On Tue, 10 Oct 2023 16:44:03 GMT, Srinivas Vamsi Parasa
wrote:
> The goal of this PR is to address the follow-up comments to the SIMD
> accelerated sort PR (#14227) which implemented AVX512 intrinsics for
> Arrays.sort() methods.
> The proposed changes are:
>
> 1) Restriction of the AVX512 so
On Wed, 11 Oct 2023 20:58:23 GMT, Srinivas Vamsi Parasa
wrote:
>> The goal of this PR is to address the follow-up comments to the SIMD
>> accelerated sort PR (#14227) which implemented AVX512 intrinsics for
>> Arrays.sort() methods.
>> The proposed changes are:
>>
>> 1) Restriction of the AVX
On Thu, 12 Oct 2023 04:41:37 GMT, Vladimir Kozlov wrote:
> My tier1-3,xcomp testing for v04 passed. I am integrating these changes. Lets
> continue discussion about changes for AMD in
> https://bugs.openjdk.org/browse/JDK-8317976.
Thank you, Vladimir!
-
PR Comment: https://git.op
On Wed, 11 Oct 2023 20:58:23 GMT, Srinivas Vamsi Parasa
wrote:
>> The goal of this PR is to address the follow-up comments to the SIMD
>> accelerated sort PR (#14227) which implemented AVX512 intrinsics for
>> Arrays.sort() methods.
>> The proposed changes are:
>>
>> 1) Restriction of the AVX
On Wed, 11 Oct 2023 20:58:23 GMT, Srinivas Vamsi Parasa
wrote:
>> The goal of this PR is to address the follow-up comments to the SIMD
>> accelerated sort PR (#14227) which implemented AVX512 intrinsics for
>> Arrays.sort() methods.
>> The proposed changes are:
>>
>> 1) Restriction of the AVX
On Wed, 11 Oct 2023 23:40:55 GMT, Sandhya Viswanathan
wrote:
> > It makes sense to let `-XX:ControlIntrinsic=` overrule
> > `VM_Version::is_intel()` check and enable the intrinsics when `AVX512DQ` is
> > supported.
>
> May be it could be done as part of
> https://bugs.openjdk.org/browse/JDK-
On Wed, 11 Oct 2023 23:38:05 GMT, Sandhya Viswanathan
wrote:
>> Also, for on-heap case the fallback implementation is equivalent to
>> intrinsified case only when offset points at the 0th element of the array.
>
> @iwanowww Yes, you are late to the party :). The fallback implementation
> could
On Wed, 11 Oct 2023 23:14:26 GMT, Vladimir Ivanov wrote:
> Proposed patch has one disadvantage: there's no way to override ergonomics
> decisions on AMD CPUs and forcibly enable the intrinsic without rebuilding
> the JVM.
>
> For many other intrinsics there are flags which enable finer grained
On Wed, 11 Oct 2023 23:25:30 GMT, Vladimir Ivanov wrote:
>> src/java.base/share/classes/java/util/DualPivotQuicksort.java line 157:
>>
>>> 155: @ForceInline
>>> 156: private static void sort(Class elemType, A array, long
>>> offset, int low, int high, SortOperation so) {
>>> 157:
On Wed, 11 Oct 2023 23:25:22 GMT, Vladimir Ivanov wrote:
>> Srinivas Vamsi Parasa has updated the pull request with a new target base
>> due to a merge or a rebase. The pull request now contains 45 commits:
>>
>> - fix code style and formatting
>> - Merge branch 'master' of https://git.openjd
On Thu, 5 Oct 2023 23:36:48 GMT, Srinivas Vamsi Parasa wrote:
>> The goal is to develop faster sort routines for x86_64 CPUs by taking
>> advantage of AVX512 instructions. This enhancement provides an order of
>> magnitude speedup for Arrays.sort() using int, long, float and double arrays.
>>
On Wed, 11 Oct 2023 20:58:23 GMT, Srinivas Vamsi Parasa
wrote:
>> The goal of this PR is to address the follow-up comments to the SIMD
>> accelerated sort PR (#14227) which implemented AVX512 intrinsics for
>> Arrays.sort() methods.
>> The proposed changes are:
>>
>> 1) Restriction of the AVX
On Wed, 11 Oct 2023 22:25:14 GMT, Erik Joelsson wrote:
>> Hi Erik (@erikj79),
>> BUILD_LIBFALLBACKLINKER is from different PR (#13079). If I understand
>> correctly, for LIB_SIMD_SORT, are you suggesting that we don't pad the lines
>> with spaces to align features into columns and instead just
On Wed, 11 Oct 2023 21:04:25 GMT, Srinivas Vamsi Parasa
wrote:
>> make/modules/java.base/Lib.gmk line 230:
>>
>>> 228: CFLAGS := $(CFLAGS_JDKLIB) $(LIBFFI_CFLAGS), \
>>> 229: LDFLAGS := $(LDFLAGS_JDKLIB) \
>>> 230: $(call SET_SHARED_LIBRARY_ORIGIN), \
>>
>> If you
On Wed, 11 Oct 2023 20:58:23 GMT, Srinivas Vamsi Parasa
wrote:
>> The goal of this PR is to address the follow-up comments to the SIMD
>> accelerated sort PR (#14227) which implemented AVX512 intrinsics for
>> Arrays.sort() methods.
>> The proposed changes are:
>>
>> 1) Restriction of the AVX
On Wed, 11 Oct 2023 21:50:10 GMT, Phil Race wrote:
>> Mikael Vidstedt has updated the pull request incrementally with two
>> additional commits since the last revision:
>>
>> - Update stale comment (again)
>> - Update stale comment
>
> Marked as reviewed by prr (Reviewer).
> @prrace I notice
On Wed, 11 Oct 2023 21:10:21 GMT, Mikael Vidstedt wrote:
>> macOS 10.x is no longer receiving updates - the most recent/last release was
>> 10.15.7 back in July of 2022. It's time to bump the target macOS version
>> (min/max) for macosx-x64. macOS 11.x is still receiving updates.
>>
>> This ch
> macOS 10.x is no longer receiving updates - the most recent/last release was
> 10.15.7 back in July of 2022. It's time to bump the target macOS version
> (min/max) for macosx-x64. macOS 11.x is still receiving updates.
>
> This change updates the target version for macosx-x64 to 11.00.00, whic
On Wed, 11 Oct 2023 18:31:44 GMT, Sandhya Viswanathan
wrote:
>> Also @forceinline in these changes only works for case when new intrinsics
>> are not used.
>> I would suggest to adapt/update JMH benchmark to cover all cases and see
>> effect @forceinline without intrinsics.
>> That will tell u
On Wed, 11 Oct 2023 17:49:14 GMT, Mikael Vidstedt wrote:
> macOS 10.x is no longer receiving updates - the most recent/last release was
> 10.15.7 back in July of 2022. It's time to bump the target macOS version
> (min/max) for macosx-x64. macOS 11.x is still receiving updates.
>
> This change
On Wed, 11 Oct 2023 21:05:28 GMT, Mikael Vidstedt wrote:
>> macOS 10.x is no longer receiving updates - the most recent/last release was
>> 10.15.7 back in July of 2022. It's time to bump the target macOS version
>> (min/max) for macosx-x64. macOS 11.x is still receiving updates.
>>
>> This ch
On Wed, 11 Oct 2023 20:48:06 GMT, Erik Joelsson wrote:
>> Srinivas Vamsi Parasa has updated the pull request incrementally with one
>> additional commit since the last revision:
>>
>> Add @ForceInline annotation to insertion and mixedInsertion sort
>
> make/modules/java.base/Lib.gmk line 230:
On Wed, 11 Oct 2023 20:31:05 GMT, Srinivas Vamsi Parasa
wrote:
>> Hi @vamsi-parasa,
>>
>> Both methods mixedInsertionSort and insertionSort are covered by intrinsics.
>> But insertionSort is run on leftmnost (one) part only and on small ( <
>> MAX_INSERTION_SORT_SIZE = 44) arrays.
>> Do we act
> The goal of this PR is to address the follow-up comments to the SIMD
> accelerated sort PR (#14227) which implemented AVX512 intrinsics for
> Arrays.sort() methods.
> The proposed changes are:
>
> 1) Restriction of the AVX512 sort acceleration to only Intel CPUs. A
> performance regression (d
On Wed, 11 Oct 2023 17:28:12 GMT, Srinivas Vamsi Parasa
wrote:
>> The goal of this PR is to address the follow-up comments to the SIMD
>> accelerated sort PR (#14227) which implemented AVX512 intrinsics for
>> Arrays.sort() methods.
>> The proposed changes are:
>>
>> 1) Restriction of the AVX
On Wed, 11 Oct 2023 20:10:12 GMT, iaroslavski wrote:
> > > > > Also @forceinline in these changes only works for case when new
> > > > > intrinsics are not used. I would suggest to adapt/update JMH
> > > > > benchmark to cover all cases and see effect @forceinline without
> > > > > intrinsics.
On Wed, 11 Oct 2023 07:10:57 GMT, iaroslavski wrote:
> To have clear picture could you please run benchmarking to compare both
> cases: current implementation and implementation with Java insertionSort only?
>
> see changes `sort(int.class, a, Unsafe.ARRAY_INT_BASE_OFFSET, low, high,
> DualPiv
On Wed, 11 Oct 2023 17:49:14 GMT, Mikael Vidstedt wrote:
> macOS 10.x is no longer receiving updates - the most recent/last release was
> 10.15.7 back in July of 2022. It's time to bump the target macOS version
> (min/max) for macosx-x64. macOS 11.x is still receiving updates.
>
> This change
On Wed, 11 Oct 2023 19:56:47 GMT, Srinivas Vamsi Parasa
wrote:
> > > > Also @forceinline in these changes only works for case when new
> > > > intrinsics are not used. I would suggest to adapt/update JMH benchmark
> > > > to cover all cases and see effect @forceinline without intrinsics. That
On Wed, 11 Oct 2023 17:28:12 GMT, Srinivas Vamsi Parasa
wrote:
>> The goal of this PR is to address the follow-up comments to the SIMD
>> accelerated sort PR (#14227) which implemented AVX512 intrinsics for
>> Arrays.sort() methods.
>> The proposed changes are:
>>
>> 1) Restriction of the AVX
On Wed, 11 Oct 2023 17:29:11 GMT, Andrew Haley wrote:
>> A bug in GCC causes shared libraries linked with -ffast-math to disable
>> denormal arithmetic. This breaks Java's floating-point semantics.
>>
>> The bug is https://gcc.gnu.org/bugzilla/show_bug.cgi?id=55522
>>
>> One solution is to sav
On Wed, 11 Oct 2023 18:43:31 GMT, Thomas Stuefe wrote:
>> `thresh` is volatile. What more is needed?
>
> Argh, sorry, missed that volatile.
And I was confused at first why there's a volatile on `tresh`. A short comment
describing the intentions would definitely help here.
-
PR Rev
On Wed, 11 Oct 2023 19:06:24 GMT, Vladimir Kozlov wrote:
>> @vnkozlov Please advice if we can integrate this PR or if you would like to
>> run some tests first.
>
> Okay. I will start testing for current changes. @sviswa7 please file RFE for
> Zen 4. If we get patch for it we do followup change
On Wed, 11 Oct 2023 17:22:56 GMT, Srinivas Vamsi Parasa
wrote:
> > Also @forceinline in these changes only works for case when new intrinsics
> > are not used. I would suggest to adapt/update JMH benchmark to cover all
> > cases and see effect @forceinline without intrinsics. That will tell us
On Wed, 11 Oct 2023 18:31:44 GMT, Sandhya Viswanathan
wrote:
>> Also @forceinline in these changes only works for case when new intrinsics
>> are not used.
>> I would suggest to adapt/update JMH benchmark to cover all cases and see
>> effect @forceinline without intrinsics.
>> That will tell u
On Wed, 11 Oct 2023 17:28:12 GMT, Srinivas Vamsi Parasa
wrote:
>> The goal of this PR is to address the follow-up comments to the SIMD
>> accelerated sort PR (#14227) which implemented AVX512 intrinsics for
>> Arrays.sort() methods.
>> The proposed changes are:
>>
>> 1) Restriction of the AVX
On Tue, 10 Oct 2023 18:40:30 GMT, R1chterScale wrote:
>> The goal of this PR is to address the follow-up comments to the SIMD
>> accelerated sort PR (#14227) which implemented AVX512 intrinsics for
>> Arrays.sort() methods.
>> The proposed changes are:
>>
>> 1) Restriction of the AVX512 sort a
On Wed, 11 Oct 2023 17:20:18 GMT, Andrew Haley wrote:
>> src/hotspot/os/bsd/os_bsd.cpp line 976:
>>
>>> 974: // same architecture as Hotspot is running on
>>> 975:
>>> 976: void *os::Bsd::dlopen_helper(const char *filename, int mode) {
>>
>> I thought BSD is switching to clang.
>
> What differ
On Tue, 10 Oct 2023 22:29:55 GMT, Vladimir Kozlov wrote:
>> Srinivas Vamsi Parasa has updated the pull request incrementally with one
>> additional commit since the last revision:
>>
>> fix whitespace in build script
>
> Also @forceinline in these changes only works for case when new intrinsi
On Wed, 11 Oct 2023 09:25:15 GMT, Andrew Haley wrote:
> > Forgive me, I might be missing something very obvious, but is there any
> > particular reason to entirely disable the SIMD accelerated sort on Zen 4
> > rather than having an alternate code path for Zen 4 where it has the
> > `compresss
macOS 10.x is no longer receiving updates - the most recent/last release was
10.15.7 back in July of 2022. It's time to bump the target macOS version
(min/max) for macosx-x64. macOS 11.x is still receiving updates.
This change updates the target version for macosx-x64 to 11.00.00, which is the
> A bug in GCC causes shared libraries linked with -ffast-math to disable
> denormal arithmetic. This breaks Java's floating-point semantics.
>
> The bug is https://gcc.gnu.org/bugzilla/show_bug.cgi?id=55522
>
> One solution is to save and restore the floating-point control word around
> System
On Wed, 11 Oct 2023 06:59:47 GMT, iaroslavski wrote:
> Also @forceinline in these changes only works for case when new intrinsics
> are not used. I would suggest to adapt/update JMH benchmark to cover all
> cases and see effect @forceinline without intrinsics. That will tell us which
> @forcei
On Wed, 11 Oct 2023 13:54:05 GMT, Thomas Stuefe wrote:
> > > I'm seeing one automated test failure on Linux x86, which I don't
> > > understand because I've excluded that test for generic-i586. If anyone
> > > understands this, please shout up.
> >
> >
> > For avoidance of doubt, the test doe
On Wed, 11 Oct 2023 17:28:12 GMT, Srinivas Vamsi Parasa
wrote:
>> The goal of this PR is to address the follow-up comments to the SIMD
>> accelerated sort PR (#14227) which implemented AVX512 intrinsics for
>> Arrays.sort() methods.
>> The proposed changes are:
>>
>> 1) Restriction of the AVX
> The goal of this PR is to address the follow-up comments to the SIMD
> accelerated sort PR (#14227) which implemented AVX512 intrinsics for
> Arrays.sort() methods.
> The proposed changes are:
>
> 1) Restriction of the AVX512 sort acceleration to only Intel CPUs. A
> performance regression (d
On Wed, 11 Oct 2023 14:03:24 GMT, Thomas Stuefe wrote:
>> Andrew Haley has updated the pull request with a new target base due to a
>> merge or a rebase. The pull request now contains 28 commits:
>>
>> - Merge branch 'JDK-8295159' of https://github.com/theRealAph/jdk into
>> JDK-8295159
>> -
On Wed, 11 Oct 2023 13:36:01 GMT, Andrew Haley wrote:
>> A bug in GCC causes shared libraries linked with -ffast-math to disable
>> denormal arithmetic. This breaks Java's floating-point semantics.
>>
>> The bug is https://gcc.gnu.org/bugzilla/show_bug.cgi?id=55522
>>
>> One solution is to sav
On Wed, 11 Oct 2023 13:38:57 GMT, Andrew Haley wrote:
> > I'm seeing one automated test failure on Linux x86, which I don't
> > understand because I've excluded that test for generic-i586. If anyone
> > understands this, please shout up.
>
> For avoidance of doubt, the test doesn't run locally
On Wed, 27 Sep 2023 07:49:48 GMT, Magnus Ihse Bursie wrote:
>> Andrew Haley has updated the pull request with a new target base due to a
>> merge or a rebase. The pull request now contains 28 commits:
>>
>> - Merge branch 'JDK-8295159' of https://github.com/theRealAph/jdk into
>> JDK-8295159
On Wed, 11 Oct 2023 13:31:22 GMT, Andrew Haley wrote:
> I'm seeing one automated test failure on Linux x86, which I don't understand
> because I've excluded that test for generic-i586. If anyone understands this,
> please shout up.
For avoidance of doubt, the test doesn't run locally, only on
On Wed, 11 Oct 2023 13:31:22 GMT, Andrew Haley wrote:
>> A bug in GCC causes shared libraries linked with -ffast-math to disable
>> denormal arithmetic. This breaks Java's floating-point semantics.
>>
>> The bug is https://gcc.gnu.org/bugzilla/show_bug.cgi?id=55522
>>
>> One solution is to sav
On Wed, 12 Oct 2022 17:00:15 GMT, Andrew Haley wrote:
>> A bug in GCC causes shared libraries linked with -ffast-math to disable
>> denormal arithmetic. This breaks Java's floating-point semantics.
>>
>> The bug is https://gcc.gnu.org/bugzilla/show_bug.cgi?id=55522
>>
>> One solution is to sav
> A bug in GCC causes shared libraries linked with -ffast-math to disable
> denormal arithmetic. This breaks Java's floating-point semantics.
>
> The bug is https://gcc.gnu.org/bugzilla/show_bug.cgi?id=55522
>
> One solution is to save and restore the floating-point control word around
> System
On Wed, 12 Oct 2022 15:59:48 GMT, Aleksey Shipilev wrote:
>> Andrew Haley has updated the pull request incrementally with one additional
>> commit since the last revision:
>>
>> 8295159: DSO created with -ffast-math breaks Java floating-point arithmetic
>
> test/hotspot/jtreg/compiler/floatin
On Mon, 9 Oct 2023 10:21:58 GMT, Frederic Thevenet
wrote:
>> When building OpenJDK on Windows using "--with-native-debug-info=external",
>> the resulting debug symbols are saved in files located in the same folder as
>> the corresponding executable or library and named by swapping the extensio
On Wed, 11 Oct 2023 02:18:15 GMT, Julian Waters wrote:
> Once integrated, this is going to spam everyone on GitHub with Windows test
> failures until the issue is fixed separately :/ (Could we perhaps split the
> test out into another change?)
I don't think @fthevenet plans on checking in a br
On Tue, 10 Oct 2023 14:46:32 GMT, Chen Liang wrote:
> We need to remove the outdated exports in `BuildMicroBenchmarks.gmk` after
> the package migration.
Removed, good catch, thanks!
-
PR Comment: https://git.openjdk.org/jdk/pull/15706#issuecomment-1756993662
> Classfile API is an internal library under package `jdk.internal.classfile`
> in JDK 21.
> This pull request turns the Classfile API into a preview feature and moves it
> into `java.lang.classfile`.
> It repackages all uses across JDK and tests and adds lots of missing Javadoc.
>
> This PR goe
59 matches
Mail list logo