Implementation notes: amd64, gpu, crypto_core/multsntrup761

Computer: gpu
Architecture: amd64
CPU ID: GenuineIntel-000206d7-bfebfbff
SUPERCOP version: 20190816
Operation: crypto_core
Primitive: multsntrup761
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
6791733603 0 019445 760 1128refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082220190816
7196163603 0 019445 760 1128refclang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments2019082220190816
7366053574 0 018773 760 1128refclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019082220190816
7559883574 0 018773 760 1128refclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019082220190816
11690642355 0 019253 760 776refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019082220190816
11952842355 0 020581 760 776refclang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082220190816
12091622355 0 020581 760 776refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082220190816
13631852355 0 020581 760 776refclang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019082220190816

Test failure

Implementation: avx
Security model: unknown
Compiler: gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer
error 111
./try: Symbol `memcpy' causes overflow in R_X86_64_PC32 relocation
Number of similar (compiler,implementation) pairs: 112, 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
cc ref
gcc ref
gcc -O2 -fomit-frame-pointer ref
gcc -O3 -fomit-frame-pointer ref
gcc -O -fomit-frame-pointer ref
gcc -Os -fomit-frame-pointer ref
gcc -fno-schedule-insns -O2 -fomit-frame-pointer ref
gcc -fno-schedule-insns -O3 -fomit-frame-pointer ref
gcc -fno-schedule-insns -O -fomit-frame-pointer ref
gcc -fno-schedule-insns -Os -fomit-frame-pointer ref
gcc -funroll-loops ref
gcc -funroll-loops -O2 -fomit-frame-pointer ref
gcc -funroll-loops -O3 -fomit-frame-pointer ref
gcc -funroll-loops -O -fomit-frame-pointer ref
gcc -funroll-loops -Os -fomit-frame-pointer ref
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer ref
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer ref
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer ref
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer ref
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -O -fomit-frame-pointer ref
gcc -funroll-loops -m64 -Os -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer ref
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer ref
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer ref
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer ref
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer ref
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer ref
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer ref
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer ref
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer ref
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer ref
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer ref
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer ref
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer ref
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer ref
gcc -m64 -O2 -fomit-frame-pointer ref
gcc -m64 -O3 -fomit-frame-pointer ref
gcc -m64 -O -fomit-frame-pointer ref
gcc -m64 -Os -fomit-frame-pointer ref
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer ref
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer ref
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer ref
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer ref
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=core2 -O2 -fomit-frame-pointer ref
gcc -m64 -march=core2 -O3 -fomit-frame-pointer ref
gcc -m64 -march=core2 -O -fomit-frame-pointer ref
gcc -m64 -march=core2 -Os -fomit-frame-pointer ref
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer ref
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer ref
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer ref
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer ref
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer ref
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer ref
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer ref
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer ref
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer ref
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer ref
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer ref
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer ref
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer ref
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer ref
gcc -m64 -march=corei7 -O -fomit-frame-pointer ref
gcc -m64 -march=corei7 -Os -fomit-frame-pointer ref
gcc -m64 -march=k8 -O2 -fomit-frame-pointer ref
gcc -m64 -march=k8 -O3 -fomit-frame-pointer ref
gcc -m64 -march=k8 -O -fomit-frame-pointer ref
gcc -m64 -march=k8 -Os -fomit-frame-pointer ref
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer ref
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer ref
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer ref
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer ref
gcc -m64 -march=nocona -O2 -fomit-frame-pointer ref
gcc -m64 -march=nocona -O3 -fomit-frame-pointer ref
gcc -m64 -march=nocona -O -fomit-frame-pointer ref
gcc -m64 -march=nocona -Os -fomit-frame-pointer ref
gcc -march=barcelona -O2 -fomit-frame-pointer ref
gcc -march=barcelona -O3 -fomit-frame-pointer ref
gcc -march=barcelona -O -fomit-frame-pointer ref
gcc -march=barcelona -Os -fomit-frame-pointer ref
gcc -march=k8 -O2 -fomit-frame-pointer ref
gcc -march=k8 -O3 -fomit-frame-pointer ref
gcc -march=k8 -O -fomit-frame-pointer ref
gcc -march=k8 -Os -fomit-frame-pointer ref
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv ref
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv ref
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv ref
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv ref
gcc -march=nocona -O2 -fomit-frame-pointer ref
gcc -march=nocona -O3 -fomit-frame-pointer ref
gcc -march=nocona -O -fomit-frame-pointer ref
gcc -march=nocona -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

Test failure

Implementation: ref
Security model: unknown
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
error 111
./try: Symbol `memcpy' causes overflow in R_X86_64_PC32 relocation
error 111
./try: Symbol `memcpy' causes overflow in R_X86_64_PC32 relocation
Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer ref
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer ref
gcc -m64 -march=barcelona -O -fomit-frame-pointer ref
gcc -m64 -march=barcelona -Os -fomit-frame-pointer ref

Compiler output

Implementation: avx
Security model: unknown
Compiler: cc
mult768.c: mult768.c: In function 'squeeze_4591_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_4591_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_4591_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:253:5: note: called from here
mult768.c: x = _mm256_blendv_epi8(xq,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:252:6: note: called from here
mult768.c: xq = sub_x16(x,const_x16(q));
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:266:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_multsntrup761_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:267:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_multsntrup761_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:268:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_multsntrup761_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:273:9: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_multsntrup761_avx' that is compiled without support for 'sse4.2'
mult768.c: x = load_x16(&f[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:275:5: error: always_inline function '_mm256_storeu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_multsntrup761_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:290:9: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_core_multsntrup761_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:290:21: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_core_multsntrup761_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_4591_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_4591_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(7)),const_x16(4591)));
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_4591_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_4591_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(7)),const_x16(4591)));
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_4591_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_4591_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(7)),const_x16(4591)));
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_4591_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(7)),const_x16(4591)));
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(7)),const_x16(4591)));
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:765:17: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_core_multsntrup761_round1' that is compiled without support for 'avx2'
mult.c: __m256i x = _mm256_add_epi16(fgi,_mm256_add_epi16(fgip,fgip1));
mult.c: ^
mult.c: mult.c:765:38: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_core_multsntrup761_round1' that is compiled without support for 'avx2'
mult.c: __m256i x = _mm256_add_epi16(fgi,_mm256_add_epi16(fgip,fgip1));
mult.c: ^
mult.c: 2 errors generated.
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