Implementation notes: amd64, kizomba, crypto_sign/picnicl5fs

Computer: kizomba
Microarchitecture: amd64; Kaby Lake (906e9)
Architecture: amd64
CPU ID: GenuineIntel-000906e9-1fc9cbf5
SUPERCOP version: 20240625
Operation: crypto_sign
Primitive: picnicl5fs

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
33639250	186060 960 0	329635 1856 1680	`optimizedct/avx2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
34600159	181394 960 0	324707 1856 1648	`optimizedct/avx2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
36702514	180966 976 0	323438 1824 1680	`optimizedct/avx2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
40933711	170033 976 0	310414 1824 1680	`optimizedct/avx2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
41286924	180710 960 0	322899 1856 1616	`optimizedct/avx2`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
41565498	170835 976 0	311766 1824 1680	`optimizedct/avx2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
41789925	167593 960 0	307675 1856 1616	`optimizedct/avx2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
43236463	163277 976 0	302462 1816 1648	`optimizedct/avx2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
47116194	163648 960 0	304477 1848 1680	`optimizedct/avx2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
49674442	174947 960 0	313678 1848 1640	`optimizedct/sse2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
49736841	172537 960 0	310926 1848 1608	`optimizedct/sse2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
55304387	169344 976 0	306849 1816 1640	`optimizedct/sse2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
55998942	163726 976 0	299689 1816 1640	`optimizedct/sse2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
57212623	162930 976 0	298337 1816 1640	`optimizedct/sse2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
57638014	169575 960 0	306870 1848 1576	`optimizedct/sse2`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
58405050	165201 976 0	302577 1816 1640	`optimizedct/c`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
58698000	157321 976 0	291513 1808 1608	`optimizedct/sse2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
62267708	168484 960 0	307062 1848 1640	`optimizedct/c`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
62276341	166618 960 0	304886 1848 1608	`optimizedct/c`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
70031851	160650 960 0	295766 1848 1576	`optimizedct/sse2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
71195196	164665 960 0	301854 1848 1576	`optimizedct/c`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
72443415	157228 960 0	293176 1840 1640	`optimizedct/sse2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
92399020	161196 976 0	297089 1816 1640	`optimizedct/c`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
92625765	157395 960 0	292414 1848 1576	`optimizedct/c`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
94911704	154468 960 0	290272 1840 1640	`optimizedct/c`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
96749847	160564 976 0	295865 1816 1640	`optimizedct/c`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
110526016	155136 976 0	289193 1808 1608	`optimizedct/c`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
851526575	1291271 4 0	1324500 888 1576	`T:ref`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
895147555	1300236 4 0	1334828 888 1640	`T:ref`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
1003671971	1294194 4 0	1329084 888 1608	`T:ref`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
1041103504	1272740 4 0	1303796 888 1576	`T:ref`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
1041628403	1261680 4 0	1293414 880 1640	`T:ref`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
1153511635	1282721 4 0	1316907 856 1640	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
1176518448	1268477 4 0	1300587 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)`