Implementation notes: aarch64, minimac, crypto_kem/ntskem13136

Computer: minimac
Architecture: aarch64
CPU ID: unknown CPU ID
SUPERCOP version: 20211108
Operation: crypto_kem
Primitive: ntskem13136

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
1408879	? ? ?	? ? ?	`T:opt`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210602	20210529
1455676	? ? ?	? ? ?	`T:opt`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210602	20210529
1537140	? ? ?	? ? ?	`T:opt`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210602	20210529
1563672	? ? ?	? ? ?	`T:opt`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210602	20210529
1732065	? ? ?	? ? ?	`T:opt`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210602	20210529
13559204	? ? ?	? ? ?	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210602	20210529
13953188	? ? ?	? ? ?	`T:ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20210602	20210529
14315841	? ? ?	? ? ?	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210602	20210529
15185540	? ? ?	? ? ?	`T:ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210602	20210529
15607924	? ? ?	? ? ?	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210602	20210529

Compiler output

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

bitslice_bma_128.c: In file included from bitslice_bma_128.c:18:
bitslice_bma_128.c: In file included from ./bitslice_bma_128.h:18:
bitslice_bma_128.c: In file included from /Library/Developer/CommandLineTools/usr/lib/clang/12.0.5/include/immintrin.h:15:
bitslice_bma_128.c: /Library/Developer/CommandLineTools/usr/lib/clang/12.0.5/include/mmintrin.h:50:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
bitslice_bma_128.c: return (__m64)__builtin_ia32_vec_init_v2si(__i, 0);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.c: /Library/Developer/CommandLineTools/usr/lib/clang/12.0.5/include/mmintrin.h:129:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
bitslice_bma_128.c: return (__m64)__builtin_ia32_packsswb((__v4hi)__m1, (__v4hi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.c: /Library/Developer/CommandLineTools/usr/lib/clang/12.0.5/include/mmintrin.h:159:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
bitslice_bma_128.c: return (__m64)__builtin_ia32_packssdw((__v2si)__m1, (__v2si)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.c: /Library/Developer/CommandLineTools/usr/lib/clang/12.0.5/include/mmintrin.h:189:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
bitslice_bma_128.c: return (__m64)__builtin_ia32_packuswb((__v4hi)__m1, (__v4hi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.c: /Library/Developer/CommandLineTools/usr/lib/clang/12.0.5/include/mmintrin.h:216:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
bitslice_bma_128.c: return (__m64)__builtin_ia32_punpckhbw((__v8qi)__m1, (__v8qi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.c: /Library/Developer/CommandLineTools/usr/lib/clang/12.0.5/include/mmintrin.h:239:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
bitslice_bma_128.c: return (__m64)__builtin_ia32_punpckhwd((__v4hi)__m1, (__v4hi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.c: /Library/Developer/CommandLineTools/usr/lib/clang/12.0.5/include/mmintrin.h:260:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
bitslice_bma_128.c: return (__m64)__builtin_ia32_punpckhdq((__v2si)__m1, (__v2si)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.c: /Library/Developer/CommandLineTools/usr/lib/clang/12.0.5/include/mmintrin.h:287:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
bitslice_bma_128.c: ...

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

Compiler	Implementations
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

bitslice_bma_128.c: In file included from bitslice_bma_128.c:18:
bitslice_bma_128.c: bitslice_bma_128.h:18:10: fatal error: immintrin.h: No such file or directory
bitslice_bma_128.c: 18 | #include <immintrin.h>
bitslice_bma_128.c: | ^~~~~~~~~~~~~
bitslice_bma_128.c: compilation terminated.

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

Compiler output

Implementation: T:opt
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

try.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/knownrandombytes.o) was built for newer macOS version (11.3) than being linked (11.0)
try.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/kernelrandombytes.o) was built for newer macOS version (11.3) than being linked (11.0)
try.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/cpucycles.o) was built for newer macOS version (11.3) than being linked (11.0)
try.c: ld: warning: could not create compact unwind for _init: registers 21 and 22 not saved contiguously in frame
try.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/libsupercop.a(crypto_rng_chacha20_ref_constbranchindex-rng.o)) was built for newer macOS version (11.3) than being linked (11.0)
try.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/knownrandombytes.o) was built for newer macOS version (11.3) than being linked (11.0)
try.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/kernelrandombytes.o) was built for newer macOS version (11.3) than being linked (11.0)
try.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/cpucycles.o) was built for newer macOS version (11.3) than being linked (11.0)
try.c: ld: warning: could not create compact unwind for _init: registers 21 and 22 not saved contiguously in frame
try.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/libsupercop.a(crypto_rng_chacha20_ref_constbranchindex-rng.o)) was built for newer macOS version (11.3) than being linked (11.0)
measure.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/fastrandombytes.o) was built for newer macOS version (11.3) than being linked (11.0)
measure.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/kernelrandombytes.o) was built for newer macOS version (11.3) than being linked (11.0)
measure.c: ld: warning: could not create compact unwind for _randombytes: registers 21 and 22 not saved contiguously in frame
measure.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/cpucycles.o) was built for newer macOS version (11.3) than being linked (11.0)
measure.c: ld: warning: could not create compact unwind for _init: registers 21 and 22 not saved contiguously in frame
measure.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/libsupercop.a(crypto_rng_chacha20_ref_constbranchindex-rng.o)) was built for newer macOS version (11.3) than being linked (11.0)

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

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

Compiler output

Implementation: T:ref
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

try.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/knownrandombytes.o) was built for newer macOS version (11.3) than being linked (11.0)
try.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/kernelrandombytes.o) was built for newer macOS version (11.3) than being linked (11.0)
try.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/cpucycles.o) was built for newer macOS version (11.3) than being linked (11.0)
try.c: ld: warning: could not create compact unwind for _init: registers 21 and 22 not saved contiguously in frame
try.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/libsupercop.a(crypto_rng_chacha20_ref_constbranchindex-rng.o)) was built for newer macOS version (11.3) than being linked (11.0)
try.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/knownrandombytes.o) was built for newer macOS version (11.3) than being linked (11.0)
try.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/cpucycles.o) was built for newer macOS version (11.3) than being linked (11.0)
try.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/kernelrandombytes.o) was built for newer macOS version (11.3) than being linked (11.0)
try.c: ld: warning: could not create compact unwind for _init: registers 21 and 22 not saved contiguously in frame
try.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/libsupercop.a(crypto_rng_chacha20_ref_constbranchindex-rng.o)) was built for newer macOS version (11.3) than being linked (11.0)
measure.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/fastrandombytes.o) was built for newer macOS version (11.3) than being linked (11.0)
measure.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/kernelrandombytes.o) was built for newer macOS version (11.3) than being linked (11.0)
measure.c: ld: warning: could not create compact unwind for _randombytes: registers 21 and 22 not saved contiguously in frame
measure.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/cpucycles.o) was built for newer macOS version (11.3) than being linked (11.0)
measure.c: ld: warning: could not create compact unwind for _init: registers 21 and 22 not saved contiguously in frame
measure.c: ld: warning: object file (/Users/djb/supercop-20210529/supercop-data/minimac/aarch64/lib/libsupercop.a(crypto_rng_chacha20_ref_constbranchindex-rng.o)) was built for newer macOS version (11.3) than being linked (11.0)

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

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

Compiler output

Implementation: T:sse2
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

bitslice_bma_128.c: In file included from bitslice_bma_128.c:17:
bitslice_bma_128.c: ./bits.h:47:9: error: unknown type name '__m128i'
bitslice_bma_128.c: typedef __m128i vector;
bitslice_bma_128.c: ^
bitslice_bma_128.c: ./bits.h:98:11: error: unknown type name '__m128i'
bitslice_bma_128.c: const __m128i a_hi = _mm_unpackhi_epi64(a, a);
bitslice_bma_128.c: ^
bitslice_bma_128.c: ./bits.h:98:26: error: implicit declaration of function '_mm_unpackhi_epi64' is invalid in C99 [-Werror,-Wimplicit-function-declaration]
bitslice_bma_128.c: const __m128i a_hi = _mm_unpackhi_epi64(a, a);
bitslice_bma_128.c: ^
bitslice_bma_128.c: ./bits.h:99:21: error: implicit declaration of function '_mm_cvtsi128_si64' is invalid in C99 [-Werror,-Wimplicit-function-declaration]
bitslice_bma_128.c: return popcount(_mm_cvtsi128_si64(a_hi)) + popcount(_mm_cvtsi128_si64(a));
bitslice_bma_128.c: ^
bitslice_bma_128.c: In file included from bitslice_bma_128.c:18:
bitslice_bma_128.c: In file included from ./bitslice_bma_128.h:18:
bitslice_bma_128.c: In file included from /Library/Developer/CommandLineTools/usr/lib/clang/12.0.5/include/immintrin.h:15:
bitslice_bma_128.c: /Library/Developer/CommandLineTools/usr/lib/clang/12.0.5/include/mmintrin.h:50:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
bitslice_bma_128.c: return (__m64)__builtin_ia32_vec_init_v2si(__i, 0);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.c: /Library/Developer/CommandLineTools/usr/lib/clang/12.0.5/include/mmintrin.h:129:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
bitslice_bma_128.c: return (__m64)__builtin_ia32_packsswb((__v4hi)__m1, (__v4hi)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.c: /Library/Developer/CommandLineTools/usr/lib/clang/12.0.5/include/mmintrin.h:159:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
bitslice_bma_128.c: return (__m64)__builtin_ia32_packssdw((__v2si)__m1, (__v2si)__m2);
bitslice_bma_128.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bitslice_bma_128.c: ...

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

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:sse2

Compiler output

Implementation: T:sse2
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

bitslice_bma_128.c: In file included from bitslice_bma_128.c:17:
bitslice_bma_128.c: bits.h:47:9: error: unknown type name '__m128i'
bitslice_bma_128.c: 47 | typedef __m128i vector;
bitslice_bma_128.c: | ^~~~~~~
bitslice_bma_128.c: bits.h: In function 'vector_popcount':
bitslice_bma_128.c: bits.h:98:11: error: unknown type name '__m128i'
bitslice_bma_128.c: 98 | const __m128i a_hi = _mm_unpackhi_epi64(a, a);
bitslice_bma_128.c: | ^~~~~~~
bitslice_bma_128.c: bits.h:98:26: warning: implicit declaration of function '_mm_unpackhi_epi64' [-Wimplicit-function-declaration]
bitslice_bma_128.c: 98 | const __m128i a_hi = _mm_unpackhi_epi64(a, a);
bitslice_bma_128.c: | ^~~~~~~~~~~~~~~~~~
bitslice_bma_128.c: bits.h:99:21: warning: implicit declaration of function '_mm_cvtsi128_si64' [-Wimplicit-function-declaration]
bitslice_bma_128.c: 99 | return popcount(_mm_cvtsi128_si64(a_hi)) + popcount(_mm_cvtsi128_si64(a));
bitslice_bma_128.c: | ^~~~~~~~~~~~~~~~~
bitslice_bma_128.c: bits.h:93:42: note: in definition of macro 'popcount'
bitslice_bma_128.c: 93 | #define popcount(x) __builtin_popcountll(x)
bitslice_bma_128.c: | ^
bitslice_bma_128.c: In file included from bitslice_bma_128.c:18:
bitslice_bma_128.c: bitslice_bma_128.h: At top level:
bitslice_bma_128.c: bitslice_bma_128.h:18:10: fatal error: immintrin.h: No such file or directory
bitslice_bma_128.c: 18 | #include <immintrin.h>
bitslice_bma_128.c: | ^~~~~~~~~~~~~
bitslice_bma_128.c: compilation terminated.

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sse2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sse2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sse2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sse2