Implementation notes: amd64, gpu, crypto_core/inv3sntrup761

Computer: gpu
Architecture: amd64
CPU ID: GenuineIntel-000206d7-bfebfbff
SUPERCOP version: 20190816
Operation: crypto_core
Primitive: inv3sntrup761
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
83650564341 0 017560 784 832refgcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer2019082120190816
84532894410 0 017544 784 832refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2019082120190816
84676894341 0 017560 784 832refgcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer2019082120190816
85349434341 0 017560 784 832refgcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2019082120190816
93779284548 0 017704 784 832refgcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer2019082120190816
93789754548 0 017552 784 832refgcc_-m64_-march=corei7_-O3_-fomit-frame-pointer2019082120190816
93928594548 0 017640 784 832refgcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2019082120190816
98983984745 0 017896 784 832refgcc_-m64_-march=core2_-O3_-fomit-frame-pointer2019082120190816
110564737557 0 023816 784 832refgcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer2019082120190816
113042797381 0 023536 784 832refgcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer2019082120190816
113227476668 0 020344 784 832refgcc_-march=barcelona_-O3_-fomit-frame-pointer2019082120190816
113705106556 0 020064 784 832refgcc_-march=k8_-O3_-fomit-frame-pointer2019082120190816
113723524120 0 017344 784 832refgcc_-O3_-fomit-frame-pointer2019082120190816
114208944120 0 017344 784 832refgcc_-m64_-O3_-fomit-frame-pointer2019082120190816
114241834658 0 020208 784 832refgcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer2019082120190816
114559414658 0 020208 784 832refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082120190816
115107186556 0 020064 784 832refgcc_-m64_-march=k8_-O3_-fomit-frame-pointer2019082120190816
1151164813336 0 020344 784 832refgcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer2019082120190816
115778447381 0 023536 784 832refgcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer2019082120190816
116016254658 0 020208 784 832refgcc_-funroll-loops_-O3_-fomit-frame-pointer2019082120190816
117583924120 0 017344 784 832refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082120190816
117717157557 0 023816 784 832refgcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer2019082120190816
118510164342 0 017352 784 832refgcc_-march=nocona_-O3_-fomit-frame-pointer2019082120190816
118834684342 0 017352 784 832refgcc_-m64_-march=nocona_-O3_-fomit-frame-pointer2019082120190816
121461064916 0 020232 784 832refgcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer2019082120190816
122911864916 0 020232 784 832refgcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer2019082120190816
255120125692 0 020733 760 1128refclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019082120190816
256128074064 0 019733 760 1128refclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2019082120190816
264845245692 0 020733 760 1128refclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019082120190816
265601914064 0 019733 760 1128refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082120190816
311200165297 0 022029 760 776refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019082120190816
313180925297 0 023357 760 776refclang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082120190816
315506595297 0 023357 760 776refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082120190816
318315305297 0 023357 760 776refclang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082120190816
450107122714 0 016797 768 832refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082120190816
456600062652 0 016645 768 832refgcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer2019082120190816
458566572714 0 016797 768 832refgcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer2019082120190816
462097452714 0 016797 768 832refgcc_-funroll-loops_-O2_-fomit-frame-pointer2019082120190816
468154952652 0 016645 768 832refgcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer2019082120190816
471292562668 0 016797 768 832refgcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer2019082120190816
475924152668 0 016797 768 832refgcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer2019082120190816
477618482634 0 016813 768 832refgcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer2019082120190816
479274072634 0 016613 768 832refgcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer2019082120190816
491732342670 0 016853 768 832refgcc_-funroll-loops_-O_-fomit-frame-pointer2019082120190816
497947152634 0 016813 768 832refgcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer2019082120190816
506677832634 0 016613 768 832refgcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer2019082120190816
508386482670 0 016853 768 832refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019082120190816
518207162670 0 016853 768 832refgcc_-funroll-loops_-m64_-O_-fomit-frame-pointer2019082120190816
56002205862 0 011661 768 832refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082120190816
56499039862 0 011661 768 832refgcc_-O2_-fomit-frame-pointer2019082120190816
57268488862 0 011621 768 832refgcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2019082120190816
57269982862 0 011613 768 832refgcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer2019082120190816
57389088836 0 011645 768 832refgcc_-m64_-march=k8_-O2_-fomit-frame-pointer2019082120190816
57398001862 0 011621 768 832refgcc_-m64_-march=core2_-O2_-fomit-frame-pointer2019082120190816
57460086862 0 011661 768 832refgcc_-m64_-O2_-fomit-frame-pointer2019082120190816
57773721862 0 011621 768 832refgcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2019082120190816
57824856862 0 011613 768 832refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2019082120190816
57880674862 0 011613 768 832refgcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2019082120190816
579028261720 0 011941 768 832refgcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer2019082120190816
58065888862 0 011613 768 832refgcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2019082120190816
58230669836 0 011645 768 832refgcc_-march=k8_-O2_-fomit-frame-pointer2019082120190816
58365531862 0 011613 768 832refgcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer2019082120190816
58941581860 0 011941 768 832refgcc_-march=barcelona_-O2_-fomit-frame-pointer2019082120190816
59120566860 0 011597 768 832refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019082120190816
59426322845 0 011565 768 832refgcc_-march=barcelona_-O_-fomit-frame-pointer2019082120190816
60405378860 0 011549 768 832refgcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2019082120190816
60663420860 0 011549 768 832refgcc_-m64_-march=corei7_-O_-fomit-frame-pointer2019082120190816
60786915860 0 011549 768 832refgcc_-m64_-march=core2_-O_-fomit-frame-pointer2019082120190816
60851903860 0 011597 768 832refgcc_-O_-fomit-frame-pointer2019082120190816
611204281690 0 011565 768 832refgcc_-m64_-march=barcelona_-O_-fomit-frame-pointer2019082120190816
61141479860 0 011549 768 832refgcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer2019082120190816
61188716860 0 011549 768 832refgcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2019082120190816
61232085845 0 011637 768 832refgcc_-march=k8_-O_-fomit-frame-pointer2019082120190816
61358646860 0 011549 768 832refgcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer2019082120190816
61364592860 0 011549 768 832refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2019082120190816
61481248860 0 011597 768 832refgcc_-m64_-O_-fomit-frame-pointer2019082120190816
61956170845 0 011637 768 832refgcc_-m64_-march=k8_-O_-fomit-frame-pointer2019082120190816
62505959860 0 011549 768 832refgcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2019082120190816
62971319766 0 010561 752 800refgcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer2019082120190816
62977044766 0 010561 752 800refgcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer2019082120190816
63013191740 0 010505 752 800refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2019082120190816
63052242742 0 010505 752 800refgcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2019082120190816
63337743742 0 010505 752 800refgcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2019082120190816
63363378766 0 010561 752 800refgcc_-funroll-loops_-Os_-fomit-frame-pointer2019082120190816
63388704742 0 010521 752 800refgcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer2019082120190816
63431642766 0 010561 752 800refgcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer2019082120190816
63767406766 0 010561 752 800refgcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer2019082120190816
63837867742 0 010521 752 800refgcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2019082120190816
63894640742 0 010505 752 800refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082120190816
63904311742 0 010505 752 800refgcc_-m64_-march=k8_-Os_-fomit-frame-pointer2019082120190816
63959424742 0 010505 752 800refgcc_-m64_-march=core2_-Os_-fomit-frame-pointer2019082120190816
63974574742 0 010505 752 800refgcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2019082120190816
63975861766 0 010561 752 800refgcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer2019082120190816
63977856742 0 010505 752 800refgcc_-m64_-Os_-fomit-frame-pointer2019082120190816
64097166742 0 010505 752 800refgcc_-m64_-march=nocona_-Os_-fomit-frame-pointer2019082120190816
64311909742 0 010521 752 800refgcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer2019082120190816
64326966766 0 010561 752 800refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082120190816
64665065742 0 010505 752 800refgcc_-march=nocona_-Os_-fomit-frame-pointer2019082120190816
64727214742 0 010505 752 800refgcc_-march=barcelona_-Os_-fomit-frame-pointer2019082120190816
648548701484 0 010505 752 800refgcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer2019082120190816
65220066742 0 010505 752 800refgcc_-Os_-fomit-frame-pointer2019082120190816
65223324742 0 010505 752 800refgcc_-march=k8_-Os_-fomit-frame-pointer2019082120190816
66432573766 0 010561 752 800refgcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer2019082120190816
67095218766 0 010561 752 800refgcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer2019082120190816
676887242437 0 016645 768 832refgcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer2019082120190816
682492922437 0 016645 768 832refgcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer2019082120190816
69912969817 0 011365 768 832refgcc_-march=nocona_-O2_-fomit-frame-pointer2019082120190816
70353984888 0 011741 768 832refgcc_-march=nocona_-O_-fomit-frame-pointer2019082120190816
71463778817 0 011365 768 832refgcc_-m64_-march=nocona_-O2_-fomit-frame-pointer2019082120190816
72924657888 0 011741 768 832refgcc_-m64_-march=nocona_-O_-fomit-frame-pointer2019082120190816
745617872458 0 016237 768 832refgcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer2019082120190816
749251142458 0 016237 768 832refgcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer2019082120190816
1484437411640 0 013718 760 792refcc2019082120190816
1488114861640 0 013718 760 792refgcc2019082120190816
1506685831640 0 013718 760 792refgcc_-funroll-loops2019082120190816

Test failure

Implementation: avx
Security model: unknown
Compiler: gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 6, namely:
CompilerImplementations
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer avx
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer avx
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer avx
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer ref
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer ref
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer ref

Compiler output

Implementation: avx
Security model: unknown
Compiler: cc
r3_recip.c: r3_recip.c: In function 'vec256_frombits':
r3_recip.c: r3_recip.c:30:12: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
r3_recip.c: vec256 b0 = _mm256_loadu_si256((vec256 *) b); b += 32; /* 0,1,...,31 */
r3_recip.c: ^~
r3_recip.c: r3_recip.c: In function 'vec256_swap':
r3_recip.c: r3_recip.c:178:20: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
r3_recip.c: static inline void vec256_swap(vec256 *f,vec256 *g,int len,vec256 mask)
r3_recip.c: ^~~~~~~~~~~
r3_recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
r3_recip.c: from r3_recip.c:3:
r3_recip.c: r3_recip.c: In function 'vec256_bit0mask':
r3_recip.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:1459:1: error: inlining failed in call to always_inline '_mm256_castsi256_si128': target specific option mismatch
r3_recip.c: _mm256_castsi256_si128 (__m256i __A)
r3_recip.c: ^~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c:230:12: note: called from here
r3_recip.c: return -(_mm_cvtsi128_si32(_mm256_castsi256_si128(f[0])) & 1);
r3_recip.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Number of similar (compiler,implementation) pairs: 3, namely:
CompilerImplementations
cc avx
gcc avx
gcc -funroll-loops avx

Compiler output

Implementation: avx
Security model: unknown
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments
r3_recip.c: r3_recip.c:362:11: error: always_inline function '_mm256_set_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'sse4.2'
r3_recip.c: F0[0] = _mm256_set_epi32(0,0,0,0,0,0,0,1);
r3_recip.c: ^
r3_recip.c: r3_recip.c:363:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'sse4.2'
r3_recip.c: F0[1] = _mm256_set1_epi32(0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:364:11: error: always_inline function '_mm256_set_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'sse4.2'
r3_recip.c: F0[2] = _mm256_set_epi32(0,0,0,0,1073741824,0,1073741824,0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:365:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'sse4.2'
r3_recip.c: F1[0] = _mm256_set1_epi32(0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:366:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'sse4.2'
r3_recip.c: F1[1] = _mm256_set1_epi32(0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:367:11: error: always_inline function '_mm256_set_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'sse4.2'
r3_recip.c: F1[2] = _mm256_set_epi32(0,0,0,0,1073741824,0,1073741824,0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:369:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'sse4.2'
r3_recip.c: V0[0] = _mm256_set1_epi32(0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:370:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'sse4.2'
r3_recip.c: V1[0] = _mm256_set1_epi32(0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:371:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'sse4.2'
r3_recip.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
clang -O3 -fomit-frame-pointer -Qunused-arguments avx
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx

Compiler output

Implementation: avx
Security model: unknown
Compiler: clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments
r3_recip.c: r3_recip.c:39:17: error: always_inline function '_mm256_unpacklo_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
r3_recip.c: vec256 c0 = _mm256_unpacklo_epi32(b0,b1); /* 0 1 2 3 32 33 34 35 4 5 6 7 36 37 38 39 ... 55 */
r3_recip.c: ^
r3_recip.c: r3_recip.c:40:17: error: always_inline function '_mm256_unpackhi_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
r3_recip.c: vec256 c1 = _mm256_unpackhi_epi32(b0,b1); /* 8 9 10 11 40 41 42 43 ... 63 */
r3_recip.c: ^
r3_recip.c: r3_recip.c:41:17: error: always_inline function '_mm256_unpacklo_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
r3_recip.c: vec256 c2 = _mm256_unpacklo_epi32(b2,b3);
r3_recip.c: ^
r3_recip.c: r3_recip.c:42:17: error: always_inline function '_mm256_unpackhi_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
r3_recip.c: vec256 c3 = _mm256_unpackhi_epi32(b2,b3);
r3_recip.c: ^
r3_recip.c: r3_recip.c:43:17: error: always_inline function '_mm256_unpacklo_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
r3_recip.c: vec256 c4 = _mm256_unpacklo_epi32(b4,b5);
r3_recip.c: ^
r3_recip.c: r3_recip.c:44:17: error: always_inline function '_mm256_unpackhi_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
r3_recip.c: vec256 c5 = _mm256_unpackhi_epi32(b4,b5);
r3_recip.c: ^
r3_recip.c: r3_recip.c:45:17: error: always_inline function '_mm256_unpacklo_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
r3_recip.c: vec256 c6 = _mm256_unpacklo_epi32(b6,b7);
r3_recip.c: ^
r3_recip.c: r3_recip.c:46:17: error: always_inline function '_mm256_unpackhi_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
r3_recip.c: vec256 c7 = _mm256_unpackhi_epi32(b6,b7);
r3_recip.c: ^
r3_recip.c: r3_recip.c:48:22: error: always_inline function '_mm256_slli_epi32' requires target feature 'avx2', but would be inlined into function 'vec256_frombits' that is compiled without support for 'avx2'
r3_recip.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments avx
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments avx
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments avx
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx

Compiler output

Implementation: avx
Security model: unknown
Compiler: gcc -O2 -fomit-frame-pointer
r3_recip.c: r3_recip.c: In function 'crypto_core_inv3sntrup761_avx':
r3_recip.c: r3_recip.c:362:9: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
r3_recip.c: F0[0] = _mm256_set_epi32(0,0,0,0,0,0,0,1);
r3_recip.c: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c: In function 'vec256_swap':
r3_recip.c: r3_recip.c:178:20: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
r3_recip.c: static inline void vec256_swap(vec256 *f,vec256 *g,int len,vec256 mask)
r3_recip.c: ^~~~~~~~~~~
r3_recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
r3_recip.c: from r3_recip.c:3:
r3_recip.c: r3_recip.c: In function 'vec256_frombits':
r3_recip.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:597:1: error: inlining failed in call to always_inline '_mm256_shuffle_epi32': target specific option mismatch
r3_recip.c: _mm256_shuffle_epi32 (__m256i __A, const int __mask)
r3_recip.c: ^~~~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c:69:7: note: called from here
r3_recip.c: h = _mm256_shuffle_epi32(h,0xd8);
r3_recip.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
r3_recip.c: from r3_recip.c:3:
r3_recip.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:1068:1: error: inlining failed in call to always_inline '_mm256_permute4x64_epi64': target specific option mismatch
r3_recip.c: _mm256_permute4x64_epi64 (__m256i __X, const int __M)
r3_recip.c: ^~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c:68:7: note: called from here
r3_recip.c: h = _mm256_permute4x64_epi64(h,0xd8);
r3_recip.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: ...

Number of similar (compiler,implementation) pairs: 84, namely:
CompilerImplementations
gcc -O2 -fomit-frame-pointer avx
gcc -O3 -fomit-frame-pointer avx
gcc -O -fomit-frame-pointer avx
gcc -Os -fomit-frame-pointer avx
gcc -fno-schedule-insns -O2 -fomit-frame-pointer avx
gcc -fno-schedule-insns -O3 -fomit-frame-pointer avx
gcc -fno-schedule-insns -O -fomit-frame-pointer avx
gcc -fno-schedule-insns -Os -fomit-frame-pointer avx
gcc -funroll-loops -O2 -fomit-frame-pointer avx
gcc -funroll-loops -O3 -fomit-frame-pointer avx
gcc -funroll-loops -O -fomit-frame-pointer avx
gcc -funroll-loops -Os -fomit-frame-pointer avx
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer avx
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer avx
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer avx
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer avx
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m64 -O -fomit-frame-pointer avx
gcc -funroll-loops -m64 -Os -fomit-frame-pointer avx
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer avx
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer avx
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer avx
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer avx
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer avx
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer avx
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer avx
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer avx
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer avx
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer avx
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer avx
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer avx
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer avx
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer avx
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer avx
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer avx
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer avx
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer avx
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer avx
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer avx
gcc -m64 -O2 -fomit-frame-pointer avx
gcc -m64 -O3 -fomit-frame-pointer avx
gcc -m64 -O -fomit-frame-pointer avx
gcc -m64 -Os -fomit-frame-pointer avx
gcc -m64 -march=core2 -O2 -fomit-frame-pointer avx
gcc -m64 -march=core2 -O3 -fomit-frame-pointer avx
gcc -m64 -march=core2 -O -fomit-frame-pointer avx
gcc -m64 -march=core2 -Os -fomit-frame-pointer avx
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer avx
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer avx
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer avx
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer avx
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer avx
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer avx
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer avx
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer avx
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer avx
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer avx
gcc -m64 -march=corei7 -O -fomit-frame-pointer avx
gcc -m64 -march=corei7 -Os -fomit-frame-pointer avx
gcc -m64 -march=k8 -O2 -fomit-frame-pointer avx
gcc -m64 -march=k8 -O3 -fomit-frame-pointer avx
gcc -m64 -march=k8 -O -fomit-frame-pointer avx
gcc -m64 -march=k8 -Os -fomit-frame-pointer avx
gcc -m64 -march=nocona -O2 -fomit-frame-pointer avx
gcc -m64 -march=nocona -O3 -fomit-frame-pointer avx
gcc -m64 -march=nocona -O -fomit-frame-pointer avx
gcc -m64 -march=nocona -Os -fomit-frame-pointer avx
gcc -march=barcelona -O2 -fomit-frame-pointer avx
gcc -march=barcelona -O3 -fomit-frame-pointer avx
gcc -march=barcelona -O -fomit-frame-pointer avx
gcc -march=barcelona -Os -fomit-frame-pointer avx
gcc -march=k8 -O2 -fomit-frame-pointer avx
gcc -march=k8 -O3 -fomit-frame-pointer avx
gcc -march=k8 -O -fomit-frame-pointer avx
gcc -march=k8 -Os -fomit-frame-pointer avx
gcc -march=nocona -O2 -fomit-frame-pointer avx
gcc -march=nocona -O3 -fomit-frame-pointer avx
gcc -march=nocona -O -fomit-frame-pointer avx
gcc -march=nocona -Os -fomit-frame-pointer avx

Compiler output

Implementation: avx
Security model: unknown
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
r3_recip.c: r3_recip.c: In function 'crypto_core_inv3sntrup761_avx':
r3_recip.c: r3_recip.c:362:9: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
r3_recip.c: F0[0] = _mm256_set_epi32(0,0,0,0,0,0,0,1);
r3_recip.c: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c: In function 'vec256_swap':
r3_recip.c: r3_recip.c:178:20: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
r3_recip.c: static inline void vec256_swap(vec256 *f,vec256 *g,int len,vec256 mask)
r3_recip.c: ^~~~~~~~~~~
r3_recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
r3_recip.c: from r3_recip.c:3:
r3_recip.c: r3_recip.c: In function 'vec256_frombits':
r3_recip.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:597:1: error: inlining failed in call to always_inline '_mm256_shuffle_epi32': target specific option mismatch
r3_recip.c: _mm256_shuffle_epi32 (__m256i __A, const int __mask)
r3_recip.c: ^~~~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c:69:7: note: called from here
r3_recip.c: h = _mm256_shuffle_epi32(h,0xd8);
r3_recip.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
r3_recip.c: from r3_recip.c:3:
r3_recip.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:1068:1: error: inlining failed in call to always_inline '_mm256_permute4x64_epi64': target specific option mismatch
r3_recip.c: _mm256_permute4x64_epi64 (__m256i __X, const int __M)
r3_recip.c: ^~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c:68:7: note: called from here
r3_recip.c: h = _mm256_permute4x64_epi64(h,0xd8);
r3_recip.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: ...
r3_recip.c: r3_recip.c: In function 'crypto_core_inv3sntrup761_avx':
r3_recip.c: r3_recip.c:362:9: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
r3_recip.c: F0[0] = _mm256_set_epi32(0,0,0,0,0,0,0,1);
r3_recip.c: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c: In function 'vec256_swap':
r3_recip.c: r3_recip.c:178:20: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
r3_recip.c: static inline void vec256_swap(vec256 *f,vec256 *g,int len,vec256 mask)
r3_recip.c: ^~~~~~~~~~~
r3_recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
r3_recip.c: from r3_recip.c:3:
r3_recip.c: r3_recip.c: In function 'vec256_frombits':
r3_recip.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:597:1: error: inlining failed in call to always_inline '_mm256_shuffle_epi32': target specific option mismatch
r3_recip.c: _mm256_shuffle_epi32 (__m256i __A, const int __mask)
r3_recip.c: ^~~~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c:69:7: note: called from here
r3_recip.c: h = _mm256_shuffle_epi32(h,0xd8);
r3_recip.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
r3_recip.c: from r3_recip.c:3:
r3_recip.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:1068:1: error: inlining failed in call to always_inline '_mm256_permute4x64_epi64': target specific option mismatch
r3_recip.c: _mm256_permute4x64_epi64 (__m256i __X, const int __M)
r3_recip.c: ^~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c:68:7: note: called from here
r3_recip.c: h = _mm256_permute4x64_epi64(h,0xd8);
r3_recip.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer avx
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer avx
gcc -m64 -march=barcelona -O -fomit-frame-pointer avx
gcc -m64 -march=barcelona -Os -fomit-frame-pointer avx

Compiler output

Implementation: avx
Security model: unknown
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer
r3_recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
r3_recip.c: from r3_recip.c:3:
r3_recip.c: r3_recip.c: In function 'vec256_frombits':
r3_recip.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:597:1: error: inlining failed in call to always_inline '_mm256_shuffle_epi32': target specific option mismatch
r3_recip.c: _mm256_shuffle_epi32 (__m256i __A, const int __mask)
r3_recip.c: ^~~~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c:69:7: note: called from here
r3_recip.c: h = _mm256_shuffle_epi32(h,0xd8);
r3_recip.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
r3_recip.c: from r3_recip.c:3:
r3_recip.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:1068:1: error: inlining failed in call to always_inline '_mm256_permute4x64_epi64': target specific option mismatch
r3_recip.c: _mm256_permute4x64_epi64 (__m256i __X, const int __M)
r3_recip.c: ^~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c:68:7: note: called from here
r3_recip.c: h = _mm256_permute4x64_epi64(h,0xd8);
r3_recip.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
r3_recip.c: from r3_recip.c:3:
r3_recip.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:588:1: error: inlining failed in call to always_inline '_mm256_shuffle_epi8': target specific option mismatch
r3_recip.c: _mm256_shuffle_epi8 (__m256i __X, __m256i __Y)
r3_recip.c: ^~~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c:67:7: note: called from here
r3_recip.c: h = _mm256_shuffle_epi8(h,TRANSPOSE);
r3_recip.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: ...

Number of similar (compiler,implementation) pairs: 16, namely:
CompilerImplementations
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer avx
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer avx
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer avx
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer avx
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer avx
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer avx
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer avx
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer avx
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer avx
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer avx
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer avx
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer avx
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv avx
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv avx
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv avx
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv avx