf on average >> 1.3x for AVX2. The benchmark numbers: >> >> >> Benchmark

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v4]

2023-12-19 Thread Scott Gibbons
> Re-write the IndexOf code without the use of the pcmpestri instruction, only > using AVX2 instructions. This change accelerates String.IndexOf on average > 1.3x for AVX2. The benchmark numbers: > > > BenchmarkScore > Latest

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v3]

2023-12-06 Thread Scott Gibbons
> Re-write the IndexOf code without the use of the pcmpestri instruction, only > using AVX2 instructions. This change accelerates String.IndexOf on average > 1.3x for AVX2. The benchmark numbers: > > > BenchmarkScore > Latest

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v2]

2023-11-29 Thread Scott Gibbons
On Wed, 29 Nov 2023 15:01:32 GMT, Scott Gibbons wrote: >> Re-write the IndexOf code without the use of the pcmpestri instruction, only >> using AVX2 instructions. This change accelerates String.IndexOf on average >> 1.3x for AVX2. The benchmark numbers: >> >> >> Benchmark

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2 [v2]

2023-11-29 Thread Scott Gibbons
> Re-write the IndexOf code without the use of the pcmpestri instruction, only > using AVX2 instructions. This change accelerates String.IndexOf on average > 1.3x for AVX2. The benchmark numbers: > > > BenchmarkScore > Latest

Re: RFR: JDK-8320448 Accelerate IndexOf using AVX2

2023-11-28 Thread Scott Gibbons
On Tue, 21 Nov 2023 00:06:19 GMT, Scott Gibbons wrote: > Re-write the IndexOf code without the use of the pcmpestri instruction, only > using AVX2 instructions. This change accelerates String.IndexOf on average > 1.3x for AVX2. The benchmark numbers: > > > Benchmark