Implementation notes: amd64, genji262, crypto_sign/dilithium3aes

Computer: genji262
Architecture: amd64
CPU ID: AuthenticAMD-00800f12-178bfbff
SUPERCOP version: 20191017
Operation: crypto_sign
Primitive: dilithium3aes

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
724988	228736 0 0	84163 816 1632	`avx2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
793452	234398 0 0	111308 864 1600	`avx2`	`icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer`	20191024	20191017
794288	234398 0 0	111308 864 1600	`avx2`	`icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer`	20191024	20191017
794772	234382 0 0	111292 864 1600	`avx2`	`icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer`	20191024	20191017
796026	234382 0 0	111292 864 1600	`avx2`	`icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer`	20191024	20191017
799326	242646 0 0	108284 864 1600	`avx2`	`icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer`	20191024	20191017
809776	247910 0 0	114916 864 1600	`avx2`	`icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer`	20191024	20191017
811140	248470 0 0	115028 864 1600	`avx2`	`icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer`	20191024	20191017
811140	256990 0 0	112348 864 1600	`avx2`	`icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer`	20191024	20191017
815694	247910 0 0	114916 864 1600	`avx2`	`icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer`	20191024	20191017
819962	248470 0 0	115028 864 1600	`avx2`	`icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer`	20191024	20191017
844800	129889 0 0	53971 816 1632	`avx2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
851092	127734 0 0	52707 816 1632	`avx2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
864512	124379 0 0	49867 808 1600	`avx2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
920040	244510 0 0	110356 864 1600	`avx2`	`icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer`	20191024	20191017
921272	244510 0 0	110356 864 1600	`avx2`	`icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer`	20191024	20191017
924264	244510 0 0	110356 864 1600	`avx2`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer`	20191024	20191017
925232	244510 0 0	110356 864 1600	`avx2`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer`	20191024	20191017
929632	258918 0 0	114364 864 1600	`avx2`	`icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer`	20191024	20191017
930732	258918 0 0	114364 864 1600	`avx2`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer`	20191024	20191017
931876	258918 0 0	114364 864 1600	`avx2`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer`	20191024	20191017
941248	258918 0 0	114364 864 1600	`avx2`	`icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer`	20191024	20191017
3778874	41519 0 0	68665 808 1600	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191024	20191017
4050398	46429 0 0	73281 808 1600	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191024	20191017
4083750	83520 0 0	114364 864 1600	`ref`	`icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer`	20191024	20191017
4083794	52689 0 0	79611 816 1632	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
4088612	83520 0 0	114364 864 1600	`ref`	`icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer`	20191024	20191017
4159430	37485 0 0	63985 808 1600	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191024	20191017
4163368	81024 0 0	110172 864 1600	`ref`	`icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer`	20191024	20191017
4172718	37485 0 0	63985 808 1600	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191024	20191017
4221690	83504 0 0	114348 864 1600	`ref`	`icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer`	20191024	20191017
4222570	83504 0 0	114348 864 1600	`ref`	`icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer`	20191024	20191017
4230556	83256 0 0	112476 864 1600	`ref`	`icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer`	20191024	20191017
4308634	24315 0 0	49955 816 1632	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
4335496	86408 0 0	116852 864 1600	`ref`	`icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer`	20191024	20191017
4341986	86296 0 0	116740 864 1600	`ref`	`icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer`	20191024	20191017
4342228	86408 0 0	116852 864 1600	`ref`	`icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer`	20191024	20191017
4343834	86296 0 0	116740 864 1600	`ref`	`icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer`	20191024	20191017
4439952	23096 0 0	47151 800 1600	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191024	20191017
4642198	85424 0 0	115916 864 1600	`ref`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer`	20191024	20191017
4643254	83232 0 0	113676 864 1600	`ref`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer`	20191024	20191017
4649128	83232 0 0	113676 864 1600	`ref`	`icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer`	20191024	20191017
4649326	85424 0 0	115916 864 1600	`ref`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer`	20191024	20191017
4651328	83232 0 0	113676 864 1600	`ref`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer`	20191024	20191017
4651746	85424 0 0	115916 864 1600	`ref`	`icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer`	20191024	20191017
4654892	85424 0 0	115916 864 1600	`ref`	`icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer`	20191024	20191017
4656476	83232 0 0	113676 864 1600	`ref`	`icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer`	20191024	20191017
4694316	23232 0 0	48579 816 1632	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
5036592	21160 0 0	45459 808 1600	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	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