Implementation notes: aarch64, hikey960, crypto_sign/picnicl3ur

Computer: hikey960
Architecture: aarch64
CPU ID: 410fd034
SUPERCOP version: 20190816
Operation: crypto_sign
Primitive: picnicl3ur
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
92543094142757 2840 16176663 3840 1608optimizedct/cgcc_-funroll-loops_-Os_-fomit-frame-pointer2019120320190816
103140513142693 2840 16176583 3840 1608optimizedct/cgcc_-Os_-fomit-frame-pointer2019120320190816
122372084160666 2056 16194140 2928 1624optimizedct/cclang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019120320190816
135414450160814 2056 16194268 2928 1624optimizedct/cclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019120320190816
146811375164867 2840 16201483 3856 1640optimizedct/cgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2019120320190816
152755425164395 2840 16201035 3856 1640optimizedct/cgcc_-O3_-fomit-frame-pointer2019120320190816
165892275153111 2840 16188011 3856 1608optimizedct/cgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2019120320190816
173759400152719 2840 16187683 3856 1608optimizedct/cgcc_-O2_-fomit-frame-pointer2019120320190816
177588250181787 2840 16219731 3856 1608optimizedct/cgcc_-funroll-loops_-O2_-fomit-frame-pointer2019120320190816
198018450192940 2840 16236071 3840 1608optimizedct/ccc2019120320190816
206638696198795 2840 16236979 3856 1640optimizedct/cgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019120320190816
234801526152935 2840 16187899 3856 1608optimizedct/cgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2019120320190816
235286546142757 2840 16176663 3840 1608optimizedct/cgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019120320190816
237745350198655 2840 16236915 3856 1640optimizedct/cgcc_-funroll-loops_-O3_-fomit-frame-pointer2019120320190816
243053660160666 2056 16194140 2928 1624optimizedct/cclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019120320190816
252736120178891 2840 16216987 3856 1608optimizedct/cgcc_-funroll-loops_-O_-fomit-frame-pointer2019120320190816
253749793152603 2840 16187499 3856 1608optimizedct/cgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019120320190816
283174875160666 2056 16194140 2928 1624optimizedct/cclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019120320190816
292099275164771 2840 16201339 3856 1640optimizedct/cgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019120320190816
292540500182151 2840 16220091 3856 1608optimizedct/cgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019120320190816
303465987192940 2840 16236071 3840 1608optimizedct/cgcc2019120320190816
304152943152603 2840 16187499 3856 1608optimizedct/cgcc_-O_-fomit-frame-pointer2019120320190816
352413900153127 2840 16188011 3856 1608optimizedct/cgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019120320190816
371228400178891 2840 16216987 3856 1608optimizedct/cgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019120320190816
390801395142693 2840 16176583 3840 1608optimizedct/cgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019120320190816
440044990192940 2840 16236071 3840 1608optimizedct/cgcc_-funroll-loops2019120320190816
5869175761034037 4 01066448 1008 1592refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019120320190816
734431456142641 2840 16176527 3840 1608optimizedct/cgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2019120320190816
7461198001046065 4 01079080 888 1608refclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019120320190816
8530960501046065 4 01079064 888 1608refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019120320190816
9205119001093611 4 01129312 1008 1624refgcc_-funroll-loops_-O3_-fomit-frame-pointer2019120320190816
9775764751036565 4 01068976 1008 1592refgcc_-O2_-fomit-frame-pointer2019120320190816
10268441811046065 4 01079080 888 1608refclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019120320190816
10642430251034409 4 01066824 1008 1592refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2019120320190816
11023798501034037 4 01066448 1008 1592refgcc_-O_-fomit-frame-pointer2019120320190816
11187551251030926 4 01062388 992 1592refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2019120320190816
11287277081050405 4 01086016 1008 1592refgcc_-funroll-loops_-O_-fomit-frame-pointer2019120320190816
11759895001050405 4 01086016 1008 1592refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019120320190816
11861203411036814 4 01069224 1008 1592refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2019120320190816
12405415501030966 4 01062428 992 1592refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019120320190816
12416904001030986 4 01062468 992 1592refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019120320190816
13156963601057271 4 01091328 1008 1624refgcc_-O3_-fomit-frame-pointer2019120320190816
16198701751062153 4 01097552 1008 1592refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019120320190816
17054392701030966 4 01062428 992 1592refgcc_-Os_-fomit-frame-pointer2019120320190816
17997234751046065 4 01079080 888 1608refclang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019120320190816
20713297911057671 4 01091680 1008 1624refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019120320190816
20984910751057316 4 01091360 1008 1624refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2019120320190816
22517916781093831 4 01129464 1008 1624refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019120320190816
23454217111036717 4 01069056 1008 1592refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019120320190816
24466908491062029 4 01097432 1008 1592refgcc_-funroll-loops_-O2_-fomit-frame-pointer2019120320190816
29799004501030986 4 01062468 992 1592refgcc_-funroll-loops_-Os_-fomit-frame-pointer2019120320190816
40637488501060099 292 01100516 1280 1592refgcc2019120320190816
41447178001060099 292 01100516 1280 1592refgcc_-funroll-loops2019120320190816
124702006501060099 292 01100516 1280 1592refcc2019120320190816

Compiler output

Implementation: optimizedct/neon
Security model: unknown
Compiler: cc
picnic2_simulate_mul.c: picnic2_simulate_mul.c: In function 'transpose_64_64_s128':
picnic2_simulate_mul.c: picnic2_simulate_mul.c:316:24: warning: implicit declaration of function '_mm_set1_epi64x' [-Wimplicit-function-declaration]
picnic2_simulate_mul.c: word128 mask = _mm_set1_epi64x(TRANSPOSE_MASKS64[i]);
picnic2_simulate_mul.c: ^~~~~~~~~~~~~~~
picnic2_simulate_mul.c: picnic2_simulate_mul.c:316:24: error: incompatible types when initializing type 'word128' using type 'int'
picnic2_simulate_mul.c: In file included from mzd_additional.h:24:0,
picnic2_simulate_mul.c: from lowmc_pars.h:15,
picnic2_simulate_mul.c: from lowmc.h:13,
picnic2_simulate_mul.c: from picnic_impl.h:13,
picnic2_simulate_mul.c: from picnic2_impl.h:18,
picnic2_simulate_mul.c: from picnic2_types.h:16,
picnic2_simulate_mul.c: from picnic2_simulate_mul.h:13,
picnic2_simulate_mul.c: from picnic2_simulate_mul.c:14:
picnic2_simulate_mul.c: picnic2_simulate_mul.c:317:40: error: incompatible type for argument 2 of 'veorq_u64'
picnic2_simulate_mul.c: word128 inv_mask = mm128_xor(mask, _mm_set1_epi64x(UINT64_C(0xFFFFFFFFFFFFFFFF)));
picnic2_simulate_mul.c: ^
picnic2_simulate_mul.c: simd.h:103:38: note: in definition of macro 'mm128_xor'
picnic2_simulate_mul.c: #define mm128_xor(l, r) veorq_u64(l, r)
picnic2_simulate_mul.c: ^
picnic2_simulate_mul.c: In file included from simd.h:21:0,
picnic2_simulate_mul.c: from mzd_additional.h:24,
picnic2_simulate_mul.c: from lowmc_pars.h:15,
picnic2_simulate_mul.c: from lowmc.h:13,
picnic2_simulate_mul.c: from picnic_impl.h:13,
picnic2_simulate_mul.c: from picnic2_impl.h:18,
picnic2_simulate_mul.c: ...

Number of similar (compiler,implementation) pairs: 23, namely:
CompilerImplementations
cc optimizedct/neon
gcc optimizedct/neon
gcc -O2 -fomit-frame-pointer optimizedct/neon
gcc -O3 -fomit-frame-pointer optimizedct/neon
gcc -O -fomit-frame-pointer optimizedct/neon
gcc -Os -fomit-frame-pointer optimizedct/neon
gcc -fno-schedule-insns -O2 -fomit-frame-pointer optimizedct/neon
gcc -fno-schedule-insns -O3 -fomit-frame-pointer optimizedct/neon
gcc -fno-schedule-insns -O -fomit-frame-pointer optimizedct/neon
gcc -fno-schedule-insns -Os -fomit-frame-pointer optimizedct/neon
gcc -funroll-loops optimizedct/neon
gcc -funroll-loops -O2 -fomit-frame-pointer optimizedct/neon
gcc -funroll-loops -O3 -fomit-frame-pointer optimizedct/neon
gcc -funroll-loops -O -fomit-frame-pointer optimizedct/neon
gcc -funroll-loops -Os -fomit-frame-pointer optimizedct/neon
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer optimizedct/neon
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer optimizedct/neon
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer optimizedct/neon
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer optimizedct/neon
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv optimizedct/neon
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv optimizedct/neon
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv optimizedct/neon
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv optimizedct/neon

Compiler output

Implementation: optimizedct/neon
Security model: unknown
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments
picnic2_simulate_mul.c: picnic2_simulate_mul.c:316:24: warning: implicit declaration of function '_mm_set1_epi64x' is invalid in C99 [-Wimplicit-function-declaration]
picnic2_simulate_mul.c: word128 mask = _mm_set1_epi64x(TRANSPOSE_MASKS64[i]);
picnic2_simulate_mul.c: ^
picnic2_simulate_mul.c: picnic2_simulate_mul.c:316:13: error: initializing 'word128' (aka 'uint64x2_t') with an expression of incompatible type 'int'
picnic2_simulate_mul.c: word128 mask = _mm_set1_epi64x(TRANSPOSE_MASKS64[i]);
picnic2_simulate_mul.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
picnic2_simulate_mul.c: picnic2_simulate_mul.c:329:57: warning: implicit declaration of function '_mm_srli_epi64' is invalid in C99 [-Wimplicit-function-declaration]
picnic2_simulate_mul.c: out128[i1 / 2] = mm128_xor(mm128_and(t1, mask), _mm_srli_epi64(mm128_and(t2, mask), width));
picnic2_simulate_mul.c: ^
picnic2_simulate_mul.c: picnic2_simulate_mul.c:331:48: warning: implicit declaration of function '_mm_slli_epi64' is invalid in C99 [-Wimplicit-function-declaration]
picnic2_simulate_mul.c: mm128_xor(mm128_and(t2, inv_mask), _mm_slli_epi64(mm128_and(t1, inv_mask), width));
picnic2_simulate_mul.c: ^
picnic2_simulate_mul.c: picnic2_simulate_mul.c:331:48: error: passing 'int' to parameter of incompatible type 'uint64x2_t' (vector of 2 'uint64_t' values)
picnic2_simulate_mul.c: mm128_xor(mm128_and(t2, inv_mask), _mm_slli_epi64(mm128_and(t1, inv_mask), width));
picnic2_simulate_mul.c: ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
picnic2_simulate_mul.c: ./simd.h:103:38: note: expanded from macro 'mm128_xor'
picnic2_simulate_mul.c: #define mm128_xor(l, r) veorq_u64(l, r)
picnic2_simulate_mul.c: ^
picnic2_simulate_mul.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/arm_neon.h:5463:55: note: passing argument to parameter '__p1' here
picnic2_simulate_mul.c: __ai uint64x2_t veorq_u64(uint64x2_t __p0, uint64x2_t __p1) {
picnic2_simulate_mul.c: ^
picnic2_simulate_mul.c: 3 warnings and 2 errors generated.

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
clang -O3 -fomit-frame-pointer -Qunused-arguments optimizedct/neon
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments optimizedct/neon
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments optimizedct/neon
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments optimizedct/neon