Re: com.sun.crypto.provider.GHASH performance fix

2015-01-30 Thread Anthony Scarpino
On 01/20/2015 01:33 AM, Florian Weimer wrote: On 01/15/2015 05:24 PM, Anthony Scarpino wrote: Anthony, could you file a bug so that I can include its number? Thanks. Here it is: https://bugs.openjdk.java.net/browse/JDK-8069072 Thanks. Updated webrev:

Re: com.sun.crypto.provider.GHASH performance fix

2015-01-20 Thread Florian Weimer
On 01/16/2015 09:18 AM, Anthony Scarpino wrote: >> On Jan 15, 2015, at 12:26 PM, Florian Weimer wrote: >> >> Yes, they are going to help quite a bit as well. The other thing we need to >> fix for TLS is that AES-GCM is a garbage collector stress test. Last time I >> looked, for each transferre

Re: com.sun.crypto.provider.GHASH performance fix

2015-01-20 Thread Florian Weimer
On 01/15/2015 05:24 PM, Anthony Scarpino wrote: >> Anthony, could you file a bug so that I can include its number? Thanks. >> > > Here it is: https://bugs.openjdk.java.net/browse/JDK-8069072 Thanks. Updated webrev: -- Florian Weimer

Re: com.sun.crypto.provider.GHASH performance fix

2015-01-16 Thread Tim Whittington
On 16/01/2015, at 9:18 pm, Anthony Scarpino wrote: >> On Jan 15, 2015, at 12:26 PM, Florian Weimer wrote: >> >> Yes, they are going to help quite a bit as well. The other thing we need to >> fix for TLS is that AES-GCM is a garbage collector stress test. Last time I >> looked, for each tra

Re: com.sun.crypto.provider.GHASH performance fix

2015-01-16 Thread Anthony Scarpino
> On Jan 15, 2015, at 12:26 PM, Florian Weimer wrote: > > Yes, they are going to help quite a bit as well. The other thing we need to > fix for TLS is that AES-GCM is a garbage collector stress test. Last time I > looked, for each transferred byte, there were four bytes allocated on the > he

Re: com.sun.crypto.provider.GHASH performance fix

2015-01-15 Thread Florian Weimer
On 01/15/2015 08:31 PM, Michael StJohns wrote: Just for curiosity, what was the improvement in performance? Tim Whittington posted independent benchmark numbers here: He could reproduce the 10x improvement quoted

Re: com.sun.crypto.provider.GHASH performance fix

2015-01-15 Thread Anthony Scarpino
Florian had posted months back about it giving 10x improvement. Hardware acceleration is an separate project as it is mostly changes to hotspot. Tony > On Jan 15, 2015, at 11:31 AM, Michael StJohns wrote: > > Just for curiosity, what was the improvement in performance? > > I'm wondering if

Re: com.sun.crypto.provider.GHASH performance fix

2015-01-15 Thread Michael StJohns
Just for curiosity, what was the improvement in performance? I'm wondering if it might be worthwhile to see if its possible to add a plugin to use the hardware instructions: http://www.intel.com/content/dam/www/public/us/en/documents/white-papers/communications-ia-galois-counter-mode-paper.pdf

Re: com.sun.crypto.provider.GHASH performance fix

2015-01-15 Thread Anthony Scarpino
On 01/15/2015 03:10 AM, Florian Weimer wrote: On 08/18/2014 02:32 PM, Florian Weimer wrote: This change addresses a severe performance regression, first introduced in JDK 8, triggered by the negotiation of a GCM cipher suite in the TLS implementation. This regression is a result of the poor per

Re: com.sun.crypto.provider.GHASH performance fix

2015-01-15 Thread Florian Weimer
On 08/18/2014 02:32 PM, Florian Weimer wrote: This change addresses a severe performance regression, first introduced in JDK 8, triggered by the negotiation of a GCM cipher suite in the TLS implementation. This regression is a result of the poor performance of the implementation of the GHASH fun

Re: com.sun.crypto.provider.GHASH performance fix

2014-11-28 Thread Tim Whittington
Hi Florian On 19/08/2014, at 12:32 am, Florian Weimer wrote: > This change addresses a severe performance regression, first introduced in > JDK 8, triggered by the negotiation of a GCM cipher suite in the TLS > implementation. This regression is a result of the poor performance of the > impl

Re: com.sun.crypto.provider.GHASH performance fix

2014-11-24 Thread Florian Weimer
On 11/20/2014 11:37 PM, Tim Whittington wrote: It looks like your GHASH implementation as posted isn’t passing the tests in TestGHASH.java. The existing JDK implementation does, and the Bouncy Castle GHASH produces the same results. I can't reproduce this. I ported the patch to current JDK

Re: com.sun.crypto.provider.GHASH performance fix

2014-11-20 Thread Tim Whittington
On 19/08/2014, at 12:32 am, Florian Weimer wrote: > This change addresses a severe performance regression, first introduced in > JDK 8, triggered by the negotiation of a GCM cipher suite in the TLS > implementation. This regression is a result of the poor performance of the > implementation

Re: com.sun.crypto.provider.GHASH performance fix

2014-08-19 Thread Florian Weimer
On 08/18/2014 11:59 PM, Anthony Scarpino wrote: Interesting changes. It's going to take me some time to look over this as I have a different projects involving GHASH that would cause a conflict with the code change layout you have posted. What kind of changes do you plan? Using intrinsics for

Re: com.sun.crypto.provider.GHASH performance fix

2014-08-18 Thread Anthony Scarpino
On 08/18/2014 05:32 AM, Florian Weimer wrote: This change addresses a severe performance regression, first introduced in JDK 8, triggered by the negotiation of a GCM cipher suite in the TLS implementation. This regression is a result of the poor performance of the implementation of the GHASH fun