Implementation notes: amd64, genji548, crypto_hash/keccakc512treed2

Computer: genji548
Architecture: amd64
CPU ID: GenuineIntel-00050654-bfebfbff
SUPERCOP version: 20191017
Operation: crypto_hash
Primitive: keccakc512treed2
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
786220632 0 029620 792 776sseu4gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
787421403 0 031332 808 776sseu4gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
787621708 0 034385 816 776sseu4gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
803621156 0 031004 808 776sseu4gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
8844102607 0 0111604 792 776sseu24gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
8920104508 0 0117185 816 776sseu24gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
8938104203 0 0114132 808 776sseu24gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
8948103972 0 0113820 808 776sseu24gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
1005027400 0 043317 856 776sseu4icc_-march=skylake-avx512_-mtune=skylake-avx512_-O2_-fomit-frame-pointer2019101920191017
1006027384 0 043861 856 776sseu4icc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer2019101920191017
1011827496 0 043621 856 776sseu4icc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer2019101920191017
1013827528 0 043333 856 776sseu4icc_-march=skylake-avx512_-mtune=skylake-avx512_-O3_-fomit-frame-pointer2019101920191017
1146431048 0 046685 856 744sseu4icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer2019101920191017
1148631048 0 046685 856 744sseu4icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer2019101920191017
1150831048 0 046685 856 744sseu4icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer2019101920191017
1151631048 0 046685 856 744sseu4icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer2019101920191017
1152831064 0 046317 856 744sseu4icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer2019101920191017
1156031064 0 046317 856 744sseu4icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer2019101920191017
1157231064 0 046317 856 744sseu4icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer2019101920191017
1160831064 0 046317 856 744sseu4icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer2019101920191017
11620135368 0 0151173 856 776sseu24icc_-march=skylake-avx512_-mtune=skylake-avx512_-O3_-fomit-frame-pointer2019101920191017
11658135304 0 0151429 856 776sseu24icc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer2019101920191017
11834136216 0 0152693 856 776sseu24icc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer2019101920191017
11842136552 0 0152469 856 776sseu24icc_-march=skylake-avx512_-mtune=skylake-avx512_-O2_-fomit-frame-pointer2019101920191017
1232233512 0 048749 856 744sseu4icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer2019101920191017
1234233512 0 048749 856 744sseu4icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer2019101920191017
1236833512 0 048749 856 744sseu4icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer2019101920191017
1241633512 0 048749 856 744sseu4icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer2019101920191017
1294433528 0 048813 856 744sseu4icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer2019101920191017
1295833528 0 048813 856 744sseu4icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer2019101920191017
1297433528 0 048813 856 744sseu4icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer2019101920191017
1302433528 0 048813 856 744sseu4icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer2019101920191017
13402151752 0 0167005 856 744sseu24icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer2019101920191017
13402151752 0 0167005 856 744sseu24icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer2019101920191017
13402151752 0 0167005 856 744sseu24icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer2019101920191017
13406151752 0 0167005 856 744sseu24icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer2019101920191017
13420151736 0 0167373 856 744sseu24icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer2019101920191017
13424151736 0 0167373 856 744sseu24icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer2019101920191017
13424151736 0 0167373 856 744sseu24icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer2019101920191017
13442151736 0 0167373 856 744sseu24icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer2019101920191017
14662164680 0 0179917 856 744sseu24icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer2019101920191017
14664164680 0 0179917 856 744sseu24icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer2019101920191017
14664164680 0 0179917 856 744sseu24icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer2019101920191017
14684164696 0 0179981 856 744sseu24icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer2019101920191017
14688164696 0 0179981 856 744sseu24icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer2019101920191017
14688164696 0 0179981 856 744sseu24icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer2019101920191017
14692164696 0 0179981 856 744sseu24icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer2019101920191017
14698164680 0 0179917 856 744sseu24icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer2019101920191017
1566239448 0 053405 856 744sseu4icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer2019101920191017
1665642376 0 056389 856 744sseu4icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer2019101920191017
17864201640 0 0215597 856 744sseu24icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer2019101920191017
18950214072 0 0228085 856 744sseu24icc_-march=corei7_-mtune=corei7_-O3_-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