Implementation notes: amd64, scw1b63b1, crypto_kem/kyber90s1024

Computer: scw1b63b1
Architecture: amd64
CPU ID: GenuineIntel-000506f1-0f8bfbff
SUPERCOP version: 20191017
Operation: crypto_kem
Primitive: kyber90s1024

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
1975648	51283 512 0	68245 1320 1576	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191223	20191017
1976030	51283 512 0	68245 1320 1576	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191223	20191017
1989270	65238 512 0	84572 1336 1608	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191223	20191017
1994256	51699 512 0	69485 1320 1576	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191223	20191017
2017810	52047 512 0	69893 1320 1576	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191223	20191017
2034826	43577 512 0	59663 1312 1576	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191223	20191017
2144718	43735 512 0	61164 1336 1608	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191223	20191017
2181186	42928 512 0	60060 1336 1608	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191223	20191017
2356148	40427 512 0	56524 1328 1576	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191223	20191017

Compiler output

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

cbd.c: cbd.c:20:26: error: always_inline function '_mm256_set1_epi32' requires target feature 'xsave', but would be inlined into function 'cbd' that is compiled without support for 'xsave'
cbd.c: const __m256i mask55 = _mm256_set1_epi32(0x55555555);
cbd.c: ^
cbd.c: cbd.c:21:26: error: always_inline function '_mm256_set1_epi32' requires target feature 'xsave', but would be inlined into function 'cbd' that is compiled without support for 'xsave'
cbd.c: const __m256i mask33 = _mm256_set1_epi32(0x33333333);
cbd.c: ^
cbd.c: cbd.c:22:26: error: always_inline function '_mm256_set1_epi32' requires target feature 'xsave', but would be inlined into function 'cbd' that is compiled without support for 'xsave'
cbd.c: const __m256i mask03 = _mm256_set1_epi32(0x03030303);
cbd.c: ^
cbd.c: cbd.c:26:12: error: always_inline function '_mm256_loadu_si256' requires target feature 'xsave', but would be inlined into function 'cbd' that is compiled without support for 'xsave'
cbd.c: ...
cbd.c: vec3 = _mm256_and_si256(mask03, vec3);
cbd.c: ^
cbd.c: cbd.c:44:12: error: always_inline function '_mm256_sub_epi8' requires target feature 'xsave', but would be inlined into function 'cbd' that is compiled without support for 'xsave'
cbd.c: vec1 = _mm256_sub_epi8(vec0, vec1);
cbd.c: ^
cbd.c: cbd.c:45:12: error: always_inline function '_mm256_sub_epi8' requires target feature 'xsave', but would be inlined into function 'cbd' that is compiled without support for 'xsave'
cbd.c: vec3 = _mm256_sub_epi8(vec2, vec3);
cbd.c: ^
cbd.c: fatal error: too many errors emitted, stopping now [-ferror-limit=]
cbd.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	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

Compiler output

Implementation: avx2
Security model: unknown
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

aes256ctr.c: aes256ctr.c:119:3: error: '__builtin_ia32_aeskeygenassist128' needs target feature aes
aes256ctr.c: BLOCK1(0x01);
aes256ctr.c: ^
aes256ctr.c: aes256ctr.c:100:11: note: expanded from macro 'BLOCK1'
aes256ctr.c: temp1 = _mm_aeskeygenassist_si128(temp2, IMM); ^
aes256ctr.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/__wmmintrin_aes.h:62:12: note: expanded from macro '_mm_aeskeygenassist_si128'
aes256ctr.c: (__m128i)__builtin_ia32_aeskeygenassist128((__v2di)(__m128i)(C), (int)(R))
aes256ctr.c: ^
aes256ctr.c: aes256ctr.c:120:3: error: '__builtin_ia32_aeskeygenassist128' needs target feature aes
aes256ctr.c: ...
aes256ctr.c: aes256ctr.c:137:3: error: '__builtin_ia32_aeskeygenassist128' needs target feature aes
aes256ctr.c: BLOCK1(0x40);
aes256ctr.c: ^
aes256ctr.c: aes256ctr.c:100:11: note: expanded from macro 'BLOCK1'
aes256ctr.c: temp1 = _mm_aeskeygenassist_si128(temp2, IMM); ^
aes256ctr.c: /usr/lib/llvm-3.8/bin/../lib/clang/3.8.1/include/__wmmintrin_aes.h:62:12: note: expanded from macro '_mm_aeskeygenassist_si128'
aes256ctr.c: (__m128i)__builtin_ia32_aeskeygenassist128((__v2di)(__m128i)(C), (int)(R))
aes256ctr.c: ^
aes256ctr.c: 13 errors generated.

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

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

Compiler output

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

cbd.c: cbd.c: In function ‘cbd’:
cbd.c: cbd.c:20:17: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
cbd.c: const __m256i mask55 = _mm256_set1_epi32(0x55555555);
cbd.c: ^~~~~~
cbd.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/6/include/immintrin.h:41:0,
cbd.c: from cbd.c:2:
cbd.c: /usr/lib/gcc/x86_64-linux-gnu/6/include/avxintrin.h:1293:1: error: inlining failed in call to always_inline ‘_mm256_set1_epi32’: target specific option mismatch
cbd.c: _mm256_set1_epi32 (int __A)
cbd.c: ^~~~~~~~~~~~~~~~~
cbd.c: cbd.c:22:17: note: called from here
cbd.c: ...
cbd.c: vec1 = _mm256_srli_epi32(vec0, 1);
cbd.c: ~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~
cbd.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/6/include/immintrin.h:41:0,
cbd.c: from cbd.c:2:
cbd.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
cbd.c: _mm256_loadu_si256 (__m256i const *__P)
cbd.c: ^~~~~~~~~~~~~~~~~~
cbd.c: cbd.c:26:10: note: called from here
cbd.c: vec0 = _mm256_loadu_si256((__m256i *)&buf[32*i]);
cbd.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

Namespace violations

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

aes256ctr.o aes256_prf T
aes256ctr.o aes256xof_absorb T
aes256ctr.o aes256xof_squeezeblocks T
aes256ctr.o br_aes_ct64_skey_expand T
aes256ctr.o br_range_enc32le T
cbd.o cbd T
indcpa.o gen_matrix T
indcpa.o indcpa_dec T
indcpa.o indcpa_enc T
indcpa.o indcpa_keypair T
ntt.o basemul T
ntt.o invntt T
ntt.o ntt T
ntt.o zetas D
ntt.o zetas_inv D
poly.o poly_add T
poly.o poly_basemul T
poly.o poly_compress T
poly.o poly_csubq T
poly.o poly_decompress T
poly.o poly_frombytes T
poly.o poly_frommont T
poly.o poly_frommsg T
poly.o poly_getnoise T
poly.o poly_invntt T
poly.o poly_ntt T
poly.o poly_reduce T
poly.o poly_sub T
poly.o poly_tobytes T
poly.o poly_tomsg T
polyvec.o polyvec_add T
polyvec.o polyvec_compress T
polyvec.o polyvec_csubq T
polyvec.o polyvec_decompress T
polyvec.o polyvec_frombytes T
polyvec.o polyvec_invntt T
polyvec.o polyvec_ntt T
polyvec.o polyvec_pointwise_acc T
polyvec.o polyvec_reduce T
polyvec.o polyvec_tobytes T
reduce.o barrett_reduce T
reduce.o csubq T
reduce.o montgomery_reduce T
sha256.o sha256 T
sha512.o sha512 T
verify.o cmov T
verify.o verify T

Number of similar (compiler,implementation) pairs: 9, namely:

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