Implementation notes: amd64, hertz, crypto_sign/dilithium3

Computer: hertz
Microarchitecture: amd64; Zen 4 (a60f12)
Architecture: amd64
CPU ID: AuthenticAMD-00a60f12-178bfbff
SUPERCOP version: 20240107
Operation: crypto_sign
Primitive: dilithium3

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
340647	103535 64 0	126562 924 1832	`avx2`	`clang-17_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231217
343860	95508 64 0	118386 924 1832	`avx2`	`clang-17_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231217
345927	76520 64 0	96924 916 1832	`avx2`	`clang-17_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231217
1188252	45504 0 0	67901 812 1896	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231217
1241390	21748 0 0	42173 812 1832	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231217
1408806	18631 0 0	37517 804 1800	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231220	20231217
1480726	65766 0 0	88826 852 1832	`ref`	`clang-17_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231217
1544803	55018 0 0	77922 852 1832	`ref`	`clang-17_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231217
1566226	19404 0 0	40156 844 1832	`ref`	`clang-17_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231220	20231217

Compiler output

Implementation: avx2
Security model: constbranchindex
Compiler: clang-17 -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

try.c: /usr/bin/ld: warning: f1600x4.o: missing .note.GNU-stack section implies executable stack
try.c: /usr/bin/ld: NOTE: This behaviour is deprecated and will be removed in a future version of the linker
try.c: /usr/bin/ld: warning: f1600x4.o: missing .note.GNU-stack section implies executable stack
try.c: /usr/bin/ld: NOTE: This behaviour is deprecated and will be removed in a future version of the linker
measure.c: /usr/bin/ld: warning: f1600x4.o: missing .note.GNU-stack section implies executable stack
measure.c: /usr/bin/ld: NOTE: This behaviour is deprecated and will be removed in a future version of the linker

Number of similar (compiler,implementation) pairs: 3, namely:

Compiler	Implementations
clang-17 -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2
clang-17 -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2
clang-17 -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2

Compiler output

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

poly.c: poly.c: In function 'crypto_sign_dilithium3_avx2_constbranchindex_poly_uniform_eta_4x':
poly.c: <command-line>: warning: 'crypto_sign_dilithium3_avx2_constbranchindex_rej_eta_avx' reading 840 bytes from a region of size 704 [-Wstringop-overread]
poly.c: config.h:3:32: note: in expansion of macro 'CRYPTO_NAMESPACE'
poly.c: 3 | #define DILITHIUM_NAMESPACE(s) CRYPTO_NAMESPACE(s)
poly.c: | ^~~~~~~~~~~~~~~~
poly.c: rejsample.h:24:21: note: in expansion of macro 'DILITHIUM_NAMESPACE'
poly.c: 24 | #define rej_eta_avx DILITHIUM_NAMESPACE(rej_eta_avx)
poly.c: | ^~~~~~~~~~~~~~~~~~~
poly.c: poly.c:596:10: note: in expansion of macro 'rej_eta_avx'
poly.c: 596 | ctr2 = rej_eta_avx(a2->coeffs, buf[2].coeffs);
poly.c: | ^~~~~~~~~~~
poly.c: <command-line>: note: referencing argument 2 of type 'const uint8_t[840]' {aka 'const unsigned char[840]'}
poly.c: config.h:3:32: note: in expansion of macro 'CRYPTO_NAMESPACE'
poly.c: 3 | #define DILITHIUM_NAMESPACE(s) CRYPTO_NAMESPACE(s)
poly.c: | ^~~~~~~~~~~~~~~~
poly.c: rejsample.h:24:21: note: in expansion of macro 'DILITHIUM_NAMESPACE'
poly.c: 24 | #define rej_eta_avx DILITHIUM_NAMESPACE(rej_eta_avx)
poly.c: | ^~~~~~~~~~~~~~~~~~~
poly.c: poly.c:596:10: note: in expansion of macro 'rej_eta_avx'
poly.c: 596 | ctr2 = rej_eta_avx(a2->coeffs, buf[2].coeffs);
poly.c: | ^~~~~~~~~~~
poly.c: <command-line>: note: in a call to function 'crypto_sign_dilithium3_avx2_constbranchindex_rej_eta_avx'
poly.c: config.h:3:32: note: in expansion of macro 'CRYPTO_NAMESPACE'
poly.c: 3 | #define DILITHIUM_NAMESPACE(s) CRYPTO_NAMESPACE(s)
poly.c: | ^~~~~~~~~~~~~~~~
poly.c: ...

Number of similar (compiler,implementation) pairs: 3, 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 -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx2