On Tue, 19 May 2026 21:55:02 GMT, Volodymyr Paprotski <[email protected]> wrote:
>> This PR: >> - changes existing AVX512 SHA3 intrinsic to be more parallel >> - adds an AVX2 SHA3 intrinsic >> - change `SHA3Parallel.java` to NR=4 (to be able to exploit the AVX512 >> parallelism while keeping doubleKeccak for platforms where double >> parallelism is preferable. I experimented with NR=8 as well, does also gain >> a few percent, but I think NR=4 is sufficient tradeoff) >> >> Performance gains: >> - `MessageDigestBench.digest`: >> - AVX2: **16%-39%** >> - AVX512: **24%-33%** >> - `SignatureBench.MLDSA.sign` >> - AVX2: **6-12%** >> - AVX512: **11%-18%** >> - `SignatureBench.MLDSA.verify` >> - AVX2: **2%-14%** >> - AVX512: **31%-40%** >> - `KEMBench.MLKEM` >> - AVX2: **~5%** >> - AVX512: **14%-23%** >> - `KEMBench.JSSE_*` >> - appears unaffected >> >> Note on intrinsics. (As noted in the code..) there are multiple entrypoints >> wrapping the same intrinsic.. >> - `SHA3.implCompress`: single blockSize of user data xored with keccak >> - `DigestBase.implCompressMultiBlock`: loop over user data and xor with >> keccak >> - `SHA3Parallel.doubleKeccak`: (still used for AVX2) no message data, just >> two state vectors >> - `SHA3Parallel.quadKeccak`: (AVX512 benefit) no message data, four state >> vectors >> >> Note 1: `make test >> TEST="micro:org.openjdk.bench.javax.crypto.full.MessageDigestBench >> micro:org.openjdk.bench.javax.crypto.full.SignatureBench.MLDSA >> micro:org.openjdk.bench.javax.crypto.full.KEMBench"` >> Note 2: I have left more targeted fuzzing and benchmarks out of this PR, but >> they are preserved at [on my >> branch](https://github.com/vpaprotsk/jdk/compare/sha3-avx-quad...vpaprotsk:jdk:sha3-avx-quad-extras?expand=1). >> If there is something you rather see pulled in.. (otherwise, can include a >> diff in JBS for 'future reference') >> >> --------- >> - [X] I confirm that I make this contribution in accordance with the >> [OpenJDK Interim AI Policy](https://openjdk.org/legal/ai). > > Volodymyr Paprotski has updated the pull request incrementally with one > additional commit since the last revision: > > second round of review from Sandhya Drive-by comments. src/hotspot/cpu/x86/stubGenerator_x86_64_sha3.cpp line 273: > 271: __ movq(T1, Address(state4, 24 * 8)); > 272: __ vshufpd(T0, T0, T1, 0b00, Assembler::AVX_128bit); > 273: __ evinserti64x2(A24, A24, T0, 0b01, Assembler::AVX_256bit); Should this also be replaced with `vinserti128`? This is still AVX-512? src/hotspot/cpu/x86/stubGenerator_x86_64_sha3.cpp line 580: > 578: // Zero out zmm0-zmm31. > 579: __ vzeroall(); > 580: for (XMMRegister rxmm = xmm16; vector_len == Assembler::AVX_512bit && > rxmm->is_valid(); rxmm = rxmm->successor()) { The loop predicate checks for `vector_len == AVX_512bit`, but is it ever set to that value? I see only sets to `128` and `256`. So this loop looks effectively dead? src/hotspot/share/opto/library_call.cpp line 8377: > 8375: } > 8376: > 8377: if (!stubAddr) return false; For this -- what I assume is a release-build safety return -- to work, `stubAddress` should be initialized to `nullptr`? ------------- PR Review: https://git.openjdk.org/jdk/pull/31125#pullrequestreview-4326638534 PR Review Comment: https://git.openjdk.org/jdk/pull/31125#discussion_r3272436408 PR Review Comment: https://git.openjdk.org/jdk/pull/31125#discussion_r3272474735 PR Review Comment: https://git.openjdk.org/jdk/pull/31125#discussion_r3272415154
