RFR: 8165404: AArch64: Implement SHA512 accelerator/intrinsic

Yangfei (Felix) felix.yang at huawei.com
Fri Jul 31 01:39:11 UTC 2020


Ping...    Any suggestions?

Thanks,
Felix

> -----Original Message-----
> From: Yangfei (Felix)
> Sent: Saturday, July 25, 2020 10:16 AM
> To: hotspot-runtime-dev at openjdk.java.net
> Cc: aarch64-port-dev at openjdk.java.net
> Subject: RFR: 8165404: AArch64: Implement SHA512 accelerator/intrinsic
> 
> Hi,
> 
>     Bug: https://bugs.openjdk.java.net/browse/JDK-8165404
>     Webrev: http://cr.openjdk.java.net/~fyang/8165404/webrev.00/
> 
>     This implement SHA-384/SHA-512 transformation using aarch64 v8.2
> SHA512 Crypto Extensions.
>     Reference implementation:
> 
> https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/tree/arch/ar
> m64/crypto/sha512-ce-core.S?h=v5.4.52
> 
>     We used QEMU system emulator which supports SHA512 instructions to
> test the functionality.
>     SHA512 basic functionality is tested with:
> http://cr.openjdk.java.net/~fyang/8165404/SHA512.java
>     Patch passed jtreg tier1-3 test with QEMU system emulator.
>     We've also verified it with full jtreg tests without SHA512 instructions on
> aarch64-linux-gnu, to make sure that there's no regression.
> 
>     We've also created a JMH for performance test:
> http://cr.openjdk.java.net/~fyang/8165404/TestSHA512.java
>     We measured the performance benefit with a cycle-accurate simulator.
>     Patch delivers more than 2x performance gain measured with the three
> different size message.
> 
>     Comments?
> 
> Thanks,
> Felix


More information about the hotspot-runtime-dev mailing list