Implementation notes: amd64, gpu, crypto_core/inv3sntrup857

Computer: gpu
Architecture: amd64
CPU ID: GenuineIntel-000206d7-bfebfbff
SUPERCOP version: 20190816
Operation: crypto_core
Primitive: inv3sntrup857

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
10039590	4341 0 0	17560 784 832	`ref`	`gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer`	20190821	20190816
10111671	4341 0 0	17560 784 832	`ref`	`gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer`	20190821	20190816
10145835	4410 0 0	17544 784 832	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20190821	20190816
10278162	4341 0 0	17560 784 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20190821	20190816
11182479	4548 0 0	17640 784 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer`	20190821	20190816
11389896	4548 0 0	17704 784 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer`	20190821	20190816
11488287	4548 0 0	17552 784 832	`ref`	`gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer`	20190821	20190816
11891799	4745 0 0	17896 784 832	`ref`	`gcc_-m64_-march=core2_-O3_-fomit-frame-pointer`	20190821	20190816
13712760	7501 0 0	23768 784 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190821	20190816
13793430	4120 0 0	17344 784 832	`ref`	`gcc_-O3_-fomit-frame-pointer`	20190821	20190816
13865274	4120 0 0	17344 784 832	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190821	20190816
13879392	13208 0 0	20280 784 832	`ref`	`gcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190821	20190816
13881975	7341 0 0	23504 784 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190821	20190816
13887348	4342 0 0	17352 784 832	`ref`	`gcc_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190821	20190816
13944901	4120 0 0	17344 784 832	`ref`	`gcc_-m64_-O3_-fomit-frame-pointer`	20190821	20190816
14053581	4342 0 0	17352 784 832	`ref`	`gcc_-march=nocona_-O3_-fomit-frame-pointer`	20190821	20190816
14070075	6564 0 0	20064 784 832	`ref`	`gcc_-march=k8_-O3_-fomit-frame-pointer`	20190821	20190816
14118183	4658 0 0	20208 784 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190821	20190816
14131587	4658 0 0	20208 784 832	`ref`	`gcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer`	20190821	20190816
14171982	6564 0 0	20064 784 832	`ref`	`gcc_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190821	20190816
14186169	7501 0 0	23768 784 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer`	20190821	20190816
14207310	6604 0 0	20280 784 832	`ref`	`gcc_-march=barcelona_-O3_-fomit-frame-pointer`	20190821	20190816
14221013	7341 0 0	23504 784 832	`ref`	`gcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer`	20190821	20190816
14276940	4916 0 0	20232 784 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190821	20190816
14415813	4658 0 0	20208 784 832	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20190821	20190816
14459877	4916 0 0	20232 784 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer`	20190821	20190816
31046829	4694 0 0	20365 760 1128	`ref`	`clang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments`	20190821	20190816
32009709	5996 0 0	21037 760 1128	`ref`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20190821	20190816
32018429	4694 0 0	20365 760 1128	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190821	20190816
32163853	5996 0 0	21037 760 1128	`ref`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20190821	20190816
38573715	5393 0 0	22125 760 776	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20190821	20190816
38896929	5393 0 0	23453 760 776	`ref`	`clang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190821	20190816
39245727	5393 0 0	23453 760 776	`ref`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190821	20190816
39935304	5393 0 0	23453 760 776	`ref`	`clang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190821	20190816
52816485	2652 0 0	16645 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190821	20190816
54506360	2714 0 0	16797 768 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190821	20190816
56097192	2668 0 0	16797 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190821	20190816
57155736	2714 0 0	16797 768 832	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20190821	20190816
57326184	2668 0 0	16797 768 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer`	20190821	20190816
58759341	2652 0 0	16645 768 832	`ref`	`gcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer`	20190821	20190816
59161800	2634 0 0	16613 768 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer`	20190821	20190816
59315023	2714 0 0	16797 768 832	`ref`	`gcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer`	20190821	20190816
59315676	2634 0 0	16813 768 832	`ref`	`gcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer`	20190821	20190816
59679876	2634 0 0	16613 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190821	20190816
61152556	2670 0 0	16853 768 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190821	20190816
62405964	2670 0 0	16853 768 832	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20190821	20190816
63082449	2670 0 0	16853 768 832	`ref`	`gcc_-funroll-loops_-m64_-O_-fomit-frame-pointer`	20190821	20190816
63194985	2634 0 0	16813 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer`	20190821	20190816
68979417	862 0 0	11613 768 832	`ref`	`gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer`	20190821	20190816
69342042	862 0 0	11661 768 832	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190821	20190816
71254083	836 0 0	11645 768 832	`ref`	`gcc_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190821	20190816
71336985	862 0 0	11661 768 832	`ref`	`gcc_-m64_-O2_-fomit-frame-pointer`	20190821	20190816
71346636	836 0 0	11645 768 832	`ref`	`gcc_-march=k8_-O2_-fomit-frame-pointer`	20190821	20190816
71542401	862 0 0	11621 768 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20190821	20190816
71903949	862 0 0	11621 768 832	`ref`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20190821	20190816
72040737	860 0 0	11941 768 832	`ref`	`gcc_-march=barcelona_-O2_-fomit-frame-pointer`	20190821	20190816
72082160	860 0 0	11549 768 832	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20190821	20190816
72084513	1720 0 0	11941 768 832	`ref`	`gcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190821	20190816
72124815	862 0 0	11613 768 832	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20190821	20190816
72169911	862 0 0	11621 768 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20190821	20190816
72172137	862 0 0	11613 768 832	`ref`	`gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer`	20190821	20190816
72232164	862 0 0	11613 768 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20190821	20190816
72246840	862 0 0	11613 768 832	`ref`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20190821	20190816
72483198	862 0 0	11661 768 832	`ref`	`gcc_-O2_-fomit-frame-pointer`	20190821	20190816
72767547	860 0 0	11549 768 832	`ref`	`gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer`	20190821	20190816
73224240	845 0 0	11565 768 832	`ref`	`gcc_-march=barcelona_-O_-fomit-frame-pointer`	20190821	20190816
74778471	860 0 0	11549 768 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20190821	20190816
74823732	860 0 0	11549 768 832	`ref`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20190821	20190816
75289659	860 0 0	11549 768 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20190821	20190816
75293994	845 0 0	11637 768 832	`ref`	`gcc_-march=k8_-O_-fomit-frame-pointer`	20190821	20190816
75309414	1690 0 0	11565 768 832	`ref`	`gcc_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190821	20190816
75460893	860 0 0	11549 768 832	`ref`	`gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer`	20190821	20190816
75523206	860 0 0	11549 768 832	`ref`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20190821	20190816
75646956	860 0 0	11549 768 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20190821	20190816
75839151	845 0 0	11637 768 832	`ref`	`gcc_-m64_-march=k8_-O_-fomit-frame-pointer`	20190821	20190816
76236201	860 0 0	11597 768 832	`ref`	`gcc_-O_-fomit-frame-pointer`	20190821	20190816
76516258	860 0 0	11597 768 832	`ref`	`gcc_-m64_-O_-fomit-frame-pointer`	20190821	20190816
76953568	860 0 0	11597 768 832	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190821	20190816
79204625	766 0 0	10561 752 800	`ref`	`gcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer`	20190821	20190816
79635111	766 0 0	10561 752 800	`ref`	`gcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer`	20190821	20190816
79694829	742 0 0	10521 752 800	`ref`	`gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer`	20190821	20190816
79766136	742 0 0	10505 752 800	`ref`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20190821	20190816
79794627	742 0 0	10521 752 800	`ref`	`gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer`	20190821	20190816
79885014	742 0 0	10521 752 800	`ref`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20190821	20190816
79962759	766 0 0	10561 752 800	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20190821	20190816
80095662	740 0 0	10505 752 800	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20190821	20190816
80104248	742 0 0	10505 752 800	`ref`	`gcc_-m64_-Os_-fomit-frame-pointer`	20190821	20190816
80158776	1484 0 0	10505 752 800	`ref`	`gcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190821	20190816
80225865	742 0 0	10505 752 800	`ref`	`gcc_-march=barcelona_-Os_-fomit-frame-pointer`	20190821	20190816
80498205	766 0 0	10561 752 800	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190821	20190816
80677401	742 0 0	10505 752 800	`ref`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20190821	20190816
80794767	742 0 0	10505 752 800	`ref`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20190821	20190816
81011193	766 0 0	10561 752 800	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190821	20190816
81036309	766 0 0	10561 752 800	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190821	20190816
81269289	742 0 0	10505 752 800	`ref`	`gcc_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190821	20190816
81413867	766 0 0	10561 752 800	`ref`	`gcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer`	20190821	20190816
81549897	742 0 0	10505 752 800	`ref`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20190821	20190816
81554145	766 0 0	10561 752 800	`ref`	`gcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer`	20190821	20190816
81669260	742 0 0	10505 752 800	`ref`	`gcc_-Os_-fomit-frame-pointer`	20190821	20190816
81844443	742 0 0	10505 752 800	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190821	20190816
82041231	742 0 0	10505 752 800	`ref`	`gcc_-march=k8_-Os_-fomit-frame-pointer`	20190821	20190816
82065126	742 0 0	10505 752 800	`ref`	`gcc_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190821	20190816
82087342	766 0 0	10561 752 800	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190821	20190816
82137195	742 0 0	10505 752 800	`ref`	`gcc_-march=nocona_-Os_-fomit-frame-pointer`	20190821	20190816
85631178	817 0 0	11365 768 832	`ref`	`gcc_-march=nocona_-O2_-fomit-frame-pointer`	20190821	20190816
87687348	888 0 0	11741 768 832	`ref`	`gcc_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190821	20190816
88234020	817 0 0	11365 768 832	`ref`	`gcc_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190821	20190816
88239513	2437 0 0	16645 768 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer`	20190821	20190816
89296350	2437 0 0	16645 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190821	20190816
89610999	888 0 0	11741 768 832	`ref`	`gcc_-march=nocona_-O_-fomit-frame-pointer`	20190821	20190816
90829344	2458 0 0	16237 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190821	20190816
92796609	2458 0 0	16237 768 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer`	20190821	20190816
187802584	1640 0 0	13718 760 792	`ref`	`gcc_-funroll-loops`	20190821	20190816
189061410	1640 0 0	13718 760 792	`ref`	`cc`	20190821	20190816
192908777	1640 0 0	13718 760 792	`ref`	`gcc`	20190821	20190816

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:

Compiler	Implementations
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:

Compiler	Implementations
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:418:11: error: always_inline function '_mm256_set_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup857_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:419:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup857_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:420:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup857_avx' that is compiled without support for 'sse4.2'
r3_recip.c: F0[2] = _mm256_set1_epi32(0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:421:11: error: always_inline function '_mm256_set_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup857_avx' that is compiled without support for 'sse4.2'
r3_recip.c: F0[3] = _mm256_set_epi32(0,0,0,0,0,4194304,0,4194304);
r3_recip.c: ^
r3_recip.c: r3_recip.c:422:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup857_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:423:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup857_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:424:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup857_avx' that is compiled without support for 'sse4.2'
r3_recip.c: F1[2] = _mm256_set1_epi32(0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:425:11: error: always_inline function '_mm256_set_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup857_avx' that is compiled without support for 'sse4.2'
r3_recip.c: F1[3] = _mm256_set_epi32(0,0,0,0,0,4194304,0,4194304);
r3_recip.c: ^
r3_recip.c: r3_recip.c:427:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup857_avx' that is compiled without support for 'sse4.2'
r3_recip.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
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:

Compiler	Implementations
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

Number of similar (compiler,implementation) pairs: 84, namely:

Compiler	Implementations
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_inv3sntrup857_avx':
r3_recip.c: r3_recip.c:418:9: 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_inv3sntrup857_avx':
r3_recip.c: r3_recip.c:418:9: 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:

Compiler	Implementations
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:

Compiler	Implementations
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