Implementation notes: amd64, bolero, crypto_sign/picnicl5fs

Computer: bolero
Microarchitecture: amd64; Broadwell+AES (406f1)
Architecture: amd64
CPU ID: GenuineIntel-000406f1-1fc9cbf5
SUPERCOP version: 20240625
Operation: crypto_sign
Primitive: picnicl5fs

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
37006688	186094 960 0	328595 1856 1648	`optimizedct/avx2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
37623856	181428 960 0	323603 1856 1648	`optimizedct/avx2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
38153716	179935 976 0	321102 1824 1680	`optimizedct/avx2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
43284884	167593 960 0	306539 1856 1616	`optimizedct/avx2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
44463536	180710 960 0	321795 1856 1616	`optimizedct/avx2`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
44533500	168979 976 0	308166 1824 1680	`optimizedct/avx2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
44647868	163118 960 0	302741 1848 1680	`optimizedct/avx2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
44964664	169544 976 0	309262 1824 1680	`optimizedct/avx2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
45911820	163309 976 0	301326 1816 1648	`optimizedct/avx2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
53758564	174965 960 0	312542 1848 1608	`optimizedct/sse2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
53868964	172555 960 0	309854 1848 1608	`optimizedct/sse2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
57678908	168296 976 0	304449 1816 1640	`optimizedct/sse2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
60650712	169575 960 0	305734 1848 1576	`optimizedct/sse2`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
60822544	162420 976 0	297185 1816 1640	`optimizedct/sse2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
61693020	164131 976 0	300169 1816 1640	`optimizedct/c`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
61824024	161876 976 0	296089 1816 1640	`optimizedct/sse2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
63543384	157332 976 0	290377 1808 1608	`optimizedct/sse2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
67708024	166636 960 0	303814 1848 1608	`optimizedct/c`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
67853256	168502 960 0	305990 1848 1608	`optimizedct/c`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
71695668	156688 960 0	291408 1840 1640	`optimizedct/sse2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
73143776	160650 960 0	294630 1848 1576	`optimizedct/sse2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
75024836	164665 960 0	300718 1848 1576	`optimizedct/c`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
92887296	157395 960 0	291214 1848 1576	`optimizedct/c`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
93480552	153928 960 0	288504 1840 1640	`optimizedct/c`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
101346812	159889 976 0	294521 1816 1640	`optimizedct/c`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
102930820	159510 976 0	293681 1816 1640	`optimizedct/c`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
125389928	155146 976 0	288057 1808 1608	`optimizedct/c`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
911833312	1291271 4 0	1323372 888 1576	`T:ref`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
926478176	1299728 4 0	1333228 888 1608	`T:ref`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
1075751948	1293806 4 0	1327524 888 1608	`T:ref`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
1091368664	1272772 4 0	1302604 888 1576	`T:ref`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
1170915312	1261688 4 0	1292190 880 1640	`T:ref`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
1212666740	1282385 4 0	1315227 856 1640	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
1285191640	1268461 4 0	1299331 856 1640	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625

Compiler output

lowmc.c: lowmc.c:54:20: warning: unused function 'sbox_s128_full' [-Wunused-function]
lowmc.c: static inline void sbox_s128_full(mzd_local_t* in, const word128* mask_a, const word128* mask_b,
lowmc.c:                    ^
lowmc.c: lowmc.c:90:23: warning: unused function 'sbox_s256_lowmc_full' [-Wunused-function]
lowmc.c: static inline word256 sbox_s256_lowmc_full(const word256 min, const word256 mask_a,
lowmc.c:                       ^
lowmc.c: 2 warnings generated.

Number of similar (implementation,compiler) pairs: 5, namely:

Implementation	Compiler
`optimizedct/avx2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/avx2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/avx2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/avx2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/avx2`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`

Compiler output

lowmc.c: lowmc.c:54:20: warning: unused function 'sbox_s128_full' [-Wunused-function]
lowmc.c: static inline void sbox_s128_full(mzd_local_t* in, const word128* mask_a, const word128* mask_b,
lowmc.c:                    ^
lowmc.c: 1 warning generated.

Number of similar (implementation,compiler) pairs: 5, namely:

Implementation	Compiler
`optimizedct/sse2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/sse2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/sse2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/sse2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/sse2`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`

Compiler output

picnic_impl.c: picnic_impl.c: In function 'mpc_LowMC_verify':
picnic_impl.c: picnic_impl.c:533:5: warning: 'mpc_matrix_mul' accessing 24 bytes in a region of size 16 [-Wstringop-overflow=]
picnic_impl.c:   533 |     mpc_matrix_mul(roundKey, keyShares, KMatrix(0, params), params, 2);
picnic_impl.c:       |     ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
picnic_impl.c: picnic_impl.c:533:5: note: referencing argument 1 of type 'uint32_t **' {aka 'unsigned int **'}
picnic_impl.c: picnic_impl.c:533:5: warning: 'mpc_matrix_mul' accessing 24 bytes in a region of size 16 [-Wstringop-overflow=]
picnic_impl.c: picnic_impl.c:533:5: note: referencing argument 2 of type 'uint32_t **' {aka 'unsigned int **'}
picnic_impl.c: picnic_impl.c:506:6: note: in a call to function 'mpc_matrix_mul'
picnic_impl.c:   506 | void mpc_matrix_mul(uint32_t* output[3], uint32_t* state[3], const uint32_t* matrix,
picnic_impl.c:       |      ^~~~~~~~~~~~~~
picnic_impl.c: picnic_impl.c:534:5: warning: 'mpc_xor' accessing 24 bytes in a region of size 16 [-Wstringop-overflow=]
picnic_impl.c:   534 |     mpc_xor(state, roundKey, params->stateSizeWords, 2);
picnic_impl.c:       |     ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
picnic_impl.c: picnic_impl.c:534:5: note: referencing argument 1 of type 'uint32_t **' {aka 'unsigned int **'}
picnic_impl.c: picnic_impl.c:534:5: warning: 'mpc_xor' accessing 24 bytes in a region of size 16 [-Wstringop-overflow=]
picnic_impl.c: picnic_impl.c:534:5: note: referencing argument 2 of type 'uint32_t **' {aka 'unsigned int **'}
picnic_impl.c: picnic_impl.c:260:6: note: in a call to function 'mpc_xor'
picnic_impl.c:   260 | void mpc_xor(uint32_t* state[3], uint32_t* in[3], uint32_t len, int players)
picnic_impl.c:       |      ^~~~~~~
picnic_impl.c: picnic_impl.c:537:9: warning: 'mpc_matrix_mul' accessing 24 bytes in a region of size 16 [-Wstringop-overflow=]
picnic_impl.c:   537 |         mpc_matrix_mul(roundKey, keyShares, KMatrix(r, params), params, 2);
picnic_impl.c:       |         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
picnic_impl.c: picnic_impl.c:537:9: note: referencing argument 1 of type 'uint32_t **' {aka 'unsigned int **'}
picnic_impl.c: picnic_impl.c:537:9: warning: 'mpc_matrix_mul' accessing 24 bytes in a region of size 16 [-Wstringop-overflow=]
picnic_impl.c: picnic_impl.c:537:9: note: referencing argument 2 of type 'uint32_t **' {aka 'unsigned int **'}
picnic_impl.c: ...

Number of similar (implementation,compiler) pairs: 2, namely:

Implementation	Compiler
`T:ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`T:ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`

Passed TIMECOP

TIMECOP iterations: 10

Number of similar (implementation,compiler) pairs: 27, namely:

Implementation	Compiler
`optimizedct/avx2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/avx2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/avx2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/avx2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/avx2`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/avx2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`optimizedct/avx2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`optimizedct/avx2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`optimizedct/avx2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`optimizedct/c`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/c`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/c`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/c`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/c`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/c`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`optimizedct/c`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`optimizedct/c`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`optimizedct/c`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`optimizedct/sse2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/sse2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/sse2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/sse2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/sse2`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`optimizedct/sse2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`optimizedct/sse2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`optimizedct/sse2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`optimizedct/sse2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`