Implementation notes: amd64, gpu, crypto_core/multsntrup857

Computer: gpu
Architecture: amd64
CPU ID: GenuineIntel-000206d7-bfebfbff
SUPERCOP version: 20190816
Operation: crypto_core
Primitive: multsntrup857

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
525508	3767 0 0	16990 776 832	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20190822	20190816
548300	3750 0 0	17070 776 832	`ref`	`gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer`	20190822	20190816
561432	3750 0 0	17070 776 832	`ref`	`gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer`	20190822	20190816
574176	3750 0 0	17070 776 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20190822	20190816
617340	3894 0 0	17150 776 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer`	20190822	20190816
618744	3894 0 0	17086 776 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer`	20190822	20190816
620043	4550 0 0	17790 776 832	`ref`	`gcc_-m64_-march=core2_-O3_-fomit-frame-pointer`	20190822	20190816
628228	3894 0 0	16998 776 832	`ref`	`gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer`	20190822	20190816
870236	4358 0 0	19573 760 1128	`ref`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20190822	20190816
910360	4358 0 0	19573 760 1128	`ref`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20190822	20190816
995944	2867 0 0	18725 760 1128	`ref`	`clang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments`	20190822	20190816
1033168	2867 0 0	18725 760 1128	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190822	20190816
1627254	2355 0 0	20597 760 776	`ref`	`clang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190822	20190816
1630521	2355 0 0	20597 760 776	`ref`	`clang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190822	20190816
1672412	2355 0 0	19269 760 776	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20190822	20190816
1694264	2355 0 0	20597 760 776	`ref`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20190822	20190816
1894056	2079 0 0	16349 768 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190822	20190816
1899180	2079 0 0	16349 768 832	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20190822	20190816
1907504	3637 0 0	19198 776 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190822	20190816
1911184	3458 0 0	19126 776 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190822	20190816
1915056	3458 0 0	19126 776 832	`ref`	`gcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer`	20190822	20190816
1916996	2176 0 0	16357 768 832	`ref`	`gcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer`	20190822	20190816
1924696	2079 0 0	16349 768 832	`ref`	`gcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer`	20190822	20190816
1935400	5751 0 0	22022 776 832	`ref`	`gcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer`	20190822	20190816
1941256	2208 0 0	16525 768 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer`	20190822	20190816
1953164	5751 0 0	22022 776 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190822	20190816
1953852	2176 0 0	16357 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190822	20190816
1974160	5823 0 0	22206 776 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190822	20190816
1978839	3637 0 0	19198 776 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer`	20190822	20190816
1979708	5823 0 0	22206 776 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer`	20190822	20190816
2016992	2208 0 0	16525 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190822	20190816
2019256	2084 0 0	16189 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190822	20190816
2039036	2084 0 0	16189 768 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer`	20190822	20190816
2080296	3458 0 0	19126 776 832	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20190822	20190816
2340400	2053 0 0	16229 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190822	20190816
2384841	2053 0 0	16229 768 832	`ref`	`gcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer`	20190822	20190816
2419632	2072 0 0	16453 768 832	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190822	20190816
2532208	2053 0 0	16429 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer`	20190822	20190816
2562120	2110 0 0	16613 768 832	`ref`	`gcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer`	20190822	20190816
2572992	2072 0 0	16453 768 832	`ref`	`gcc_-funroll-loops_-m64_-O_-fomit-frame-pointer`	20190822	20190816
2611684	2110 0 0	16613 768 832	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190822	20190816
2625676	2072 0 0	16453 768 832	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20190822	20190816
2642652	2053 0 0	16429 768 832	`ref`	`gcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer`	20190822	20190816
2870019	536 0 0	10597 760 800	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190822	20190816
2992152	587 0 0	11493 768 832	`ref`	`gcc_-march=barcelona_-O_-fomit-frame-pointer`	20190822	20190816
3008200	1861 0 0	15214 776 832	`ref`	`gcc_-m64_-O3_-fomit-frame-pointer`	20190822	20190816
3011124	4331 0 0	18118 776 832	`ref`	`gcc_-march=barcelona_-O3_-fomit-frame-pointer`	20190822	20190816
3011176	1861 0 0	15214 776 832	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20190822	20190816
3032520	715 0 0	11717 768 832	`ref`	`gcc_-march=k8_-O2_-fomit-frame-pointer`	20190822	20190816
3034128	677 0 0	11605 768 832	`ref`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20190822	20190816
3040936	669 0 0	11653 768 832	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20190822	20190816
3042287	779 0 0	12045 768 832	`ref`	`gcc_-march=barcelona_-O2_-fomit-frame-pointer`	20190822	20190816
3042796	677 0 0	11605 768 832	`ref`	`gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer`	20190822	20190816
3048123	1861 0 0	15214 776 832	`ref`	`gcc_-O3_-fomit-frame-pointer`	20190822	20190816
3050928	677 0 0	11613 768 832	`ref`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20190822	20190816
3053936	669 0 0	11653 768 832	`ref`	`gcc_-O2_-fomit-frame-pointer`	20190822	20190816
3054480	8662 0 0	18118 776 832	`ref`	`gcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20190822	20190816
3064124	677 0 0	11605 768 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20190822	20190816
3067696	677 0 0	11613 768 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20190822	20190816
3076968	1558 0 0	12045 768 832	`ref`	`gcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20190822	20190816
3097428	669 0 0	11653 768 832	`ref`	`gcc_-m64_-O2_-fomit-frame-pointer`	20190822	20190816
3104528	4227 0 0	17854 776 832	`ref`	`gcc_-march=k8_-O3_-fomit-frame-pointer`	20190822	20190816
3108756	677 0 0	11613 768 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20190822	20190816
3112056	4227 0 0	17854 776 832	`ref`	`gcc_-m64_-march=k8_-O3_-fomit-frame-pointer`	20190822	20190816
3114784	860 0 0	11709 768 832	`ref`	`gcc_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20190822	20190816
3118076	677 0 0	11605 768 832	`ref`	`gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer`	20190822	20190816
3126284	715 0 0	11717 768 832	`ref`	`gcc_-m64_-march=k8_-O2_-fomit-frame-pointer`	20190822	20190816
3184740	2254 0 0	15478 776 832	`ref`	`gcc_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20190822	20190816
3187024	860 0 0	11709 768 832	`ref`	`gcc_-march=nocona_-O2_-fomit-frame-pointer`	20190822	20190816
3232400	587 0 0	11549 768 832	`ref`	`gcc_-march=k8_-O_-fomit-frame-pointer`	20190822	20190816
3241212	536 0 0	10597 760 800	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20190822	20190816
3243704	2254 0 0	15478 776 832	`ref`	`gcc_-march=nocona_-O3_-fomit-frame-pointer`	20190822	20190816
3256128	592 0 0	11525 768 832	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20190822	20190816
3262240	529 0 0	10557 760 800	`ref`	`gcc_-march=k8_-Os_-fomit-frame-pointer`	20190822	20190816
3271404	661 0 0	11589 768 832	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20190822	20190816
3290292	529 0 0	10557 760 800	`ref`	`gcc_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190822	20190816
3295688	592 0 0	11445 768 832	`ref`	`gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer`	20190822	20190816
3306776	592 0 0	11445 768 832	`ref`	`gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer`	20190822	20190816
3309480	592 0 0	11525 768 832	`ref`	`gcc_-m64_-O_-fomit-frame-pointer`	20190822	20190816
3314752	536 0 0	10597 760 800	`ref`	`gcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer`	20190822	20190816
3314820	1058 0 0	10557 760 800	`ref`	`gcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190822	20190816
3315090	529 0 0	10557 760 800	`ref`	`gcc_-Os_-fomit-frame-pointer`	20190822	20190816
3320052	592 0 0	11445 768 832	`ref`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20190822	20190816
3329848	529 0 0	10557 760 800	`ref`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20190822	20190816
3332292	529 0 0	10557 760 800	`ref`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20190822	20190816
3335613	529 0 0	10557 760 800	`ref`	`gcc_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190822	20190816
3340020	592 0 0	11525 768 832	`ref`	`gcc_-O_-fomit-frame-pointer`	20190822	20190816
3343032	529 0 0	10573 760 800	`ref`	`gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer`	20190822	20190816
3350200	529 0 0	10557 760 800	`ref`	`gcc_-m64_-Os_-fomit-frame-pointer`	20190822	20190816
3352269	529 0 0	10557 760 800	`ref`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20190822	20190816
3353540	632 0 0	11749 768 832	`ref`	`gcc_-m64_-march=nocona_-O_-fomit-frame-pointer`	20190822	20190816
3363832	536 0 0	10597 760 800	`ref`	`gcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer`	20190822	20190816
3367412	592 0 0	11445 768 832	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20190822	20190816
3375460	529 0 0	10573 760 800	`ref`	`gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer`	20190822	20190816
3378360	529 0 0	10557 760 800	`ref`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20190822	20190816
3382684	529 0 0	10573 760 800	`ref`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20190822	20190816
3384380	592 0 0	11445 768 832	`ref`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20190822	20190816
3390476	529 0 0	10557 760 800	`ref`	`gcc_-march=nocona_-Os_-fomit-frame-pointer`	20190822	20190816
3393624	592 0 0	11445 768 832	`ref`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20190822	20190816
3398599	592 0 0	11445 768 832	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20190822	20190816
3404460	592 0 0	11445 768 832	`ref`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20190822	20190816
3411136	536 0 0	10597 760 800	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20190822	20190816
3414648	1174 0 0	11493 768 832	`ref`	`gcc_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20190822	20190816
3422868	529 0 0	10557 760 800	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20190822	20190816
3429748	536 0 0	10597 760 800	`ref`	`gcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer`	20190822	20190816
3431196	536 0 0	10597 760 800	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer`	20190822	20190816
3452308	536 0 0	10597 760 800	`ref`	`gcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer`	20190822	20190816
3452520	529 0 0	10557 760 800	`ref`	`gcc_-march=barcelona_-Os_-fomit-frame-pointer`	20190822	20190816
3453836	536 0 0	10597 760 800	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20190822	20190816
3468316	587 0 0	11549 768 832	`ref`	`gcc_-m64_-march=k8_-O_-fomit-frame-pointer`	20190822	20190816
3470464	632 0 0	11749 768 832	`ref`	`gcc_-march=nocona_-O_-fomit-frame-pointer`	20190822	20190816
3646539	527 0 0	10557 760 800	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20190822	20190816
9407616	1004 0 0	13238 760 792	`ref`	`gcc_-funroll-loops`	20190822	20190816
10144396	1004 0 0	13238 760 792	`ref`	`cc`	20190822	20190816
10506364	1004 0 0	13238 760 792	`ref`	`gcc`	20190822	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

mult1024.c: mult1024.c: In function 'squeeze_5167_x16':
mult1024.c: mult1024.c:19:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult1024.c: {
mult1024.c: ^
mult1024.c: mult1024.c:18:17: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
mult1024.c: static int16x16 squeeze_5167_x16(int16x16 x)
mult1024.c: ^~~~~~~~~~~~~~~~
mult1024.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult1024.c: from mult1024.c:2:
mult1024.c: mult1024.c: In function 'freeze_5167_x16':
mult1024.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:207:1: error: inlining failed in call to always_inline '_mm256_blendv_epi8': target specific option mismatch
mult1024.c: _mm256_blendv_epi8 (__m256i __X, __m256i __Y, __m256i __M)
mult1024.c: ^~~~~~~~~~~~~~~~~~
mult1024.c: mult1024.c:291:5: note: called from here
mult1024.c: x = _mm256_blendv_epi8(xq,x,mask);
mult1024.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult1024.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult1024.c: from mult1024.c:2:
mult1024.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
mult1024.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult1024.c: ^~~~~~~~~~~~~~~~
mult1024.c: mult1024.c:290:6: note: called from here
mult1024.c: xq = sub_x16(x,const_x16(q));
mult1024.c: ~~~^~~~~~~~~~~~~~~~~~~~~~~~~
mult1024.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
mult1024.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

mult1024.c: mult1024.c:304:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_multsntrup857_avx' that is compiled without support for 'sse4.2'
mult1024.c: x = const_x16(0);
mult1024.c: ^
mult1024.c: mult1024.c:10:19: note: expanded from macro 'const_x16'
mult1024.c: #define const_x16 _mm256_set1_epi16
mult1024.c: ^
mult1024.c: mult1024.c:305:36: error: always_inline function '_mm256_storeu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_multsntrup857_avx' that is compiled without support for 'sse4.2'
mult1024.c: for (i = p&~15;i < 1024;i += 16) store_x16(&f[i],x);
mult1024.c: ^
mult1024.c: mult1024.c:9:24: note: expanded from macro 'store_x16'
mult1024.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1024.c: ^
mult1024.c: mult1024.c:306:36: error: always_inline function '_mm256_storeu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_multsntrup857_avx' that is compiled without support for 'sse4.2'
mult1024.c: for (i = p&~15;i < 1024;i += 16) store_x16(&g[i],x);
mult1024.c: ^
mult1024.c: mult1024.c:9:24: note: expanded from macro 'store_x16'
mult1024.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1024.c: ^
mult1024.c: mult1024.c:311:9: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_multsntrup857_avx' that is compiled without support for 'sse4.2'
mult1024.c: x = load_x16(&f[i]);
mult1024.c: ^
mult1024.c: mult1024.c:8:21: note: expanded from macro 'load_x16'
mult1024.c: #define load_x16(p) _mm256_loadu_si256((int16x16 *) (p))
mult1024.c: ^
mult1024.c: mult1024.c:313:5: error: always_inline function '_mm256_storeu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_multsntrup857_avx' that is compiled without support for 'sse4.2'
mult1024.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

mult1024.c: mult1024.c:328:9: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_core_multsntrup857_avx' that is compiled without support for 'avx2'
mult1024.c: x = add_x16(fgi,add_x16(fgip,fgip1));
mult1024.c: ^
mult1024.c: mult1024.c:11:17: note: expanded from macro 'add_x16'
mult1024.c: #define add_x16 _mm256_add_epi16
mult1024.c: ^
mult1024.c: mult1024.c:328:21: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_core_multsntrup857_avx' that is compiled without support for 'avx2'
mult1024.c: x = add_x16(fgi,add_x16(fgip,fgip1));
mult1024.c: ^
mult1024.c: mult1024.c:11:17: note: expanded from macro 'add_x16'
mult1024.c: #define add_x16 _mm256_add_epi16
mult1024.c: ^
mult1024.c: 2 errors generated.

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

mult1024.c: mult1024.c: In function 'squeeze_5167_x16':
mult1024.c: mult1024.c:19:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult1024.c: {
mult1024.c: ^
mult1024.c: mult1024.c: In function 'squeeze_7681_x16':
mult1024.c: mult1024.c:23:17: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
mult1024.c: static int16x16 squeeze_7681_x16(int16x16 x)
mult1024.c: ^~~~~~~~~~~~~~~~
mult1024.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult1024.c: from mult1024.c:2:
mult1024.c: mult1024.c: In function 'squeeze_5167_x16':
mult1024.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
mult1024.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult1024.c: ^~~~~~~~~~~~~~~~
mult1024.c: mult1024.c:12:17: note: called from here
mult1024.c: #define sub_x16 _mm256_sub_epi16
mult1024.c: ^
mult1024.c: mult1024.c:20:10: note: in expansion of macro 'sub_x16'
mult1024.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(6)),const_x16(5167)));
mult1024.c: ^~~~~~~
mult1024.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult1024.c: from mult1024.c:2:
mult1024.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:553:1: error: inlining failed in call to always_inline '_mm256_mullo_epi16': target specific option mismatch
mult1024.c: _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult1024.c: ^~~~~~~~~~~~~~~~~~
mult1024.c: ...
mult1024.c: mult1024.c: In function 'squeeze_5167_x16':
mult1024.c: mult1024.c:19:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult1024.c: {
mult1024.c: ^
mult1024.c: mult1024.c: In function 'squeeze_7681_x16':
mult1024.c: mult1024.c:23:17: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
mult1024.c: static int16x16 squeeze_7681_x16(int16x16 x)
mult1024.c: ^~~~~~~~~~~~~~~~
mult1024.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult1024.c: from mult1024.c:2:
mult1024.c: mult1024.c: In function 'squeeze_5167_x16':
mult1024.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
mult1024.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult1024.c: ^~~~~~~~~~~~~~~~
mult1024.c: mult1024.c:12:17: note: called from here
mult1024.c: #define sub_x16 _mm256_sub_epi16
mult1024.c: ^
mult1024.c: mult1024.c:20:10: note: in expansion of macro 'sub_x16'
mult1024.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(6)),const_x16(5167)));
mult1024.c: ^~~~~~~
mult1024.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult1024.c: from mult1024.c:2:
mult1024.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:553:1: error: inlining failed in call to always_inline '_mm256_mullo_epi16': target specific option mismatch
mult1024.c: _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult1024.c: ^~~~~~~~~~~~~~~~~~
mult1024.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

mult1024.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult1024.c: from mult1024.c:2:
mult1024.c: mult1024.c: In function 'squeeze_5167_x16':
mult1024.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
mult1024.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult1024.c: ^~~~~~~~~~~~~~~~
mult1024.c: mult1024.c:12:17: note: called from here
mult1024.c: #define sub_x16 _mm256_sub_epi16
mult1024.c: ^
mult1024.c: mult1024.c:20:10: note: in expansion of macro 'sub_x16'
mult1024.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(6)),const_x16(5167)));
mult1024.c: ^~~~~~~
mult1024.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult1024.c: from mult1024.c:2:
mult1024.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:553:1: error: inlining failed in call to always_inline '_mm256_mullo_epi16': target specific option mismatch
mult1024.c: _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult1024.c: ^~~~~~~~~~~~~~~~~~
mult1024.c: mult1024.c:12:17: note: called from here
mult1024.c: #define sub_x16 _mm256_sub_epi16
mult1024.c: ^
mult1024.c: mult1024.c:20:10: note: in expansion of macro 'sub_x16'
mult1024.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(6)),const_x16(5167)));
mult1024.c: ^~~~~~~
mult1024.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult1024.c: from mult1024.c:2:
mult1024.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