Implementation notes: amd64, h8atom, crypto_auth/siphash24

Computer: h8atom
Microarchitecture: amd64; Bonnell (30661)
Architecture: amd64
CPU ID: GenuineIntel-00030661-bfebfbff
SUPERCOP version: 20240107
Operation: crypto_auth
Primitive: siphash24
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
7133702 0 013684 816 744T:little2clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
7133702 0 014860 816 744T:little2clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
7140807 0 013796 816 744T:ref_leclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
7140807 0 014972 816 744T:ref_leclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
7147686 0 014860 816 744T:littleclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
7147807 0 012812 816 744T:ref_leclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
7161699 0 011934 808 744T:little2clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
7168686 0 013684 816 744T:littleclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
7175792 0 012030 808 744T:ref_leclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
7182761 0 014870 776 832T:littlegcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
7196652 0 013414 776 832T:littlegcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
7203957 0 013686 776 832T:ref_legcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
7210910 0 013630 776 832T:little2gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
7210910 0 014974 776 832T:little2gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
7217957 0 015022 776 832T:ref_legcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
7588875 0 013205 768 832T:little2gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
7917703 0 014844 816 744T:little2clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
7938807 0 014956 816 744T:ref_leclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
7945692 0 012692 816 744T:little2clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
7952625 0 011841 752 800T:littlegcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
8085716 0 013101 768 832T:littlegcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
8330685 0 014844 816 744T:littleclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
8386953 0 013285 768 832T:ref_legcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
8736887 0 012041 752 800T:little2gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
8743984 0 012153 752 800T:ref_legcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
9534489 0 011742 808 744T:littleclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
9905526 0 012540 816 744T:littleclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
251091197 0 015372 816 744T:sse2-1clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
25900997 0 015164 816 744T:mmxclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
266911214 0 014228 816 744T:sse2-1clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
266981214 0 015404 816 744T:sse2-1clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
274891014 0 014020 816 744T:mmxclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
274891014 0 015196 816 744T:mmxclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
289871267 0 015366 776 832T:mmxgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
297781299 0 015398 776 832T:sse2-1gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
33705630 0 011886 808 744T:mmxclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
34104908 0 013686 776 832T:sse2-1gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
34475783 0 012001 752 800T:mmxgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
34804758 0 011993 752 800T:sse2-1gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
34923903 0 013285 768 832T:mmxgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
35203746 0 012014 808 744T:sse2-1clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
35259922 0 013325 768 832T:sse2-1gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
35595892 0 013662 776 832T:mmxgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
36015662 0 012684 816 744T:mmxclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
363231373 0 013308 816 744T:sse2-1clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
54705769 0 013748 816 744T:sandy2clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
54705769 0 014924 816 744T:sandy2clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
54712754 0 011982 808 744T:sandy2clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
54719734 0 013732 816 744T:sandyclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
54719734 0 014908 816 744T:sandyclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
55153841 0 014950 776 832T:sandygcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
55160700 0 013462 776 832T:sandygcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
55475759 0 012756 816 744T:sandy2clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
55573982 0 013694 776 832T:sandy2gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
55573974 0 015038 776 832T:sandy2gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
55937656 0 011873 752 800T:sandygcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
55944930 0 013253 768 832T:sandy2gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
56273769 0 014908 816 744T:sandy2clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
56322938 0 012097 752 800T:sandy2gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
56469738 0 013117 768 832T:sandygcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121520231212
56665733 0 014892 816 744T:sandyclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
57106526 0 012540 816 744T:sandyclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212
60928507 0 011758 808 744T:sandyclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121520231212

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