RFR: JDK-8314901: AES-GCM interleaved implementation using AVX2 instructions [v4]

Daniel Jeliński djelinski at openjdk.org
Tue Oct 10 06:42:59 UTC 2023


On Mon, 9 Oct 2023 04:58:10 GMT, Smita Kamath <svkamath at openjdk.org> wrote:

>> Hi All, 
>> I would like to submit AES-GCM optimization for x86_64 architectures using AVX2 instructions. This optimization interleaves AES and GHASH operations.
>> 
>> Below are the performance numbers on my desktop system with -XX:UseAVX=2 option:
>> 
>> |Benchmark | Data Size | Base version (ops/s) | Patched version (ops/s) | Speedup
>> |-------------|------------|---------------|------------------|-----------|
>> |full.AESGCMBench.decrypt | 8192 | 526274.678 | 670014.543 | 1.27
>> full.AESGCMBench.encrypt | 8192 | 538293.315 | 680716.207 | 1.26
>> small.AESGCMBench.decrypt | 8192 |  527854.353 |663131.48 | 1.25
>> small.AESGCMBench.encrypt | 8192 |  548193.804 | 683624.232 |1.24
>> full.AESGCMBench.decryptMultiPart | 8192 |  299865.766 | 299815.851 | 0.99
>> full.AESGCMBench.encryptMultiPart | 8192 |  534406.564 |539235.462 | 1.00
>> small.AESGCMBench.decryptMultiPart | 8192 |  299960.202 |298913.629 | 0.99
>> small.AESGCMBench.encryptMultiPart | 8192 | 542669.258 | 540552.293 | 0.99
>>   |   |   |   |  
>> full.AESGCMBench.decrypt | 16384 |  307266.364 |390397.778 | 1.27
>> full.AESGCMBench.encrypt | 16384 | 311491.901 | 397279.681 | 1.27
>> small.AESGCMBench.decrypt | 16384 |  306257.801 | 389531.665 |1.27
>> small.AESGCMBench.encrypt | 16384 |  311468.972 | 397804.753 | 1.27
>> full.AESGCMBench.decryptMultiPart | 16384 |  159634.341 | 181271.487 | 1.13
>> full.AESGCMBench.encryptMultiPart | 16384 | 308980.992 | 385606.113 | 1.24
>> small.AESGCMBench.decryptMultiPart | 16384 | 160476.064 |181019.205 |  1.12
>> small.AESGCMBench.encryptMultiPart | 16384 | 308382.656 | 391126.417 | 1.26
>>   |   |   |   |  
>> full.AESGCMBench.decrypt | 32768 |  162284.703 | 213257.481 |1.31
>> full.AESGCMBench.encrypt | 32768 |  164833.104 | 215568.639 | 1.30
>> small.AESGCMBench.decrypt | 32768 |  164416.491 | 213422.347 | 1.29
>> small.AESGCMBench.encrypt | 32768 |  166619.205 | 214584.208 |1.28
>> full.AESGCMBench.decryptMultiPart | 32768 |  83306.239 | 93762.988 |1.12
>> full.AESGCMBench.encryptMultiPart | 32768 | 166109.391 |211701.969 |  1.27
>> small.AESGCMBench.decryptMultiPart | 32768 | 83792.559 | 94530.786 | 1.12
>> small.AESGCMBench.encryptMultiPart | 32768 |  162975.904 |212085.047 | 1.30
>>   |   |   |   |  
>> full.AESGCMBench.decrypt | 65536 | 85765.835 | 112244.611 | 1.30
>> full.AESGCMBench.encrypt | 65536 |  86471.805 | 113320.536 |1.31
>> small.AESGCMBench.decrypt | 65536 |  84490.816 | 112122.358 |1.32
>> small.AESGCMBench.encrypt | 65536 | 85403.025 | 112741.811 |  1.32
>> full.AES...
>
> Smita Kamath has updated the pull request incrementally with one additional commit since the last revision:
> 
>   Updated code as per review comments, added new comments for every method

src/hotspot/cpu/x86/assembler_x86.cpp line 1335:

> 1333: 
> 1334: void Assembler::addb(Register dst, int imm8) {
> 1335:   prefix(dst);

This will miscompile code for rsi/rdi/rsp/rbp; the operation will use ah/bh/ch/dh instead of sil/dil/spl/bpl. I believe you need `prefix_and_encode(dst->encoding(), true);`. See: https://github.com/openjdk/jdk/blob/7e1cf54df79bc8010c40acd4f84c11dcba0d3dac/src/hotspot/cpu/x86/assembler_x86.cpp#L6257-L6258

-------------

PR Review Comment: https://git.openjdk.org/jdk/pull/15410#discussion_r1350528886


More information about the security-dev mailing list