Implementation notes: amd64, hertz, crypto_aead/aezv3

Computer: hertz
Microarchitecture: amd64; Zen 4 (a60f12)
Architecture: amd64
CPU ID: AuthenticAMD-00a60f12-178bfbff
SUPERCOP version: 20240425
Operation: crypto_aead
Primitive: aezv3

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
1820	18045 0 0	44783 828 1096	`T:aesni`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
1820	18061 0 0	44911 828 1096	`T:aesni`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
1835	9358 0 0	30128 820 1096	`T:aesni`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
1874	17596 0 0	41525 804 1160	`T:aesni`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
1876	10479 0 0	32429 804 1096	`T:aesni`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
1959	9145 0 0	28608 780 1064	`T:aesni`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
618809	38309 0 0	65630 844 1096	`T:ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
688382	37536 0 0	64734 844 1096	`T:ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
825310	53108 0 0	77380 828 1160	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
833367	25852 0 0	48076 828 1096	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
913436	25438 0 0	46528 836 1096	`T:ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
1187904	22673 0 0	42391 804 1064	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217

Compiler output

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

aez_ni.c: In function 'load_partial',
aez_ni.c: inlined from 'load_partial' at aez_ni.c:119:16,
aez_ni.c: inlined from 'cipher_aez_tiny' at aez_ni.c:498:18,
aez_ni.c: inlined from 'aez_encrypt' at aez_ni.c:588:9,
aez_ni.c: inlined from 'crypto_aead_aezv3_aesni_timingleaks_encrypt' at aez_ni.c:637:5:
aez_ni.c: aez_ni.c:123:46: warning: '__builtin_memcpy' writing between 4294967264 and 4294967279 bytes into a region of size 16 overflows the destination [-Wstringop-overflow=]
aez_ni.c: 123 | for (i=0; i<n; i++) ((char*)&tmp)[i] = ((char*)p)[i];
aez_ni.c: | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~
aez_ni.c: aez_ni.c: In function 'crypto_aead_aezv3_aesni_timingleaks_encrypt':
aez_ni.c: aez_ni.c:122:17: note: destination object 'tmp' of size 16
aez_ni.c: 122 | __m128i tmp; unsigned i;
aez_ni.c: | ^~~

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

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

Compiler output

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

aez_ref.c: In function 'xor_bytes',
aez_ref.c: inlined from 'AEZcore' at aez_ref.c:299:38:
aez_ref.c: aez_ref.c:64:29: warning: writing 32 bytes into a region of size 16 [-Wstringop-overflow=]
aez_ref.c: 64 | while (n) { n--; dst[n] = src1[n] ^ src2[n]; }
aez_ref.c: | ~~~~~~~^~~~~~~~~~~~~~~~~~~
aez_ref.c: aez_ref.c: In function 'AEZcore':
aez_ref.c: aez_ref.c:247:10: note: at offset [0, 15] into destination object 'tmp' of size 16
aez_ref.c: 247 | byte tmp[16], X[16], Y[16], S[16];
aez_ref.c: | ^~~
aez_ref.c: In function 'xor_bytes',
aez_ref.c: inlined from 'AEZcore.constprop' at aez_ref.c:299:38:
aez_ref.c: aez_ref.c:64:29: warning: writing 32 bytes into a region of size 16 [-Wstringop-overflow=]
aez_ref.c: 64 | while (n) { n--; dst[n] = src1[n] ^ src2[n]; }
aez_ref.c: | ~~~~~~~^~~~~~~~~~~~~~~~~~~
aez_ref.c: aez_ref.c: In function 'AEZcore.constprop':
aez_ref.c: aez_ref.c:247:10: note: at offset [0, 15] into destination object 'tmp' of size 16
aez_ref.c: 247 | byte tmp[16], X[16], Y[16], S[16];
aez_ref.c: | ^~~

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

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