Implementation notes: amd64, genji346, crypto_sign/dilithium3

Computer: genji346
Architecture: amd64
CPU ID: AuthenticAMD-00830f10-178bfbff
SUPERCOP version: 20191017
Operation: crypto_sign
Primitive: dilithium3

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
607440	225890 0 0	253227 832 1632	`avx2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
661080	236982 0 0	267628 880 1600	`avx2`	`icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer`	20191025	20191017
662160	236966 0 0	267612 880 1600	`avx2`	`icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer`	20191025	20191017
662920	236982 0 0	267628 880 1600	`avx2`	`icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer`	20191025	20191017
662940	236966 0 0	267612 880 1600	`avx2`	`icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer`	20191025	20191017
682960	245366 0 0	274332 880 1600	`avx2`	`icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer`	20191025	20191017
696340	250478 0 0	280724 880 1600	`avx2`	`icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer`	20191025	20191017
698140	251038 0 0	281284 880 1600	`avx2`	`icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer`	20191025	20191017
700820	251038 0 0	281284 880 1600	`avx2`	`icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer`	20191025	20191017
712620	259694 0 0	288716 880 1600	`avx2`	`icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer`	20191025	20191017
771180	129778 0 0	155091 832 1632	`avx2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
780720	247254 0 0	277516 880 1600	`avx2`	`icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer`	20191025	20191017
780820	247254 0 0	277516 880 1600	`avx2`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer`	20191025	20191017
780900	247254 0 0	277516 880 1600	`avx2`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer`	20191025	20191017
781800	247254 0 0	277516 880 1600	`avx2`	`icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer`	20191025	20191017
801760	250478 0 0	280724 880 1600	`avx2`	`icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer`	20191025	20191017
812000	127946 0 0	152971 832 1632	`avx2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
812840	261662 0 0	291956 880 1600	`avx2`	`icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer`	20191025	20191017
812880	261662 0 0	291956 880 1600	`avx2`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer`	20191025	20191017
813300	261662 0 0	291956 880 1600	`avx2`	`icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer`	20191025	20191017
844640	125480 0 0	149907 824 1600	`avx2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
844680	261662 0 0	291956 880 1600	`avx2`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer`	20191025	20191017
1919160	35363 0 0	62593 824 1600	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191025	20191017
2077400	18959 0 0	44507 832 1632	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
2105200	44388 0 0	72003 832 1632	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
2191460	73872 0 0	104380 880 1600	`ref`	`icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer`	20191025	20191017
2203660	73872 0 0	104380 880 1600	`ref`	`icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer`	20191025	20191017
2234560	73984 0 0	104492 880 1600	`ref`	`icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer`	20191025	20191017
2239940	73984 0 0	104492 880 1600	`ref`	`icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer`	20191025	20191017
2257080	69888 0 0	100796 880 1600	`ref`	`icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer`	20191025	20191017
2258440	69888 0 0	100796 880 1600	`ref`	`icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer`	20191025	20191017
2259340	70800 0 0	100084 880 1600	`ref`	`icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer`	20191025	20191017
2326120	69872 0 0	100780 880 1600	`ref`	`icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer`	20191025	20191017
2342240	69872 0 0	100780 880 1600	`ref`	`icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer`	20191025	20191017
2360880	37165 0 0	64097 824 1600	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191025	20191017
2423920	66696 0 0	95924 880 1600	`ref`	`icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer`	20191025	20191017
2480440	28093 0 0	54705 824 1600	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191025	20191017
2483720	28093 0 0	54705 824 1600	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191025	20191017
2487420	16874 0 0	41139 824 1600	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
2498800	18242 0 0	42335 816 1600	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191025	20191017
2514760	18077 0 0	43307 832 1632	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
2749440	68608 0 0	99132 880 1600	`ref`	`icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer`	20191025	20191017
2762960	68608 0 0	99132 880 1600	`ref`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer`	20191025	20191017
2768240	68608 0 0	99132 880 1600	`ref`	`icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer`	20191025	20191017
2768660	68608 0 0	99132 880 1600	`ref`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer`	20191025	20191017
2888440	72720 0 0	103276 880 1600	`ref`	`icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer`	20191025	20191017
2892120	72720 0 0	103276 880 1600	`ref`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer`	20191025	20191017
2892860	72720 0 0	103276 880 1600	`ref`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer`	20191025	20191017
2901900	72720 0 0	103276 880 1600	`ref`	`icc_-march=sandybridge_-mtune=sandybridge_-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