Implementation notes: amd64, gpu, crypto_core/inv3sntrup653

Computer: gpu
Architecture: amd64
CPU ID: GenuineIntel-000206d7-bfebfbff
SUPERCOP version: 20190816
Operation: crypto_core
Primitive: inv3sntrup653

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
6122739	5224 0 0	18440 784 832	`ref`	`gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer`	20190821	20190816
6162618	5224 0 0	18440 784 832	`ref`	`gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer`	20190821	20190816
6492577	5224 0 0	18440 784 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20190821	20190816
6562008	5381 0 0	18504 784 832	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20190821	20190816
6890097	5538 0 0	18544 784 832	`ref`	`gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer`	20190821	20190816
6905751	5538 0 0	18632 784 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer`	20190821	20190816
7079502	5538 0 0	18696 784 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer`	20190821	20190816
7345084	5753 0 0	18904 784 832	`ref`	`gcc_-m64_-march=core2_-O3_-fomit-frame-pointer`	20190821	20190816
8267859	15000 0 0	21176 784 832	`ref`	`gcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190821	20190816
8293751	5689 0 0	21248 784 832	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20190821	20190816
8385033	7500 0 0	21176 784 832	`ref`	`gcc_-march=barcelona_-O3_-fomit-frame-pointer`	20190821	20190816
8439124	5689 0 0	21248 784 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190821	20190816
8476341	5346 0 0	18344 784 832	`ref`	`gcc_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190821	20190816
8478867	8440 0 0	24592 784 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190821	20190816
8479180	5024 0 0	18256 784 832	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190821	20190816
8506236	7420 0 0	20928 784 832	`ref`	`gcc_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190821	20190816
8573264	5024 0 0	18256 784 832	`ref`	`gcc_-m64_-O3_-fomit-frame-pointer`	20190821	20190816
8574990	7420 0 0	20928 784 832	`ref`	`gcc_-march=k8_-O3_-fomit-frame-pointer`	20190821	20190816
8619920	5346 0 0	18344 784 832	`ref`	`gcc_-march=nocona_-O3_-fomit-frame-pointer`	20190821	20190816
8645900	8440 0 0	24592 784 832	`ref`	`gcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer`	20190821	20190816
8673645	5689 0 0	21248 784 832	`ref`	`gcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer`	20190821	20190816
8710771	8640 0 0	24904 784 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190821	20190816
8744641	8640 0 0	24904 784 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer`	20190821	20190816
8753081	5024 0 0	18256 784 832	`ref`	`gcc_-O3_-fomit-frame-pointer`	20190821	20190816
8842192	6055 0 0	21368 784 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190821	20190816
8932704	6055 0 0	21368 784 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer`	20190821	20190816
18389128	5881 0 0	21565 760 1128	`ref`	`clang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments`	20190821	20190816
18748039	5500 0 0	20541 760 1128	`ref`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20190821	20190816
18967476	5500 0 0	20541 760 1128	`ref`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20190821	20190816
18970448	5881 0 0	21565 760 1128	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190821	20190816
22787196	5198 0 0	21933 760 776	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20190821	20190816
22856220	5198 0 0	23261 760 776	`ref`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190821	20190816
23121376	5198 0 0	23261 760 776	`ref`	`clang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190821	20190816
23249916	5198 0 0	23261 760 776	`ref`	`clang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190821	20190816
32243832	2762 0 0	16845 768 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190821	20190816
32343066	2693 0 0	16861 768 832	`ref`	`gcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer`	20190821	20190816
32732185	2708 0 0	16693 768 832	`ref`	`gcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer`	20190821	20190816
33283285	2708 0 0	16693 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190821	20190816
33515608	2762 0 0	16845 768 832	`ref`	`gcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer`	20190821	20190816
33877572	2762 0 0	16845 768 832	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20190821	20190816
34014677	2732 0 0	16861 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190821	20190816
34400133	2732 0 0	16861 768 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer`	20190821	20190816
35767518	2727 0 0	16917 768 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190821	20190816
35800567	2693 0 0	16861 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer`	20190821	20190816
36287952	2693 0 0	16677 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190821	20190816
36379241	2693 0 0	16677 768 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer`	20190821	20190816
36908213	2727 0 0	16917 768 832	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20190821	20190816
37125499	2727 0 0	16917 768 832	`ref`	`gcc_-funroll-loops_-m64_-O_-fomit-frame-pointer`	20190821	20190816
40464972	836 0 0	11645 768 832	`ref`	`gcc_-march=k8_-O2_-fomit-frame-pointer`	20190821	20190816
40795644	862 0 0	11661 768 832	`ref`	`gcc_-O2_-fomit-frame-pointer`	20190821	20190816
41262623	860 0 0	11941 768 832	`ref`	`gcc_-march=barcelona_-O2_-fomit-frame-pointer`	20190821	20190816
41780955	862 0 0	11613 768 832	`ref`	`gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer`	20190821	20190816
41795337	862 0 0	11621 768 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20190821	20190816
41941576	1720 0 0	11941 768 832	`ref`	`gcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190821	20190816
42062391	862 0 0	11613 768 832	`ref`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20190821	20190816
42106761	862 0 0	11621 768 832	`ref`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20190821	20190816
42209556	862 0 0	11661 768 832	`ref`	`gcc_-m64_-O2_-fomit-frame-pointer`	20190821	20190816
42239264	862 0 0	11613 768 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20190821	20190816
42244380	862 0 0	11621 768 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20190821	20190816
42416808	862 0 0	11613 768 832	`ref`	`gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer`	20190821	20190816
42617637	862 0 0	11613 768 832	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20190821	20190816
42762224	836 0 0	11645 768 832	`ref`	`gcc_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190821	20190816
43089866	862 0 0	11661 768 832	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190821	20190816
43332354	845 0 0	11565 768 832	`ref`	`gcc_-march=barcelona_-O_-fomit-frame-pointer`	20190821	20190816
43494600	860 0 0	11597 768 832	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190821	20190816
43841274	845 0 0	11637 768 832	`ref`	`gcc_-m64_-march=k8_-O_-fomit-frame-pointer`	20190821	20190816
43981092	860 0 0	11597 768 832	`ref`	`gcc_-O_-fomit-frame-pointer`	20190821	20190816
44123833	860 0 0	11549 768 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20190821	20190816
44166290	860 0 0	11597 768 832	`ref`	`gcc_-m64_-O_-fomit-frame-pointer`	20190821	20190816
44180441	860 0 0	11549 768 832	`ref`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20190821	20190816
44211148	860 0 0	11549 768 832	`ref`	`gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer`	20190821	20190816
44333850	860 0 0	11549 768 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20190821	20190816
44430216	860 0 0	11549 768 832	`ref`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20190821	20190816
44430416	860 0 0	11549 768 832	`ref`	`gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer`	20190821	20190816
44467605	860 0 0	11549 768 832	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20190821	20190816
44544640	860 0 0	11549 768 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20190821	20190816
44671358	1690 0 0	11565 768 832	`ref`	`gcc_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190821	20190816
44921055	845 0 0	11637 768 832	`ref`	`gcc_-march=k8_-O_-fomit-frame-pointer`	20190821	20190816
46119600	742 0 0	10505 752 800	`ref`	`gcc_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190821	20190816
46375050	742 0 0	10505 752 800	`ref`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20190821	20190816
46522749	766 0 0	10561 752 800	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20190821	20190816
46630805	766 0 0	10561 752 800	`ref`	`gcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer`	20190821	20190816
46813665	1484 0 0	10505 752 800	`ref`	`gcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190821	20190816
46834136	742 0 0	10505 752 800	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190821	20190816
47199100	742 0 0	10505 752 800	`ref`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20190821	20190816
47209656	742 0 0	10505 752 800	`ref`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20190821	20190816
47309419	742 0 0	10505 752 800	`ref`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20190821	20190816
47325876	766 0 0	10561 752 800	`ref`	`gcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer`	20190821	20190816
47382764	742 0 0	10505 752 800	`ref`	`gcc_-m64_-Os_-fomit-frame-pointer`	20190821	20190816
47444915	742 0 0	10505 752 800	`ref`	`gcc_-march=barcelona_-Os_-fomit-frame-pointer`	20190821	20190816
47448204	742 0 0	10521 752 800	`ref`	`gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer`	20190821	20190816
47451969	742 0 0	10505 752 800	`ref`	`gcc_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190821	20190816
47505351	766 0 0	10561 752 800	`ref`	`gcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer`	20190821	20190816
47548413	742 0 0	10505 752 800	`ref`	`gcc_-march=nocona_-Os_-fomit-frame-pointer`	20190821	20190816
47616357	742 0 0	10521 752 800	`ref`	`gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer`	20190821	20190816
47639745	742 0 0	10521 752 800	`ref`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20190821	20190816
47649041	742 0 0	10505 752 800	`ref`	`gcc_-march=k8_-Os_-fomit-frame-pointer`	20190821	20190816
47744187	766 0 0	10561 752 800	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190821	20190816
47770431	742 0 0	10505 752 800	`ref`	`gcc_-Os_-fomit-frame-pointer`	20190821	20190816
47778824	766 0 0	10561 752 800	`ref`	`gcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer`	20190821	20190816
47833233	766 0 0	10561 752 800	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190821	20190816
47995736	740 0 0	10505 752 800	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20190821	20190816
48046888	766 0 0	10561 752 800	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190821	20190816
49402500	2494 0 0	16709 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190821	20190816
49551113	2494 0 0	16709 768 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer`	20190821	20190816
49917591	766 0 0	10561 752 800	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190821	20190816
51077560	817 0 0	11365 768 832	`ref`	`gcc_-march=nocona_-O2_-fomit-frame-pointer`	20190821	20190816
51177258	817 0 0	11365 768 832	`ref`	`gcc_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190821	20190816
52542624	2516 0 0	16301 768 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer`	20190821	20190816
52818759	888 0 0	11741 768 832	`ref`	`gcc_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190821	20190816
53589840	2516 0 0	16301 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190821	20190816
53744740	888 0 0	11741 768 832	`ref`	`gcc_-march=nocona_-O_-fomit-frame-pointer`	20190821	20190816
97953855	1640 0 0	13718 760 792	`ref`	`gcc_-funroll-loops`	20190821	20190816
109169736	1640 0 0	13718 760 792	`ref`	`cc`	20190821	20190816
110549576	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:362:11: error: always_inline function '_mm256_set_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup653_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_inv3sntrup653_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_inv3sntrup653_avx' that is compiled without support for 'sse4.2'
r3_recip.c: F0[2] = _mm256_set_epi32(0,0,0,0,8,0,8,0);
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_inv3sntrup653_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_inv3sntrup653_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_inv3sntrup653_avx' that is compiled without support for 'sse4.2'
r3_recip.c: F1[2] = _mm256_set_epi32(0,0,0,0,8,0,8,0);
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_inv3sntrup653_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_inv3sntrup653_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_inv3sntrup653_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_inv3sntrup653_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_inv3sntrup653_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:

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