On Thu, 8 Dec 2022 18:24:03 GMT, Andrew Haley wrote:
>> Anthony Scarpino has updated the pull request incrementally with three
>> additional commits since the last revision:
>>
>> - editor screwed up
>> - why won't this merge hell stop 2
>> - why won't this merge hell stop 3
>
> What benchma
On Tue, 6 Dec 2022 20:29:56 GMT, Anthony Scarpino wrote:
>> I would like a review of an update to the GCM code. A recent report showed
>> that GCM memory usage for TLS was very large. This was a result of in-place
>> buffers, which TLS uses, and how the code handled the combined intrinsic
>>
> I would like a review of an update to the GCM code. A recent report showed
> that GCM memory usage for TLS was very large. This was a result of in-place
> buffers, which TLS uses, and how the code handled the combined intrinsic
> method during decryption. A temporary buffer was used because
> I would like a review of an update to the GCM code. A recent report showed
> that GCM memory usage for TLS was very large. This was a result of in-place
> buffers, which TLS uses, and how the code handled the combined intrinsic
> method during decryption. A temporary buffer was used because
> I would like a review of an update to the GCM code. A recent report showed
> that GCM memory usage for TLS was very large. This was a result of in-place
> buffers, which TLS uses, and how the code handled the combined intrinsic
> method during decryption. A temporary buffer was used because
> I would like a review of an update to the GCM code. A recent report showed
> that GCM memory usage for TLS was very large. This was a result of in-place
> buffers, which TLS uses, and how the code handled the combined intrinsic
> method during decryption. A temporary buffer was used because
On Thu, 1 Dec 2022 04:19:37 GMT, Anthony Scarpino wrote:
>> I would like a review of an update to the GCM code. A recent report showed
>> that GCM memory usage for TLS was very large. This was a result of in-place
>> buffers, which TLS uses, and how the code handled the combined intrinsic
>>
On Thu, 1 Dec 2022 04:10:32 GMT, Anthony Scarpino wrote:
>> src/java.base/share/classes/com/sun/crypto/provider/GaloisCounterMode.java
>> line 778:
>>
>>> 776: gctr, ghash);
>>> 777: } else {
>>> 778: int ofs = src.arrayOff
On Thu, 1 Dec 2022 04:19:37 GMT, Anthony Scarpino wrote:
>> I would like a review of an update to the GCM code. A recent report showed
>> that GCM memory usage for TLS was very large. This was a result of in-place
>> buffers, which TLS uses, and how the code handled the combined intrinsic
>>
> I would like a review of an update to the GCM code. A recent report showed
> that GCM memory usage for TLS was very large. This was a result of in-place
> buffers, which TLS uses, and how the code handled the combined intrinsic
> method during decryption. A temporary buffer was used because
On Thu, 1 Dec 2022 02:10:01 GMT, Valerie Peng wrote:
>> Anthony Scarpino has updated the pull request incrementally with one
>> additional commit since the last revision:
>>
>> comment cleanup & finesse ByteBuffer implGCMCrypt better
>
> src/java.base/share/classes/com/sun/crypto/provider/Gal
On Mon, 21 Nov 2022 18:20:09 GMT, Anthony Scarpino
wrote:
>> I would like a review of an update to the GCM code. A recent report showed
>> that GCM memory usage for TLS was very large. This was a result of in-place
>> buffers, which TLS uses, and how the code handled the combined intrinsic
On Mon, 21 Nov 2022 18:20:09 GMT, Anthony Scarpino
wrote:
>> I would like a review of an update to the GCM code. A recent report showed
>> that GCM memory usage for TLS was very large. This was a result of in-place
>> buffers, which TLS uses, and how the code handled the combined intrinsic
On Wed, 16 Nov 2022 16:55:39 GMT, Mark Powers wrote:
>> Anthony Scarpino has updated the pull request incrementally with one
>> additional commit since the last revision:
>>
>> comment cleanup & finesse ByteBuffer implGCMCrypt better
>
> src/java.base/share/classes/com/sun/crypto/provider/Gal
On Fri, 18 Nov 2022 05:19:31 GMT, Anthony Scarpino
wrote:
>> src/java.base/share/classes/com/sun/crypto/provider/GaloisCounterMode.java
>> line 694:
>>
>>> 692: int originalOutOfs = 0;
>>> 693:
>>> 694: // True if op is in-place array decryption with the input &
>>> output
>>
On Wed, 16 Nov 2022 17:01:50 GMT, Mark Powers wrote:
>> Anthony Scarpino has updated the pull request incrementally with one
>> additional commit since the last revision:
>>
>> comment cleanup & finesse ByteBuffer implGCMCrypt better
>
> src/java.base/share/classes/com/sun/crypto/provider/Gal
On Sun, 13 Nov 2022 02:54:10 GMT, Anthony Scarpino
wrote:
> I would like a review of an update to the GCM code. A recent report showed
> that GCM memory usage for TLS was very large. This was a result of in-place
> buffers, which TLS uses, and how the code handled the combined intrinsic
> m
> I would like a review of an update to the GCM code. A recent report showed
> that GCM memory usage for TLS was very large. This was a result of in-place
> buffers, which TLS uses, and how the code handled the combined intrinsic
> method during decryption. A temporary buffer was used because
On Wed, 16 Nov 2022 16:57:14 GMT, Mark Powers wrote:
>> I would like a review of an update to the GCM code. A recent report showed
>> that GCM memory usage for TLS was very large. This was a result of in-place
>> buffers, which TLS uses, and how the code handled the combined intrinsic
>> met
On Wed, 16 Nov 2022 17:38:19 GMT, Mark Powers wrote:
>> I would like a review of an update to the GCM code. A recent report showed
>> that GCM memory usage for TLS was very large. This was a result of in-place
>> buffers, which TLS uses, and how the code handled the combined intrinsic
>> met
On Thu, 17 Nov 2022 18:24:07 GMT, Anthony Scarpino
wrote:
> Looking at this, it's not related to the same in-place issues. This is a
> result of the combined intrinsics requirement . Maybe some better tuning can
> be done, but I think this is unavoidable. I can consider this in a future PR
Th
On Wed, 16 Nov 2022 18:48:58 GMT, Anthony Scarpino
wrote:
> Thanks for looking into this, @ascarpino!
>
> In testing this using a local build, it improves performance in cases using
> heap buffers (a super-set of the socket case), however servers which use
> direct byte-buffers still exhibit
On Sun, 13 Nov 2022 02:54:10 GMT, Anthony Scarpino
wrote:
> I would like a review of an update to the GCM code. A recent report showed
> that GCM memory usage for TLS was very large. This was a result of in-place
> buffers, which TLS uses, and how the code handled the combined intrinsic
> m
On Wed, 16 Nov 2022 17:00:37 GMT, Mark Powers wrote:
>> I would like a review of an update to the GCM code. A recent report showed
>> that GCM memory usage for TLS was very large. This was a result of in-place
>> buffers, which TLS uses, and how the code handled the combined intrinsic
>> met
On Wed, 16 Nov 2022 18:19:30 GMT, Anthony Scarpino
wrote:
>> It's possibly worth noting that while this is merely fixing a regression for
>> x86, it's very likely a decent sized performance improvement on arm64, where
>> intrinsics for AES-GCM (depending on JVM vendor) aren't added until after
On Wed, 16 Nov 2022 16:18:15 GMT, James Baker wrote:
> It's possibly worth noting that while this is merely fixing a regression for
> x86, it's very likely a decent sized performance improvement on arm64, where
> intrinsics for AES-GCM (depending on JVM vendor) aren't added until after
> Java
On Sun, 13 Nov 2022 02:54:10 GMT, Anthony Scarpino
wrote:
> I would like a review of an update to the GCM code. A recent report showed
> that GCM memory usage for TLS was very large. This was a result of in-place
> buffers, which TLS uses, and how the code handled the combined intrinsic
> m
On Sun, 13 Nov 2022 02:54:10 GMT, Anthony Scarpino
wrote:
> I would like a review of an update to the GCM code. A recent report showed
> that GCM memory usage for TLS was very large. This was a result of in-place
> buffers, which TLS uses, and how the code handled the combined intrinsic
> m
On Sun, 13 Nov 2022 02:54:10 GMT, Anthony Scarpino
wrote:
> I would like a review of an update to the GCM code. A recent report showed
> that GCM memory usage for TLS was very large. This was a result of in-place
> buffers, which TLS uses, and how the code handled the combined intrinsic
> m
On Sun, 13 Nov 2022 02:54:10 GMT, Anthony Scarpino
wrote:
> I would like a review of an update to the GCM code. A recent report showed
> that GCM memory usage for TLS was very large. This was a result of in-place
> buffers, which TLS uses, and how the code handled the combined intrinsic
> m
I would like a review of an update to the GCM code. A recent report showed
that GCM memory usage for TLS was very large. This was a result of in-place
buffers, which TLS uses, and how the code handled the combined intrinsic method
during decryption. A temporary buffer was used because the com
31 matches
Mail list logo
