Implementation notes: amd64, speed2supercop, crypto_sign/picnicl3fs

Computer: speed2supercop
Microarchitecture: amd64; Haswell+AES (306c3)
Architecture: amd64
CPU ID: GenuineIntel-000306c3-1fc9cbf5
SUPERCOP version: 20240625
Operation: crypto_sign
Primitive: picnicl3fs

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
20215252	145561 768 0	287509 1632 1632	`optimizedct/avx2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
20548984	149992 768 0	292077 1632 1632	`optimizedct/avx2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
21144680	141884 784 0	282075 1600 1664	`optimizedct/avx2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
23457312	131207 784 0	270067 1600 1664	`optimizedct/avx2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
23951040	131688 768 0	269949 1632 1600	`optimizedct/avx2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
24277132	130455 784 0	268987 1600 1664	`optimizedct/avx2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
24583904	145217 768 0	286085 1632 1600	`optimizedct/avx2`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
24702876	126738 768 0	265903 1624 1664	`optimizedct/avx2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
25542068	124897 784 0	262419 1592 1632	`optimizedct/avx2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
28832132	135534 768 0	272020 1624 1600	`optimizedct/sse2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
29893828	139165 768 0	275852 1624 1600	`optimizedct/sse2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
31166784	130532 784 0	265275 1592 1632	`optimizedct/sse2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
31607004	124347 784 0	257723 1592 1632	`optimizedct/sse2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
32414252	123760 784 0	256835 1592 1632	`optimizedct/sse2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
33149772	126615 784 0	261195 1592 1632	`optimizedct/c`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
34773944	134362 768 0	269789 1624 1568	`optimizedct/sse2`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
36297928	119226 784 0	251203 1584 1600	`optimizedct/sse2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
36530984	129645 768 0	266028 1624 1600	`optimizedct/c`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
36767476	133276 768 0	269860 1624 1600	`optimizedct/c`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
39686512	124817 768 0	257581 1624 1568	`optimizedct/sse2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
40950192	120318 768 0	254014 1616 1632	`optimizedct/sse2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
42872812	129705 768 0	265013 1624 1568	`optimizedct/c`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
47636576	122008 784 0	255251 1592 1632	`optimizedct/c`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
47915884	121656 768 0	254333 1624 1568	`optimizedct/c`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
49237076	117663 768 0	251278 1616 1632	`optimizedct/c`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
49951036	121550 784 0	254491 1592 1632	`optimizedct/c`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
59166164	117180 784 0	249075 1584 1600	`optimizedct/c`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
433533368	1285885 4 0	1317710 864 1568	`T:ref`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
456528364	1272371 4 0	1301550 864 1568	`T:ref`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
457637876	1261765 4 0	1291671 856 1632	`T:ref`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
470923292	1292102 4 0	1325182 864 1600	`T:ref`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
493370280	1281807 4 0	1313541 824 1632	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
494151000	1287832 4 0	1320990 864 1600	`T:ref`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
496571836	1266264 4 0	1296029 824 1632	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
558251488	1255905 4 0	1284229 816 1600	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
602457628	1261285 4 0	1290733 824 1632	`T:ref`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	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 (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/avx2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/avx2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/avx2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/avx2`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`

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 (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/sse2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/sse2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/sse2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/sse2`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`

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 *[3]' {aka 'unsigned int *[3]'}
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 *[3]' {aka 'unsigned int *[3]'}
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 *[3]' {aka 'unsigned int *[3]'}
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 *[3]' {aka 'unsigned int *[3]'}
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 *[3]' {aka 'unsigned int *[3]'}
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 *[3]' {aka 'unsigned int *[3]'}
picnic_impl.c: ...

Number of similar (implementation,compiler) pairs: 4, namely:

Implementation	Compiler
`T:ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`T:ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`T:ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`T:ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`

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 (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/avx2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/avx2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/avx2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/avx2`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/avx2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`optimizedct/avx2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`optimizedct/avx2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`optimizedct/avx2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`optimizedct/c`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/c`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/c`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/c`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/c`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/c`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`optimizedct/c`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`optimizedct/c`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`optimizedct/c`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`optimizedct/sse2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/sse2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/sse2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/sse2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/sse2`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`optimizedct/sse2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`optimizedct/sse2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`optimizedct/sse2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`optimizedct/sse2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`