Implementation notes: amd64, genji346, crypto_sign/dilithium3aes

Computer: genji346
Architecture: amd64
CPU ID: AuthenticAMD-00830f10-178bfbff
SUPERCOP version: 20191017
Operation: crypto_sign
Primitive: dilithium3aes

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
479420	225984 0 0	84291 832 1632	`avx2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
557160	234382 0 0	111396 880 1600	`avx2`	`icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer`	20191025	20191017
557220	234398 0 0	111412 880 1600	`avx2`	`icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer`	20191025	20191017
557360	234382 0 0	111396 880 1600	`avx2`	`icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer`	20191025	20191017
559160	234398 0 0	111412 880 1600	`avx2`	`icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer`	20191025	20191017
573440	248470 0 0	115132 880 1600	`avx2`	`icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer`	20191025	20191017
573960	247910 0 0	115020 880 1600	`avx2`	`icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer`	20191025	20191017
574720	247910 0 0	115020 880 1600	`avx2`	`icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer`	20191025	20191017
598960	129474 0 0	53947 832 1632	`avx2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
604340	242646 0 0	108388 880 1600	`avx2`	`icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer`	20191025	20191017
617280	256990 0 0	112452 880 1600	`avx2`	`icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer`	20191025	20191017
632460	124378 0 0	49971 824 1600	`avx2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
644980	127279 0 0	52651 832 1632	`avx2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
676660	248470 0 0	115132 880 1600	`avx2`	`icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer`	20191025	20191017
701040	244510 0 0	110460 880 1600	`avx2`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer`	20191025	20191017
701740	244510 0 0	110460 880 1600	`avx2`	`icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer`	20191025	20191017
701860	244510 0 0	110460 880 1600	`avx2`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer`	20191025	20191017
713460	258918 0 0	114468 880 1600	`avx2`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer`	20191025	20191017
713760	258918 0 0	114468 880 1600	`avx2`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer`	20191025	20191017
713980	258918 0 0	114468 880 1600	`avx2`	`icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer`	20191025	20191017
714260	258918 0 0	114468 880 1600	`avx2`	`icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer`	20191025	20191017
723460	244510 0 0	110460 880 1600	`avx2`	`icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer`	20191025	20191017
3694880	41519 0 0	68769 824 1600	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191025	20191017
3747760	46429 0 0	73385 824 1600	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191025	20191017
3763260	53527 0 0	81115 832 1632	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
3799900	83520 0 0	114468 880 1600	`ref`	`icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer`	20191025	20191017
3820700	83520 0 0	114468 880 1600	`ref`	`icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer`	20191025	20191017
3890880	37485 0 0	64089 824 1600	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191025	20191017
3893880	37485 0 0	64089 824 1600	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191025	20191017
3907340	24250 0 0	49899 832 1632	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
3917160	81024 0 0	110276 880 1600	`ref`	`icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer`	20191025	20191017
3938700	83504 0 0	114452 880 1600	`ref`	`icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer`	20191025	20191017
3939540	83504 0 0	114452 880 1600	`ref`	`icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer`	20191025	20191017
4081280	86296 0 0	116844 880 1600	`ref`	`icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer`	20191025	20191017
4081940	86408 0 0	116956 880 1600	`ref`	`icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer`	20191025	20191017
4103540	83256 0 0	112580 880 1600	`ref`	`icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer`	20191025	20191017
4105340	86296 0 0	116844 880 1600	`ref`	`icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer`	20191025	20191017
4153180	86408 0 0	116956 880 1600	`ref`	`icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer`	20191025	20191017
4252380	23096 0 0	47255 816 1600	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191025	20191017
4270020	23228 0 0	48571 832 1632	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
4390300	83232 0 0	113780 880 1600	`ref`	`icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer`	20191025	20191017
4402840	83232 0 0	113780 880 1600	`ref`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer`	20191025	20191017
4413420	83232 0 0	113780 880 1600	`ref`	`icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer`	20191025	20191017
4429380	83232 0 0	113780 880 1600	`ref`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer`	20191025	20191017
4429940	85424 0 0	116020 880 1600	`ref`	`icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer`	20191025	20191017
4439200	21160 0 0	45563 824 1600	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191025	20191017
4454360	85424 0 0	116020 880 1600	`ref`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer`	20191025	20191017
4455420	85424 0 0	116020 880 1600	`ref`	`icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer`	20191025	20191017
4456960	85424 0 0	116020 880 1600	`ref`	`icc_-march=corei7-avx_-mtune=corei7-avx_-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