Implementation notes: amd64, margaux, crypto_auth/siphash24

Computer: margaux
Microarchitecture: amd64; Core 2 65nm (6fb)
Architecture: amd64
CPU ID: GenuineIntel-000006fb-bfebfbff
SUPERCOP version: 20240107
Operation: crypto_auth
Primitive: siphash24
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
5594652 0 013949 804 992T:littlegcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
5595625 0 012296 780 960T:littlegcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
5829685 0 014395 844 928T:littleclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
5829685 0 015507 844 928T:littleclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
5829685 0 015283 844 928T:littleclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
5968761 0 015237 804 992T:littlegcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
6079875 0 013644 796 992T:little2gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
6096692 0 013107 844 928T:little2clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
6109699 0 012301 836 928T:little2clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
6111702 0 014395 844 928T:little2clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
6111702 0 015507 844 928T:little2clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
6129806 0 013227 844 928T:ref_leclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
6141953 0 013724 796 992T:ref_legcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
6160806 0 014507 844 928T:ref_leclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
6160806 0 015619 844 928T:ref_leclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
6160807 0 015395 844 928T:ref_leclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
6187703 0 015283 844 928T:little2clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
6196957 0 014221 804 992T:ref_legcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
6196957 0 015389 804 992T:ref_legcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
6203910 0 014165 804 992T:little2gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
6203910 0 015341 804 992T:little2gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
6209791 0 012397 836 928T:ref_leclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
6275716 0 013540 796 992T:littlegcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
6366525 0 012955 844 928T:littleclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
6370488 0 012109 836 928T:littleclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
6874887 0 012496 780 960T:little2gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
6916984 0 012592 780 960T:ref_legcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
7505930 0 013692 796 992T:sandy2gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
7690733 0 014443 844 928T:sandyclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
7690733 0 015555 844 928T:sandyclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
7690733 0 015331 844 928T:sandyclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
7781982 0 014229 804 992T:sandy2gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
7915753 0 012365 836 928T:sandy2clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
7931700 0 013997 804 992T:sandygcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
7954974 0 015405 804 992T:sandy2gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
7972768 0 014459 844 928T:sandy2clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
7972768 0 015571 844 928T:sandy2clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
7972769 0 015347 844 928T:sandy2clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
7998841 0 015317 804 992T:sandygcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
8037656 0 012328 780 960T:sandygcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
8041738 0 013556 796 992T:sandygcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
8071758 0 013171 844 928T:sandy2clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
8124525 0 012955 844 928T:sandyclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
8219938 0 012552 780 960T:sandy2gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
9624997 0 015827 844 928T:mmxclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
9624997 0 015603 844 928T:mmxclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
9750997 0 014715 844 928T:mmxclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
101191267 0 015733 804 992T:mmxgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
10144612 0 012253 836 928T:mmxclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
10187922 0 013764 796 992T:sse2-1gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
102221299 0 015765 804 992T:sse2-1gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
10260645 0 013083 844 928T:mmxclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
103931197 0 015811 844 928T:sse2-1clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
105191197 0 016035 844 928T:sse2-1clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
106331197 0 014923 844 928T:sse2-1clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
10666908 0 014221 804 992T:sse2-1gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
10872903 0 013724 796 992T:mmxgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
109841341 0 013691 844 928T:sse2-1clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
11234738 0 012381 836 928T:sse2-1clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
12861506 0 012141 836 928T:sandyclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121420231212
22575892 0 014197 804 992T:mmxgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
23722783 0 012456 780 960T:mmxgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121420231212
24096758 0 012432 780 960T:sse2-1gcc_-march=native_-mtune=native_-Os_-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