Implementation notes: amd64, comet, crypto_aead/romulusm

Computer: comet
Microarchitecture: amd64; Comet Lake (806ec)
Architecture: amd64
CPU ID: GenuineIntel-000806ec-bfebfbff
SUPERCOP version: 20240107
Operation: crypto_aead
Primitive: romulusm

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
264914	10949 0 0	23551 756 1056	`aadomn/x86`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240106	20231222
266791	14143 0 0	32185 852 1088	`aadomn/x86`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240106	20231222
266976	10958 0 0	24913 852 1024	`aadomn/x86`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240106	20231222
267582	10452 0 0	25175 844 1088	`aadomn/x86`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240106	20231222
267642	13967 0 0	31713 852 1056	`aadomn/x86`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240106	20231222
269879	11965 0 0	26260 780 1088	`aadomn/x86`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240106	20231222
269945	13357 0 0	29540 780 1088	`aadomn/x86`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240106	20231222
277414	11541 0 0	25363 772 1088	`aadomn/x86`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240106	20231222
1012906	35857 640 0	53465 1596 1088	`aadomn/opt32`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240106	20231222
1014514	35441 640 0	52753 1596 1056	`aadomn/opt32`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240106	20231222
1082766	31638 640 0	47561 1500 1024	`aadomn/opt32`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240106	20231222
1394961	23438 640 0	37537 1500 1024	`aadomn/opt32`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240106	20231222
1495636	21986 640 0	36052 1428 1088	`aadomn/opt32`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240106	20231222
1557392	20211 640 0	32951 1404 1056	`aadomn/opt32`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240106	20231222
1561926	19391 12 0	35777 864 1024	`T:ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240106	20231222
1598336	19899 640 0	34503 1492 1088	`aadomn/opt32`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240106	20231222
1642852	32090 640 0	48460 1428 1088	`aadomn/opt32`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240106	20231222
1718020	21449 12 0	39345 864 1088	`T:ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240106	20231222
1726885	17443 12 0	35065 864 1056	`T:ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240106	20231222
1751498	24941 640 0	39420 1428 1088	`aadomn/opt32`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240106	20231222
2112541	28031 12 0	44380 792 1088	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240106	20231222
5766345	8150 12 0	22580 792 1088	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240106	20231222
6132434	10494 12 0	24569 864 1024	`T:ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240106	20231222
6173757	5336 12 0	18047 768 1056	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240106	20231222
6335840	6854 12 0	21711 856 1088	`T:ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240106	20231222
7564775	6082 12 0	20027 784 1088	`T:ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240106	20231222

Test failure

Implementation: T:fixslice_opt32
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

error 111
crypto_aead_decrypt returns nonzero

Number of similar (compiler,implementation) pairs: 9, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:fixslice_opt32
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:fixslice_opt32
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:fixslice_opt32
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:fixslice_opt32
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:fixslice_opt32
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:fixslice_opt32
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:fixslice_opt32
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:fixslice_opt32
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:fixslice_opt32

Test failure

Implementation: T:opt32t
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

error 111
crypto_aead_decrypt allows trivial forgeries

Number of similar (compiler,implementation) pairs: 9, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:opt32t
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:opt32t
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:opt32t
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:opt32t
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:opt32t
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:opt32t
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:opt32t
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:opt32t
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:opt32t

Compiler output

Implementation: aadomn/x86
Security model: constbranchindex
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

skinny128.c: skinny128.c:115:5: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'skinny128_384_plus' that is compiled without support for 'ssse3'
skinny128.c: DOUBLE_ROUND(rtk_23);
skinny128.c: ^
skinny128.c: skinny128.c:78:5: note: expanded from macro 'DOUBLE_ROUND'
skinny128.c: SBOX_ARK_EVEN(rtk_23); \
skinny128.c: ^
skinny128.c: skinny128.c:23:13: note: expanded from macro 'SBOX_ARK_EVEN'
skinny128.c: state = _mm_shuffle_epi8(s1, state); /* apply inner S-box S1 */ \
skinny128.c: ^
skinny128.c: skinny128.c:115:5: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'skinny128_384_plus' that is compiled without support for 'ssse3'
skinny128.c: skinny128.c:78:5: note: expanded from macro 'DOUBLE_ROUND'
skinny128.c: SBOX_ARK_EVEN(rtk_23); \
skinny128.c: ^
skinny128.c: skinny128.c:24:13: note: expanded from macro 'SBOX_ARK_EVEN'
skinny128.c: tmp0 = _mm_shuffle_epi8(s0, tmp0); /* apply inner S-box S0 */ \
skinny128.c: ^
skinny128.c: skinny128.c:115:5: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'skinny128_384_plus' that is compiled without support for 'ssse3'
skinny128.c: skinny128.c:78:5: note: expanded from macro 'DOUBLE_ROUND'
skinny128.c: SBOX_ARK_EVEN(rtk_23); \
skinny128.c: ^
skinny128.c: skinny128.c:32:13: note: expanded from macro 'SBOX_ARK_EVEN'
skinny128.c: tmp0 = _mm_shuffle_epi8(s3, tmp0); /* apply inner S-box S3 */ \
skinny128.c: ^
skinny128.c: skinny128.c:115:5: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'skinny128_384_plus' that is compiled without support for 'ssse3'
skinny128.c: skinny128.c:78:5: note: expanded from macro 'DOUBLE_ROUND'
skinny128.c: ...

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	aadomn/x86

Compiler output

Implementation: T:fixslice_opt32
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE

decrypt.c: decrypt.c: In function 'crypto_aead_romulusm_fixslice_opt32_timingleaks_decrypt':
decrypt.c: decrypt.c:56:22: warning: writing 1 byte into a region of size 0 [-Wstringop-overflow=]
decrypt.c: 56 | state[i] ^= m[i];
decrypt.c: | ~~~~~~~~~^~~~~~~
decrypt.c: decrypt.c:24:8: note: at offset 16 into destination object 'state' of size 16
decrypt.c: 24 | u8 state[BLOCKBYTES], pad[BLOCKBYTES];
decrypt.c: | ^~~~~

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:fixslice_opt32