RFR(S) 8205398: AES-CBC decryption algorithm using AVX512 instructions

[Kamath, Smita]

Hi Vladimir,

I ran all tests for AES-CBC in TestAESMain.java using SDE. The new code produced correct results.

Regards,
Smita



-----Original Message-----
From: Vladimir Kozlov [mailto:vladimir.kozlov at oracle.com] 
Sent: Wednesday, June 20, 2018 2:51 PM
To: Kamath, Smita <smita.kamath at intel.com>
Cc: Rukmannagari, Shravya <shravya.rukmannagari at intel.com>; hotspot compiler <hotspot-compiler-dev at openjdk.java.net>
Subject: Re: RFR(S) 8205398: AES-CBC decryption algorithm using AVX512 instructions

Hi, Smita

Changes looks fine to me.

Can you run set of tests defined in
test/hotspot/jtreg/compiler/codegen/aes/TestAESMain.java on Intel SDE to make sure new code produce correct result?

Thanks,
Vladimir

On 6/20/18 1:50 PM, Kamath, Smita wrote:
> Hi Vladimir,
> 
> As per "Intel Architecture Instruction Set Extensions and Future 
> Features Programming Reference"  manual [1], vector aes decrypt 
> (vaesdec and vaesdeclast) instructions will be supported in future 
> Intel ISA. I have updated AES-CBC decryption algorithm to take 
> advantage of these instructions. Shravya(cc'ed) and I are 
> co-contributors. Shay Gueron and Regev Shemy (regev.shemy at intel.com 
> <mailto:regev.shemy at intel.com>) are the authors of the algorithm.
> 
> I have tested  the algorithm with Intel SDE [2] to confirm encoding 
> and semantics are correctly implemented.
> 
> Please take a look and let me know if you have any questions or comments.
> 
> http://cr.openjdk.java.net/~vdeshpande/AES_CBC_AVX512/webrev.00/
> 
> [1]
> https://software.intel.com/sites/default/files/managed/c5/15/architect
> ure-instruction-set-extensions-programming-reference.pdf
> 
> [2]
> https://software.intel.com/en-us/articles/intel-software-development-e
> mulator
> 
> 
> [3] https://bugs.openjdk.java.net/browse/JDK-8205398
> 
> Thanks,
> 
> Smita
>