Implementation notes: amd64, genji262, crypto_kem/ntskem1380

Computer: genji262
Architecture: amd64
CPU ID: AuthenticAMD-00800f12-178bfbff
SUPERCOP version: 20191017
Operation: crypto_kem
Primitive: ntskem1380

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
1313972	98808 84 16	123149 960 1640	`avx2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
1346092	81943 84 16	104677 960 1640	`avx2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
1389762	83734 84 16	106597 960 1640	`avx2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
1412114	90050 84 16	114421 960 1640	`sse2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
1444586	73935 84 16	96693 960 1640	`sse2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
1501588	75718 84 16	98621 960 1640	`sse2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
1536810	184648 108 16	214221 1032 1608	`opt`	`icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer`	20191024	20191017
1552738	184648 108 16	214221 1032 1608	`opt`	`icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer`	20191024	20191017
1571746	184648 108 16	214221 1032 1608	`opt`	`icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer`	20191024	20191017
1582724	108268 84 16	134371 928 1576	`opt`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191024	20191017
1590402	87905 84 16	113363 928 1576	`opt`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191024	20191017
1611170	87905 84 16	113363 928 1576	`opt`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191024	20191017
1621026	144032 108 16	173653 1032 1608	`opt`	`icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer`	20191024	20191017
1632840	144032 108 16	173653 1032 1608	`opt`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer`	20191024	20191017
1641750	147080 108 16	175477 1032 1608	`opt`	`icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer`	20191024	20191017
1653960	155560 108 16	185533 1032 1608	`opt`	`icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer`	20191024	20191017
1661418	155544 108 16	185517 1032 1608	`opt`	`icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer`	20191024	20191017
1675740	144032 108 16	173653 1032 1608	`opt`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer`	20191024	20191017
1676950	155560 108 16	185533 1032 1608	`opt`	`icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer`	20191024	20191017
1681944	144032 108 16	173653 1032 1608	`opt`	`icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer`	20191024	20191017
1683132	144640 108 16	172981 1032 1608	`opt`	`icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer`	20191024	20191017
1689754	146144 108 16	175797 1032 1608	`opt`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer`	20191024	20191017
1695144	146144 108 16	175797 1032 1608	`opt`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer`	20191024	20191017
1698092	155544 108 16	185517 1032 1608	`opt`	`icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer`	20191024	20191017
1701326	184648 108 16	214221 1032 1608	`opt`	`icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer`	20191024	20191017
1705440	146144 108 16	175797 1032 1608	`opt`	`icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer`	20191024	20191017
1710258	146144 108 16	175797 1032 1608	`opt`	`icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer`	20191024	20191017
1725372	66255 84 16	89649 920 1576	`opt`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191024	20191017
1728540	131745 84 16	158091 928 1576	`opt`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191024	20191017
1802438	89610 84 16	115645 960 1640	`opt`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
1827738	69462 84 16	94093 960 1640	`opt`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
1840872	76520 84 16	98476 952 1608	`avx2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
1971882	69971 84 16	91948 952 1608	`sse2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
1982728	67799 84 16	92117 960 1640	`opt`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
2427062	63303 84 16	86708 952 1608	`opt`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
12868328	36689 76 16	63531 928 1576	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191024	20191017
12953468	33555 76 16	59723 928 1576	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191024	20191017
12987106	33555 76 16	59723 928 1576	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191024	20191017
13219822	89336 100 16	117669 1000 1608	`ref`	`icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer`	20191024	20191017
13314092	37254 76 16	63867 928 1576	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191024	20191017
13410804	87768 100 16	117381 1000 1608	`ref`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer`	20191024	20191017
13433420	87768 100 16	117381 1000 1608	`ref`	`icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer`	20191024	20191017
13443936	87768 100 16	117381 1000 1608	`ref`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer`	20191024	20191017
13464528	103152 100 16	133117 1000 1608	`ref`	`icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer`	20191024	20191017
13465408	91704 100 16	120093 1000 1608	`ref`	`icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer`	20191024	20191017
13475110	103152 100 16	133117 1000 1608	`ref`	`icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer`	20191024	20191017
13485406	87768 100 16	117381 1000 1608	`ref`	`icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer`	20191024	20191017
13497880	103168 100 16	133133 1000 1608	`ref`	`icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer`	20191024	20191017
13534972	103168 100 16	133133 1000 1608	`ref`	`icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer`	20191024	20191017
13547270	130184 100 16	159749 1000 1608	`ref`	`icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer`	20191024	20191017
13553540	130184 100 16	159749 1000 1608	`ref`	`icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer`	20191024	20191017
13564298	130184 100 16	159749 1000 1608	`ref`	`icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer`	20191024	20191017
13607726	90488 100 16	120133 1000 1608	`ref`	`icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer`	20191024	20191017
13609882	90488 100 16	120133 1000 1608	`ref`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer`	20191024	20191017
13614194	90488 100 16	120133 1000 1608	`ref`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer`	20191024	20191017
13619980	90488 100 16	120133 1000 1608	`ref`	`icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer`	20191024	20191017
13779018	25061 76 16	49693 928 1640	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
13824646	130184 100 16	159749 1000 1608	`ref`	`icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer`	20191024	20191017
13875840	35466 76 16	61541 928 1640	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
14043920	23189 76 16	47477 928 1640	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
14550316	21678 76 16	45065 920 1576	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191024	20191017
17021730	20046 76 16	43428 920 1608	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017

Test failure

Implementation: opt
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	opt
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer	opt
icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer	opt
icc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer	opt
icc -march=skylake-avx512 -mtune=skylake-avx512 -O2 -fomit-frame-pointer	opt
icc -march=skylake-avx512 -mtune=skylake-avx512 -O3 -fomit-frame-pointer	opt
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

bitslice_bma_128.c: In file included from bitslice_bma_128.c:17:
bitslice_bma_128.c: In file included from ./bitslice_bma_128.h:18:
bitslice_bma_128.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/immintrin.h:27:
bitslice_bma_128.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]
bitslice_bma_128.c: extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
bitslice_bma_128.c: ^
bitslice_bma_128.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]
bitslice_bma_128.c: extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
bitslice_bma_128.c: ^
bitslice_bma_128.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]
bitslice_bma_128.c: extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
bitslice_bma_128.c: ^
bitslice_bma_128.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]
bitslice_bma_128.c: extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
bitslice_bma_128.c: ^
bitslice_bma_128.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]
bitslice_bma_128.c: extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
bitslice_bma_128.c: ^
bitslice_bma_128.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]
bitslice_bma_128.c: extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
bitslice_bma_128.c: ^
bitslice_bma_128.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]
bitslice_bma_128.c: extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
bitslice_bma_128.c: ^
bitslice_bma_128.c: /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/mmintrin.h:103:74: warning: unknown attribute '__artificial__' ignored [-Wunknown-attributes]
bitslice_bma_128.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

Compiler output

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

nts_kem.c: nts_kem.c(717): error: expression must have integral type
nts_kem.c: v[i] = ~v[i];
nts_kem.c: ^
nts_kem.c:
nts_kem.c: compilation aborted for nts_kem.c (code 2)

Number of similar (compiler,implementation) pairs: 38, namely:

Compiler	Implementations
icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer	avx2
icc -march=broadwell -mtune=broadwell -O3 -fomit-frame-pointer	avx2
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer	avx2
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer	avx2
icc -march=core-avx2 -mtune=core-avx2 -O2 -fomit-frame-pointer	avx2
icc -march=core-avx2 -mtune=core-avx2 -O3 -fomit-frame-pointer	avx2
icc -march=haswell -mtune=haswell -O2 -fomit-frame-pointer	avx2
icc -march=haswell -mtune=haswell -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=skylake -mtune=skylake -O2 -fomit-frame-pointer	avx2
icc -march=skylake -mtune=skylake -O3 -fomit-frame-pointer	avx2
icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer	sse2
icc -march=broadwell -mtune=broadwell -O3 -fomit-frame-pointer	sse2
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer	sse2
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer	sse2
icc -march=core-avx-i -mtune=core-avx-i -O2 -fomit-frame-pointer	sse2
icc -march=core-avx-i -mtune=core-avx-i -O3 -fomit-frame-pointer	sse2
icc -march=core-avx2 -mtune=core-avx2 -O2 -fomit-frame-pointer	sse2
icc -march=core-avx2 -mtune=core-avx2 -O3 -fomit-frame-pointer	sse2
icc -march=corei7-avx -mtune=corei7-avx -O2 -fomit-frame-pointer	sse2
icc -march=corei7-avx -mtune=corei7-avx -O3 -fomit-frame-pointer	sse2
icc -march=corei7 -mtune=corei7 -O2 -fomit-frame-pointer	sse2
icc -march=corei7 -mtune=corei7 -O3 -fomit-frame-pointer	sse2
icc -march=haswell -mtune=haswell -O2 -fomit-frame-pointer	sse2
icc -march=haswell -mtune=haswell -O3 -fomit-frame-pointer	sse2
icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer	sse2
icc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer	sse2
icc -march=ivybridge -mtune=ivybridge -O2 -fomit-frame-pointer	sse2
icc -march=ivybridge -mtune=ivybridge -O3 -fomit-frame-pointer	sse2
icc -march=sandybridge -mtune=sandybridge -O2 -fomit-frame-pointer	sse2
icc -march=sandybridge -mtune=sandybridge -O3 -fomit-frame-pointer	sse2
icc -march=skylake-avx512 -mtune=skylake-avx512 -O2 -fomit-frame-pointer	sse2
icc -march=skylake-avx512 -mtune=skylake-avx512 -O3 -fomit-frame-pointer	sse2
icc -march=skylake -mtune=skylake -O2 -fomit-frame-pointer	sse2
icc -march=skylake -mtune=skylake -O3 -fomit-frame-pointer	sse2

Compiler output

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

nts_kem.c: nts_kem.c(373): error: a value of type "union __m256i" cannot be assigned to an entity of type "vector"
nts_kem.c: Q[i][NTS_KEM_PARAM_R_VEC-1] = _mm256_setzero_si256();
nts_kem.c: ^
nts_kem.c:
nts_kem.c: nts_kem.c(409): error: a value of type "union __m256i" cannot be assigned to an entity of type "vector"
nts_kem.c: c_c[i] = _mm256_setzero_si256();
nts_kem.c: ^
nts_kem.c:
nts_kem.c: nts_kem.c(517): error: a value of type "union __m256i" cannot be used to initialize an entity of type "vector"
nts_kem.c: vector allones = _mm256_set1_epi64x(-1);
nts_kem.c: ^
nts_kem.c:
nts_kem.c: nts_kem.c(592): warning #167: argument of type "vector (*)[13]" is incompatible with parameter of type "__m256i (*)[13]"
nts_kem.c: bitslice_fft(evals, sigma);
nts_kem.c: ^
nts_kem.c:
nts_kem.c: nts_kem.c(608): warning #167: argument of type "vector *" is incompatible with parameter of type "const __m256i *"
nts_kem.c: error[i] = vector_ff_or(evals[i]);
nts_kem.c: ^
nts_kem.c:
nts_kem.c: nts_kem.c(608): error: a value of type "__m256i" cannot be assigned to an entity of type "vector"
nts_kem.c: error[i] = vector_ff_or(evals[i]);
nts_kem.c: ^
nts_kem.c:
nts_kem.c: nts_kem.c(609): error: argument of type "vector" is incompatible with parameter of type "union __m256i"
nts_kem.c: ...

Number of similar (compiler,implementation) pairs: 10, namely:

Compiler	Implementations
icc -march=core-avx-i -mtune=core-avx-i -O2 -fomit-frame-pointer	avx2
icc -march=core-avx-i -mtune=core-avx-i -O3 -fomit-frame-pointer	avx2
icc -march=corei7-avx -mtune=corei7-avx -O2 -fomit-frame-pointer	avx2
icc -march=corei7-avx -mtune=corei7-avx -O3 -fomit-frame-pointer	avx2
icc -march=corei7 -mtune=corei7 -O2 -fomit-frame-pointer	avx2
icc -march=corei7 -mtune=corei7 -O3 -fomit-frame-pointer	avx2
icc -march=ivybridge -mtune=ivybridge -O2 -fomit-frame-pointer	avx2
icc -march=ivybridge -mtune=ivybridge -O3 -fomit-frame-pointer	avx2
icc -march=sandybridge -mtune=sandybridge -O2 -fomit-frame-pointer	avx2
icc -march=sandybridge -mtune=sandybridge -O3 -fomit-frame-pointer	avx2

Compiler output

Implementation: sse2
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

bitslice_bma_128.c: In file included from bitslice_bma_128.c:17:
bitslice_bma_128.c: In file included from ./bits.h:28:
bitslice_bma_128.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/immintrin.h:27:
bitslice_bma_128.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]
bitslice_bma_128.c: extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
bitslice_bma_128.c: ^
bitslice_bma_128.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]
bitslice_bma_128.c: extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
bitslice_bma_128.c: ^
bitslice_bma_128.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]
bitslice_bma_128.c: extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
bitslice_bma_128.c: ^
bitslice_bma_128.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]
bitslice_bma_128.c: extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
bitslice_bma_128.c: ^
bitslice_bma_128.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]
bitslice_bma_128.c: extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
bitslice_bma_128.c: ^
bitslice_bma_128.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]
bitslice_bma_128.c: extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
bitslice_bma_128.c: ^
bitslice_bma_128.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]
bitslice_bma_128.c: extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
bitslice_bma_128.c: ^
bitslice_bma_128.c: /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/mmintrin.h:103:74: warning: unknown attribute '__artificial__' ignored [-Wunknown-attributes]
bitslice_bma_128.c: ...

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

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse2
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse2
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse2
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	sse2