Implementation notes: amd64, genji202, crypto_aead/pi32cipher128v1

Computer: genji202
Architecture: amd64
CPU ID: GenuineIntel-000306f2-bfebfbff
SUPERCOP version: 20171020
Operation: crypto_aead
Primitive: pi32cipher128v1
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
161136? ? ?? ? ?optimized_nonSSEicc_-xCORE-AVX2_-O2_-fomit-frame-pointer2017111320171020
163632? ? ?? ? ?optimized_nonSSEicc_-xCORE-AVX-I_-O2_-fomit-frame-pointer2017111320171020
163800? ? ?? ? ?optimized_nonSSEicc2017111320171020
164520? ? ?? ? ?optimized_nonSSEicc_-xCORE-AVX-I_-O3_-fomit-frame-pointer2017111320171020
164760? ? ?? ? ?optimized_nonSSEicc_-xCORE-AVX2_-O3_-fomit-frame-pointer2017111320171020
170752? ? ?? ? ?optimized_nonSSEicc_-no-vec2017111320171020
186456? ? ?? ? ?reficc_-xCORE-AVX-I_-O3_-fomit-frame-pointer2017111320171020
190568? ? ?? ? ?reficc_-xCORE-AVX2_-O3_-fomit-frame-pointer2017111320171020
191996? ? ?? ? ?reficc2017111320171020
193380? ? ?? ? ?reficc_-xCORE-AVX2_-O2_-fomit-frame-pointer2017111320171020
193900? ? ?? ? ?reficc_-xCORE-AVX-I_-O2_-fomit-frame-pointer2017111320171020
193952? ? ?? ? ?reficc_-no-vec2017111320171020
883540? ? ?? ? ?optimized_nonSSEcc2017111320171020
1049484? ? ?? ? ?refcc2017111320171020

Test failure

Implementation: crypto_aead/pi32cipher128v1/optimized_nonSSE
Compiler: gcc
error 111
crypto_aead_decrypt returns nonzero
Number of similar (compiler,implementation) pairs: 212, namely:
CompilerImplementations
gcc optimized_nonSSE ref
gcc -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -O -fomit-frame-pointer optimized_nonSSE ref
gcc -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -fno-schedule-insns -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -fno-schedule-insns -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -fno-schedule-insns -O -fomit-frame-pointer optimized_nonSSE ref
gcc -fno-schedule-insns -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops optimized_nonSSE ref
gcc -funroll-loops -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -O -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -m64 -O -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -m64 -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer optimized_nonSSE ref
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -O -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=core2 -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=core2 -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=core2 -O -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=core2 -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=corei7 -O -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=corei7 -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=k8 -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=k8 -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=k8 -O -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=k8 -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=nocona -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=nocona -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=nocona -O -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=nocona -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -march=barcelona -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -march=barcelona -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -march=barcelona -O -fomit-frame-pointer optimized_nonSSE ref
gcc -march=barcelona -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -march=k8 -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -march=k8 -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -march=k8 -O -fomit-frame-pointer optimized_nonSSE ref
gcc -march=k8 -Os -fomit-frame-pointer optimized_nonSSE ref
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv optimized_nonSSE ref
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv optimized_nonSSE ref
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv optimized_nonSSE ref
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv optimized_nonSSE ref
gcc -march=nocona -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -march=nocona -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -march=nocona -O -fomit-frame-pointer optimized_nonSSE ref
gcc -march=nocona -Os -fomit-frame-pointer optimized_nonSSE ref

Test failure

Implementation: crypto_aead/pi32cipher128v1/optimized_nonSSE
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
error 111
crypto_aead_decrypt returns nonzero
error 111
crypto_aead_decrypt returns nonzero
Number of similar (compiler,implementation) pairs: 8, namely:
CompilerImplementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=barcelona -O -fomit-frame-pointer optimized_nonSSE ref
gcc -m64 -march=barcelona -Os -fomit-frame-pointer optimized_nonSSE ref