Implementation notes: amd64, rumba5, crypto_hash/fugue2

Computer: rumba5
Architecture: amd64
CPU ID: AuthenticAMD-00800f11-178bfbff
SUPERCOP version: 20181113
Operation: crypto_hash
Primitive: fugue2
TimeImplementationCompilerBenchmark dateSUPERCOP version
21664cop_opt32gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer2018051520171218
21760cop_opt32gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer2018051520171218
21920cop_opt32gcc -funroll-loops -O2 -fomit-frame-pointer2018051520171218
21920cop_opt32gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer2018051520171218
21920cop_opt32gcc -funroll-loops -m64 -O2 -fomit-frame-pointer2018051520171218
21952cop_opt32gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer2018051520171218
21952cop_opt32gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer2018051520171218
21984cop_opt32gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer2018051520171218
21984cop_opt32gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer2018051520171218
21984cop_opt32gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2018051520171218
21984cop_opt32gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2018051520171218
22016cop_opt32gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer2018051520171218
22016cop_opt32gcc -m64 -march=corei7 -O2 -fomit-frame-pointer2018051520171218
22048cop_opt32gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer2018051520171218
22048cop_opt32gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer2018051520171218
22048cop_opt32gcc -m64 -march=core2 -O2 -fomit-frame-pointer2018051520171218
22048cop_opt32gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2018051520171218
22048cop_opt32gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer2018051520171218
22080cop_opt32gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer2018051520171218
22080cop_opt32gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer2018051520171218
22080cop_opt32gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer2018051520171218
22080cop_opt32gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2018051520171218
22112cop_opt32gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2018051520171218
22144cop_opt32gcc -funroll-loops -O3 -fomit-frame-pointer2018051520171218
22144cop_opt32gcc -funroll-loops -m64 -O3 -fomit-frame-pointer2018051520171218
22144cop_opt32gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2018051520171218
22144cop_opt32gcc -m64 -march=corei7 -O3 -fomit-frame-pointer2018051520171218
22176cop_opt32gcc -O2 -fomit-frame-pointer2018051520171218
22176cop_opt32gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer2018051520171218
22176cop_opt32gcc -m64 -O2 -fomit-frame-pointer2018051520171218
22176cop_opt32gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer2018051520171218
22176cop_opt32gcc -m64 -march=core2 -O3 -fomit-frame-pointer2018051520171218
22176cop_opt32gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer2018051520171218
22208cop_opt32gcc -fno-schedule-insns -O2 -fomit-frame-pointer2018051520171218
22208cop_opt32gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer2018051520171218
22336cop_opt32gcc -m64 -march=barcelona -O3 -fomit-frame-pointer2018051520171218
22336cop_opt32gcc -m64 -march=k8 -O2 -fomit-frame-pointer2018051520171218
22336cop_opt32gcc -march=barcelona -O2 -fomit-frame-pointer2018051520171218
22336cop_opt32gcc -march=k8 -O2 -fomit-frame-pointer2018051520171218
22368cop_opt32gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer2018051520171218
22368cop_opt32gcc -m64 -march=barcelona -O2 -fomit-frame-pointer2018051520171218
22368cop_opt32gcc -m64 -march=k8 -O3 -fomit-frame-pointer2018051520171218
22368cop_opt32gcc -march=barcelona -O3 -fomit-frame-pointer2018051520171218
22368cop_opt32gcc -march=k8 -O3 -fomit-frame-pointer2018051520171218
22400cop_opt32gcc -funroll-loops -m64 -O -fomit-frame-pointer2018051520171218
22432cop_opt32gcc -fno-schedule-insns -O3 -fomit-frame-pointer2018051520171218
22432cop_opt32gcc -funroll-loops -O -fomit-frame-pointer2018051520171218
22464cop_opt32gcc -m64 -O3 -fomit-frame-pointer2018051520171218
22496cop_opt32gcc -O3 -fomit-frame-pointer2018051520171218
22560cop_opt32gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer2018051520171218
22560cop_opt32gcc -funroll-loops -march=k8 -O -fomit-frame-pointer2018051520171218
22592cop_opt32gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer2018051520171218
22624cop_opt32gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer2018051520171218
22656cop_opt32gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer2018051520171218
22688cop_opt32gcc -m64 -march=core-avx2 -O -fomit-frame-pointer2018051520171218
22784cop_opt32gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer2018051520171218
22784cop_opt32gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer2018051520171218
22784cop_opt32gcc -m64 -march=k8 -O -fomit-frame-pointer2018051520171218
22784cop_opt32gcc -march=barcelona -O -fomit-frame-pointer2018051520171218
22784cop_opt32gcc -march=k8 -O -fomit-frame-pointer2018051520171218
22848cop_opt32gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer2018051520171218
22848cop_opt32gcc -m64 -march=nocona -O3 -fomit-frame-pointer2018051520171218
22848cop_opt32gcc -march=nocona -O3 -fomit-frame-pointer2018051520171218
22880cop_opt32gcc -fno-schedule-insns -O -fomit-frame-pointer2018051520171218
22880cop_opt32gcc -m64 -O -fomit-frame-pointer2018051520171218
22880cop_opt32gcc -m64 -march=barcelona -O -fomit-frame-pointer2018051520171218
22880cop_opt32gcc -m64 -march=core-avx-i -O -fomit-frame-pointer2018051520171218
22880cop_opt32gcc -m64 -march=core2 -O -fomit-frame-pointer2018051520171218
22880cop_opt32gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer2018051520171218
22880cop_opt32gcc -m64 -march=corei7-avx -O -fomit-frame-pointer2018051520171218
22880cop_opt32gcc -m64 -march=corei7 -O -fomit-frame-pointer2018051520171218
22912cop_opt32gcc -O -fomit-frame-pointer2018051520171218
22944cop_opt32gcc -march=nocona -O2 -fomit-frame-pointer2018051520171218
22976cop_opt32gcc -m64 -march=nocona -O2 -fomit-frame-pointer2018051520171218
23104cop_opt32gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer2018051520171218
23136cop_opt32gcc -funroll-loops -march=nocona -O -fomit-frame-pointer2018051520171218
23168cop_opt32gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2018051520171218
23264cop_opt32gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer2018051520171218
23264cop_opt32gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2018051520171218
23360cop_opt32gcc -march=nocona -O -fomit-frame-pointer2018051520171218
23392cop_opt32gcc -m64 -march=nocona -O -fomit-frame-pointer2018051520171218
26176cop_opt32gcc -m64 -march=barcelona -Os -fomit-frame-pointer2018051520171218
26176cop_opt32gcc -m64 -march=k8 -Os -fomit-frame-pointer2018051520171218
26208cop_opt32gcc -m64 -Os -fomit-frame-pointer2018051520171218
26208cop_opt32gcc -march=barcelona -Os -fomit-frame-pointer2018051520171218
26208cop_opt32gcc -march=k8 -Os -fomit-frame-pointer2018051520171218
26240cop_opt32gcc -Os -fomit-frame-pointer2018051520171218
26240cop_opt32gcc -m64 -march=core2 -Os -fomit-frame-pointer2018051520171218
26272cop_opt32gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer2018051520171218
26304cop_opt32gcc -fno-schedule-insns -Os -fomit-frame-pointer2018051520171218
26304cop_opt32gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer2018051520171218
26368cop_opt32gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2018051520171218
26368cop_opt32gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2018051520171218
26400cop_opt32gcc -m64 -march=nocona -Os -fomit-frame-pointer2018051520171218
26432cop_opt32gcc -march=nocona -Os -fomit-frame-pointer2018051520171218
26496cop_opt32gcc -funroll-loops -Os -fomit-frame-pointer2018051520171218
26496cop_opt32gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer2018051520171218
26496cop_opt32gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer2018051520171218
26496cop_opt32gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer2018051520171218
26496cop_opt32gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer2018051520171218
26528cop_opt32gcc -funroll-loops -m64 -Os -fomit-frame-pointer2018051520171218
26528cop_opt32gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer2018051520171218
26528cop_opt32gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer2018051520171218
26656cop_opt32gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer2018051520171218
26656cop_opt32gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer2018051520171218
26688cop_opt32gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer2018051520171218
26720cop_opt32gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer2018051520171218
26784cop_opt32gcc -m64 -march=corei7 -Os -fomit-frame-pointer2018051520171218
79200cop_opt32gcc -funroll-loops2018051520171218
79360cop_opt32gcc2018051520171218
79904cop_opt32cc2018051520171218

Compiler output

Implementation: crypto_hash/fugue2/cop_opt32
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments
hash.c: hash.c:33:28: warning: signed shift result (0x3F743CBE000000) requires 55 bits to represent, but 'int' only has 32 bits [-Wshift-overflow]
hash.c: HO2BE_4(0xa6de572c), HO2BE_4(0x3f743cbe), HO2BE_4(0x4105b317), HO2BE_4(0x4580a1c6)};
hash.c: ^~~~~~~~~~~~~~~~~~~
hash.c: ./aestab_t.h:19:26: note: expanded from macro 'HO2BE_4'
hash.c: #define HO2BE_4(_x) ((_xgt;>gt;8)&0xff00)|(_x>gt;>gt;24))
hash.c: ~~^ ~~
hash.c: hash.c:33:28: warning: signed shift result (0x3F743CBE00) requires 39 bits to represent, but 'int' only has 32 bits [-Wshift-overflow]
hash.c: HO2BE_4(0xa6de572c), HO2BE_4(0x3f743cbe), HO2BE_4(0x4105b317), HO2BE_4(0x4580a1c6)};
hash.c: ^~~~~~~~~~~~~~~~~~~
hash.c: ./aestab_t.h:19:36: note: expanded from macro 'HO2BE_4'
hash.c: #define HO2BE_4(_x) ((_xgt;>gt;8)&0xff00)|(_x>gt;>gt;24))
hash.c: ~~^ ~
hash.c: hash.c:33:49: warning: signed shift result (0x4105B317000000) requires 56 bits to represent, but 'int' only has 32 bits [-Wshift-overflow]
hash.c: HO2BE_4(0xa6de572c), HO2BE_4(0x3f743cbe), HO2BE_4(0x4105b317), HO2BE_4(0x4580a1c6)};
hash.c: ^~~~~~~~~~~~~~~~~~~
hash.c: ./aestab_t.h:19:26: note: expanded from macro 'HO2BE_4'
hash.c: #define HO2BE_4(_x) ((_xgt;>gt;8)&0xff00)|(_x>gt;>gt;24))
hash.c: ~~^ ~~
hash.c: hash.c:33:49: warning: signed shift result (0x4105B31700) requires 40 bits to represent, but 'int' only has 32 bits [-Wshift-overflow]
hash.c: HO2BE_4(0xa6de572c), HO2BE_4(0x3f743cbe), HO2BE_4(0x4105b317), HO2BE_4(0x4580a1c6)};
hash.c: ^~~~~~~~~~~~~~~~~~~
hash.c: ./aestab_t.h:19:36: note: expanded from macro 'HO2BE_4'
hash.c: #define HO2BE_4(_x) ((_xgt;>gt;8)&0xff00)|(_x>gt;>gt;24))
hash.c: ~~^ ~
hash.c: hash.c:33:70: warning: signed shift result (0x4580A1C6000000) requires 56 bits to represent, but 'int' only has 32 bits [-Wshift-overflow]
hash.c: ...

Number of similar (compiler,implementation) pairs: 10, namely:
CompilerImplementations
clang -O3 -fomit-frame-pointer -Qunused-arguments cop_opt32
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments cop_opt32
clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments cop_opt32
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments cop_opt32
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments cop_opt32
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments cop_opt32
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments cop_opt32
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments cop_opt32
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments cop_opt32
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments cop_opt32