Implementation notes: amd64, hydra7, crypto_sign/dilithium3aes

Computer: hydra7
Microarchitecture: amd64; Sandy Bridge+AES (206a7)
Architecture: amd64
CPU ID: GenuineIntel-000206a7-bfebfbff
SUPERCOP version: 20231107
Operation: crypto_sign
Primitive: dilithium3aes

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
3684426	46403 0 0	65805 812 1792	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230609	20230530
3891553	26195 0 0	44549 812 1792	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230609	20230530
4262909	24805 0 0	42773 812 1792	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230609	20230530
5879973	23214 0 0	40061 804 1760	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230609	20230530

Compiler output

Implementation: avx2
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

poly.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
poly.c: from poly.c:2:
poly.c: poly.c: In function 'crypto_sign_dilithium3aes_avx2_constbranchindex_poly_reduce':
poly.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:815:1: error: inlining failed in call to 'always_inline' '_mm256_sub_epi32': target specific option mismatch
poly.c: 815 | _mm256_sub_epi32 (__m256i __A, __m256i __B)
poly.c: | ^~~~~~~~~~~~~~~~
poly.c: poly.c:53:9: note: called from here
poly.c: 53 | f = _mm256_sub_epi32(f,g);
poly.c: | ^~~~~~~~~~~~~~~~~~~~~
poly.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
poly.c: from poly.c:2:
poly.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:560:1: error: inlining failed in call to 'always_inline' '_mm256_mullo_epi32': target specific option mismatch
poly.c: 560 | _mm256_mullo_epi32 (__m256i __A, __m256i __B)
poly.c: | ^~~~~~~~~~~~~~~~~~
poly.c: poly.c:52:9: note: called from here
poly.c: 52 | g = _mm256_mullo_epi32(g,q);
poly.c: | ^~~~~~~~~~~~~~~~~~~~~~~
poly.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
poly.c: from poly.c:2:
poly.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:724:1: error: inlining failed in call to 'always_inline' '_mm256_srai_epi32': target specific option mismatch
poly.c: 724 | _mm256_srai_epi32 (__m256i __A, int __B)
poly.c: | ^~~~~~~~~~~~~~~~~
poly.c: poly.c:51:9: note: called from here
poly.c: 51 | g = _mm256_srai_epi32(g,23);
poly.c: | ^~~~~~~~~~~~~~~~~~~~~~~
poly.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx2