Implementation notes: amd64, scw1b63b1, crypto_core/inv3sntrup761

Computer: scw1b63b1
Architecture: amd64
CPU ID: GenuineIntel-000506f1-0f8bfbff
SUPERCOP version: 20191017
Operation: crypto_core
Primitive: inv3sntrup761

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
6490052	4556 0 0	17734 816 832	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191214	20191017
19591884	1929 0 0	13521 784 760	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191214	20191017
19594852	1929 0 0	12697 784 760	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191214	20191017
19628128	1929 0 0	12697 784 760	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191214	20191017
24408932	3064 0 0	14729 784 760	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191214	20191017
31419622	697 0 0	10547 776 760	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191214	20191017
43115460	837 0 0	11779 800 832	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191214	20191017
43658094	808 0 0	11499 800 832	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191214	20191017
44686166	722 0 0	10367 784 800	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191214	20191017

Compiler output

Implementation: avx
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

r3_recip.c: r3_recip.c:362:11: error: always_inline function '_mm256_set_epi32' requires target feature 'xsave', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'xsave'
r3_recip.c: F0[0] = _mm256_set_epi32(0,0,0,0,0,0,0,1);
r3_recip.c: ^
r3_recip.c: r3_recip.c:363:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'xsave', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'xsave'
r3_recip.c: F0[1] = _mm256_set1_epi32(0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:364:11: error: always_inline function '_mm256_set_epi32' requires target feature 'xsave', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'xsave'
r3_recip.c: F0[2] = _mm256_set_epi32(0,0,0,0,1073741824,0,1073741824,0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:365:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'xsave', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'xsave'
r3_recip.c: ...
r3_recip.c: R0[2] = _mm256_set1_epi32(0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:381:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'xsave', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'xsave'
r3_recip.c: R1[2] = _mm256_set1_epi32(0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:395:15: error: always_inline function '_mm256_set1_epi32' requires target feature 'xsave', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'xsave'
r3_recip.c: swapvec = _mm256_set1_epi32(swapmask);
r3_recip.c: ^
r3_recip.c: fatal error: too many errors emitted, stopping now [-ferror-limit=]
r3_recip.c: 20 errors generated.

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: avx
Security model: unknown
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

r3_recip.c: r3_recip.c:362:11: error: always_inline function '_mm256_set_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'sse4.2'
r3_recip.c: F0[0] = _mm256_set_epi32(0,0,0,0,0,0,0,1);
r3_recip.c: ^
r3_recip.c: r3_recip.c:363:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'sse4.2'
r3_recip.c: F0[1] = _mm256_set1_epi32(0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:364:11: error: always_inline function '_mm256_set_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'sse4.2'
r3_recip.c: F0[2] = _mm256_set_epi32(0,0,0,0,1073741824,0,1073741824,0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:365:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'sse4.2'
r3_recip.c: ...
r3_recip.c: R0[2] = _mm256_set1_epi32(0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:381:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'sse4.2'
r3_recip.c: R1[2] = _mm256_set1_epi32(0);
r3_recip.c: ^
r3_recip.c: r3_recip.c:395:15: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_core_inv3sntrup761_avx' that is compiled without support for 'sse4.2'
r3_recip.c: swapvec = _mm256_set1_epi32(swapmask);
r3_recip.c: ^
r3_recip.c: fatal error: too many errors emitted, stopping now [-ferror-limit=]
r3_recip.c: 20 errors generated.

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: avx
Security model: unknown
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

r3_recip.c: r3_recip.c: In function ‘crypto_core_inv3sntrup761_avx’:
r3_recip.c: r3_recip.c:362:9: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
r3_recip.c: F0[0] = _mm256_set_epi32(0,0,0,0,0,0,0,1);
r3_recip.c: ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c: In function ‘vec256_swap’:
r3_recip.c: r3_recip.c:178:20: note: The ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
r3_recip.c: static inline void vec256_swap(vec256 *f,vec256 *g,int len,vec256 mask)
r3_recip.c: ^~~~~~~~~~~
r3_recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/6/include/immintrin.h:43:0,
r3_recip.c: from r3_recip.c:3:
r3_recip.c: ...
r3_recip.c: vec256 b1 = _mm256_loadu_si256((vec256 *) b); b += 32; /* 32,33,... */
r3_recip.c: ^~
r3_recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/6/include/immintrin.h:41:0,
r3_recip.c: from r3_recip.c:3:
r3_recip.c: /usr/lib/gcc/x86_64-linux-gnu/6/include/avxintrin.h:894:1: error: inlining failed in call to always_inline ‘_mm256_loadu_si256’: target specific option mismatch
r3_recip.c: _mm256_loadu_si256 (__m256i const *__P)
r3_recip.c: ^~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c:30:12: note: called from here
r3_recip.c: vec256 b0 = _mm256_loadu_si256((vec256 *) b); b += 32; /* 0,1,...,31 */
r3_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