Implementation notes: amd64, gpu, crypto_core/mult3sntrup761

Computer: gpu
Architecture: amd64
CPU ID: GenuineIntel-000206d7-bfebfbff
SUPERCOP version: 20190816
Operation: crypto_core
Primitive: mult3sntrup761
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
4517723986 0 019717 760 1128refclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2019082220190816
4652853941 0 019029 760 1128refclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019082220190816
4801353986 0 019717 760 1128refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082220190816
4896603941 0 019029 760 1128refclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019082220190816
5344324152 0 017246 776 832refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2019082220190816
7249142722 0 020837 760 776refclang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082220190816
7321242722 0 020837 760 776refclang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082220190816
7344212722 0 020837 760 776refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082220190816
7602782722 0 019509 760 776refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019082220190816
14272243460 0 018902 776 832refgcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer2019082220190816
14342884566 0 020822 776 832refgcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer2019082220190816
14528521941 0 016133 768 832refgcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer2019082220190816
14627964566 0 020822 776 832refgcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer2019082220190816
14650443460 0 018902 776 832refgcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer2019082220190816
14698001925 0 016069 768 832refgcc_-funroll-loops_-O2_-fomit-frame-pointer2019082220190816
14737681771 0 015749 768 832refgcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer2019082220190816
14840001771 0 015749 768 832refgcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer2019082220190816
14875761877 0 015933 768 832refgcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer2019082220190816
15034244478 0 020622 776 832refgcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer2019082220190816
15089821925 0 016069 768 832refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082220190816
15439681877 0 015933 768 832refgcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer2019082220190816
15442803526 0 019070 776 832refgcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer2019082220190816
15471243526 0 019070 776 832refgcc_-funroll-loops_-O3_-fomit-frame-pointer2019082220190816
15545881941 0 016133 768 832refgcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer2019082220190816
15614683526 0 019070 776 832refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082220190816
15762004478 0 020622 776 832refgcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer2019082220190816
15820601925 0 016069 768 832refgcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer2019082220190816
22928762526 0 016765 768 832refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019082220190816
23167772679 0 015814 776 832refgcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer2019082220190816
2351811634 0 011429 768 832refgcc_-m64_-march=corei7_-O2_-fomit-frame-pointer2019082220190816
23551021765 0 014990 776 832refgcc_-O3_-fomit-frame-pointer2019082220190816
23588222810 0 015926 776 832refgcc_-m64_-march=core2_-O3_-fomit-frame-pointer2019082220190816
2373000634 0 011437 768 832refgcc_-m64_-march=core2_-O2_-fomit-frame-pointer2019082220190816
23764803429 0 016926 776 832refgcc_-m64_-march=k8_-O3_-fomit-frame-pointer2019082220190816
2382800634 0 011493 768 832refgcc_-m64_-O2_-fomit-frame-pointer2019082220190816
23830122413 0 015606 776 832refgcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer2019082220190816
23914821314 0 011805 768 832refgcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer2019082220190816
23960682413 0 015606 776 832refgcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer2019082220190816
2397368634 0 011493 768 832refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019082220190816
24047691765 0 014990 776 832refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019082220190816
2406896634 0 011429 768 832refgcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer2019082220190816
24069643477 0 017142 776 832refgcc_-march=barcelona_-O3_-fomit-frame-pointer2019082220190816
2417008634 0 011437 768 832refgcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer2019082220190816
2421044634 0 011437 768 832refgcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer2019082220190816
2421800634 0 011429 768 832refgcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer2019082220190816
2422193657 0 011805 768 832refgcc_-march=barcelona_-O2_-fomit-frame-pointer2019082220190816
24239132413 0 015606 776 832refgcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer2019082220190816
2425284634 0 011429 768 832refgcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer2019082220190816
2425692634 0 011493 768 832refgcc_-O2_-fomit-frame-pointer2019082220190816
2430612601 0 011477 768 832refgcc_-m64_-march=k8_-O2_-fomit-frame-pointer2019082220190816
24438001765 0 014990 776 832refgcc_-m64_-O3_-fomit-frame-pointer2019082220190816
24456212679 0 015662 776 832refgcc_-m64_-march=corei7_-O3_-fomit-frame-pointer2019082220190816
24469981919 0 015014 776 832refgcc_-march=nocona_-O3_-fomit-frame-pointer2019082220190816
24635163429 0 016926 776 832refgcc_-march=k8_-O3_-fomit-frame-pointer2019082220190816
24986842679 0 015750 776 832refgcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer2019082220190816
25120686954 0 017142 776 832refgcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer2019082220190816
25472721919 0 015014 776 832refgcc_-m64_-march=nocona_-O3_-fomit-frame-pointer2019082220190816
2566032601 0 011477 768 832refgcc_-march=k8_-O2_-fomit-frame-pointer2019082220190816
2583630611 0 011325 768 832refgcc_-m64_-march=nocona_-O2_-fomit-frame-pointer2019082220190816
2609948611 0 011325 768 832refgcc_-march=nocona_-O2_-fomit-frame-pointer2019082220190816
26351822491 0 016525 768 832refgcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer2019082220190816
27640802375 0 016749 768 832refgcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer2019082220190816
2768844578 0 010409 752 800refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082220190816
28161932526 0 016765 768 832refgcc_-funroll-loops_-m64_-O_-fomit-frame-pointer2019082220190816
28214202375 0 016749 768 832refgcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer2019082220190816
28356882491 0 016725 768 832refgcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer2019082220190816
28391082491 0 016525 768 832refgcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer2019082220190816
2844843561 0 010353 752 800refgcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer2019082220190816
28691082526 0 016765 768 832refgcc_-funroll-loops_-O_-fomit-frame-pointer2019082220190816
2871492591 0 011381 768 832refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2019082220190816
29079802491 0 016725 768 832refgcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer2019082220190816
3059820561 0 010353 752 800refgcc_-m64_-march=core2_-Os_-fomit-frame-pointer2019082220190816
3075360561 0 010369 752 800refgcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer2019082220190816
3087280561 0 010369 752 800refgcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer2019082220190816
3105048561 0 010353 752 800refgcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer2019082220190816
3111172561 0 010353 752 800refgcc_-m64_-march=corei7_-Os_-fomit-frame-pointer2019082220190816
3115784578 0 010409 752 800refgcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer2019082220190816
3132985578 0 010409 752 800refgcc_-funroll-loops_-Os_-fomit-frame-pointer2019082220190816
3167292575 0 010393 752 800refgcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer2019082220190816
3209876561 0 010369 752 800refgcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer2019082220190816
3225843578 0 010409 752 800refgcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer2019082220190816
3228192561 0 010353 752 800refgcc_-Os_-fomit-frame-pointer2019082220190816
32567491122 0 010353 752 800refgcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer2019082220190816
3265568578 0 010409 752 800refgcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer2019082220190816
3269231561 0 010353 752 800refgcc_-march=k8_-Os_-fomit-frame-pointer2019082220190816
3272328561 0 010353 752 800refgcc_-m64_-Os_-fomit-frame-pointer2019082220190816
3280540561 0 010353 752 800refgcc_-march=barcelona_-Os_-fomit-frame-pointer2019082220190816
3307647558 0 010353 752 800refgcc_-m64_-march=nocona_-Os_-fomit-frame-pointer2019082220190816
3318228575 0 010393 752 800refgcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer2019082220190816
3333240561 0 010353 752 800refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019082220190816
3333486661 0 011453 768 832refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019082220190816
3350232561 0 010353 752 800refgcc_-m64_-march=k8_-Os_-fomit-frame-pointer2019082220190816
3352080578 0 010409 752 800refgcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer2019082220190816
3353672578 0 010409 752 800refgcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer2019082220190816
3422037650 0 011477 768 832refgcc_-m64_-march=k8_-O_-fomit-frame-pointer2019082220190816
34230681300 0 011421 768 832refgcc_-m64_-march=barcelona_-O_-fomit-frame-pointer2019082220190816
3424901661 0 011373 768 832refgcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer2019082220190816
3426272650 0 011477 768 832refgcc_-march=k8_-O_-fomit-frame-pointer2019082220190816
3436935661 0 011373 768 832refgcc_-m64_-march=core2_-O_-fomit-frame-pointer2019082220190816
3466512558 0 010353 752 800refgcc_-march=nocona_-Os_-fomit-frame-pointer2019082220190816
3477169690 0 011661 768 832refgcc_-m64_-march=nocona_-O_-fomit-frame-pointer2019082220190816
3499572661 0 011373 768 832refgcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer2019082220190816
3501760661 0 011453 768 832refgcc_-m64_-O_-fomit-frame-pointer2019082220190816
3531180690 0 011661 768 832refgcc_-march=nocona_-O_-fomit-frame-pointer2019082220190816
3555548661 0 011373 768 832refgcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer2019082220190816
3555698650 0 011421 768 832refgcc_-march=barcelona_-O_-fomit-frame-pointer2019082220190816
3599604661 0 011373 768 832refgcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer2019082220190816
3632120661 0 011453 768 832refgcc_-O_-fomit-frame-pointer2019082220190816
3693712661 0 011373 768 832refgcc_-m64_-march=corei7_-O_-fomit-frame-pointer2019082220190816
3722496546 0 010345 752 800refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2019082220190816
3725697661 0 011373 768 832refgcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer2019082220190816
3729759658 0 011381 768 832refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2019082220190816
75696631096 0 013206 760 792refgcc_-funroll-loops2019082220190816
81573281096 0 013206 760 792refcc2019082220190816
85889371096 0 013206 760 792refgcc2019082220190816

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: 9, namely:
CompilerImplementations
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer avx
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer avx
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer avx
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer ref
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer ref
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer ref
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer round1
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer round1
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer round1

Compiler output

Implementation: avx
Security model: unknown
Compiler: cc
mult768.c: mult768.c: In function 'squeeze_3_x16':
mult768.c: mult768.c:19:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult768.c: {
mult768.c: ^
mult768.c: mult768.c:18:17: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
mult768.c: static int16x16 squeeze_3_x16(int16x16 x)
mult768.c: ^~~~~~~~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: mult768.c: In function 'freeze_3_x16':
mult768.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
mult768.c: _mm256_blendv_epi8 (__m256i __X, __m256i __Y, __m256i __M)
mult768.c: ^~~~~~~~~~~~~~~~~~
mult768.c: mult768.c:195:5: note: called from here
mult768.c: x = _mm256_blendv_epi8(x3,x,mask);
mult768.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
mult768.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: mult768.c:194:6: note: called from here
mult768.c: x3 = sub_x16(x,const_x16(3));
mult768.c: ~~~^~~~~~~~~~~~~~~~~~~~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
mult768.c: ...

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

Compiler output

Implementation: avx
Security model: unknown
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments
mult768.c: mult768.c:208:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_mult3sntrup761_avx' that is compiled without support for 'sse4.2'
mult768.c: x = const_x16(0);
mult768.c: ^
mult768.c: mult768.c:10:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c: ^
mult768.c: mult768.c:209:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_mult3sntrup761_avx' that is compiled without support for 'sse4.2'
mult768.c: for (i = p&~15;i < 768;i += 16) store_x16(&f[i],x);
mult768.c: ^
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c: ^
mult768.c: mult768.c:210:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_mult3sntrup761_avx' that is compiled without support for 'sse4.2'
mult768.c: for (i = p&~15;i < 768;i += 16) store_x16(&g[i],x);
mult768.c: ^
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c: ^
mult768.c: mult768.c:227:20: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_mult3sntrup761_avx' that is compiled without support for 'sse4.2'
mult768.c: int16x16 fgi = load_x16(&fg[i]);
mult768.c: ^
mult768.c: mult768.c:8:21: note: expanded from macro 'load_x16'
mult768.c: #define load_x16(p) _mm256_loadu_si256((int16x16 *) (p))
mult768.c: ^
mult768.c: mult768.c:228:21: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_mult3sntrup761_avx' that is compiled without support for 'sse4.2'
mult768.c: ...

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

Compiler output

Implementation: avx
Security model: unknown
Compiler: clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments
mult768.c: mult768.c:230:9: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_core_mult3sntrup761_avx' that is compiled without support for 'avx2'
mult768.c: x = add_x16(fgi,add_x16(fgip,fgip1));
mult768.c: ^
mult768.c: mult768.c:11:17: note: expanded from macro 'add_x16'
mult768.c: #define add_x16 _mm256_add_epi16
mult768.c: ^
mult768.c: mult768.c:230:21: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_core_mult3sntrup761_avx' that is compiled without support for 'avx2'
mult768.c: x = add_x16(fgi,add_x16(fgip,fgip1));
mult768.c: ^
mult768.c: mult768.c:11:17: note: expanded from macro 'add_x16'
mult768.c: #define add_x16 _mm256_add_epi16
mult768.c: ^
mult768.c: 2 errors generated.

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

Compiler output

Implementation: avx
Security model: unknown
Compiler: gcc -O2 -fomit-frame-pointer
mult768.c: mult768.c: In function 'squeeze_3_x16':
mult768.c: mult768.c:19:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult768.c: {
mult768.c: ^
mult768.c: mult768.c: In function 'squeeze_7681_x16':
mult768.c: mult768.c:23:17: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
mult768.c: static int16x16 squeeze_7681_x16(int16x16 x)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: mult768.c: In function 'squeeze_3_x16':
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
mult768.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(10923)),const_x16(3)));
mult768.c: ^~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:553:1: error: inlining failed in call to always_inline '_mm256_mullo_epi16': target specific option mismatch
mult768.c: _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~~~
mult768.c: ...

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

Compiler output

Implementation: avx
Security model: unknown
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
mult768.c: mult768.c: In function 'squeeze_3_x16':
mult768.c: mult768.c:19:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult768.c: {
mult768.c: ^
mult768.c: mult768.c: In function 'squeeze_7681_x16':
mult768.c: mult768.c:23:17: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
mult768.c: static int16x16 squeeze_7681_x16(int16x16 x)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: mult768.c: In function 'squeeze_3_x16':
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
mult768.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(10923)),const_x16(3)));
mult768.c: ^~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:553:1: error: inlining failed in call to always_inline '_mm256_mullo_epi16': target specific option mismatch
mult768.c: _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~~~
mult768.c: ...
mult768.c: mult768.c: In function 'squeeze_3_x16':
mult768.c: mult768.c:19:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult768.c: {
mult768.c: ^
mult768.c: mult768.c: In function 'squeeze_7681_x16':
mult768.c: mult768.c:23:17: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
mult768.c: static int16x16 squeeze_7681_x16(int16x16 x)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: mult768.c: In function 'squeeze_3_x16':
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
mult768.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(10923)),const_x16(3)));
mult768.c: ^~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:553:1: error: inlining failed in call to always_inline '_mm256_mullo_epi16': target specific option mismatch
mult768.c: _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~~~
mult768.c: ...

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

Compiler output

Implementation: avx
Security model: unknown
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: mult768.c: In function 'squeeze_3_x16':
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
mult768.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(10923)),const_x16(3)));
mult768.c: ^~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:553:1: error: inlining failed in call to always_inline '_mm256_mullo_epi16': target specific option mismatch
mult768.c: _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult768.c: ^~~~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c: #define sub_x16 _mm256_sub_epi16
mult768.c: ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c: return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(10923)),const_x16(3)));
mult768.c: ^~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
mult768.c: from mult768.c:2:
mult768.c: ...

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

Compiler output

Implementation: round1
Security model: unknown
Compiler: cc
mult.c: mult.c: In function 'add':
mult.c: mult.c:81:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult.c: {
mult.c: ^
mult.c: mult.c: In function 'fastsub':
mult.c: mult.c:90:22: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
mult.c: static inline __m256 fastsub(__m256 x,__m256 y)
mult.c: ^~~~~~~
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:85:0,
mult.c: from mult.c:2:
mult.c: mult.c: In function 'fastadd':
mult.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/fmaintrin.h:63:1: error: inlining failed in call to always_inline '_mm256_fmadd_ps': target specific option mismatch
mult.c: _mm256_fmadd_ps (__m256 __A, __m256 __B, __m256 __C)
mult.c: ^~~~~~~~~~~~~~~
mult.c: mult.c:87:10: note: called from here
mult.c: return _mm256_fmadd_ps(y,v1_float,x);
mult.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
mult.c: from mult.c:2:
mult.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:1310:1: error: inlining failed in call to always_inline '_mm256_set1_ps': target specific option mismatch
mult.c: _mm256_set1_ps (float __A)
mult.c: ^~~~~~~~~~~~~~
mult.c: mult.c:87:10: note: called from here
mult.c: return _mm256_fmadd_ps(y,v1_float,x);
mult.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Number of similar (compiler,implementation) pairs: 3, namely:
CompilerImplementations
cc round1
gcc round1
gcc -funroll-loops round1

Compiler output

Implementation: round1
Security model: unknown
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments
mult.c: mult.c:146:22: error: invalid output size for constraint '=&x'
mult.c: MULSTEP_fromzero(0,h0,h1,h2,h3,h4)
mult.c: ^
mult.c: mult.c:148:26: error: invalid output size for constraint '+x'
mult.c: MULSTEP_noload(j + 1,h1,h2,h3,h4,h0)
mult.c: ^
mult.c: mult.c:149:26: error: invalid output size for constraint '+x'
mult.c: MULSTEP_noload(j + 2,h2,h3,h4,h0,h1)
mult.c: ^
mult.c: mult.c:150:26: error: invalid output size for constraint '+x'
mult.c: MULSTEP_noload(j + 3,h3,h4,h0,h1,h2)
mult.c: ^
mult.c: mult.c:151:26: error: invalid output size for constraint '+x'
mult.c: MULSTEP_noload(j + 4,h4,h0,h1,h2,h3)
mult.c: ^
mult.c: mult.c:152:26: error: invalid output size for constraint '+x'
mult.c: MULSTEP_noload(j + 5,h0,h1,h2,h3,h4)
mult.c: ^
mult.c: mult.c:154:24: error: invalid output size for constraint '+x'
mult.c: MULSTEP_noload(j + 1,h1,h2,h3,h4,h0)
mult.c: ^
mult.c: mult.c:155:24: error: invalid output size for constraint '+x'
mult.c: MULSTEP_noload(j + 2,h2,h3,h4,h0,h1)
mult.c: ^
mult.c: mult.c:156:24: error: invalid output size for constraint '+x'
mult.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
clang -O3 -fomit-frame-pointer -Qunused-arguments round1
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments round1
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments round1
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments round1

Compiler output

Implementation: round1
Security model: unknown
Compiler: clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments
mult.c: mult.c:522:11: error: always_inline function '_mm256_add_epi8' requires target feature 'avx2', but would be inlined into function 'mult768_mix2_m256i' that is compiled without support for 'avx2'
mult.c: g01 = _mm256_add_epi8(g0,g1); gkara[i][8] = g01;
mult.c: ^
mult.c: mult.c:523:11: error: always_inline function '_mm256_add_epi8' requires target feature 'avx2', but would be inlined into function 'mult768_mix2_m256i' that is compiled without support for 'avx2'
mult.c: g23 = _mm256_add_epi8(g2,g3); gkara[i][9] = g23;
mult.c: ^
mult.c: mult.c:524:11: error: always_inline function '_mm256_add_epi8' requires target feature 'avx2', but would be inlined into function 'mult768_mix2_m256i' that is compiled without support for 'avx2'
mult.c: g45 = _mm256_add_epi8(g4,g5); gkara[i][10] = g45;
mult.c: ^
mult.c: mult.c:525:11: error: always_inline function '_mm256_add_epi8' requires target feature 'avx2', but would be inlined into function 'mult768_mix2_m256i' that is compiled without support for 'avx2'
mult.c: g67 = _mm256_add_epi8(g6,g7); gkara[i][11] = g67;
mult.c: ^
mult.c: mult.c:532:11: error: always_inline function '_mm256_add_epi8' requires target feature 'avx2', but would be inlined into function 'mult768_mix2_m256i' that is compiled without support for 'avx2'
mult.c: g02 = _mm256_add_epi8(g0,g2); gkara[i][16] = g02;
mult.c: ^
mult.c: mult.c:533:11: error: always_inline function '_mm256_add_epi8' requires target feature 'avx2', but would be inlined into function 'mult768_mix2_m256i' that is compiled without support for 'avx2'
mult.c: g04 = _mm256_add_epi8(g0,g4); gkara[i][22] = g04;
mult.c: ^
mult.c: mult.c:534:11: error: always_inline function '_mm256_add_epi8' requires target feature 'avx2', but would be inlined into function 'mult768_mix2_m256i' that is compiled without support for 'avx2'
mult.c: g46 = _mm256_add_epi8(g4,g6); gkara[i][19] = g46;
mult.c: ^
mult.c: mult.c:535:11: error: always_inline function '_mm256_add_epi8' requires target feature 'avx2', but would be inlined into function 'mult768_mix2_m256i' that is compiled without support for 'avx2'
mult.c: g26 = _mm256_add_epi8(g2,g6); gkara[i][24] = g26;
mult.c: ^
mult.c: mult.c:542:11: error: always_inline function '_mm256_add_epi8' requires target feature 'avx2', but would be inlined into function 'mult768_mix2_m256i' that is compiled without support for 'avx2'
mult.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments round1
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments round1
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments round1
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments round1

Compiler output

Implementation: round1
Security model: unknown
Compiler: gcc -O2 -fomit-frame-pointer
mult.c: mult.c: In function 'add':
mult.c: mult.c:81:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult.c: {
mult.c: ^
mult.c: mult.c: In function 'squeezeadd16':
mult.c: mult.c:109:23: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
mult.c: static inline __m256i squeezeadd16(__m256i x,__m256i y)
mult.c: ^~~~~~~~~~~~
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:85:0,
mult.c: from mult.c:2:
mult.c: mult.c: In function 'fastadd':
mult.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/fmaintrin.h:63:1: error: inlining failed in call to always_inline '_mm256_fmadd_ps': target specific option mismatch
mult.c: _mm256_fmadd_ps (__m256 __A, __m256 __B, __m256 __C)
mult.c: ^~~~~~~~~~~~~~~
mult.c: mult.c:87:10: note: called from here
mult.c: return _mm256_fmadd_ps(y,v1_float,x);
mult.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
mult.c: from mult.c:2:
mult.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:1310:1: error: inlining failed in call to always_inline '_mm256_set1_ps': target specific option mismatch
mult.c: _mm256_set1_ps (float __A)
mult.c: ^~~~~~~~~~~~~~
mult.c: mult.c:87:10: note: called from here
mult.c: return _mm256_fmadd_ps(y,v1_float,x);
mult.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Number of similar (compiler,implementation) pairs: 84, namely:
CompilerImplementations
gcc -O2 -fomit-frame-pointer round1
gcc -O3 -fomit-frame-pointer round1
gcc -O -fomit-frame-pointer round1
gcc -Os -fomit-frame-pointer round1
gcc -fno-schedule-insns -O2 -fomit-frame-pointer round1
gcc -fno-schedule-insns -O3 -fomit-frame-pointer round1
gcc -fno-schedule-insns -O -fomit-frame-pointer round1
gcc -fno-schedule-insns -Os -fomit-frame-pointer round1
gcc -funroll-loops -O2 -fomit-frame-pointer round1
gcc -funroll-loops -O3 -fomit-frame-pointer round1
gcc -funroll-loops -O -fomit-frame-pointer round1
gcc -funroll-loops -Os -fomit-frame-pointer round1
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer round1
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer round1
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer round1
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer round1
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer round1
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer round1
gcc -funroll-loops -m64 -O -fomit-frame-pointer round1
gcc -funroll-loops -m64 -Os -fomit-frame-pointer round1
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer round1
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer round1
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer round1
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer round1
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer round1
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer round1
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer round1
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer round1
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer round1
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer round1
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer round1
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer round1
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer round1
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer round1
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer round1
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer round1
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer round1
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer round1
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer round1
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer round1
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer round1
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer round1
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer round1
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer round1
gcc -m64 -O2 -fomit-frame-pointer round1
gcc -m64 -O3 -fomit-frame-pointer round1
gcc -m64 -O -fomit-frame-pointer round1
gcc -m64 -Os -fomit-frame-pointer round1
gcc -m64 -march=core2 -O2 -fomit-frame-pointer round1
gcc -m64 -march=core2 -O3 -fomit-frame-pointer round1
gcc -m64 -march=core2 -O -fomit-frame-pointer round1
gcc -m64 -march=core2 -Os -fomit-frame-pointer round1
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer round1
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer round1
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer round1
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer round1
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer round1
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer round1
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer round1
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer round1
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer round1
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer round1
gcc -m64 -march=corei7 -O -fomit-frame-pointer round1
gcc -m64 -march=corei7 -Os -fomit-frame-pointer round1
gcc -m64 -march=k8 -O2 -fomit-frame-pointer round1
gcc -m64 -march=k8 -O3 -fomit-frame-pointer round1
gcc -m64 -march=k8 -O -fomit-frame-pointer round1
gcc -m64 -march=k8 -Os -fomit-frame-pointer round1
gcc -m64 -march=nocona -O2 -fomit-frame-pointer round1
gcc -m64 -march=nocona -O3 -fomit-frame-pointer round1
gcc -m64 -march=nocona -O -fomit-frame-pointer round1
gcc -m64 -march=nocona -Os -fomit-frame-pointer round1
gcc -march=barcelona -O2 -fomit-frame-pointer round1
gcc -march=barcelona -O3 -fomit-frame-pointer round1
gcc -march=barcelona -O -fomit-frame-pointer round1
gcc -march=barcelona -Os -fomit-frame-pointer round1
gcc -march=k8 -O2 -fomit-frame-pointer round1
gcc -march=k8 -O3 -fomit-frame-pointer round1
gcc -march=k8 -O -fomit-frame-pointer round1
gcc -march=k8 -Os -fomit-frame-pointer round1
gcc -march=nocona -O2 -fomit-frame-pointer round1
gcc -march=nocona -O3 -fomit-frame-pointer round1
gcc -march=nocona -O -fomit-frame-pointer round1
gcc -march=nocona -Os -fomit-frame-pointer round1

Compiler output

Implementation: round1
Security model: unknown
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
mult.c: mult.c: In function 'add':
mult.c: mult.c:81:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult.c: {
mult.c: ^
mult.c: mult.c: In function 'squeezeadd16':
mult.c: mult.c:109:23: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
mult.c: static inline __m256i squeezeadd16(__m256i x,__m256i y)
mult.c: ^~~~~~~~~~~~
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:85:0,
mult.c: from mult.c:2:
mult.c: mult.c: In function 'fastadd':
mult.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/fmaintrin.h:63:1: error: inlining failed in call to always_inline '_mm256_fmadd_ps': target specific option mismatch
mult.c: _mm256_fmadd_ps (__m256 __A, __m256 __B, __m256 __C)
mult.c: ^~~~~~~~~~~~~~~
mult.c: mult.c:87:10: note: called from here
mult.c: return _mm256_fmadd_ps(y,v1_float,x);
mult.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
mult.c: from mult.c:2:
mult.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:1310:1: error: inlining failed in call to always_inline '_mm256_set1_ps': target specific option mismatch
mult.c: _mm256_set1_ps (float __A)
mult.c: ^~~~~~~~~~~~~~
mult.c: mult.c:87:10: note: called from here
mult.c: return _mm256_fmadd_ps(y,v1_float,x);
mult.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: mult.c: In function 'add':
mult.c: mult.c:81:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult.c: {
mult.c: ^
mult.c: mult.c: In function 'squeezeadd16':
mult.c: mult.c:109:23: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
mult.c: static inline __m256i squeezeadd16(__m256i x,__m256i y)
mult.c: ^~~~~~~~~~~~
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:85:0,
mult.c: from mult.c:2:
mult.c: mult.c: In function 'fastadd':
mult.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/fmaintrin.h:63:1: error: inlining failed in call to always_inline '_mm256_fmadd_ps': target specific option mismatch
mult.c: _mm256_fmadd_ps (__m256 __A, __m256 __B, __m256 __C)
mult.c: ^~~~~~~~~~~~~~~
mult.c: mult.c:87:10: note: called from here
mult.c: return _mm256_fmadd_ps(y,v1_float,x);
mult.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
mult.c: from mult.c:2:
mult.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:1310:1: error: inlining failed in call to always_inline '_mm256_set1_ps': target specific option mismatch
mult.c: _mm256_set1_ps (float __A)
mult.c: ^~~~~~~~~~~~~~
mult.c: mult.c:87:10: note: called from here
mult.c: return _mm256_fmadd_ps(y,v1_float,x);
mult.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer round1
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer round1
gcc -m64 -march=barcelona -O -fomit-frame-pointer round1
gcc -m64 -march=barcelona -Os -fomit-frame-pointer round1

Compiler output

Implementation: round1
Security model: unknown
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:85:0,
mult.c: from mult.c:2:
mult.c: mult.c: In function 'fastadd':
mult.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/fmaintrin.h:63:1: error: inlining failed in call to always_inline '_mm256_fmadd_ps': target specific option mismatch
mult.c: _mm256_fmadd_ps (__m256 __A, __m256 __B, __m256 __C)
mult.c: ^~~~~~~~~~~~~~~
mult.c: mult.c:87:10: note: called from here
mult.c: return _mm256_fmadd_ps(y,v1_float,x);
mult.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:85:0,
mult.c: from mult.c:2:
mult.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/fmaintrin.h:63:1: error: inlining failed in call to always_inline '_mm256_fmadd_ps': target specific option mismatch
mult.c: _mm256_fmadd_ps (__m256 __A, __m256 __B, __m256 __C)
mult.c: ^~~~~~~~~~~~~~~
mult.c: mult.c:87:10: note: called from here
mult.c: return _mm256_fmadd_ps(y,v1_float,x);
mult.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Number of similar (compiler,implementation) pairs: 16, namely:
CompilerImplementations
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer round1
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer round1
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer round1
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer round1
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer round1
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer round1
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer round1
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer round1
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer round1
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer round1
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer round1
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer round1
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv round1
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv round1
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv round1
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv round1