Implementation notes: amd64, titan0, crypto_kem/ntruhrss701

Computer: titan0
Microarchitecture: amd64; Haswell+AES (306c3)
Architecture: amd64
CPU ID: GenuineIntel-000306c3-bfebfbff
SUPERCOP version: 20240716
Operation: crypto_kem
Primitive: ntruhrss701

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
89265	153887 67296 0	242627 68180 1728	`avx2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
91909	135393 67296 0	222836 68124 1760	`avx2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
93009	138282 67296 0	225507 68180 1728	`avx2`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
93137	145153 67296 0	233611 68180 1728	`avx2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
100236	129560 67296 0	215109 68172 1792	`avx2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
101976	130729 67296 0	216156 68124 1760	`avx2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
107061	130535 67296 0	215363 68180 1728	`avx2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
112397	130691 67296 0	215660 68124 1760	`avx2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
115366	130443 67296 0	214348 68116 1728	`avx2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
851318	72429 0 0	150781 884 1728	`compact`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
868055	52221 0 0	130309 884 1728	`compact`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
931266	32552 0 0	110262 828 1760	`compact`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
1258178	36751 0 0	113621 884 1728	`compact`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
3788373	30838 0 0	108997 884 1728	`ref`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
3799640	42259 0 0	120605 884 1728	`ref`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
3923872	19967 0 0	97029 884 1728	`ref`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
3973829	7266 0 0	82005 884 1728	`compact`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
4214243	7966 0 0	83215 876 1792	`ref`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
4371684	6374 0 0	81863 876 1792	`compact`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
4786811	16577 0 0	93758 828 1760	`ref`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
4792825	8078 0 0	83374 828 1760	`ref`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
5003730	5642 0 0	81302 828 1760	`compact`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
9132490	7329 0 0	81054 820 1728	`ref`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
9587421	4269 0 0	78518 820 1728	`compact`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
11946182	7207 0 0	81925 884 1728	`ref`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
11956454	7763 0 0	82476 820 1760	`ref`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716
12283916	4831 0 0	80076 820 1760	`compact`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240720	20240716

Compiler output

owcpa.c: owcpa.c:44:40: warning: argument 3 of type 'const unsigned char[1400]' with mismatched bound [-Warray-parameter=]
owcpa.c:    44 |                    const unsigned char seed[NTRU_SAMPLE_FG_BYTES])
owcpa.c:       |                    ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~
owcpa.c: In file included from owcpa.c:1:
owcpa.c: owcpa.h:14:40: note: previously declared as 'const unsigned char[32]'
owcpa.c:    14 |                    const unsigned char seed[NTRU_SEEDBYTES]);
owcpa.c:       |                    ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~
owcpa.c: owcpa.c: In function 'crypto_kem_ntruhrss701_avx2_constbranchindex_owcpa_keypair':
owcpa.c: <command-line>: warning: 'crypto_kem_ntruhrss701_avx2_constbranchindex_sample_fg' reading 1400 bytes from a region of size 32 [-Wstringop-overread]
owcpa.c: <command-line>: note: in definition of macro 'CRYPTO_NAMESPACE'
owcpa.c: owcpa.c:54:3: note: in expansion of macro 'sample_fg'
owcpa.c:    54 |   sample_fg(f,g,seed);
owcpa.c:       |   ^~~~~~~~~
owcpa.c: <command-line>: note: referencing argument 3 of type 'const unsigned char *'
owcpa.c: <command-line>: note: in definition of macro 'CRYPTO_NAMESPACE'
owcpa.c: owcpa.c:54:3: note: in expansion of macro 'sample_fg'
owcpa.c:    54 |   sample_fg(f,g,seed);
owcpa.c:       |   ^~~~~~~~~
owcpa.c: <command-line>: note: in a call to function 'crypto_kem_ntruhrss701_avx2_constbranchindex_sample_fg'
owcpa.c: <command-line>: note: in definition of macro 'CRYPTO_NAMESPACE'
owcpa.c: sample.h:10:6: note: in expansion of macro 'sample_fg'
owcpa.c:    10 | void sample_fg(poly *f, poly *g, const unsigned char uniformbytes[NTRU_SAMPLE_FG_BYTES]);
owcpa.c:       |      ^~~~~~~~~
pack3.c: pack3.c:3:36: warning: argument 1 of type 'unsigned char[280]' with mismatched bound [-Warray-parameter=]
pack3.c:     3 | void poly_S3_tobytes(unsigned char msg[NTRU_OWCPA_MSGBYTES], const poly *a)
pack3.c:       |                      ~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~
pack3.c: In file included from pack3.c:1:
pack3.c: poly.h:33:36: note: previously declared as 'unsigned char[140]'
pack3.c:    33 | void poly_S3_tobytes(unsigned char msg[NTRU_PACK_TRINARY_BYTES], const poly *a);
pack3.c:       |                      ~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~
pack3.c: pack3.c:19:53: warning: argument 2 of type 'const unsigned char[280]' with mismatched bound [-Warray-parameter=]
pack3.c:    19 | void poly_S3_frombytes(poly *r, const unsigned char msg[NTRU_OWCPA_MSGBYTES])
pack3.c:       |                                 ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~
pack3.c: In file included from pack3.c:1:
pack3.c: poly.h:34:53: note: previously declared as 'const unsigned char[140]'
pack3.c:    34 | void poly_S3_frombytes(poly *r, const unsigned char msg[NTRU_PACK_TRINARY_BYTES]);
pack3.c:       |                                 ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~

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

Implementation	Compiler
`avx2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`

Compiler output

owcpa.c: owcpa.c:44:40: warning: argument 3 of type 'const unsigned char[1400]' with mismatched bound [-Warray-parameter=]
owcpa.c:    44 |                    const unsigned char seed[NTRU_SAMPLE_FG_BYTES])
owcpa.c:       |                    ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~
owcpa.c: In file included from owcpa.c:1:
owcpa.c: owcpa.h:14:40: note: previously declared as 'const unsigned char[32]'
owcpa.c:    14 |                    const unsigned char seed[NTRU_SEEDBYTES]);
owcpa.c:       |                    ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~
owcpa.c: owcpa.c: In function 'crypto_kem_ntruhrss701_ref_constbranchindex_owcpa_keypair':
owcpa.c: <command-line>: warning: 'crypto_kem_ntruhrss701_ref_constbranchindex_sample_fg' reading 1400 bytes from a region of size 32 [-Wstringop-overread]
owcpa.c: <command-line>: note: in definition of macro 'CRYPTO_NAMESPACE'
owcpa.c: owcpa.c:54:3: note: in expansion of macro 'sample_fg'
owcpa.c:    54 |   sample_fg(f,g,seed);
owcpa.c:       |   ^~~~~~~~~
owcpa.c: <command-line>: note: referencing argument 3 of type 'const unsigned char *'
owcpa.c: <command-line>: note: in definition of macro 'CRYPTO_NAMESPACE'
owcpa.c: owcpa.c:54:3: note: in expansion of macro 'sample_fg'
owcpa.c:    54 |   sample_fg(f,g,seed);
owcpa.c:       |   ^~~~~~~~~
owcpa.c: <command-line>: note: in a call to function 'crypto_kem_ntruhrss701_ref_constbranchindex_sample_fg'
owcpa.c: <command-line>: note: in definition of macro 'CRYPTO_NAMESPACE'
owcpa.c: sample.h:10:6: note: in expansion of macro 'sample_fg'
owcpa.c:    10 | void sample_fg(poly *f, poly *g, const unsigned char uniformbytes[NTRU_SAMPLE_FG_BYTES]);
owcpa.c:       |      ^~~~~~~~~
pack3.c: pack3.c:3:36: warning: argument 1 of type 'unsigned char[280]' with mismatched bound [-Warray-parameter=]
pack3.c:     3 | void poly_S3_tobytes(unsigned char msg[NTRU_OWCPA_MSGBYTES], const poly *a)
pack3.c:       |                      ~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~
pack3.c: In file included from pack3.c:1:
pack3.c: poly.h:32:36: note: previously declared as 'unsigned char[140]'
pack3.c:    32 | void poly_S3_tobytes(unsigned char msg[NTRU_PACK_TRINARY_BYTES], const poly *a);
pack3.c:       |                      ~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~
pack3.c: pack3.c:19:53: warning: argument 2 of type 'const unsigned char[280]' with mismatched bound [-Warray-parameter=]
pack3.c:    19 | void poly_S3_frombytes(poly *r, const unsigned char msg[NTRU_OWCPA_MSGBYTES])
pack3.c:       |                                 ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~
pack3.c: In file included from pack3.c:1:
pack3.c: poly.h:33:53: note: previously declared as 'const unsigned char[140]'
pack3.c:    33 | void poly_S3_frombytes(poly *r, const unsigned char msg[NTRU_PACK_TRINARY_BYTES]);
pack3.c:       |                                 ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~

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

Implementation	Compiler
`ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`

Passed TIMECOP

TIMECOP iterations: 1

Number of similar (implementation,compiler) pairs: 27, namely:

Implementation	Compiler
`avx2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`compact`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`compact`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`compact`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`compact`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`compact`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`compact`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`compact`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`compact`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`compact`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`