Implementation notes: amd64, hydra5, crypto_auth/siphash24

Computer: hydra5
Microarchitecture: amd64; K10 32nm (300f10)
Architecture: amd64
CPU ID: AuthenticAMD-00300f10-178bfbff
SUPERCOP version: 20240107
Operation: crypto_auth
Primitive: siphash24
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
4404957 0 014533 804 992T:ref_legcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
4404957 0 015861 804 992T:ref_legcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
4405953 0 013668 796 992T:ref_legcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
4752703 0 014384 860 928T:little2clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
4752703 0 015272 860 928T:little2clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
4752703 0 015272 860 928T:little2clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
4758693 0 013064 860 928T:little2clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
4761874 0 013588 796 992T:little2gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
4762777 0 015709 804 992T:littlegcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
4763910 0 015797 804 992T:little2gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
4764910 0 014461 804 992T:little2gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
4771625 0 012288 780 960T:littlegcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
4778684 0 014293 804 992T:littlegcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
4944699 0 012290 852 928T:little2clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
5145807 0 015400 860 928T:ref_leclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
5146807 0 014512 860 928T:ref_leclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
5146807 0 015400 860 928T:ref_leclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
5146807 0 013200 860 928T:ref_leclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
5290791 0 012386 852 928T:ref_leclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
5335685 0 014384 860 928T:littleclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
5335685 0 015272 860 928T:littleclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
5335685 0 015272 860 928T:littleclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
5543984 0 012568 780 960T:ref_legcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
5633714 0 013484 796 992T:littlegcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
5749525 0 012912 860 928T:littleclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
5929887 0 012472 780 960T:little2gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
5930488 0 012098 852 928T:littleclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
98641197 0 015816 860 928T:sse2-1clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
100321197 0 014928 860 928T:sse2-1clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
100321197 0 015816 860 928T:sse2-1clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
10206911 0 013700 796 992T:mmxgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
10232738 0 012386 852 928T:sse2-1clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
102341342 0 013664 860 928T:sse2-1clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
10277940 0 014565 804 992T:sse2-1gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
10460932 0 013724 796 992T:sse2-1gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
109761331 0 016269 804 992T:sse2-1gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
11425645 0 013040 860 928T:mmxclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
116431347 0 016285 804 992T:mmxgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
11651612 0 012226 852 928T:mmxclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
11780997 0 015592 860 928T:mmxclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
11781997 0 014704 860 928T:mmxclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
11781997 0 015592 860 928T:mmxclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
12020783 0 012448 780 960T:mmxgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
12197924 0 014541 804 992T:mmxgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
13347769 0 014448 860 928T:sandy2clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
13347753 0 012354 852 928T:sandy2clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
13349769 0 015336 860 928T:sandy2clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
13349769 0 015336 860 928T:sandy2clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
13353733 0 015336 860 928T:sandyclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
13354733 0 014448 860 928T:sandyclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
13354759 0 013128 860 928T:sandy2clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
13355733 0 015336 860 928T:sandyclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
13358929 0 013652 796 992T:sandy2gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
13364990 0 015893 804 992T:sandy2gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
13365990 0 014557 804 992T:sandy2gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
13367656 0 012320 780 960T:sandygcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
13421736 0 013516 796 992T:sandygcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
14133938 0 012528 780 960T:sandy2gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
14137758 0 012408 780 960T:sse2-1gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
14157541 0 012944 860 928T:sandyclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
14515841 0 015773 804 992T:sandygcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
14525506 0 012130 852 928T:sandyclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
14525716 0 014325 804 992T:sandygcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212

Compiler output

Implementation: T:sse2-1
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
siphash.c: siphash.c:24:9: warning: '_mm_roti_epi64' macro redefined [-Wmacro-redefined]
siphash.c: #define _mm_roti_epi64(x, c) ((16 == (c)) ? _mm_shufflelo_epi16((x), _MM_SHUFFLE(2,1,0,3)) : _mm_xor_si128(_mm_slli_epi64((x), (c)), _mm_srli_epi64((x), 64-(c))))
siphash.c: ^
siphash.c: /usr/lib/llvm-14/lib/clang/14.0.0/include/xopintrin.h:236:9: note: previous definition is here
siphash.c: #define _mm_roti_epi64(A, N) \
siphash.c: ^
siphash.c: 1 warning generated.
Number of similar (compiler,implementation) pairs: 5, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:sse2-1
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:sse2-1
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:sse2-1
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:sse2-1
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:sse2-1

Compiler output

Implementation: T:sse41
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
siphash.c: siphash.c:27:9: warning: '_mm_roti_epi64' macro redefined [-Wmacro-redefined]
siphash.c: #define _mm_roti_epi64(x, c) (((c) == 16) ? rotate16((x)) : _mm_xor_si128(_mm_slli_epi64((x), (c)), _mm_srli_epi64((x), 64-(c))))
siphash.c: ^
siphash.c: /usr/lib/llvm-14/lib/clang/14.0.0/include/xopintrin.h:236:9: note: previous definition is here
siphash.c: #define _mm_roti_epi64(A, N) \
siphash.c: ^
siphash.c: siphash.c:70:39: error: '__builtin_ia32_pblendw128' needs target feature sse4.1
siphash.c: for(k = 0; k < SIPHASH_ROUNDS; ++k) COMPRESS(v02,v13);
siphash.c: ^
siphash.c: siphash.c:60:3: note: expanded from macro 'COMPRESS'
siphash.c: HALF_ROUND(v02,v13,13,16); \
siphash.c: ^
siphash.c: siphash.c:53:60: note: expanded from macro 'HALF_ROUND'
siphash.c: b1 = _mm_roti_epi64(b, s); b2 = _mm_roti_epi64(b, t); b = _mm_blend_epi16(b1, b2, 0xF0); \
siphash.c: ^
siphash.c: /usr/lib/llvm-14/lib/clang/14.0.0/include/smmintrin.h:520:14: note: expanded from macro '_mm_blend_epi16'
siphash.c: ((__m128i) __builtin_ia32_pblendw128 ((__v8hi)(__m128i)(V1), \
siphash.c: ^
siphash.c: siphash.c:70:39: error: '__builtin_ia32_pblendw128' needs target feature sse4.1
siphash.c: siphash.c:62:3: note: expanded from macro 'COMPRESS'
siphash.c: HALF_ROUND(v02,v13,17,21); \
siphash.c: ^
siphash.c: siphash.c:53:60: note: expanded from macro 'HALF_ROUND'
siphash.c: b1 = _mm_roti_epi64(b, s); b2 = _mm_roti_epi64(b, t); b = _mm_blend_epi16(b1, b2, 0xF0); \
siphash.c: ^
siphash.c: ...
Number of similar (compiler,implementation) pairs: 5, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:sse41
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:sse41
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:sse41
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:sse41
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:sse41

Compiler output

Implementation: T:sse41
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE
siphash.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:39,
siphash.c: from /usr/lib/gcc/x86_64-linux-gnu/11/include/x86intrin.h:32,
siphash.c: from siphash.c:2:
siphash.c: siphash.c: In function 'siphash':
siphash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/smmintrin.h:166:1: error: inlining failed in call to 'always_inline' '_mm_blend_epi16': target specific option mismatch
siphash.c: 166 | _mm_blend_epi16 (__m128i __X, __m128i __Y, const int __M)
siphash.c: | ^~~~~~~~~~~~~~~
siphash.c: siphash.c:53:67: note: called from here
siphash.c: 53 | b1 = _mm_roti_epi64(b, s); b2 = _mm_roti_epi64(b, t); b = _mm_blend_epi16(b1, b2, 0xF0); \
siphash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
siphash.c: siphash.c:62:17: note: in expansion of macro 'HALF_ROUND'
siphash.c: 62 | HALF_ROUND(v02,v13,17,21); \
siphash.c: | ^~~~~~~~~~
siphash.c: siphash.c:70:53: note: in expansion of macro 'COMPRESS'
siphash.c: 70 | for(k = 0; k < SIPHASH_ROUNDS; ++k) COMPRESS(v02,v13);
siphash.c: | ^~~~~~~~
siphash.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:39,
siphash.c: from /usr/lib/gcc/x86_64-linux-gnu/11/include/x86intrin.h:32,
siphash.c: from siphash.c:2:
siphash.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/smmintrin.h:166:1: error: inlining failed in call to 'always_inline' '_mm_blend_epi16': target specific option mismatch
siphash.c: 166 | _mm_blend_epi16 (__m128i __X, __m128i __Y, const int __M)
siphash.c: | ^~~~~~~~~~~~~~~
siphash.c: siphash.c:53:67: note: called from here
siphash.c: 53 | b1 = _mm_roti_epi64(b, s); b2 = _mm_roti_epi64(b, t); b = _mm_blend_epi16(b1, b2, 0xF0); \
siphash.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
siphash.c: ...
Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE T:sse41
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE T:sse41
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE T:sse41
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE T:sse41