Implementation notes: amd64, speed2supercop, crypto_sign/picnicl1ur

Computer: speed2supercop
Microarchitecture: amd64; Haswell+AES (306c3)
Architecture: amd64
CPU ID: GenuineIntel-000306c3-1fc9cbf5
SUPERCOP version: 20240625
Operation: crypto_sign
Primitive: picnicl1ur

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
10633272	90767 528 0	232189 1392 1632	`optimizedct/avx2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
10728272	93462 528 0	235053 1392 1632	`optimizedct/avx2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
11367348	88225 544 0	227915 1360 1664	`optimizedct/avx2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
11747964	72062 528 0	210623 1384 1664	`optimizedct/avx2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
12006048	89591 528 0	229893 1392 1600	`optimizedct/avx2`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
12190260	76894 528 0	214637 1392 1600	`optimizedct/avx2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
12839716	77388 544 0	215723 1360 1664	`optimizedct/avx2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
13261916	76618 544 0	214643 1360 1664	`optimizedct/avx2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
13813056	69367 544 0	206435 1352 1632	`optimizedct/avx2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
14193556	83235 528 0	219437 1384 1600	`optimizedct/sse2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
14234284	80722 528 0	216733 1384 1600	`optimizedct/sse2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
14564692	77005 544 0	211243 1352 1632	`optimizedct/sse2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
15048868	70335 544 0	203251 1352 1632	`optimizedct/sse2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
15445132	65486 528 0	198702 1376 1632	`optimizedct/sse2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
15470724	69749 544 0	202299 1352 1632	`optimizedct/sse2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
15658976	69905 528 0	202205 1384 1568	`optimizedct/sse2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
15812936	79215 528 0	214109 1384 1568	`optimizedct/sse2`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
15859584	73759 544 0	207891 1352 1632	`optimizedct/c`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
15961372	76952 528 0	213061 1384 1600	`optimizedct/c`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
15995532	74993 528 0	210869 1384 1600	`optimizedct/c`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
16832872	67954 544 0	200715 1352 1632	`optimizedct/c`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
17084560	63731 544 0	195275 1344 1600	`optimizedct/sse2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
17726392	74192 528 0	208949 1384 1568	`optimizedct/c`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
18109168	67501 544 0	199955 1352 1632	`optimizedct/c`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
18500252	66906 528 0	199029 1384 1568	`optimizedct/c`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
19092560	62947 528 0	196038 1376 1632	`optimizedct/c`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
21541236	61623 544 0	193075 1344 1600	`optimizedct/c`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
119642212	1272371 4 0	1301486 864 1568	`T:ref`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
122543876	1292102 4 0	1325182 864 1600	`T:ref`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
123856728	1285885 4 0	1317710 864 1568	`T:ref`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
125773352	1261765 4 0	1291671 856 1632	`T:ref`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
129674868	1287832 4 0	1320926 864 1600	`T:ref`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
137385112	1266264 4 0	1296029 824 1632	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
140543008	1281807 4 0	1313541 824 1632	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
170096316	1261285 4 0	1290733 824 1632	`T:ref`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
175151588	1255905 4 0	1284229 816 1600	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-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)`