Implementation notes: amd64, hydra8, crypto_sign/picnicl5fs

Computer: hydra8
Microarchitecture: amd64; Ivy Bridge+AES (306a9)
Architecture: amd64
CPU ID: GenuineIntel-000306a9-bfebfbff
SUPERCOP version: 20240625
Operation: crypto_sign
Primitive: picnicl5fs

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
74526375	166834 960 0	325266 1892 1728	`optimizedct/sse2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
74898870	176169 960 0	339523 1900 1760	`optimizedct/avx2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
75272787	180212 960 0	345515 1900 1760	`optimizedct/avx2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
75303917	169085 960 0	329466 1892 1728	`optimizedct/sse2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
78030947	180782 960 0	344715 1900 1760	`optimizedct/avx2`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
78493534	169647 960 0	328650 1892 1728	`optimizedct/sse2`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
78664210	168459 976 0	326888 1844 1792	`optimizedct/sse2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
79067881	180554 976 0	343985 1852 1824	`optimizedct/avx2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
79838835	170091 976 0	332697 1852 1824	`optimizedct/avx2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
80250043	162559 976 0	320200 1844 1792	`optimizedct/sse2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
83013078	162154 976 0	319288 1844 1792	`optimizedct/sse2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
83630018	169591 976 0	331713 1852 1824	`optimizedct/avx2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
84220891	164289 976 0	322616 1844 1792	`optimizedct/c`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
85196180	163905 976 0	324785 1844 1792	`optimizedct/avx2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
85302701	157496 976 0	313328 1836 1760	`optimizedct/sse2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
90379007	164375 960 0	324642 1892 1728	`optimizedct/c`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
90574331	162668 960 0	321018 1892 1728	`optimizedct/c`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
90971903	168218 960 0	330155 1900 1760	`optimizedct/avx2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
91297685	161041 960 0	317978 1892 1728	`optimizedct/sse2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
92234030	156676 960 0	313324 1884 1728	`optimizedct/sse2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
92315155	163295 960 0	324917 1892 1760	`optimizedct/avx2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
93416318	164737 960 0	323634 1892 1728	`optimizedct/c`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
116242427	157773 960 0	314626 1892 1728	`optimizedct/c`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
116433548	160028 976 0	317536 1844 1792	`optimizedct/c`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
119306800	153910 960 0	310420 1884 1728	`optimizedct/c`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
128071881	159788 976 0	316816 1844 1792	`optimizedct/c`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
154961586	155310 976 0	311072 1836 1760	`optimizedct/c`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
1029776500	1291551 4 0	1387811 940 1728	`T:ref`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
1167416564	1292611 4 0	1390203 940 1728	`T:ref`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
1206070573	1287032 4 0	1383019 940 1728	`T:ref`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
1300777390	1282325 4 0	1378450 884 1792	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
1418397507	1273086 4 0	1367227 940 1728	`T:ref`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
1424893208	1262359 4 0	1356117 932 1728	`T:ref`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
1508830764	1268879 4 0	1363842 884 1792	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	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)`