Implementation notes: amd64, genji548, crypto_hash/keccakc256treed2

Computer: genji548
Architecture: amd64
CPU ID: GenuineIntel-00050654-bfebfbff
SUPERCOP version: 20191017
Operation: crypto_hash
Primitive: keccakc256treed2
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
678620585 0 029572 792 776sseu4gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
680421353 0 031284 808 776sseu4gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
681421481 0 034161 816 776sseu4gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
693021080 0 030924 808 776sseu4gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
7618102560 0 0111556 792 776sseu24gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
7696104281 0 0116961 816 776sseu24gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
7702104153 0 0114084 808 776sseu24gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
7732103896 0 0113740 808 776sseu24gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
863827464 0 043381 856 776sseu4icc_-march=skylake-avx512_-mtune=skylake-avx512_-O2_-fomit-frame-pointer2019101920191017
865827416 0 043893 856 776sseu4icc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer2019101920191017
870827528 0 043653 856 776sseu4icc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer2019101920191017
870827592 0 043397 856 776sseu4icc_-march=skylake-avx512_-mtune=skylake-avx512_-O3_-fomit-frame-pointer2019101920191017
976031112 0 046749 856 744sseu4icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer2019101920191017
981231112 0 046749 856 744sseu4icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer2019101920191017
982831112 0 046749 856 744sseu4icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer2019101920191017
986631096 0 046349 856 744sseu4icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer2019101920191017
987031096 0 046349 856 744sseu4icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer2019101920191017
987431096 0 046349 856 744sseu4icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer2019101920191017
987631096 0 046349 856 744sseu4icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer2019101920191017
9952135336 0 0151461 856 776sseu24icc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer2019101920191017
9952135432 0 0151237 856 776sseu24icc_-march=skylake-avx512_-mtune=skylake-avx512_-O3_-fomit-frame-pointer2019101920191017
10034136248 0 0152725 856 776sseu24icc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer2019101920191017
10144136616 0 0152533 856 776sseu24icc_-march=skylake-avx512_-mtune=skylake-avx512_-O2_-fomit-frame-pointer2019101920191017
1064633560 0 048845 856 744sseu4icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer2019101920191017
1070033576 0 048813 856 744sseu4icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer2019101920191017
1071233560 0 048845 856 744sseu4icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer2019101920191017
1071833576 0 048813 856 744sseu4icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer2019101920191017
1075833576 0 048813 856 744sseu4icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer2019101920191017
1076433560 0 048845 856 744sseu4icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer2019101920191017
1083233560 0 048845 856 744sseu4icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer2019101920191017
1083633576 0 048813 856 744sseu4icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer2019101920191017
11442151800 0 0167437 856 744sseu24icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer2019101920191017
11468151800 0 0167437 856 744sseu24icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer2019101920191017
11474151800 0 0167437 856 744sseu24icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer2019101920191017
11480151800 0 0167437 856 744sseu24icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer2019101920191017
11502151784 0 0167037 856 744sseu24icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer2019101920191017
11504151784 0 0167037 856 744sseu24icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer2019101920191017
11512151784 0 0167037 856 744sseu24icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer2019101920191017
11642151784 0 0167037 856 744sseu24icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer2019101920191017
12556164744 0 0179981 856 744sseu24icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer2019101920191017
12558164744 0 0179981 856 744sseu24icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer2019101920191017
12558164744 0 0179981 856 744sseu24icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer2019101920191017
12558164744 0 0179981 856 744sseu24icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer2019101920191017
12580164728 0 0180013 856 744sseu24icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer2019101920191017
12580164728 0 0180013 856 744sseu24icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer2019101920191017
12580164728 0 0180013 856 744sseu24icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer2019101920191017
12582164728 0 0180013 856 744sseu24icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer2019101920191017
1346239480 0 053437 856 744sseu4icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer2019101920191017
1439242408 0 056421 856 744sseu4icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer2019101920191017
15346201672 0 0215629 856 744sseu24icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer2019101920191017
16288214104 0 0228117 856 744sseu24icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer2019101920191017
1800631112 0 046749 856 744sseu4icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer2019101920191017

Test failure

Implementation: sseu24
Security model: unknown
Compiler: icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer sseu24
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer sseu24
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer sseu4
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer sseu4

Compiler output

Implementation: xopu24
Security model: unknown
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE
DoublePermutation.c: In file included from /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/x86intrin.h:38,
DoublePermutation.c: from DoublePermutation.c:17:
DoublePermutation.c: DoublePermutation.c: In function 'KeccakDoublePermutationOnWords':
DoublePermutation.c: /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/xopintrin.h:266:1: error: inlining failed in call to always_inline '_mm_roti_epi64': target specific option mismatch
DoublePermutation.c: 266 | _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 /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/x86intrin.h:38,
DoublePermutation.c: from DoublePermutation.c:17:
DoublePermutation.c: /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/xopintrin.h:266:1: error: inlining failed in call to always_inline '_mm_roti_epi64': target specific option mismatch
DoublePermutation.c: 266 | _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:
CompilerImplementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE xopu24
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE xopu24
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE xopu24
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE xopu24

Compiler output

Implementation: xopu24
Security model: unknown
Compiler: icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer
DoublePermutation.c: DoublePermutation.c(507): warning #266: function "_mm_roti_epi64" declared implicitly
DoublePermutation.c: rounds
DoublePermutation.c: ^
DoublePermutation.c:
DoublePermutation.c: DoublePermutation.c(507): error: argument of type "int" is incompatible with parameter of type "union __m128i"
DoublePermutation.c: rounds
DoublePermutation.c: ^
DoublePermutation.c:
DoublePermutation.c: DoublePermutation.c(507): error: argument of type "int" is incompatible with parameter of type "union __m128i"
DoublePermutation.c: rounds
DoublePermutation.c: ^
DoublePermutation.c:
DoublePermutation.c: DoublePermutation.c(507): error: argument of type "int" is incompatible with parameter of type "union __m128i"
DoublePermutation.c: rounds
DoublePermutation.c: ^
DoublePermutation.c:
DoublePermutation.c: DoublePermutation.c(507): error: argument of type "int" is incompatible with parameter of type "union __m128i"
DoublePermutation.c: rounds
DoublePermutation.c: ^
DoublePermutation.c:
DoublePermutation.c: DoublePermutation.c(507): error: argument of type "int" is incompatible with parameter of type "union __m128i"
DoublePermutation.c: rounds
DoublePermutation.c: ^
DoublePermutation.c:
DoublePermutation.c: DoublePermutation.c(507): error: a value of type "int" cannot be assigned to an entity of type "V128"
DoublePermutation.c: ...

Number of similar (compiler,implementation) pairs: 24, namely:
CompilerImplementations
icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer xopu24
icc -march=broadwell -mtune=broadwell -O3 -fomit-frame-pointer xopu24
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer xopu24
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer xopu24
icc -march=core-avx-i -mtune=core-avx-i -O2 -fomit-frame-pointer xopu24
icc -march=core-avx-i -mtune=core-avx-i -O3 -fomit-frame-pointer xopu24
icc -march=core-avx2 -mtune=core-avx2 -O2 -fomit-frame-pointer xopu24
icc -march=core-avx2 -mtune=core-avx2 -O3 -fomit-frame-pointer xopu24
icc -march=corei7-avx -mtune=corei7-avx -O2 -fomit-frame-pointer xopu24
icc -march=corei7-avx -mtune=corei7-avx -O3 -fomit-frame-pointer xopu24
icc -march=corei7 -mtune=corei7 -O2 -fomit-frame-pointer xopu24
icc -march=corei7 -mtune=corei7 -O3 -fomit-frame-pointer xopu24
icc -march=haswell -mtune=haswell -O2 -fomit-frame-pointer xopu24
icc -march=haswell -mtune=haswell -O3 -fomit-frame-pointer xopu24
icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer xopu24
icc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer xopu24
icc -march=ivybridge -mtune=ivybridge -O2 -fomit-frame-pointer xopu24
icc -march=ivybridge -mtune=ivybridge -O3 -fomit-frame-pointer xopu24
icc -march=sandybridge -mtune=sandybridge -O2 -fomit-frame-pointer xopu24
icc -march=sandybridge -mtune=sandybridge -O3 -fomit-frame-pointer xopu24
icc -march=skylake-avx512 -mtune=skylake-avx512 -O2 -fomit-frame-pointer xopu24
icc -march=skylake-avx512 -mtune=skylake-avx512 -O3 -fomit-frame-pointer xopu24
icc -march=skylake -mtune=skylake -O2 -fomit-frame-pointer xopu24
icc -march=skylake -mtune=skylake -O3 -fomit-frame-pointer xopu24