Implementation notes: aarch64, hikey960, crypto_sign/picnic2l1fs

Computer: hikey960
Architecture: aarch64
CPU ID: 410fd034
SUPERCOP version: 20190816
Operation: crypto_sign
Primitive: picnic2l1fs
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
656871201102414 2056 16135852 2928 1624optimizedct/cclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019120220190816
661440452124207 2600 16161587 3616 1608optimizedct/cgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019120220190816
662556321102414 2056 16135852 2928 1624optimizedct/cclang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019120220190816
714311357120931 2600 16158483 3616 1608optimizedct/cgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019120220190816
1066723875106435 2600 16142499 3616 1640optimizedct/cgcc_-O3_-fomit-frame-pointer2019120220190816
1090858050123819 2600 16161203 3616 1608optimizedct/cgcc_-funroll-loops_-O2_-fomit-frame-pointer2019120220190816
113071815084685 2600 16118095 3600 1608optimizedct/cgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2019120220190816
1138901625102414 2056 16135852 2928 1624optimizedct/cclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019120220190816
114716002584737 2600 16118151 3600 1608optimizedct/cgcc_-Os_-fomit-frame-pointer2019120220190816
1194554250120931 2600 16158483 3616 1608optimizedct/cgcc_-funroll-loops_-O_-fomit-frame-pointer2019120220190816
119589457594651 2600 16129003 3616 1608optimizedct/cgcc_-O_-fomit-frame-pointer2019120220190816
1236270825102562 2056 16135980 2928 1624optimizedct/cclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019120220190816
126663438095175 2600 16129499 3616 1608optimizedct/cgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019120220190816
1267641826106819 2600 16142819 3616 1640optimizedct/cgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019120220190816
1317348393140843 2600 16178475 3616 1640optimizedct/cgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019120220190816
155594073894743 2600 16129139 3616 1608optimizedct/cgcc_-O2_-fomit-frame-pointer2019120220190816
163976785595159 2600 16129515 3616 1608optimizedct/cgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2019120220190816
183869266084737 2600 16118151 3600 1608optimizedct/cgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019120220190816
1942638750140687 2600 16178387 3616 1640optimizedct/cgcc_-funroll-loops_-O3_-fomit-frame-pointer2019120220190816
1948016700106891 2600 16142947 3616 1640optimizedct/cgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2019120220190816
218537910094967 2600 16129363 3616 1608optimizedct/cgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2019120220190816
22349272681093831 4 01129408 1008 1624refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019120220190816
22448140471062029 4 01097376 1008 1592refgcc_-funroll-loops_-O2_-fomit-frame-pointer2019120220190816
22727155501057671 4 01091616 1008 1624refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019120220190816
22756647061093611 4 01129256 1008 1624refgcc_-funroll-loops_-O3_-fomit-frame-pointer2019120220190816
23328873171036814 4 01069168 1008 1592refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2019120220190816
23455650331030962 4 01062428 992 1592refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019120220190816
23695313671030982 4 01062476 992 1592refgcc_-funroll-loops_-Os_-fomit-frame-pointer2019120220190816
23942172241046057 4 01079016 888 1608refclang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019120220190816
2414607975135040 2600 16173591 3600 1608optimizedct/ccc2019120220190816
2426146425135040 2600 16173591 3600 1608optimizedct/cgcc_-funroll-loops2019120220190816
273695197584801 2600 16118239 3600 1608optimizedct/cgcc_-funroll-loops_-Os_-fomit-frame-pointer2019120220190816
281886997584801 2600 16118239 3600 1608optimizedct/cgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019120220190816
310127895094651 2600 16129003 3616 1608optimizedct/cgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019120220190816
43093030501036565 4 01068920 1008 1592refgcc_-O2_-fomit-frame-pointer2019120220190816
43650722251057316 4 01091304 1008 1624refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2019120220190816
44082922861030982 4 01062476 992 1592refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019120220190816
44902617561046057 4 01079016 888 1608refclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019120220190816
45041994801046057 4 01079016 888 1608refclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019120220190816
45110767561046057 4 01079000 888 1608refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019120220190816
47517106451050397 4 01085960 1008 1592refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019120220190816
48105296721050397 4 01085960 1008 1592refgcc_-funroll-loops_-O_-fomit-frame-pointer2019120220190816
49956410251034401 4 01066768 1008 1592refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2019120220190816
51462239221062153 4 01097496 1008 1592refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019120220190816
53097646891036717 4 01068992 1008 1592refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019120220190816
56721064051030922 4 01062388 992 1592refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2019120220190816
58185602531030962 4 01062428 992 1592refgcc_-Os_-fomit-frame-pointer2019120220190816
68849756241034029 4 01066392 1008 1592refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019120220190816
69816649141034029 4 01066392 1008 1592refgcc_-O_-fomit-frame-pointer2019120220190816
7736465081135040 2600 16173591 3600 1608optimizedct/cgcc2019120220190816
95183067101057271 4 01091272 1008 1624refgcc_-O3_-fomit-frame-pointer2019120220190816

Test failure

Implementation: ref
Security model: unknown
Compiler: cc
error 142
Alarm clock

Number of similar (compiler,implementation) pairs: 3, namely:
CompilerImplementations
cc ref
gcc ref
gcc -funroll-loops ref

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