Implementation notes: aarch64, pi4b, crypto_aead/ketjemajorv2

Computer: pi4b
Microarchitecture: aarch64; Cortex-A72 (410fd083)
Architecture: aarch64
CPU ID: 410fd083
SUPERCOP version: 20240716
Operation: crypto_aead
Primitive: ketjemajorv2

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
42654	7413 0 0	27259 872 864	`T:ARMv8A`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
42654	7413 0 0	28371 872 880	`T:ARMv8A`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
42654	7361 0 0	27403 872 864	`T:ARMv8A`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
42654	7013 0 0	25339 856 856	`T:ARMv8A`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
74676	45709 0 0	67497 896 872	`T:generic64`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
78232	47957 0 0	69745 896 872	`T:generic64lc`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
81788	47329 0 0	68370 880 880	`T:generic64`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
85344	48573 0 0	69618 880 880	`T:generic64lc`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
86233	46061 0 0	66034 880 864	`T:generic64`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
91567	46365 0 0	66338 880 864	`T:generic64lc`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
99568	42293 0 0	60818 864 856	`T:generic64lc`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
100457	44213 0 0	64258 880 864	`T:generic64`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
101346	44909 0 0	64954 880 864	`T:generic64lc`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
104013	47441 0 0	65962 864 856	`T:generic64`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
170616	8433 0 0	30217 896 872	`T:compact`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
184834	11499 0 0	32467 872 880	`T:compact`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
214249	18861 0 0	40633 896 872	`T:generic32`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
227488	18585 0 0	38586 880 864	`T:generic32`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
227488	21717 0 0	42770 880 880	`T:generic32`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
230251	15273 0 0	33794 864 856	`T:generic32`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
232918	15753 0 0	35818 880 864	`T:generic32`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
255924	6834 0 0	26755 872 864	`T:compact`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
369668	6942 0 0	26923 872 864	`T:compact`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
469194	6077 0 0	24531 856 856	`T:compact`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
3395980	84362 1192 47	97130 1904 960	`T:ref`	`g++_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
4992624	63539 1192 47	81362 1920 944	`T:ref`	`g++_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
7262241	59203 1192 47	84896 1920 944	`T:ref`	`g++_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625
9595866	47016 1192 47	63941 1872 904	`T:ref`	`g++_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240629	20240625

Compiler output

KeccakP-1600-armv8a-neon.s: <instantiation>:18:18: error: invalid operand for instruction
KeccakP-1600-armv8a-neon.s:     mov     v5.2d[0], v0.2d[1]            // v5 = (A[4] ^ A[14]) || ????
KeccakP-1600-armv8a-neon.s:                  ^
KeccakP-1600-armv8a-neon.s: KeccakP-1600-armv8a-neon.s:524:5: note: while in macro instantiation
KeccakP-1600-armv8a-neon.s:     KeccakRound
KeccakP-1600-armv8a-neon.s:     ^
KeccakP-1600-armv8a-neon.s: <instantiation>:23:18: error: invalid operand for instruction
KeccakP-1600-armv8a-neon.s:     mov     v4.2d[1], v3.2d[0]            // v4 = B[4] || B[3]
KeccakP-1600-armv8a-neon.s:                  ^
KeccakP-1600-armv8a-neon.s: KeccakP-1600-armv8a-neon.s:524:5: note: while in macro instantiation
KeccakP-1600-armv8a-neon.s:     KeccakRound
KeccakP-1600-armv8a-neon.s:     ^
KeccakP-1600-armv8a-neon.s: <instantiation>:57:18: error: invalid operand for instruction
KeccakP-1600-armv8a-neon.s:     mov     x11, v20.2d[0]                // x11   = A[1]
KeccakP-1600-armv8a-neon.s:                  ^
KeccakP-1600-armv8a-neon.s: KeccakP-1600-armv8a-neon.s:524:5: note: while in macro instantiation
KeccakP-1600-armv8a-neon.s:     KeccakRound
KeccakP-1600-armv8a-neon.s:     ^
KeccakP-1600-armv8a-neon.s: <instantiation>:2:18: error: invalid operand for instruction
KeccakP-1600-armv8a-neon.s:     mov     x10, v25.2d[0]
KeccakP-1600-armv8a-neon.s:                  ^
KeccakP-1600-armv8a-neon.s: <instantiation>:59:5: note: while in macro instantiation
KeccakP-1600-armv8a-neon.s:     RhoPi   v25.2d[0], x11, x10, 1        // A[10] = ROTL64(A[1], 1)
KeccakP-1600-armv8a-neon.s:     ^
KeccakP-1600-armv8a-neon.s: KeccakP-1600-armv8a-neon.s:524:5: note: while in macro instantiation
KeccakP-1600-armv8a-neon.s: ...

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`T:ARMv8A`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`

Compiler output

Keccak-f.cpp: In file included from Keccak-f.cpp:17:
Keccak-f.cpp: Keccak-f.h: In instantiation of 'void KeccakF::forward(std::vector<Lane>&) const [with Lane = long long unsigned int]':
Keccak-f.cpp: Keccak-f.cpp:175:12:   required from here
Keccak-f.cpp: Keccak-f.h:473:33: warning: comparison of integer expressions of different signedness: 'int' and 'unsigned int' [-Wsign-compare]
Keccak-f.cpp:   473 |     for(int i=startRoundIndex; i<startRoundIndex+nrRounds; i++)
Keccak-f.cpp:       |                                ~^~~~~~~~~~~~~~~~~~~~~~~~~

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

Implementation	Compiler
`T:ref`	`g++ -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`T:ref`	`g++ -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`T:ref`	`g++ -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`T:ref`	`g++ -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`