Implementation notes: aarch64, pi4b, crypto_aead/lunarkeyakv2

Computer: pi4b
Microarchitecture: aarch64; Cortex-A72 (410fd083)
Architecture: aarch64
CPU ID: 410fd083
SUPERCOP version: 20240107
Operation: crypto_aead
Primitive: lunarkeyakv2

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
90069	96866 0 0	98707 808 840	`T:generic64lc`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
91266	118364 0 0	117842 840 856	`T:generic64`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231225	20231222
91560	113844 0 0	115251 824 864	`T:generic64`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
92107	122440 0 0	121914 840 856	`T:generic64lc`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231225	20231222
92437	109524 0 0	111163 824 848	`T:generic64`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
92923	110556 0 0	112187 824 848	`T:generic64lc`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
93086	115888 0 0	117291 824 864	`T:generic64lc`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
95192	103730 0 0	105579 808 840	`T:generic64`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
96346	108312 0 0	109243 824 848	`T:generic64`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
96489	109572 0 0	114619 824 848	`T:generic64lc`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
115695	69139 0 12	65749 856 856	`T:reference`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231225	20231222
120252	60232 0 0	62426 840 856	`T:compact`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231225	20231222
151864	57304 0 0	59227 824 864	`T:ARMv8A`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
151869	54764 0 0	57427 824 848	`T:ARMv8A`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
152475	46550 0 0	49203 808 840	`T:ARMv8A`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
153392	55760 0 0	61859 824 848	`T:ARMv8A`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
200786	61218 0 12	59334 840 864	`T:reference`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
219928	62322 0 0	64779 824 864	`T:compact`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
266020	78284 0 0	77754 840 856	`T:generic32lc`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231225	20231222
266149	76488 0 0	75962 840 856	`T:generic32`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231225	20231222
272442	66308 0 0	67354 832 848	`T:generic32lc`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
272960	65472 0 0	66514 832 848	`T:generic32`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
287243	56198 0 0	58162 816 840	`T:generic32`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
287744	56770 0 0	58722 816 840	`T:generic32lc`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
300856	75020 0 0	76522 832 864	`T:generic32lc`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
300995	73612 0 0	75114 832 864	`T:generic32`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
312323	67268 0 0	68994 832 848	`T:generic32`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
312493	68172 0 0	69898 832 848	`T:generic32lc`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
490826	51141 0 0	54539 824 848	`T:compact`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
519971	51945 0 0	54939 824 848	`T:compact`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
615200	42540 0 0	45939 808 840	`T:compact`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
965706	57979 0 12	61102 840 848	`T:reference`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
1095793	48341 0 12	52259 824 840	`T:reference`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
1474238	59447 0 12	57854 840 848	`T:reference`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
2859478	58895 648 5	83718 1848 904	`T:refnew`	`g++_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
2873667	57268 552 5	82005 1752 904	`T:ref`	`g++_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
3445691	46108 648 5	70515 1872 888	`T:refnew`	`g++_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
3489563	44519 552 5	68822 1768 888	`T:ref`	`g++_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
3779866	72364 0 12	69013 856 856	`T:reference32bits`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231225	20231222
4253802	65629 0 12	63854 840 864	`T:reference32bits`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
5867316	60795 0 12	68070 840 848	`T:reference32bits`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
6008592	50517 0 12	54483 824 840	`T:reference32bits`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
6505925	61903 0 12	60382 840 848	`T:reference32bits`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
6557819	25271 648 5	47762 1808 840	`T:refnew`	`g++_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
6611761	24859 552 5	47104 1712 840	`T:ref`	`g++_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
6888988	43912 552 5	67846 1768 888	`T:ref`	`g++_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222
6907194	45108 648 5	69148 1872 888	`T:refnew`	`g++_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231225	20231222

Compiler output

Implementation: T:ARMv8A
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

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:511:5: 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:511:5: 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:511:5: 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:511:5: note: while in macro instantiation
KeccakP-1600-armv8a-neon.s: ...

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

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:ARMv8A

Compiler output

Implementation: T:compact
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

KeccakP-200-compact.c: KeccakP-200-compact.c:20:36: warning: '/*' within block comment [-Wcomment]
KeccakP-200-compact.c: /* #define DIVISION_INSTRUCTION /* comment if no division instruction or more compact when not using division */
KeccakP-200-compact.c: ^
KeccakP-200-compact.c: 1 warning generated.
KeccakP-800-compact.c: KeccakP-800-compact.c:27:36: warning: '/*' within block comment [-Wcomment]
KeccakP-800-compact.c: /* #define DIVISION_INSTRUCTION /* comment if no division instruction or more compact when not using division */
KeccakP-800-compact.c: ^
KeccakP-800-compact.c: 1 warning generated.

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

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:compact

Compiler output

Implementation: T:ref
Security model: timingleaks
Compiler: g++ -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

Keyakv2.cpp: In file included from Keyakv2.h:21,
Keyakv2.cpp: from Keyakv2.cpp:16:
Keyakv2.cpp: Motorist.h:31:5: warning: 'template<class> class std::auto_ptr' is deprecated: use 'std::unique_ptr' instead [-Wdeprecated-declarations]
Keyakv2.cpp: 31 | auto_ptr<UINT8> state;
Keyakv2.cpp: | ^~~~~~~~
Keyakv2.cpp: In file included from /usr/include/c++/11/memory:76,
Keyakv2.cpp: from Motorist.h:20,
Keyakv2.cpp: from Keyakv2.h:21,
Keyakv2.cpp: from Keyakv2.cpp:16:
Keyakv2.cpp: /usr/include/c++/11/bits/unique_ptr.h:57:28: note: declared here
Keyakv2.cpp: 57 | template<typename> class auto_ptr;
Keyakv2.cpp: | ^~~~~~~~
Motorist.cpp: In file included from Motorist.cpp:17:
Motorist.cpp: Motorist.h:31:5: warning: 'template<class> class std::auto_ptr' is deprecated: use 'std::unique_ptr' instead [-Wdeprecated-declarations]
Motorist.cpp: 31 | auto_ptr<UINT8> state;
Motorist.cpp: | ^~~~~~~~
Motorist.cpp: In file included from /usr/include/c++/11/memory:76,
Motorist.cpp: from Motorist.h:20,
Motorist.cpp: from Motorist.cpp:17:
Motorist.cpp: /usr/include/c++/11/bits/unique_ptr.h:57:28: note: declared here
Motorist.cpp: 57 | template<typename> class auto_ptr;
Motorist.cpp: | ^~~~~~~~
encrypt.cpp: In file included from Keyakv2.h:21,
encrypt.cpp: from encrypt.cpp:22:
encrypt.cpp: Motorist.h:31:5: warning: 'template<class> class std::auto_ptr' is deprecated: use 'std::unique_ptr' instead [-Wdeprecated-declarations]
encrypt.cpp: 31 | auto_ptr<UINT8> state;
encrypt.cpp: | ^~~~~~~~
encrypt.cpp: In file included from /usr/include/c++/11/memory:76,
encrypt.cpp: from Motorist.h:20,
encrypt.cpp: from Keyakv2.h:21,
encrypt.cpp: from encrypt.cpp:22:
encrypt.cpp: /usr/include/c++/11/bits/unique_ptr.h:57:28: note: declared here
encrypt.cpp: 57 | template<typename> class auto_ptr;
encrypt.cpp: | ^~~~~~~~

Number of similar (compiler,implementation) pairs: 8, namely:

Compiler	Implementations
g++ -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ref
g++ -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ref
g++ -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ref
g++ -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ref
g++ -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:refnew
g++ -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:refnew
g++ -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:refnew
g++ -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:refnew