Implementation notes: amd64, hydra8, crypto_kem/lightsaber2

Computer: hydra8
Architecture: amd64
CPU ID: GenuineIntel-000306a9-bfebfbff
SUPERCOP version: 20191221
Operation: crypto_kem
Primitive: lightsaber2

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
245772	82414 0 0	102615 808 1624	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191224	20191221
250808	75331 0 0	93703 808 1624	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191224	20191221
252552	65130 0 0	83863 808 1624	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191224	20191221
254032	65130 0 0	83863 808 1624	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191224	20191221
545052	63866 0 0	82597 792 1656	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191224	20191221
768904	14663 0 0	30189 800 1624	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191224	20191221
852520	13774 0 0	30269 792 1656	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191224	20191221
914020	15187 0 0	31797 792 1656	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191224	20191221
997392	13426 0 0	29109 784 1624	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191224	20191221

Compiler output

Implementation: crypto_kem/lightsaber2/avx2
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

SABER_indcpa.c: In file included from SABER_indcpa.c:8:
SABER_indcpa.c: In file included from ././polymul/toom_cook_4/toom-cook_4way.c:1:
SABER_indcpa.c: ././polymul/toom_cook_4/scm_avx.c:50:13: error: always_inline function '_mm256_mullo_epi16' requires target feature 'avx2', but would be inlined into function 'schoolbook_avx_new1' that is compiled without support for 'avx2'
SABER_indcpa.c: c_avx[0] = _mm256_mullo_epi16 (a[0], b[0]);
SABER_indcpa.c: ^
SABER_indcpa.c: ././polymul/toom_cook_4/scm_avx.c:51:13: error: always_inline function '_mm256_mullo_epi16' requires target feature 'avx2', but would be inlined into function 'schoolbook_avx_new1' that is compiled without support for 'avx2'
SABER_indcpa.c: c_avx[1] = _mm256_mullo_epi16 (a[0], b[1]);
SABER_indcpa.c: ^
SABER_indcpa.c: ././polymul/toom_cook_4/scm_avx.c:52:9: error: always_inline function '_mm256_mullo_epi16' requires target feature 'avx2', but would be inlined into function 'schoolbook_avx_new1' that is compiled without support for 'avx2'
SABER_indcpa.c: temp = _mm256_mullo_epi16 (a[1], b[0]);
SABER_indcpa.c: ^
SABER_indcpa.c: ././polymul/toom_cook_4/scm_avx.c:53:13: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'schoolbook_avx_new1' that is compiled without support for 'avx2'
SABER_indcpa.c: c_avx[1] = _mm256_add_epi16(c_avx[1], temp);
SABER_indcpa.c: ^
SABER_indcpa.c: ././polymul/toom_cook_4/scm_avx.c:54:13: error: always_inline function '_mm256_mullo_epi16' requires target feature 'avx2', but would be inlined into function 'schoolbook_avx_new1' that is compiled without support for 'avx2'
SABER_indcpa.c: c_avx[2] = _mm256_mullo_epi16 (a[0], b[2]);
SABER_indcpa.c: ^
SABER_indcpa.c: ././polymul/toom_cook_4/scm_avx.c:55:9: error: always_inline function '_mm256_mullo_epi16' requires target feature 'avx2', but would be inlined into function 'schoolbook_avx_new1' that is compiled without support for 'avx2'
SABER_indcpa.c: temp = _mm256_mullo_epi16 (a[1], b[1]);
SABER_indcpa.c: ^
SABER_indcpa.c: ././polymul/toom_cook_4/scm_avx.c:56:13: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'schoolbook_avx_new1' that is compiled without support for 'avx2'
SABER_indcpa.c: c_avx[2] = _mm256_add_epi16(c_avx[2], temp);
SABER_indcpa.c: ^
SABER_indcpa.c: ././polymul/toom_cook_4/scm_avx.c:57:9: error: always_inline function '_mm256_mullo_epi16' requires target feature 'avx2', but would be inlined into function 'schoolbook_avx_new1' that is compiled without support for 'avx2'
SABER_indcpa.c: temp = _mm256_mullo_epi16 (a[2], b[0]);
SABER_indcpa.c: ...

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2

Compiler output

Implementation: crypto_kem/lightsaber2/avx2
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

SABER_indcpa.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
SABER_indcpa.c: from SABER_indcpa.h:4,
SABER_indcpa.c: from SABER_indcpa.c:4:
SABER_indcpa.c: ./polymul/toom_cook_4/scm_avx.c: In function 'schoolbook_avx_new1':
SABER_indcpa.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
SABER_indcpa.c: _mm256_mullo_epi16 (__m256i __A, __m256i __B)
SABER_indcpa.c: ^~~~~~~~~~~~~~~~~~
SABER_indcpa.c: In file included from ./polymul/toom_cook_4/toom-cook_4way.c:1:0,
SABER_indcpa.c: from SABER_indcpa.c:8:
SABER_indcpa.c: ./polymul/toom_cook_4/scm_avx.c:532:14: note: called from here
SABER_indcpa.c: c_avx[30] = _mm256_mullo_epi16 (a[15], b[15]);
SABER_indcpa.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
SABER_indcpa.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
SABER_indcpa.c: from SABER_indcpa.h:4,
SABER_indcpa.c: from SABER_indcpa.c:4:
SABER_indcpa.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:112:1: error: inlining failed in call to always_inline '_mm256_add_epi16': target specific option mismatch
SABER_indcpa.c: _mm256_add_epi16 (__m256i __A, __m256i __B)
SABER_indcpa.c: ^~~~~~~~~~~~~~~~
SABER_indcpa.c: In file included from ./polymul/toom_cook_4/toom-cook_4way.c:1:0,
SABER_indcpa.c: from SABER_indcpa.c:8:
SABER_indcpa.c: ./polymul/toom_cook_4/scm_avx.c:531:14: note: called from here
SABER_indcpa.c: c_avx[29] = _mm256_add_epi16(c_avx[29], temp);
SABER_indcpa.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
SABER_indcpa.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
SABER_indcpa.c: from SABER_indcpa.h:4,
SABER_indcpa.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx2