Implementation notes: amd64, nucnuc, crypto_dh/curve2251

Computer: nucnuc
Microarchitecture: amd64; Airmont (406c3)
Architecture: amd64
CPU ID: GenuineIntel-000406c3-bfebfbff
SUPERCOP version: 20230530
Operation: crypto_dh
Primitive: curve2251

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
1069663	64389 385024 956	85881 385892 2712	`T:relic/amd64-clmul`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20221012	20221005
1074577	52226 385024 1104	74015 385900 2904	`T:relic/amd64-clmul`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20221012	20221005
1094367	47301 385024 956	67513 385892 2712	`T:relic/amd64-clmul`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20221012	20221005
1105473	40071 385024 1104	60679 385900 2904	`T:relic/amd64-clmul`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20221012	20221005
1111295	52765 385024 956	74625 385892 2712	`T:relic/amd64-clmul`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20221012	20221005
1112648	32206 385024 956	51147 385892 2712	`T:relic/amd64-clmul`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20221012	20221005
1112793	32234 385024 1104	52221 385892 2904	`T:relic/amd64-clmul`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20221012	20221005
1134031	28825 385024 1104	47895 385892 2904	`T:relic/amd64-clmul`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20221012	20221005
1134287	32254 385024 956	51867 385892 2712	`T:relic/amd64-clmul`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20221012	20221005
2130024	37121 385024 1104	56047 385892 2904	`T:relic/amd64-ssse3`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20221012	20221005
2167280	60522 385024 1104	82103 385900 2904	`T:relic/amd64-ssse3`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20221012	20221005
2194356	40530 385024 1104	60373 385892 2904	`T:relic/amd64-ssse3`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20221012	20221005
2213667	48367 385024 1104	68831 385900 2904	`T:relic/amd64-ssse3`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20221012	20221005
5753440	27141 0 8	61534 860 1816	`T:mpfq`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20221012	20221005
6293732	17587 0 8	50878 860 1816	`T:mpfq`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20221012	20221005
6392753	16623 0 8	49318 860 1816	`T:mpfq`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20221012	20221005
6439589	12095 0 8	43860 860 1816	`T:mpfq`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20221012	20221005

Test failure

Implementation: T:relic/amd64-avx
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

error 111

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

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:relic/amd64-avx
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:relic/amd64-avx
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:relic/amd64-avx
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:relic/amd64-avx
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:relic/amd64-avx
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:relic/amd64-avx
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:relic/amd64-avx
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:relic/amd64-avx
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:relic/amd64-avx

Compiler output

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

curve2_251.c: In file included from curve2_251.c:8:
curve2_251.c: In file included from ./field.h:1:
curve2_251.c: In file included from ./mpfq_2_251.h:5:
curve2_251.c: ./x86_64/mpfq_2_251.h:900:14: error: use of unknown builtin '__builtin_ia32_pslldqi128' [-Wimplicit-function-declaration]
curve2_251.c: r.s = t0 ^ SHLD(t1, 64);
curve2_251.c: ^
curve2_251.c: ./x86_64/mpfq_2_251.h:748:25: note: expanded from macro 'SHLD'
curve2_251.c: #define SHLD(x,r) (v2di)__builtin_ia32_pslldqi128 ((gcc43bugfix) (x),(r))
curve2_251.c: ^
curve2_251.c: ./x86_64/mpfq_2_251.h:900:14: error: invalid conversion between vector type 'v2di' (vector of 2 'uint64_t' values) and integer type 'int' of different size
curve2_251.c: r.s = t0 ^ SHLD(t1, 64);
curve2_251.c: ^~~~~~~~~~~~
curve2_251.c: ./x86_64/mpfq_2_251.h:748:19: note: expanded from macro 'SHLD'
curve2_251.c: #define SHLD(x,r) (v2di)__builtin_ia32_pslldqi128 ((gcc43bugfix) (x),(r))
curve2_251.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
curve2_251.c: ./x86_64/mpfq_2_251.h:907:14: error: use of unknown builtin '__builtin_ia32_psrldqi128' [-Wimplicit-function-declaration]
curve2_251.c: r.s = t2 ^ SHRD(t1, 64);
curve2_251.c: ^
curve2_251.c: ./x86_64/mpfq_2_251.h:749:25: note: expanded from macro 'SHRD'
curve2_251.c: #define SHRD(x,r) (v2di)__builtin_ia32_psrldqi128 ((gcc43bugfix) (x),(r))
curve2_251.c: ^
curve2_251.c: ./x86_64/mpfq_2_251.h:907:14: error: invalid conversion between vector type 'v2di' (vector of 2 'uint64_t' values) and integer type 'int' of different size
curve2_251.c: r.s = t2 ^ SHRD(t1, 64);
curve2_251.c: ^~~~~~~~~~~~
curve2_251.c: ./x86_64/mpfq_2_251.h:749:19: note: expanded from macro 'SHRD'
curve2_251.c: ...

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

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

Compiler output

Implementation: T:relic/amd64-avx
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

Number of similar (compiler,implementation) pairs: 10, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:relic/amd64-avx
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:relic/amd64-avx
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:relic/amd64-avx
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:relic/amd64-avx
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:relic/amd64-avx
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:relic/amd64-clmul
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:relic/amd64-clmul
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:relic/amd64-clmul
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:relic/amd64-clmul
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:relic/amd64-clmul

Compiler output

Implementation: T:relic/amd64-avx
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:relic/amd64-avx
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:relic/amd64-avx
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:relic/amd64-avx
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:relic/amd64-avx

Compiler output

Implementation: T:relic/amd64-clmul
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

relic.c: In file included from relic.c:4:
relic.c: src/relic_rand.c: In function 'rand_init':
relic.c: src/relic_rand.c:117:8: warning: implicit declaration of function 'time' [-Wimplicit-function-declaration]
relic.c: 117 | srand(time(NULL));
relic.c: | ^~~~
try.c: /usr/bin/ld: libcrypto_dh_curve2251.a(relic_low.o): warning: relocation in read-only section `.eh_frame'
try.c: /usr/bin/ld: warning: creating DT_TEXTREL in a PIE
try.c: /usr/bin/ld: libcrypto_dh_curve2251.a(relic_low.o): warning: relocation in read-only section `.eh_frame'
try.c: /usr/bin/ld: warning: creating DT_TEXTREL in a PIE
measure.c: /usr/bin/ld: libcrypto_dh_curve2251.a(relic_low.o): warning: relocation in read-only section `.eh_frame'
measure.c: /usr/bin/ld: warning: creating DT_TEXTREL in a PIE

Number of similar (compiler,implementation) pairs: 8, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:relic/amd64-clmul
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:relic/amd64-clmul
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:relic/amd64-clmul
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:relic/amd64-clmul
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:relic/amd64-ssse3
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:relic/amd64-ssse3
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:relic/amd64-ssse3
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:relic/amd64-ssse3

Compiler output

Implementation: T:relic/amd64-ssse3
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

relic.c: In file included from relic.c:4:
relic.c: ./src/relic_rand.c:117:8: warning: implicit declaration of function 'time' is invalid in C99 [-Wimplicit-function-declaration]
relic.c: srand(time(NULL));
relic.c: ^
relic.c: 1 warning generated.
relic_low.S: ./src/low/relic_fb_mul_low.s:2339:2: error: changed section type for .note.GNU-stack, expected: 0x7
relic_low.S: .section .note.GNU-stack,"",@progbits
relic_low.S: ^

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

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:relic/amd64-ssse3
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:relic/amd64-ssse3
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:relic/amd64-ssse3
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:relic/amd64-ssse3
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:relic/amd64-ssse3