Implementation notes: x86, gpu, crypto_core/mult3sntrup653

Computer: gpu
Architecture: x86
CPU ID: GenuineIntel-000206d7-bfebfbff
SUPERCOP version: 20190816
Operation: crypto_core
Primitive: mult3sntrup653
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
9411631824 0 018064 392 768refgcc_-funroll-loops_-m32_-march=nocona_-O2_-fomit-frame-pointer2019082220190816
9770801824 0 018064 392 768refgcc_-funroll-loops_-m32_-march=prescott_-O2_-fomit-frame-pointer2019082220190816
10630982830 0 019613 396 768refgcc_-funroll-loops_-m32_-march=prescott_-O3_-fomit-frame-pointer2019082220190816
10752211833 0 017916 392 768refgcc_-funroll-loops_-m32_-march=pentium4_-O2_-fomit-frame-pointer2019082220190816
10981623888 0 022089 396 768refgcc_-funroll-loops_-m32_-march=k8_-O3_-fomit-frame-pointer2019082220190816
11082922830 0 019613 396 768refgcc_-funroll-loops_-m32_-march=nocona_-O3_-fomit-frame-pointer2019082220190816
11091681958 0 019654 400 768refgcc_-funroll-loops_-m32_-march=athlon_-O3_-fomit-frame-pointer2019082220190816
11157721913 0 018349 396 768refgcc_-funroll-loops_-m32_-O2_-fomit-frame-pointer2019082220190816
11248321936 0 019442 400 768refgcc_-funroll-loops_-m32_-O3_-fomit-frame-pointer2019082220190816
11260801921 0 018868 392 768refgcc_-funroll-loops_-m32_-march=barcelona_-O2_-fomit-frame-pointer2019082220190816
11440741876 0 018904 392 768refgcc_-funroll-loops_-m32_-march=pentiumpro_-O2_-fomit-frame-pointer2019082220190816
11445091897 0 018064 392 768refgcc_-funroll-loops_-m32_-march=k8_-O2_-fomit-frame-pointer2019082220190816
11455602719 0 019449 396 768refgcc_-funroll-loops_-m32_-march=pentium4_-O3_-fomit-frame-pointer2019082220190816
11507403228 0 022204 392 768refgcc_-funroll-loops_-m32_-march=pentium-m_-O3_-fomit-frame-pointer2019082220190816
11545771937 0 018165 396 768refgcc_-funroll-loops_-m32_-march=athlon_-O2_-fomit-frame-pointer2019082220190816
11641681876 0 019716 392 768refgcc_-funroll-loops_-m32_-march=pentium-m_-O2_-fomit-frame-pointer2019082220190816
11728443919 0 022841 396 768refgcc_-funroll-loops_-m32_-march=barcelona_-O3_-fomit-frame-pointer2019082220190816
11800321876 0 018904 392 768refgcc_-funroll-loops_-m32_-march=pentium2_-O2_-fomit-frame-pointer2019082220190816
11911802506 0 021644 392 768refgcc_-funroll-loops_-m32_-march=pentium3_-O3_-fomit-frame-pointer2019082220190816
11915132506 0 021436 392 768refgcc_-funroll-loops_-m32_-march=pentiumpro_-O3_-fomit-frame-pointer2019082220190816
11926201876 0 018904 392 768refgcc_-funroll-loops_-m32_-march=pentium3_-O2_-fomit-frame-pointer2019082220190816
11966312506 0 021436 392 768refgcc_-funroll-loops_-m32_-march=pentium2_-O3_-fomit-frame-pointer2019082220190816
13355491764 0 017868 392 768refgcc_-funroll-loops_-m32_-march=i386_-O_-fomit-frame-pointer2019082220190816
17081133161 0 018854 400 768refgcc_-m32_-march=corei7_-O3_-fomit-frame-pointer2019082220190816
17369433360 0 019042 400 768refgcc_-m32_-march=core2_-O3_-fomit-frame-pointer2019082220190816
1739475856 0 016358 400 768refgcc_-m32_-march=athlon_-O3_-fomit-frame-pointer2019082220190816
1744359592 0 013685 396 768refgcc_-m32_-march=corei7-avx_-O2_-fomit-frame-pointer2019082220190816
1760004592 0 013701 396 768refgcc_-m32_-march=corei7_-O2_-fomit-frame-pointer2019082220190816
1761126592 0 013685 396 768refgcc_-m32_-march=core-avx-i_-O2_-fomit-frame-pointer2019082220190816
17679323073 0 019042 400 768refgcc_-m32_-march=core-avx-i_-O3_-fomit-frame-pointer2019082220190816
1770774582 0 013552 392 768refgcc_-m32_-march=k8_-O2_-fomit-frame-pointer2019082220190816
1774137590 0 013397 396 768refgcc_-m32_-march=athlon_-O2_-fomit-frame-pointer2019082220190816
17787083161 0 018854 400 768refgcc_-m32_-march=core2_-msse4_-O3_-fomit-frame-pointer2019082220190816
17802443161 0 018802 400 768refgcc_-m32_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2019082220190816
1789086592 0 013685 396 768refgcc_-m32_-march=native_-mtune=native_-O2_-fomit-frame-pointer2019082220190816
1790816592 0 013701 396 768refgcc_-m32_-march=core2_-msse4_-O2_-fomit-frame-pointer2019082220190816
17935742022 0 017369 396 768refgcc_-m32_-march=nocona_-O3_-fomit-frame-pointer2019082220190816
18105121976 0 018317 396 768refgcc_-funroll-loops_-m32_-march=k6-3_-O_-fomit-frame-pointer2019082220190816
18118383439 0 019437 396 768refgcc_-m32_-march=k8_-O3_-fomit-frame-pointer2019082220190816
18242672053 0 018253 396 768refgcc_-funroll-loops_-m32_-march=athlon_-O_-fomit-frame-pointer2019082220190816
18266883073 0 019042 400 768refgcc_-m32_-march=corei7-avx_-O3_-fomit-frame-pointer2019082220190816
18318032022 0 017369 396 768refgcc_-m32_-march=prescott_-O3_-fomit-frame-pointer2019082220190816
1832264592 0 013701 396 768refgcc_-m32_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2019082220190816
18326251841 0 018153 396 768refgcc_-funroll-loops_-m32_-march=pentium_-O_-fomit-frame-pointer2019082220190816
18402843073 0 019042 400 768refgcc_-m32_-march=native_-mtune=native_-O3_-fomit-frame-pointer2019082220190816
18519721976 0 018317 396 768refgcc_-funroll-loops_-m32_-march=k6_-O_-fomit-frame-pointer2019082220190816
1861758592 0 013717 396 768refgcc_-m32_-march=core2_-O2_-fomit-frame-pointer2019082220190816
1867116620 0 013340 392 768refgcc_-m32_-march=nocona_-O2_-fomit-frame-pointer2019082220190816
1870540558 0 013292 392 768refgcc_-m32_-march=pentium4_-O2_-fomit-frame-pointer2019082220190816
18740247118 0 020045 396 768refgcc_-m32_-march=barcelona_-O3_-fomit-frame-pointer2019082220190816
18746281764 0 018188 392 768refgcc_-funroll-loops_-m32_-march=i486_-O_-fomit-frame-pointer2019082220190816
18806702040 0 018385 396 768refgcc_-funroll-loops_-m32_-O_-fomit-frame-pointer2019082220190816
1884692592 0 013713 396 768refgcc_-m32_-O2_-fomit-frame-pointer2019082220190816
18849121998 0 018400 392 768refgcc_-funroll-loops_-m32_-march=k8_-O_-fomit-frame-pointer2019082220190816
1884980620 0 013340 392 768refgcc_-m32_-march=prescott_-O2_-fomit-frame-pointer2019082220190816
18865121981 0 018612 392 768refgcc_-funroll-loops_-m32_-march=nocona_-O_-fomit-frame-pointer2019082220190816
18889081308 0 014360 392 768refgcc_-m32_-march=barcelona_-O2_-fomit-frame-pointer2019082220190816
18894272031 0 018660 392 768refgcc_-funroll-loops_-m32_-march=pentium4_-O_-fomit-frame-pointer2019082220190816
19011211976 0 018317 396 768refgcc_-funroll-loops_-m32_-march=k6-2_-O_-fomit-frame-pointer2019082220190816
19066521998 0 018580 392 768refgcc_-funroll-loops_-m32_-march=barcelona_-O_-fomit-frame-pointer2019082220190816
19236561886 0 019176 392 768refgcc_-funroll-loops_-m32_-march=pentium3_-O_-fomit-frame-pointer2019082220190816
19249291666 0 017969 396 768refgcc_-funroll-loops_-m32_-march=k6-2_-O2_-fomit-frame-pointer2019082220190816
19303801796 0 019000 392 768refgcc_-funroll-loops_-m32_-march=i486_-O3_-fomit-frame-pointer2019082220190816
19415761919 0 017221 396 768refgcc_-m32_-march=pentium4_-O3_-fomit-frame-pointer2019082220190816
19505341841 0 018153 396 768refgcc_-funroll-loops_-m32_-march=pentium-mmx_-O_-fomit-frame-pointer2019082220190816
19545811981 0 018612 392 768refgcc_-funroll-loops_-m32_-march=prescott_-O_-fomit-frame-pointer2019082220190816
19663351818 0 019762 400 768refgcc_-funroll-loops_-m32_-march=k6-2_-O3_-fomit-frame-pointer2019082220190816
19931102073 0 019617 396 768refgcc_-funroll-loops_-m32_-march=pentium-mmx_-O3_-fomit-frame-pointer2019082220190816
1994116819 0 016434 400 768refgcc_-m32_-O3_-fomit-frame-pointer2019082220190816
19967582073 0 019617 396 768refgcc_-funroll-loops_-m32_-march=pentium_-O3_-fomit-frame-pointer2019082220190816
20293291818 0 019154 400 768refgcc_-funroll-loops_-m32_-march=k6_-O3_-fomit-frame-pointer2019082220190816
20301781710 0 017552 392 768refgcc_-funroll-loops_-m32_-march=i386_-O3_-fomit-frame-pointer2019082220190816
20310571818 0 019762 400 768refgcc_-funroll-loops_-m32_-march=k6-3_-O3_-fomit-frame-pointer2019082220190816
20324941666 0 017969 396 768refgcc_-funroll-loops_-m32_-march=k6-3_-O2_-fomit-frame-pointer2019082220190816
20350321562 0 017448 392 768refgcc_-funroll-loops_-m32_-march=i386_-O2_-fomit-frame-pointer2019082220190816
20419561666 0 017969 396 768refgcc_-funroll-loops_-m32_-march=k6_-O2_-fomit-frame-pointer2019082220190816
20654011720 0 018285 396 768refgcc_-funroll-loops_-m32_-march=pentium_-O2_-fomit-frame-pointer2019082220190816
20669491610 0 018324 392 768refgcc_-funroll-loops_-m32_-march=i486_-O2_-fomit-frame-pointer2019082220190816
20672281886 0 019176 392 768refgcc_-funroll-loops_-m32_-march=pentium2_-O_-fomit-frame-pointer2019082220190816
20749471720 0 018285 396 768refgcc_-funroll-loops_-m32_-march=pentium-mmx_-O2_-fomit-frame-pointer2019082220190816
2088270532 0 012196 384 768refgcc_-funroll-loops_-m32_-march=i386_-Os_-fomit-frame-pointer2019082220190816
2088369629 0 013693 396 768refgcc_-m32_-march=pentium-mmx_-O2_-fomit-frame-pointer2019082220190816
21158821886 0 019296 392 768refgcc_-funroll-loops_-m32_-march=pentium-m_-O_-fomit-frame-pointer2019082220190816
21359281886 0 019176 392 768refgcc_-funroll-loops_-m32_-march=pentiumpro_-O_-fomit-frame-pointer2019082220190816
2166920917 0 016680 392 768refgcc_-m32_-march=i486_-O3_-fomit-frame-pointer2019082220190816
2186451834 0 015244 392 768refgcc_-m32_-march=i386_-O3_-fomit-frame-pointer2019082220190816
2210540593 0 013164 392 768refgcc_-m32_-march=i386_-O2_-fomit-frame-pointer2019082220190816
2224168601 0 013837 396 768refgcc_-m32_-march=k6_-O2_-fomit-frame-pointer2019082220190816
2229417883 0 017090 400 768refgcc_-m32_-march=k6-2_-O3_-fomit-frame-pointer2019082220190816
2231944621 0 013924 392 768refgcc_-m32_-march=i486_-O2_-fomit-frame-pointer2019082220190816
2248341927 0 016957 396 768refgcc_-m32_-march=pentium_-O3_-fomit-frame-pointer2019082220190816
2259524619 0 013301 396 768refgcc_-m32_-march=corei7-avx_-O_-fomit-frame-pointer2019082220190816
22642681230 0 013408 392 768refgcc_-m32_-march=barcelona_-O_-fomit-frame-pointer2019082220190816
2276928591 0 012372 384 768refgcc_-m32_-march=k6-3_-Os_-fomit-frame-pointer2019082220190816
2283860627 0 013417 396 768refgcc_-m32_-march=k6_-O_-fomit-frame-pointer2019082220190816
2284479585 0 012340 384 768refgcc_-funroll-loops_-m32_-march=k6-3_-Os_-fomit-frame-pointer2019082220190816
2298105601 0 013837 396 768refgcc_-m32_-march=k6-3_-O2_-fomit-frame-pointer2019082220190816
2298552619 0 013301 396 768refgcc_-m32_-march=core2_-O_-fomit-frame-pointer2019082220190816
2308731591 0 012372 384 768refgcc_-m32_-march=k6_-Os_-fomit-frame-pointer2019082220190816
2310128619 0 013293 396 768refgcc_-m32_-O_-fomit-frame-pointer2019082220190816
2311086591 0 012372 384 768refgcc_-m32_-march=k6-2_-Os_-fomit-frame-pointer2019082220190816
2320324540 0 012244 384 768refgcc_-m32_-march=core2_-msse4_-Os_-fomit-frame-pointer2019082220190816
2321260619 0 013301 396 768refgcc_-m32_-march=core2_-msse4.1_-O_-fomit-frame-pointer2019082220190816
2321553629 0 013693 396 768refgcc_-m32_-march=pentium_-O2_-fomit-frame-pointer2019082220190816
2322693538 0 012196 384 768refgcc_-funroll-loops_-m32_-march=pentium-mmx_-Os_-fomit-frame-pointer2019082220190816
2325072627 0 013417 396 768refgcc_-m32_-march=k6-3_-O_-fomit-frame-pointer2019082220190816
2325729615 0 013152 392 768refgcc_-m32_-march=k8_-O_-fomit-frame-pointer2019082220190816
2328264617 0 013037 396 768refgcc_-m32_-march=athlon_-O_-fomit-frame-pointer2019082220190816
2329731619 0 013301 396 768refgcc_-m32_-march=core2_-msse4_-O_-fomit-frame-pointer2019082220190816
2335734627 0 013417 396 768refgcc_-m32_-march=k6-2_-O_-fomit-frame-pointer2019082220190816
2341912540 0 012228 384 768refgcc_-m32_-march=core-avx-i_-Os_-fomit-frame-pointer2019082220190816
2350809585 0 012340 384 768refgcc_-funroll-loops_-m32_-march=k6_-Os_-fomit-frame-pointer2019082220190816
2356776538 0 012196 384 768refgcc_-funroll-loops_-m32_-march=pentium_-Os_-fomit-frame-pointer2019082220190816
2361960883 0 017090 400 768refgcc_-m32_-march=k6-3_-O3_-fomit-frame-pointer2019082220190816
2366991585 0 012340 384 768refgcc_-funroll-loops_-m32_-march=k6-2_-Os_-fomit-frame-pointer2019082220190816
2371592540 0 012228 384 768refgcc_-m32_-march=native_-mtune=native_-Os_-fomit-frame-pointer2019082220190816
2381088883 0 016898 400 768refgcc_-m32_-march=k6_-O3_-fomit-frame-pointer2019082220190816
2388712540 0 012228 384 768refgcc_-m32_-march=corei7-avx_-Os_-fomit-frame-pointer2019082220190816
2391816601 0 013837 396 768refgcc_-m32_-march=k6-2_-O2_-fomit-frame-pointer2019082220190816
2397156540 0 012228 384 768refgcc_-m32_-march=pentium-mmx_-Os_-fomit-frame-pointer2019082220190816
2410092538 0 012196 384 768refgcc_-funroll-loops_-m32_-march=athlon_-Os_-fomit-frame-pointer2019082220190816
2411118617 0 013364 392 768refgcc_-m32_-march=pentium4_-O_-fomit-frame-pointer2019082220190816
2411325540 0 012260 384 768refgcc_-m32_-march=nocona_-Os_-fomit-frame-pointer2019082220190816
2411880650 0 013317 396 768refgcc_-m32_-march=pentium_-O_-fomit-frame-pointer2019082220190816
2416752652 0 013416 392 768refgcc_-m32_-march=i486_-O_-fomit-frame-pointer2019082220190816
2419626619 0 013301 396 768refgcc_-m32_-march=corei7_-O_-fomit-frame-pointer2019082220190816
2424676540 0 012244 384 768refgcc_-m32_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2019082220190816
2425148927 0 016957 396 768refgcc_-m32_-march=pentium-mmx_-O3_-fomit-frame-pointer2019082220190816
2425536532 0 012196 384 768refgcc_-funroll-loops_-m32_-march=i486_-Os_-fomit-frame-pointer2019082220190816
24298121080 0 012260 384 768refgcc_-m32_-march=barcelona_-Os_-fomit-frame-pointer2019082220190816
2434401536 0 012212 384 768refgcc_-m32_-march=i486_-Os_-fomit-frame-pointer2019082220190816
2438352540 0 012244 384 768refgcc_-m32_-march=corei7_-Os_-fomit-frame-pointer2019082220190816
2445764540 0 012228 384 768refgcc_-m32_-march=pentium_-Os_-fomit-frame-pointer2019082220190816
2451784540 0 012260 384 768refgcc_-m32_-march=core2_-Os_-fomit-frame-pointer2019082220190816
2455376619 0 013301 396 768refgcc_-m32_-march=native_-mtune=native_-O_-fomit-frame-pointer2019082220190816
2458146540 0 012260 384 768refgcc_-m32_-march=pentium4_-Os_-fomit-frame-pointer2019082220190816
2458680538 0 012244 384 768refgcc_-funroll-loops_-m32_-march=k8_-Os_-fomit-frame-pointer2019082220190816
2462463538 0 012244 384 768refgcc_-funroll-loops_-m32_-march=barcelona_-Os_-fomit-frame-pointer2019082220190816
2466272675 0 013412 392 768refgcc_-m32_-march=prescott_-O_-fomit-frame-pointer2019082220190816
2470167540 0 012212 384 768refgcc_-m32_-march=athlon_-Os_-fomit-frame-pointer2019082220190816
2472848536 0 012212 384 768refgcc_-m32_-march=i386_-Os_-fomit-frame-pointer2019082220190816
2475581540 0 012260 384 768refgcc_-m32_-march=prescott_-Os_-fomit-frame-pointer2019082220190816
2478844650 0 013317 396 768refgcc_-m32_-march=pentium-mmx_-O_-fomit-frame-pointer2019082220190816
2489109538 0 012228 384 768refgcc_-funroll-loops_-m32_-march=nocona_-Os_-fomit-frame-pointer2019082220190816
2500596619 0 013301 396 768refgcc_-m32_-march=core-avx-i_-O_-fomit-frame-pointer2019082220190816
2528148540 0 012212 384 768refgcc_-m32_-Os_-fomit-frame-pointer2019082220190816
2537145538 0 012228 384 768refgcc_-funroll-loops_-m32_-march=prescott_-Os_-fomit-frame-pointer2019082220190816
2544712540 0 012260 384 768refgcc_-m32_-march=k8_-Os_-fomit-frame-pointer2019082220190816
2557188652 0 013144 392 768refgcc_-m32_-march=i386_-O_-fomit-frame-pointer2019082220190816
2565320675 0 013412 392 768refgcc_-m32_-march=nocona_-O_-fomit-frame-pointer2019082220190816
2577112538 0 012196 384 768refgcc_-funroll-loops_-m32_-Os_-fomit-frame-pointer2019082220190816
2577376538 0 012228 384 768refgcc_-funroll-loops_-m32_-march=pentium4_-Os_-fomit-frame-pointer2019082220190816
2658193606 0 013724 392 768refgcc_-m32_-march=pentiumpro_-O2_-fomit-frame-pointer2019082220190816
2665104606 0 014080 392 768refgcc_-m32_-march=pentium-m_-O2_-fomit-frame-pointer2019082220190816
2709915961 0 017144 392 768refgcc_-m32_-march=pentium3_-O3_-fomit-frame-pointer2019082220190816
2731176961 0 016936 392 768refgcc_-m32_-march=pentium2_-O3_-fomit-frame-pointer2019082220190816
2755272606 0 013400 392 768refgcc_-m32_-march=pentiumpro_-O_-fomit-frame-pointer2019082220190816
2759860961 0 016936 392 768refgcc_-m32_-march=pentiumpro_-O3_-fomit-frame-pointer2019082220190816
2760120606 0 013724 392 768refgcc_-m32_-march=pentium3_-O2_-fomit-frame-pointer2019082220190816
2773053606 0 013724 392 768refgcc_-m32_-march=pentium2_-O2_-fomit-frame-pointer2019082220190816
2792058606 0 013400 392 768refgcc_-m32_-march=pentium2_-O_-fomit-frame-pointer2019082220190816
28003882087 0 018440 392 768refgcc_-m32_-march=pentium-m_-O3_-fomit-frame-pointer2019082220190816
2997990606 0 013400 392 768refgcc_-m32_-march=pentium3_-O_-fomit-frame-pointer2019082220190816
3003159606 0 013440 392 768refgcc_-m32_-march=pentium-m_-O_-fomit-frame-pointer2019082220190816
3088080521 0 012132 384 768refgcc_-funroll-loops_-m32_-march=pentiumpro_-Os_-fomit-frame-pointer2019082220190816
3170739521 0 012132 384 768refgcc_-funroll-loops_-m32_-march=pentium2_-Os_-fomit-frame-pointer2019082220190816
3246165521 0 012164 384 768refgcc_-funroll-loops_-m32_-march=pentium-m_-Os_-fomit-frame-pointer2019082220190816
3259400518 0 012148 384 768refgcc_-m32_-march=pentiumpro_-Os_-fomit-frame-pointer2019082220190816
3315999518 0 012148 384 768refgcc_-m32_-march=pentium3_-Os_-fomit-frame-pointer2019082220190816
3317538518 0 012180 384 768refgcc_-m32_-march=pentium-m_-Os_-fomit-frame-pointer2019082220190816
3386007521 0 012132 384 768refgcc_-funroll-loops_-m32_-march=pentium3_-Os_-fomit-frame-pointer2019082220190816
3473928518 0 012148 384 768refgcc_-m32_-march=pentium2_-Os_-fomit-frame-pointer2019082220190816

Test failure

Implementation: avx
Security model: unknown
Compiler: gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 6, namely:
CompilerImplementations
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer avx
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer avx
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer avx
gcc -m32 -march=core-avx2 -O2 -fomit-frame-pointer ref
gcc -m32 -march=core-avx2 -O -fomit-frame-pointer ref
gcc -m32 -march=core-avx2 -Os -fomit-frame-pointer ref

Compiler output

Implementation: avx
Security model: unknown
Compiler: gcc -funroll-loops -m32 -O2 -fomit-frame-pointer
mult768.c: mult768.c: In function 'squeeze_3_x16':
mult768.c: mult768.c:19:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult768.c: {
mult768.c: ^
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
mult768.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(10923)),const_x16(3)));
mult768.c: ^~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:553:1: error: inlining failed in call to always_inline '_mm256_mullo_epi16': target specific option mismatch
mult768.c: _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(10923)),const_x16(3)));
mult768.c: ...

Number of similar (compiler,implementation) pairs: 156, namely:
CompilerImplementations
gcc -funroll-loops -m32 -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -O -fomit-frame-pointer avx
gcc -funroll-loops -m32 -Os -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=athlon -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=athlon -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=athlon -O -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=athlon -Os -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=barcelona -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=barcelona -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=barcelona -O -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=barcelona -Os -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=i386 -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=i386 -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=i386 -O -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=i386 -Os -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=i486 -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=i486 -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=i486 -O -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=i486 -Os -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=k6-2 -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=k6-2 -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=k6-2 -O -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=k6-2 -Os -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=k6-3 -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=k6-3 -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=k6-3 -O -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=k6-3 -Os -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=k6 -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=k6 -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=k6 -O -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=k6 -Os -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=k8 -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=k8 -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=k8 -O -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=k8 -Os -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=nocona -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=nocona -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=nocona -O -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=nocona -Os -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium-m -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium-m -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium-m -O -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium-m -Os -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium-mmx -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium-mmx -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium-mmx -O -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium-mmx -Os -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium2 -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium2 -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium2 -O -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium2 -Os -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium3 -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium3 -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium3 -O -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium3 -Os -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium4 -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium4 -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium4 -O -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium4 -Os -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium -O -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentium -Os -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentiumpro -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentiumpro -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentiumpro -O -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=pentiumpro -Os -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=prescott -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=prescott -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=prescott -O -fomit-frame-pointer avx
gcc -funroll-loops -m32 -march=prescott -Os -fomit-frame-pointer avx
gcc -m32 -O2 -fomit-frame-pointer avx
gcc -m32 -O3 -fomit-frame-pointer avx
gcc -m32 -O -fomit-frame-pointer avx
gcc -m32 -Os -fomit-frame-pointer avx
gcc -m32 -march=athlon -O2 -fomit-frame-pointer avx
gcc -m32 -march=athlon -O3 -fomit-frame-pointer avx
gcc -m32 -march=athlon -O -fomit-frame-pointer avx
gcc -m32 -march=athlon -Os -fomit-frame-pointer avx
gcc -m32 -march=core2 -O2 -fomit-frame-pointer avx
gcc -m32 -march=core2 -O3 -fomit-frame-pointer avx
gcc -m32 -march=core2 -O -fomit-frame-pointer avx
gcc -m32 -march=core2 -Os -fomit-frame-pointer avx
gcc -m32 -march=core2 -msse4.1 -O2 -fomit-frame-pointer avx
gcc -m32 -march=core2 -msse4.1 -O3 -fomit-frame-pointer avx
gcc -m32 -march=core2 -msse4.1 -O -fomit-frame-pointer avx
gcc -m32 -march=core2 -msse4.1 -Os -fomit-frame-pointer avx
gcc -m32 -march=core2 -msse4 -O2 -fomit-frame-pointer avx
gcc -m32 -march=core2 -msse4 -O3 -fomit-frame-pointer avx
gcc -m32 -march=core2 -msse4 -O -fomit-frame-pointer avx
gcc -m32 -march=core2 -msse4 -Os -fomit-frame-pointer avx
gcc -m32 -march=corei7 -O2 -fomit-frame-pointer avx
gcc -m32 -march=corei7 -O3 -fomit-frame-pointer avx
gcc -m32 -march=corei7 -O -fomit-frame-pointer avx
gcc -m32 -march=corei7 -Os -fomit-frame-pointer avx
gcc -m32 -march=i386 -O2 -fomit-frame-pointer avx
gcc -m32 -march=i386 -O3 -fomit-frame-pointer avx
gcc -m32 -march=i386 -O -fomit-frame-pointer avx
gcc -m32 -march=i386 -Os -fomit-frame-pointer avx
gcc -m32 -march=i486 -O2 -fomit-frame-pointer avx
gcc -m32 -march=i486 -O3 -fomit-frame-pointer avx
gcc -m32 -march=i486 -O -fomit-frame-pointer avx
gcc -m32 -march=i486 -Os -fomit-frame-pointer avx
gcc -m32 -march=k6-2 -O2 -fomit-frame-pointer avx
gcc -m32 -march=k6-2 -O3 -fomit-frame-pointer avx
gcc -m32 -march=k6-2 -O -fomit-frame-pointer avx
gcc -m32 -march=k6-2 -Os -fomit-frame-pointer avx
gcc -m32 -march=k6-3 -O2 -fomit-frame-pointer avx
gcc -m32 -march=k6-3 -O3 -fomit-frame-pointer avx
gcc -m32 -march=k6-3 -O -fomit-frame-pointer avx
gcc -m32 -march=k6-3 -Os -fomit-frame-pointer avx
gcc -m32 -march=k6 -O2 -fomit-frame-pointer avx
gcc -m32 -march=k6 -O3 -fomit-frame-pointer avx
gcc -m32 -march=k6 -O -fomit-frame-pointer avx
gcc -m32 -march=k6 -Os -fomit-frame-pointer avx
gcc -m32 -march=k8 -O2 -fomit-frame-pointer avx
gcc -m32 -march=k8 -O3 -fomit-frame-pointer avx
gcc -m32 -march=k8 -O -fomit-frame-pointer avx
gcc -m32 -march=k8 -Os -fomit-frame-pointer avx
gcc -m32 -march=nocona -O2 -fomit-frame-pointer avx
gcc -m32 -march=nocona -O3 -fomit-frame-pointer avx
gcc -m32 -march=nocona -O -fomit-frame-pointer avx
gcc -m32 -march=nocona -Os -fomit-frame-pointer avx
gcc -m32 -march=pentium-m -O2 -fomit-frame-pointer avx
gcc -m32 -march=pentium-m -O3 -fomit-frame-pointer avx
gcc -m32 -march=pentium-m -O -fomit-frame-pointer avx
gcc -m32 -march=pentium-m -Os -fomit-frame-pointer avx
gcc -m32 -march=pentium-mmx -O2 -fomit-frame-pointer avx
gcc -m32 -march=pentium-mmx -O3 -fomit-frame-pointer avx
gcc -m32 -march=pentium-mmx -O -fomit-frame-pointer avx
gcc -m32 -march=pentium-mmx -Os -fomit-frame-pointer avx
gcc -m32 -march=pentium2 -O2 -fomit-frame-pointer avx
gcc -m32 -march=pentium2 -O3 -fomit-frame-pointer avx
gcc -m32 -march=pentium2 -O -fomit-frame-pointer avx
gcc -m32 -march=pentium2 -Os -fomit-frame-pointer avx
gcc -m32 -march=pentium3 -O2 -fomit-frame-pointer avx
gcc -m32 -march=pentium3 -O3 -fomit-frame-pointer avx
gcc -m32 -march=pentium3 -O -fomit-frame-pointer avx
gcc -m32 -march=pentium3 -Os -fomit-frame-pointer avx
gcc -m32 -march=pentium4 -O2 -fomit-frame-pointer avx
gcc -m32 -march=pentium4 -O3 -fomit-frame-pointer avx
gcc -m32 -march=pentium4 -O -fomit-frame-pointer avx
gcc -m32 -march=pentium4 -Os -fomit-frame-pointer avx
gcc -m32 -march=pentium -O2 -fomit-frame-pointer avx
gcc -m32 -march=pentium -O3 -fomit-frame-pointer avx
gcc -m32 -march=pentium -O -fomit-frame-pointer avx
gcc -m32 -march=pentium -Os -fomit-frame-pointer avx
gcc -m32 -march=pentiumpro -O2 -fomit-frame-pointer avx
gcc -m32 -march=pentiumpro -O3 -fomit-frame-pointer avx
gcc -m32 -march=pentiumpro -O -fomit-frame-pointer avx
gcc -m32 -march=pentiumpro -Os -fomit-frame-pointer avx
gcc -m32 -march=prescott -O2 -fomit-frame-pointer avx
gcc -m32 -march=prescott -O3 -fomit-frame-pointer avx
gcc -m32 -march=prescott -O -fomit-frame-pointer avx
gcc -m32 -march=prescott -Os -fomit-frame-pointer avx

Compiler output

Implementation: avx
Security model: unknown
Compiler: gcc -m32 -march=barcelona -O2 -fomit-frame-pointer
mult768.c: mult768.c: In function 'squeeze_3_x16':
mult768.c: mult768.c:19:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult768.c: {
mult768.c: ^
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
mult768.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(10923)),const_x16(3)));
mult768.c: ^~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:553:1: error: inlining failed in call to always_inline '_mm256_mullo_epi16': target specific option mismatch
mult768.c: _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(10923)),const_x16(3)));
mult768.c: ...
mult768.c: mult768.c: In function 'squeeze_3_x16':
mult768.c: mult768.c:19:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult768.c: {
mult768.c: ^
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
mult768.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(10923)),const_x16(3)));
mult768.c: ^~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:553:1: error: inlining failed in call to always_inline '_mm256_mullo_epi16': target specific option mismatch
mult768.c: _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(10923)),const_x16(3)));
mult768.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -m32 -march=barcelona -O2 -fomit-frame-pointer avx
gcc -m32 -march=barcelona -O3 -fomit-frame-pointer avx
gcc -m32 -march=barcelona -O -fomit-frame-pointer avx
gcc -m32 -march=barcelona -Os -fomit-frame-pointer avx

Compiler output

Implementation: avx
Security model: unknown
Compiler: gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: mult768.c: In function 'squeeze_3_x16':
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
mult768.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(10923)),const_x16(3)));
mult768.c: ^~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:553:1: error: inlining failed in call to always_inline '_mm256_mullo_epi16': target specific option mismatch
mult768.c: _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(10923)),const_x16(3)));
mult768.c: ^~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: ...

Number of similar (compiler,implementation) pairs: 12, namely:
CompilerImplementations
gcc -m32 -march=core-avx-i -O2 -fomit-frame-pointer avx
gcc -m32 -march=core-avx-i -O3 -fomit-frame-pointer avx
gcc -m32 -march=core-avx-i -O -fomit-frame-pointer avx
gcc -m32 -march=core-avx-i -Os -fomit-frame-pointer avx
gcc -m32 -march=corei7-avx -O2 -fomit-frame-pointer avx
gcc -m32 -march=corei7-avx -O3 -fomit-frame-pointer avx
gcc -m32 -march=corei7-avx -O -fomit-frame-pointer avx
gcc -m32 -march=corei7-avx -Os -fomit-frame-pointer avx
gcc -m32 -march=native -mtune=native -O2 -fomit-frame-pointer avx
gcc -m32 -march=native -mtune=native -O3 -fomit-frame-pointer avx
gcc -m32 -march=native -mtune=native -O -fomit-frame-pointer avx
gcc -m32 -march=native -mtune=native -Os -fomit-frame-pointer avx