Implementation notes: amd64, genji346, crypto_sign/dilithium2

Computer: genji346
Architecture: amd64
CPU ID: AuthenticAMD-00830f10-178bfbff
SUPERCOP version: 20191017
Operation: crypto_sign
Primitive: dilithium2

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
616540	226363 0 0	253707 832 1632	`avx2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
689300	236419 0 0	267060 880 1600	`avx2`	`icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer`	20191025	20191017
689820	236435 0 0	267076 880 1600	`avx2`	`icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer`	20191025	20191017
689860	236435 0 0	267076 880 1600	`avx2`	`icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer`	20191025	20191017
690380	236419 0 0	267060 880 1600	`avx2`	`icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer`	20191025	20191017
707540	244787 0 0	273748 880 1600	`avx2`	`icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer`	20191025	20191017
723640	250491 0 0	280732 880 1600	`avx2`	`icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer`	20191025	20191017
727120	249931 0 0	280172 880 1600	`avx2`	`icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer`	20191025	20191017
732600	250491 0 0	280732 880 1600	`avx2`	`icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer`	20191025	20191017
746100	259115 0 0	288132 880 1600	`avx2`	`icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer`	20191025	20191017
775220	129556 0 0	154867 832 1632	`avx2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
802180	127512 0 0	152539 832 1632	`avx2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
814600	246659 0 0	276916 880 1600	`avx2`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer`	20191025	20191017
814920	246659 0 0	276916 880 1600	`avx2`	`icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer`	20191025	20191017
815040	246659 0 0	276916 880 1600	`avx2`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer`	20191025	20191017
816460	246659 0 0	276916 880 1600	`avx2`	`icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer`	20191025	20191017
821160	249931 0 0	280172 880 1600	`avx2`	`icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer`	20191025	20191017
844940	261067 0 0	291356 880 1600	`avx2`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer`	20191025	20191017
845580	261067 0 0	291356 880 1600	`avx2`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer`	20191025	20191017
847200	261067 0 0	291356 880 1600	`avx2`	`icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer`	20191025	20191017
868080	261067 0 0	291356 880 1600	`avx2`	`icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer`	20191025	20191017
924280	125200 0 0	149619 824 1600	`avx2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
1974380	34223 0 0	61441 824 1600	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191025	20191017
2020080	44565 0 0	72179 832 1632	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
2169020	19069 0 0	44619 832 1632	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
2190580	69976 0 0	100884 880 1600	`ref`	`icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer`	20191025	20191017
2190760	69976 0 0	100884 880 1600	`ref`	`icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer`	20191025	20191017
2196440	36043 0 0	62961 824 1600	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191025	20191017
2328820	17990 0 0	43227 832 1632	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
2380980	26981 0 0	53585 824 1600	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191025	20191017
2385440	69960 0 0	100868 880 1600	`ref`	`icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer`	20191025	20191017
2399020	26981 0 0	53585 824 1600	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191025	20191017
2405860	66768 0 0	95996 880 1600	`ref`	`icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer`	20191025	20191017
2415680	69960 0 0	100868 880 1600	`ref`	`icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer`	20191025	20191017
2447920	73976 0 0	104484 880 1600	`ref`	`icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer`	20191025	20191017
2453240	73976 0 0	104484 880 1600	`ref`	`icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer`	20191025	20191017
2453520	74088 0 0	104596 880 1600	`ref`	`icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer`	20191025	20191017
2457280	74088 0 0	104596 880 1600	`ref`	`icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer`	20191025	20191017
2468580	18223 0 0	42319 816 1600	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191025	20191017
2473160	70888 0 0	100172 880 1600	`ref`	`icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer`	20191025	20191017
2620820	16886 0 0	41147 824 1600	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
2706760	68680 0 0	99204 880 1600	`ref`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer`	20191025	20191017
2707940	68680 0 0	99204 880 1600	`ref`	`icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer`	20191025	20191017
2709860	68680 0 0	99204 880 1600	`ref`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer`	20191025	20191017
2715220	68680 0 0	99204 880 1600	`ref`	`icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer`	20191025	20191017
2890260	72792 0 0	103348 880 1600	`ref`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer`	20191025	20191017
2890740	72792 0 0	103348 880 1600	`ref`	`icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer`	20191025	20191017
2916580	72792 0 0	103348 880 1600	`ref`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer`	20191025	20191017
2942160	72792 0 0	103348 880 1600	`ref`	`icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer`	20191025	20191017

Test failure

Implementation: avx2
Security model: unknown
Compiler: icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 12, namely:

Compiler	Implementations
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer	avx2
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer	avx2
icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer	avx2
icc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer	avx2
icc -march=skylake-avx512 -mtune=skylake-avx512 -O2 -fomit-frame-pointer	avx2
icc -march=skylake-avx512 -mtune=skylake-avx512 -O3 -fomit-frame-pointer	avx2
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer	ref
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer	ref
icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer	ref
icc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer	ref
icc -march=skylake-avx512 -mtune=skylake-avx512 -O2 -fomit-frame-pointer	ref
icc -march=skylake-avx512 -mtune=skylake-avx512 -O3 -fomit-frame-pointer	ref

Compiler output

Implementation: avx2
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

KeccakP-1600-times4-SIMD256.c: In file included from KeccakP-1600-times4-SIMD256.c:19:
KeccakP-1600-times4-SIMD256.c: In file included from /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/smmintrin.h:32:
KeccakP-1600-times4-SIMD256.c: In file included from /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/tmmintrin.h:31:
KeccakP-1600-times4-SIMD256.c: In file included from /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/pmmintrin.h:31:
KeccakP-1600-times4-SIMD256.c: In file included from /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/emmintrin.h:31:
KeccakP-1600-times4-SIMD256.c: In file included from /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/xmmintrin.h:31:
KeccakP-1600-times4-SIMD256.c: /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/mmintrin.h:55:72: warning: unknown attribute '__artificial__' ignored [-Wunknown-attributes]
KeccakP-1600-times4-SIMD256.c: extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/mmintrin.h:61:72: warning: unknown attribute '__artificial__' ignored [-Wunknown-attributes]
KeccakP-1600-times4-SIMD256.c: extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/mmintrin.h:68:74: warning: unknown attribute '__artificial__' ignored [-Wunknown-attributes]
KeccakP-1600-times4-SIMD256.c: extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/mmintrin.h:74:74: warning: unknown attribute '__artificial__' ignored [-Wunknown-attributes]
KeccakP-1600-times4-SIMD256.c: extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/mmintrin.h:84:74: warning: unknown attribute '__artificial__' ignored [-Wunknown-attributes]
KeccakP-1600-times4-SIMD256.c: extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/mmintrin.h:90:74: warning: unknown attribute '__artificial__' ignored [-Wunknown-attributes]
KeccakP-1600-times4-SIMD256.c: extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/mmintrin.h:97:74: warning: unknown attribute '__artificial__' ignored [-Wunknown-attributes]
KeccakP-1600-times4-SIMD256.c: ...

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2