Implementation notes: amd64, zen3, crypto_hash/keccakc512treed2

Computer: zen3
Architecture: amd64
CPU ID: AuthenticAMD-00a20f10-178bfbff
SUPERCOP version: 20211108
Operation: crypto_hash
Primitive: keccakc512treed2

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
9442	27914 0 0	39256 836 952	`T:sseu4`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220206	20211108
9459	27601 0 0	38568 836 952	`T:sseu4`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220206	20211108
9507	28181 0 0	41480 836 952	`T:sseu4`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220206	20211108
9535	28002 0 0	39312 860 888	`T:sseu4`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220206	20211108
9560	28485 0 0	47800 860 920	`T:sseu4`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220206	20211108
9566	28485 0 0	47560 860 920	`T:sseu4`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220206	20211108
9604	27627 0 0	38718 852 888	`T:sseu4`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20220206	20211108
10291	27363 0 0	37271 812 920	`T:sseu4`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220206	20211108
11492	139077 0 0	152376 836 952	`T:sseu24`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220206	20211108
11574	138326 0 0	149288 836 952	`T:sseu24`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220206	20211108
11607	138522 0 0	149864 836 952	`T:sseu24`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220206	20211108
12178	137767 0 0	147687 812 920	`T:sseu24`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20220206	20211108

Test failure

Implementation: T:sseu24
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

error 111

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

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:sseu24
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:sseu24
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:sseu24
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:sseu24

Compiler output

Implementation: T:sseu24
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

DoublePermutation.c: DoublePermutation.c:507:5: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'KeccakDoublePermutationOnWords' that is compiled without support for 'ssse3'
DoublePermutation.c: rounds
DoublePermutation.c: ^
DoublePermutation.c: ./KeccakF-1600-unrolling.macros:17:5: note: expanded from macro 'rounds'
DoublePermutation.c: thetaRhoPiChiIotaPrepareTheta( 0, A, E) \
DoublePermutation.c: ^
DoublePermutation.c: DoublePermutation.c:136:11: note: expanded from macro 'thetaRhoPiChiIotaPrepareTheta'
DoublePermutation.c: Bko = ROL64in128_8(A##mu); \
DoublePermutation.c: ^
DoublePermutation.c: DoublePermutation.c:38:37: note: expanded from macro 'ROL64in128_8'
DoublePermutation.c: #define ROL64in128_8(a) _mm_shuffle_epi8(a, CONST128(rho8))
DoublePermutation.c: ^
DoublePermutation.c: DoublePermutation.c:507:5: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'KeccakDoublePermutationOnWords' that is compiled without support for 'ssse3'
DoublePermutation.c: ./KeccakF-1600-unrolling.macros:17:5: note: expanded from macro 'rounds'
DoublePermutation.c: thetaRhoPiChiIotaPrepareTheta( 0, A, E) \
DoublePermutation.c: ^
DoublePermutation.c: DoublePermutation.c:161:11: note: expanded from macro 'thetaRhoPiChiIotaPrepareTheta'
DoublePermutation.c: Bmu = ROL64in128_56(A##so); \
DoublePermutation.c: ^
DoublePermutation.c: DoublePermutation.c:39:37: note: expanded from macro 'ROL64in128_56'
DoublePermutation.c: #define ROL64in128_56(a) _mm_shuffle_epi8(a, CONST128(rho56))
DoublePermutation.c: ^
DoublePermutation.c: DoublePermutation.c:507:5: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'KeccakDoublePermutationOnWords' that is compiled without support for 'ssse3'
DoublePermutation.c: ./KeccakF-1600-unrolling.macros:18:5: note: expanded from macro 'rounds'
DoublePermutation.c: thetaRhoPiChiIotaPrepareTheta( 1, E, A) \
DoublePermutation.c: ...

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

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:sseu24

Compiler output

Implementation: T:sseu4
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

DoublePermutation.c: DoublePermutation.c:507:5: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'KeccakDoublePermutationOnWords' that is compiled without support for 'ssse3'
DoublePermutation.c: rounds
DoublePermutation.c: ^
DoublePermutation.c: ./KeccakF-1600-unrolling.macros:90:9: note: expanded from macro 'rounds'
DoublePermutation.c: thetaRhoPiChiIotaPrepareTheta(i , A, E) \
DoublePermutation.c: ^
DoublePermutation.c: DoublePermutation.c:136:11: note: expanded from macro 'thetaRhoPiChiIotaPrepareTheta'
DoublePermutation.c: Bko = ROL64in128_8(A##mu); \
DoublePermutation.c: ^
DoublePermutation.c: DoublePermutation.c:38:37: note: expanded from macro 'ROL64in128_8'
DoublePermutation.c: #define ROL64in128_8(a) _mm_shuffle_epi8(a, CONST128(rho8))
DoublePermutation.c: ^
DoublePermutation.c: DoublePermutation.c:507:5: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'KeccakDoublePermutationOnWords' that is compiled without support for 'ssse3'
DoublePermutation.c: ./KeccakF-1600-unrolling.macros:90:9: note: expanded from macro 'rounds'
DoublePermutation.c: thetaRhoPiChiIotaPrepareTheta(i , A, E) \
DoublePermutation.c: ^
DoublePermutation.c: DoublePermutation.c:161:11: note: expanded from macro 'thetaRhoPiChiIotaPrepareTheta'
DoublePermutation.c: Bmu = ROL64in128_56(A##so); \
DoublePermutation.c: ^
DoublePermutation.c: DoublePermutation.c:39:37: note: expanded from macro 'ROL64in128_56'
DoublePermutation.c: #define ROL64in128_56(a) _mm_shuffle_epi8(a, CONST128(rho56))
DoublePermutation.c: ^
DoublePermutation.c: DoublePermutation.c:507:5: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'KeccakDoublePermutationOnWords' that is compiled without support for 'ssse3'
DoublePermutation.c: ./KeccakF-1600-unrolling.macros:91:9: note: expanded from macro 'rounds'
DoublePermutation.c: thetaRhoPiChiIotaPrepareTheta(i+1, E, A) \
DoublePermutation.c: ...

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

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:sseu4

Compiler output

Implementation: T:xopu24
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

DoublePermutation.c: DoublePermutation.c:507:5: error: '__builtin_ia32_vprotqi' needs target feature xop
DoublePermutation.c: rounds
DoublePermutation.c: ^
DoublePermutation.c: ./KeccakF-1600-unrolling.macros:17:5: note: expanded from macro 'rounds'
DoublePermutation.c: thetaRhoPiChiIotaPrepareTheta( 0, A, E) \
DoublePermutation.c: ^
DoublePermutation.c: DoublePermutation.c:78:21: note: expanded from macro 'thetaRhoPiChiIotaPrepareTheta'
DoublePermutation.c: Da = XOR128(Cu, ROL64in128(Ce, 1)); \
DoublePermutation.c: ^
DoublePermutation.c: DoublePermutation.c:33:37: note: expanded from macro 'ROL64in128'
DoublePermutation.c: #define ROL64in128(a, o) _mm_roti_epi64(a, o)
DoublePermutation.c: ^
DoublePermutation.c: /usr/lib/clang/13.0.0/include/xopintrin.h:237:12: note: expanded from macro '_mm_roti_epi64'
DoublePermutation.c: (__m128i)__builtin_ia32_vprotqi((__v2di)(__m128i)(A), (N))
DoublePermutation.c: ^
DoublePermutation.c: DoublePermutation.c:507:5: error: '__builtin_ia32_vprotqi' needs target feature xop
DoublePermutation.c: ./KeccakF-1600-unrolling.macros:17:5: note: expanded from macro 'rounds'
DoublePermutation.c: thetaRhoPiChiIotaPrepareTheta( 0, A, E) \
DoublePermutation.c: ^
DoublePermutation.c: DoublePermutation.c:79:21: note: expanded from macro 'thetaRhoPiChiIotaPrepareTheta'
DoublePermutation.c: De = XOR128(Ca, ROL64in128(Ci, 1)); \
DoublePermutation.c: ^
DoublePermutation.c: DoublePermutation.c:33:37: note: expanded from macro 'ROL64in128'
DoublePermutation.c: #define ROL64in128(a, o) _mm_roti_epi64(a, o)
DoublePermutation.c: ^
DoublePermutation.c: ...

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:xopu24
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:xopu24
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:xopu24
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:xopu24
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:xopu24

Compiler output

Implementation: T:xopu24
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

DoublePermutation.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/11.1.0/include/x86intrin.h:38,
DoublePermutation.c: from DoublePermutation.c:17:
DoublePermutation.c: DoublePermutation.c: In function ‘KeccakDoublePermutationOnWords’:
DoublePermutation.c: /usr/lib/gcc/x86_64-pc-linux-gnu/11.1.0/include/xopintrin.h:272:1: error: inlining failed in call to ‘always_inline’ ‘_mm_roti_epi64’: target specific option mismatch
DoublePermutation.c: 272 | _mm_roti_epi64(__m128i __A, const int __B)
DoublePermutation.c: | ^~~~~~~~~~~~~~
DoublePermutation.c: DoublePermutation.c:33:37: note: called from here
DoublePermutation.c: 33 | #define ROL64in128(a, o) _mm_roti_epi64(a, o)
DoublePermutation.c: | ^~~~~~~~~~~~~~~~~~~~
DoublePermutation.c: DoublePermutation.c:276:11: note: in expansion of macro ‘ROL64in128’
DoublePermutation.c: 276 | Bsu = ROL64in128(A##se, 2); \
DoublePermutation.c: | ^~~~~~~~~~
DoublePermutation.c: KeccakF-1600-unrolling.macros:40:5: note: in expansion of macro ‘thetaRhoPiChiIota’
DoublePermutation.c: 40 | thetaRhoPiChiIota(23, E, A) \
DoublePermutation.c: | ^~~~~~~~~~~~~~~~~
DoublePermutation.c: DoublePermutation.c:507:5: note: in expansion of macro ‘rounds’
DoublePermutation.c: 507 | rounds
DoublePermutation.c: | ^~~~~~
DoublePermutation.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/11.1.0/include/x86intrin.h:38,
DoublePermutation.c: from DoublePermutation.c:17:
DoublePermutation.c: /usr/lib/gcc/x86_64-pc-linux-gnu/11.1.0/include/xopintrin.h:272:1: error: inlining failed in call to ‘always_inline’ ‘_mm_roti_epi64’: target specific option mismatch
DoublePermutation.c: 272 | _mm_roti_epi64(__m128i __A, const int __B)
DoublePermutation.c: | ^~~~~~~~~~~~~~
DoublePermutation.c: DoublePermutation.c:33:37: note: called from here
DoublePermutation.c: 33 | #define ROL64in128(a, o) _mm_roti_epi64(a, o)
DoublePermutation.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:xopu24
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:xopu24
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:xopu24
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:xopu24