Implementation notes: amd64, h3neo, crypto_kem/lac192

Computer: h3neo
Microarchitecture: amd64; K10 45nm (100f63)
Architecture: amd64
CPU ID: AuthenticAMD-00100f63-078bfbff
SUPERCOP version: 20231107
Operation: crypto_kem
Primitive: lac192

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
3471986	19053 18600 300	34388 19532 1984	`T:opt`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231122	20231107
3571590	27815 18624 324	44492 19540 2048	`T:opt`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231122	20231107
3684775	20579 18624 324	35628 19540 2048	`T:opt`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231122	20231107
4004944	16698 18624 324	31252 19532 2016	`T:opt`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231122	20231107
4988425	16993 18600 300	31878 19524 1984	`T:opt`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231122	20231107
5079134	25442 18600 300	41414 19540 1984	`T:opt`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231122	20231107
5081143	28109 18600 300	44238 19540 1984	`T:opt`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231122	20231107
5082495	22718 18600 300	38292 19532 1984	`T:opt`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231122	20231107
11914331	24426 0 60	40166 932 1728	`T:ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231122	20231107
11987108	27205 0 60	43118 932 1728	`T:ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231122	20231107
12000864	21981 0 60	37364 924 1728	`T:ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231122	20231107
12477661	27790 0 60	44252 908 1792	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231122	20231107
12484639	16212 0 60	30854 916 1728	`T:ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231122	20231107
19666259	20637 0 60	36396 908 1792	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231122	20231107
19839491	17414 0 60	32564 924 1728	`T:ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231122	20231107
20230225	19417 0 60	34308 908 1792	`T:ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231122	20231107
21050629	15654 0 60	30012 900 1760	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231122	20231107

Checksum failure

Implementation: T:opt
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

ec0bf71001731dea9af39da465c1a4f2d5fb272bb2bff1017a23306198cbd7ea

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:opt

Compiler output

Implementation: T:avx2
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

bin-lwe.c: bin-lwe.c:91:10: error: always_inline function '_mm256_set_epi16' requires target feature 'avx', but would be inlined into function 'poly_mul' that is compiled without support for 'avx'
bin-lwe.c: tmp_one=_mm256_set_epi16(1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1);
bin-lwe.c: ^
bin-lwe.c: bin-lwe.c:91:10: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
bin-lwe.c: bin-lwe.c:103:9: error: always_inline function '_mm256_setzero_si256' requires target feature 'avx', but would be inlined into function 'poly_mul' that is compiled without support for 'avx'
bin-lwe.c: tmp2 =_mm256_setzero_si256();
bin-lwe.c: ^
bin-lwe.c: bin-lwe.c:103:9: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
bin-lwe.c: bin-lwe.c:106:11: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'poly_mul' that is compiled without support for 'avx'
bin-lwe.c: tmp0 = _mm256_loadu_si256((__m256i *)(v_p+j));
bin-lwe.c: ^
bin-lwe.c: bin-lwe.c:106:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
bin-lwe.c: bin-lwe.c:107:11: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'poly_mul' that is compiled without support for 'avx'
bin-lwe.c: tmp1 = _mm256_loadu_si256((__m256i *)(s+j));
bin-lwe.c: ^
bin-lwe.c: bin-lwe.c:107:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
bin-lwe.c: bin-lwe.c:108:11: error: always_inline function '_mm256_maddubs_epi16' requires target feature 'avx2', but would be inlined into function 'poly_mul' that is compiled without support for 'avx2'
bin-lwe.c: tmp0 = _mm256_maddubs_epi16(tmp0, tmp1);
bin-lwe.c: ^
bin-lwe.c: bin-lwe.c:108:11: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
bin-lwe.c: bin-lwe.c:109:11: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'poly_mul' that is compiled without support for 'avx2'
bin-lwe.c: tmp2 = _mm256_add_epi16(tmp2, tmp0);
bin-lwe.c: ^
bin-lwe.c: bin-lwe.c:109:11: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
bin-lwe.c: bin-lwe.c:111:11: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'poly_mul' that is compiled without support for 'avx'
bin-lwe.c: ...

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

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

Compiler output

Implementation: T:avx2
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

bin-lwe.c: bin-lwe.c: In function 'poly_mul':
bin-lwe.c: bin-lwe.c:91:16: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
bin-lwe.c: 91 | tmp_one=_mm256_set_epi16(1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1);
bin-lwe.c: | ~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bin-lwe.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:43,
bin-lwe.c: from bin-lwe.c:1:
bin-lwe.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avxintrin.h:1273:1: error: inlining failed in call to 'always_inline' '_mm256_set_epi16': target specific option mismatch
bin-lwe.c: 1273 | _mm256_set_epi16 (short __q15, short __q14, short __q13, short __q12,
bin-lwe.c: | ^~~~~~~~~~~~~~~~
bin-lwe.c: bin-lwe.c:91:17: note: called from here
bin-lwe.c: 91 | tmp_one=_mm256_set_epi16(1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1);
bin-lwe.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bin-lwe.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:43,
bin-lwe.c: from bin-lwe.c:1:
bin-lwe.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avxintrin.h:1242:1: error: inlining failed in call to 'always_inline' '_mm256_setzero_si256': target specific option mismatch
bin-lwe.c: 1242 | _mm256_setzero_si256 (void)
bin-lwe.c: | ^~~~~~~~~~~~~~~~~~~~
bin-lwe.c: bin-lwe.c:103:23: note: called from here
bin-lwe.c: 103 | tmp2 =_mm256_setzero_si256();
bin-lwe.c: | ^~~~~~~~~~~~~~~~~~~~~~
bin-lwe.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
bin-lwe.c: from bin-lwe.c:1:
bin-lwe.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:112:1: error: inlining failed in call to 'always_inline' '_mm256_add_epi16': target specific option mismatch
bin-lwe.c: 112 | _mm256_add_epi16 (__m256i __A, __m256i __B)
bin-lwe.c: | ^~~~~~~~~~~~~~~~
bin-lwe.c: ...

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

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