Implementation notes: amd64, margaux, crypto_core/invsntrup761

Computer: margaux
Architecture: amd64
CPU ID: GenuineIntel-000006fb-bfebfbff
SUPERCOP version: 20191221
Operation: crypto_core
Primitive: invsntrup761

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
22611438	3118 0 0	15974 744 832	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191221	20191221
34821432	1133 0 0	11723 728 832	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191221	20191221
36304614	886 0 0	10734 784 760	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191221	20191221
36893277	984 0 0	11347 728 832	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191221	20191221
38570418	2346 0 0	13256 792 760	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191221	20191221
38572641	2346 0 0	13256 792 760	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191221	20191221
38945511	2346 0 0	14192 792 760	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191221	20191221
39609486	2315 0 0	14032 792 760	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191221	20191221
48915387	878 0 0	10419 720 800	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191221	20191221

Compiler output

Implementation: crypto_core/invsntrup761/avx
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

recip.c: recip.c:83:19: error: always_inline function '_mm256_set1_epi16' requires target feature 'xsave', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'xsave'
recip.c: __m256i f0vec = _mm256_set1_epi16(f0);
recip.c: ^
recip.c: recip.c:84:19: error: always_inline function '_mm256_set1_epi16' requires target feature 'xsave', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'xsave'
recip.c: __m256i g0vec = _mm256_set1_epi16(g0);
recip.c: ^
recip.c: recip.c:85:23: error: always_inline function '_mm256_mullo_epi16' requires target feature 'xsave', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'xsave'
recip.c: __m256i f0vecqinv = _mm256_mullo_epi16(f0vec,qinvvec);
recip.c: ^
recip.c: recip.c:85:48: error: always_inline function '_mm256_set1_epi16' requires target feature 'xsave', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'xsave'
recip.c: __m256i f0vecqinv = _mm256_mullo_epi16(f0vec,qinvvec);
recip.c: ^
recip.c: recip.c:69:17: note: expanded from macro 'qinvvec'
recip.c: #define qinvvec _mm256_set1_epi16(qinv)
recip.c: ^
recip.c: recip.c:86:23: error: always_inline function '_mm256_mullo_epi16' requires target feature 'xsave', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'xsave'
recip.c: __m256i g0vecqinv = _mm256_mullo_epi16(g0vec,qinvvec);
recip.c: ^
recip.c: recip.c:86:48: error: always_inline function '_mm256_set1_epi16' requires target feature 'xsave', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'xsave'
recip.c: __m256i g0vecqinv = _mm256_mullo_epi16(g0vec,qinvvec);
recip.c: ^
recip.c: recip.c:69:17: note: expanded from macro 'qinvvec'
recip.c: #define qinvvec _mm256_set1_epi16(qinv)
recip.c: ^
recip.c: recip.c:87:21: error: always_inline function '_mm256_set1_epi32' requires target feature 'xsave', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'xsave'
recip.c: ...

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

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx

Compiler output

Implementation: crypto_core/invsntrup761/avx
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

recip.c: recip.c:83:19: error: always_inline function '_mm256_set1_epi16' requires target feature 'sse4.2', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'sse4.2'
recip.c: __m256i f0vec = _mm256_set1_epi16(f0);
recip.c: ^
recip.c: recip.c:84:19: error: always_inline function '_mm256_set1_epi16' requires target feature 'sse4.2', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'sse4.2'
recip.c: __m256i g0vec = _mm256_set1_epi16(g0);
recip.c: ^
recip.c: recip.c:85:23: error: always_inline function '_mm256_mullo_epi16' requires target feature 'sse4.2', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'sse4.2'
recip.c: __m256i f0vecqinv = _mm256_mullo_epi16(f0vec,qinvvec);
recip.c: ^
recip.c: recip.c:85:48: error: always_inline function '_mm256_set1_epi16' requires target feature 'sse4.2', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'sse4.2'
recip.c: __m256i f0vecqinv = _mm256_mullo_epi16(f0vec,qinvvec);
recip.c: ^
recip.c: recip.c:69:17: note: expanded from macro 'qinvvec'
recip.c: #define qinvvec _mm256_set1_epi16(qinv)
recip.c: ^
recip.c: recip.c:86:23: error: always_inline function '_mm256_mullo_epi16' requires target feature 'sse4.2', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'sse4.2'
recip.c: __m256i g0vecqinv = _mm256_mullo_epi16(g0vec,qinvvec);
recip.c: ^
recip.c: recip.c:86:48: error: always_inline function '_mm256_set1_epi16' requires target feature 'sse4.2', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'sse4.2'
recip.c: __m256i g0vecqinv = _mm256_mullo_epi16(g0vec,qinvvec);
recip.c: ^
recip.c: recip.c:69:17: note: expanded from macro 'qinvvec'
recip.c: #define qinvvec _mm256_set1_epi16(qinv)
recip.c: ^
recip.c: recip.c:87:21: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'vectormodq_swapeliminate' that is compiled without support for 'sse4.2'
recip.c: ...

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx

Compiler output

Implementation: crypto_core/invsntrup761/avx
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

recip.c: recip.c: In function 'montproduct':
recip.c: recip.c:72:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
recip.c: {
recip.c: ^
recip.c: recip.c:71:23: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
recip.c: static inline __m256i montproduct(__m256i x,__m256i y,__m256i yqinv)
recip.c: ^
recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
recip.c: from recip.c:1:
recip.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avx2intrin.h:808:1: error: inlining failed in call to always_inline '_mm256_sub_epi16': target specific option mismatch
recip.c: _mm256_sub_epi16 (__m256i __A, __m256i __B)
recip.c: ^
recip.c: recip.c:78:10: error: called from here
recip.c: return _mm256_sub_epi16(hi,e);
recip.c: ^
recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
recip.c: from recip.c:1:
recip.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avx2intrin.h:546:1: error: inlining failed in call to always_inline '_mm256_mulhi_epi16': target specific option mismatch
recip.c: _mm256_mulhi_epi16 (__m256i __A, __m256i __B)
recip.c: ^
recip.c: recip.c:77:5: error: called from here
recip.c: e = _mm256_mulhi_epi16(d,qvec);
recip.c: ^
recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:41:0,
recip.c: from recip.c:1:
recip.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx