Implementation notes: aarch64, pi3bplus, crypto_sign/picnicl3ur

Computer: pi3bplus
Architecture: aarch64
CPU ID: 410fd034
SUPERCOP version: 20200702
Operation: crypto_sign
Primitive: picnicl3ur
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
275969706131833 2224 13169730 3136 1608optimizedct/neongcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020050420200417
278946950127833 2224 13164538 3136 1592optimizedct/neongcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020050420200417
284169798124833 2320 13161211 3144 1592optimizedct/cclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020050420200417
286132100128641 2224 13166418 3136 1608optimizedct/cgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020050420200417
294189904121133 2224 13156786 3120 1576optimizedct/neongcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020050420200417
306965838128445 2224 13165122 3136 1592optimizedct/neongcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020050420200417
320951272125629 2224 13162218 3136 1592optimizedct/cgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020050420200417
350914038126117 2224 13162674 3136 1592optimizedct/cgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020050420200417
358074274119077 2224 13154594 3120 1576optimizedct/cgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020050420200417
13417782561278321 4 01314680 928 1592refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020050420200417
13599097121265131 4 01300376 928 1576refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020050420200417
13642260931270355 100 01305985 936 1576refclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020050420200417
19676954841261795 4 01296984 928 1576refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020050420200417
23808010421257121 4 01291208 912 1560refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020050420200417

Compiler output

Implementation: crypto_sign/picnicl3ur/optimizedct/neon
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
bitstream.c: In file included from bitstream.c:11:
bitstream.c: In file included from ./bitstream.h:15:
bitstream.c: In file included from ./mzd_additional.h:24:
bitstream.c: ./simd.h:146:17: error: argument to '__builtin_neon_vshlq_n_v' must be a constant integer
bitstream.c: vorrq_u64(mm128_shift_left(data[1], count), mm128_shift_right_64_127(data[0], 128 - count));
bitstream.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitstream.c: ./simd.h:132:13: note: expanded from macro 'mm128_shift_left'
bitstream.c: vorrq_u64(mm128_sl_u64(data, count), mm128_sr_u64(vextq_u64(mm128_zero, data, 1), 64 - count))
bitstream.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
bitstream.c: ./simd.h:114:30: note: expanded from macro 'mm128_sl_u64'
bitstream.c: (__builtin_constant_p(s) ? vshlq_n_u64((x), (s)) : vshlq_u64((x), vdupq_n_s64(s)))
bitstream.c: ^~~~~~~~~~~~~~~~~~~~~
bitstream.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/arm_neon.h:24909:24: note: expanded from macro 'vshlq_n_u64'
bitstream.c: __ret = (uint64x2_t) __builtin_neon_vshlq_n_v((int8x16_t)__s0, __p1, 51); \
bitstream.c: ^ ~~~~
bitstream.c: In file included from bitstream.c:11:
bitstream.c: In file included from ./bitstream.h:15:
bitstream.c: In file included from ./mzd_additional.h:24:
bitstream.c: ./simd.h:146:17: error: argument to '__builtin_neon_vshrq_n_v' must be a constant integer
bitstream.c: vorrq_u64(mm128_shift_left(data[1], count), mm128_shift_right_64_127(data[0], 128 - count));
bitstream.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitstream.c: ./simd.h:132:40: note: expanded from macro 'mm128_shift_left'
bitstream.c: vorrq_u64(mm128_sl_u64(data, count), mm128_sr_u64(vextq_u64(mm128_zero, data, 1), 64 - count))
bitstream.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitstream.c: ./simd.h:116:30: note: expanded from macro 'mm128_sr_u64'
bitstream.c: ...

Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE optimizedct/neon

Namespace violations

Implementation: crypto_sign/picnicl3ur/ref
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
api.o params D
hash.o HashFinal T
hash.o HashInit T
hash.o HashSqueeze T
hash.o HashUpdate T
hash.o HashUpdateIntLE T
hash.o fromLittleEndian T
hash.o toLittleEndian T
lowmc_constants.o KMatrix T
lowmc_constants.o KMatrixInv T
lowmc_constants.o LMatrix T
lowmc_constants.o LMatrixInv T
lowmc_constants.o RConstant T
picnic.o get_param_set T
picnic.o get_transform T
picnic.o is_picnic3 T
picnic.o picnic_get_param_name T
picnic.o picnic_keygen T
picnic.o picnic_read_private_key T
picnic.o picnic_read_public_key T
picnic.o picnic_sign T
picnic.o picnic_signature_size T
picnic.o picnic_validate_keypair T
picnic.o picnic_verify T
picnic.o picnic_write_private_key T
picnic.o picnic_write_public_key T
picnic.o print_signature T
picnic3_impl.o ceil_log2 T
picnic3_impl.o deserializeSignature2 T
picnic3_impl.o serializeSignature2 T
picnic3_impl.o sign_picnic3 T
picnic3_impl.o verify_picnic3 T
picnic_impl.o Commit T
picnic_impl.o G T
picnic_impl.o H3 T
picnic_impl.o LowMCEnc T
picnic_impl.o arePaddingBitsZero T
picnic_impl.o computeSeeds T
picnic_impl.o createRandomTape T
picnic_impl.o deserializeSignature T
picnic_impl.o getBit T
picnic_impl.o getBitFromWordArray T
picnic_impl.o getChallenge T
picnic_impl.o matrix_mul T
picnic_impl.o mpc_AND T
picnic_impl.o mpc_AND_verify T
picnic_impl.o mpc_LowMC T
picnic_impl.o mpc_LowMC_verify T
picnic_impl.o mpc_matrix_mul T
picnic_impl.o mpc_substitution T
picnic_impl.o mpc_substitution_verify T
picnic_impl.o mpc_xor T
picnic_impl.o mpc_xor_constant T
picnic_impl.o mpc_xor_constant_verify T
picnic_impl.o numBytes T
picnic_impl.o parity T
picnic_impl.o printHex T
picnic_impl.o prove T
picnic_impl.o random_bytes_supercop T
picnic_impl.o serializeSignature T
picnic_impl.o setBit T
picnic_impl.o setBitInWordArray T
picnic_impl.o setChallenge T
picnic_impl.o sign_picnic1 T
picnic_impl.o verify T
picnic_impl.o verifyProof T
picnic_impl.o xor_array T
picnic_impl.o xor_three T
picnic_impl.o zeroTrailingBits T
picnic_types.o allocateCommitments T
picnic_types.o allocateCommitments2 T
picnic_types.o allocateGCommitments T
picnic_types.o allocateInputs T
picnic_types.o allocateMsgs T
picnic_types.o allocateProof T
picnic_types.o allocateProof2 T
picnic_types.o allocateRandomTape T
picnic_types.o allocateSeeds T
picnic_types.o allocateShares T
picnic_types.o allocateSignature T
picnic_types.o allocateSignature2 T
picnic_types.o allocateView T
picnic_types.o allocateViews T
picnic_types.o freeCommitments T
picnic_types.o freeCommitments2 T
picnic_types.o freeGCommitments T
picnic_types.o freeInputs T
picnic_types.o freeMsgs T
picnic_types.o freeProof T
picnic_types.o freeProof2 T
picnic_types.o freeRandomTape T
picnic_types.o freeSeeds T
picnic_types.o freeShares T
picnic_types.o freeSignature T
picnic_types.o freeSignature2 T
picnic_types.o freeView T
picnic_types.o freeViews T
picnic_types.o getTapeSizeBytes T
tree.o addMerkleNodes T
tree.o buildMerkleTree T
tree.o createTree T
tree.o exists T
tree.o expandSeeds T
tree.o freeTree T
tree.o generateSeeds T
tree.o getLeaf T
tree.o getLeaves T
tree.o getParent T
tree.o getSibling T
tree.o hasLeftChild T
tree.o hasRightChild T
tree.o hasSibling T
tree.o hashSeed T
tree.o isLeafNode T
tree.o isLeftChild T
tree.o openMerkleTree T
tree.o openMerkleTreeSize T
tree.o printLeaves T
tree.o printSeeds T
tree.o reconstructSeeds T
tree.o revealSeeds T
tree.o revealSeedsSize T
tree.o verifyMerkleTree T

Number of similar (compiler,implementation) pairs: 5, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE ref
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE ref
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE ref
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE ref
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE ref

Namespace violations

Implementation: crypto_sign/picnicl3ur/optimizedct/c
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
bitstream.o bitstream_get_bits T
bitstream.o bitstream_get_bits_32 T
bitstream.o bitstream_get_bits_8 T
bitstream.o bitstream_put_bits T
bitstream.o bitstream_put_bits_32 T
bitstream.o bitstream_put_bits_8 T
io.o mzd_from_char_array T
io.o mzd_to_char_array T
lowmc.o lowmc_get_implementation T
lowmc.o lowmc_store_get_implementation T
lowmc_192_192_30.o lowmc_192_192_30 D
mpc_lowmc.o get_zkbpp_lowmc_implementation T
mpc_lowmc.o get_zkbpp_lowmc_verify_implementation T
mpc_lowmc.o get_zkbpp_share_implentation T
mzd_additional.o mzd_addmul_v_uint64_128 T
mzd_additional.o mzd_addmul_v_uint64_129 T
mzd_additional.o mzd_addmul_v_uint64_192 T
mzd_additional.o mzd_addmul_v_uint64_256 T
mzd_additional.o mzd_addmul_v_uint64_30_192 T
mzd_additional.o mzd_and_uint64_128 T
mzd_additional.o mzd_and_uint64_192 T
mzd_additional.o mzd_and_uint64_256 T
mzd_additional.o mzd_copy_uint64_128 T
mzd_additional.o mzd_copy_uint64_192 T
mzd_additional.o mzd_copy_uint64_256 T
mzd_additional.o mzd_local_free T
mzd_additional.o mzd_local_free_multiple T
mzd_additional.o mzd_local_init_ex T
mzd_additional.o mzd_local_init_multiple_ex T
mzd_additional.o mzd_mul_v_parity_uint64_192_30 T
mzd_additional.o mzd_mul_v_uint64_128 T
mzd_additional.o mzd_mul_v_uint64_129 T
mzd_additional.o mzd_mul_v_uint64_192 T
mzd_additional.o mzd_mul_v_uint64_192_960 T
mzd_additional.o mzd_mul_v_uint64_256 T
mzd_additional.o mzd_shift_left_uint64_128 T
mzd_additional.o mzd_shift_left_uint64_192 T
mzd_additional.o mzd_shift_left_uint64_256 T
mzd_additional.o mzd_shift_right_uint64_128 T
mzd_additional.o mzd_shift_right_uint64_192 T
mzd_additional.o mzd_shift_right_uint64_256 T
mzd_additional.o mzd_shuffle_192_30 T
mzd_additional.o mzd_xor_uint64_128 T
mzd_additional.o mzd_xor_uint64_192 T
mzd_additional.o mzd_xor_uint64_256 T
mzd_additional.o mzd_xor_uint64_960 T
picnic.o picnic_get_lowmc_block_size T
picnic.o picnic_get_param_name T
picnic.o picnic_get_private_key_size T
picnic.o picnic_get_public_key_size T
picnic.o picnic_keygen T
picnic.o picnic_read_private_key T
picnic.o picnic_read_public_key T
picnic.o picnic_sign T
picnic.o picnic_signature_size T
picnic.o picnic_sk_to_pk T
picnic.o picnic_validate_keypair T
picnic.o picnic_verify T
picnic.o picnic_write_private_key T
picnic.o picnic_write_public_key T
picnic_impl.o impl_sign T
picnic_impl.o impl_verify T
picnic_instances.o picnic_instance_get T
randomness.o rand_bits T
randomness.o rand_bytes T

Number of similar (compiler,implementation) pairs: 5, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE optimizedct/c
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE optimizedct/c
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE optimizedct/c
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE optimizedct/c
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE optimizedct/c

Namespace violations

Implementation: crypto_sign/picnicl3ur/optimizedct/neon
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE
bitstream.o bitstream_get_bits T
bitstream.o bitstream_get_bits_32 T
bitstream.o bitstream_get_bits_8 T
bitstream.o bitstream_put_bits T
bitstream.o bitstream_put_bits_32 T
bitstream.o bitstream_put_bits_8 T
io.o mzd_from_char_array T
io.o mzd_to_char_array T
lowmc.o lowmc_get_implementation T
lowmc.o lowmc_store_get_implementation T
lowmc_192_192_30.o lowmc_192_192_30 D
mpc_lowmc.o get_zkbpp_lowmc_implementation T
mpc_lowmc.o get_zkbpp_lowmc_verify_implementation T
mpc_lowmc.o get_zkbpp_share_implentation T
mzd_additional.o mzd_addmul_v_s128_128 T
mzd_additional.o mzd_addmul_v_s128_129 T
mzd_additional.o mzd_addmul_v_s128_192 T
mzd_additional.o mzd_addmul_v_s128_256 T
mzd_additional.o mzd_addmul_v_s128_30_192 T
mzd_additional.o mzd_addmul_v_uint64_128 T
mzd_additional.o mzd_addmul_v_uint64_129 T
mzd_additional.o mzd_addmul_v_uint64_192 T
mzd_additional.o mzd_addmul_v_uint64_256 T
mzd_additional.o mzd_addmul_v_uint64_30_192 T
mzd_additional.o mzd_and_s128_128 T
mzd_additional.o mzd_and_s128_256 T
mzd_additional.o mzd_and_uint64_128 T
mzd_additional.o mzd_and_uint64_192 T
mzd_additional.o mzd_and_uint64_256 T
mzd_additional.o mzd_copy_s128_128 T
mzd_additional.o mzd_copy_s128_256 T
mzd_additional.o mzd_copy_uint64_128 T
mzd_additional.o mzd_copy_uint64_192 T
mzd_additional.o mzd_copy_uint64_256 T
mzd_additional.o mzd_local_free T
mzd_additional.o mzd_local_free_multiple T
mzd_additional.o mzd_local_init_ex T
mzd_additional.o mzd_local_init_multiple_ex T
mzd_additional.o mzd_mul_v_parity_uint64_192_30 T
mzd_additional.o mzd_mul_v_s128_128 T
mzd_additional.o mzd_mul_v_s128_129 T
mzd_additional.o mzd_mul_v_s128_192 T
mzd_additional.o mzd_mul_v_s128_192_1024 T
mzd_additional.o mzd_mul_v_s128_256 T
mzd_additional.o mzd_mul_v_uint64_128 T
mzd_additional.o mzd_mul_v_uint64_129 T
mzd_additional.o mzd_mul_v_uint64_192 T
mzd_additional.o mzd_mul_v_uint64_192_960 T
mzd_additional.o mzd_mul_v_uint64_256 T
mzd_additional.o mzd_shift_left_uint64_128 T
mzd_additional.o mzd_shift_left_uint64_192 T
mzd_additional.o mzd_shift_left_uint64_256 T
mzd_additional.o mzd_shift_right_uint64_128 T
mzd_additional.o mzd_shift_right_uint64_192 T
mzd_additional.o mzd_shift_right_uint64_256 T
mzd_additional.o mzd_shuffle_192_30 T
mzd_additional.o mzd_xor_s128_1024 T
mzd_additional.o mzd_xor_s128_128 T
mzd_additional.o mzd_xor_s128_256 T
mzd_additional.o mzd_xor_uint64_128 T
mzd_additional.o mzd_xor_uint64_192 T
mzd_additional.o mzd_xor_uint64_256 T
mzd_additional.o mzd_xor_uint64_960 T
picnic.o picnic_get_lowmc_block_size T
picnic.o picnic_get_param_name T
picnic.o picnic_get_private_key_size T
picnic.o picnic_get_public_key_size T
picnic.o picnic_keygen T
picnic.o picnic_read_private_key T
picnic.o picnic_read_public_key T
picnic.o picnic_sign T
picnic.o picnic_signature_size T
picnic.o picnic_sk_to_pk T
picnic.o picnic_validate_keypair T
picnic.o picnic_verify T
picnic.o picnic_write_private_key T
picnic.o picnic_write_public_key T
picnic_impl.o impl_sign T
picnic_impl.o impl_verify T
picnic_instances.o picnic_instance_get T
randomness.o rand_bits T
randomness.o rand_bytes T

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE optimizedct/neon
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE optimizedct/neon
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE optimizedct/neon
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE optimizedct/neon