On Mon, 13 Sep 2021 12:48:14 GMT, Andrew Haley <[email protected]> wrote:
>> Performance dropped up to 10% for 1k data after 8267125 for CPUs that do not >> support the new intrinsic. Tests run were crypto.full.AESGCMBench and >> crypto.full.AESGCMByteBuffer from the jmh micro benchmarks. >> >> The problem is each instance of GHASH allocates 96 extra longs for the >> AVX512+VAES intrinsic regardless if the intrinsic is used. This extra table >> space should be allocated differently so that non-supporting CPUs do not >> suffer this penalty. This issue also affects non-Intel CPUs too. > > src/hotspot/share/opto/library_call.cpp line 6796: > >> 6794: >> 6795: Node* avx512_subkeyHtbl = new_array(klass_node, intcon(96), 0); >> 6796: if (avx512_subkeyHtbl == NULL) return false; > > This looks very Intel-specific, but it's in generic code. Please make this > constant 96 a symbol and push it into a header file in the x86 back end. Likewise, the name prefix "avx512_" isn't appropriate for code that will certainly be used by other targets. ------------- PR: https://git.openjdk.java.net/jdk/pull/5402
