Implementation notes: amd64, comet, crypto_kem/mceliece348864pcf

Computer: comet
Microarchitecture: amd64; Comet Lake (806ec)
Architecture: amd64
CPU ID: GenuineIntel-000806ec-bfebfbff
SUPERCOP version: 20240625
Operation: crypto_kem
Primitive: mceliece348864pcf

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
155168	160422 0 0	214497 876 1792	`avx`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
155243	120861 0 0	174937 876 1728	`avx`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
157773	111956 0 0	165404 788 1760	`avx`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
174799	70610 0 0	122220 788 1760	`avx`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
175078	68212 0 0	119671 860 1792	`avx`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
179428	69924 0 0	121065 868 1728	`avx`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
188391	66193 0 0	117340 788 1760	`avx`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
189168	61272 0 0	111260 780 1728	`avx`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
228216	112129 0 0	163513 860 1728	`sse`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
229199	150830 0 0	202145 860 1792	`sse`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
231503	151746 0 0	203460 788 1760	`sse`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
252474	72746 0 0	122436 788 1760	`sse`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
254125	65698 0 0	114823 852 1792	`sse`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
264531	68470 0 0	116993 860 1728	`sse`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
267629	64557 0 0	113740 788 1760	`sse`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
270576	59537 0 0	107556 780 1728	`sse`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
635155	74717 0 0	128660 788 1760	`vec`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
659960	106548 0 0	160585 860 1728	`vec`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
711703	77877 0 0	132681 860 1728	`vec`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
726068	102363 0 0	157273 860 1792	`vec`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
751339	42115 0 0	94191 860 1792	`vec`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
797129	44390 0 0	96468 788 1760	`vec`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
873498	40806 0 0	92553 868 1728	`vec`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
1102019	33025 0 0	83572 780 1728	`vec`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
1256420	39641 0 0	91340 788 1760	`vec`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
69834158	48521 0 0	99673 860 1728	`ref`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
73520737	33353 0 0	84654 796 1760	`ref`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
75705276	40627 0 0	92793 860 1728	`ref`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
76034484	55828 0 0	108257 860 1792	`ref`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
78234304	16002 0 0	65407 852 1792	`ref`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
82021492	14114 0 0	62844 788 1760	`ref`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
85140458	10801 0 0	58422 788 1728	`ref`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
110081410	14918 0 0	63713 860 1728	`ref`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625
110212122	16055 0 0	65470 796 1760	`ref`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240709	20240625

Compiler output

decrypt.c: decrypt.c:220:11: warning: AVX vector return of type 'vec256' (aka '__m256i') without 'avx' enabled changes the ABI [-Wpsabi]
decrypt.c:         allone = vec256_set1_16b(0xFFFF);
decrypt.c:                  ^
decrypt.c: decrypt.c:224:17: warning: AVX vector return of type 'vec256' (aka '__m256i') without 'avx' enabled changes the ABI [-Wpsabi]
decrypt.c:                 error256[i] = vec256_or_reduce(eval[i]);
decrypt.c:                               ^
decrypt.c: decrypt.c:225:17: warning: AVX vector argument of type 'vec256' (aka '__m256i') without 'avx' enabled changes the ABI [-Wpsabi]
decrypt.c:                 error256[i] = vec256_xor(error256[i], allone);
decrypt.c:                               ^
decrypt.c: decrypt.c:153:12: warning: AVX vector return of type 'vec256' (aka '__m256i') without 'avx' enabled changes the ABI [-Wpsabi]
decrypt.c:                 out[i] = vec256_set4x(v[0], v[1], v[2], v[3]);
decrypt.c:                          ^
decrypt.c: In file included from decrypt.c:15:
decrypt.c: In file included from ./fft_tr.h:11:
decrypt.c: ./vec256.h:35:10: error: always_inline function '_mm256_set_epi64x' requires target feature 'avx', but would be inlined into function 'vec256_set4x' that is compiled without support for 'avx'
decrypt.c:         return  _mm256_set_epi64x(a3, a2, a1, a0);
decrypt.c:                 ^
decrypt.c: ./vec256.h:35:10: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decrypt.c: decrypt.c:59:15: warning: AVX vector argument of type 'vec256' (aka '__m256i') without 'avx' enabled changes the ABI [-Wpsabi]
decrypt.c:                 out[i][j] = vec256_and(inv[i][j], recv[i]);
decrypt.c:                             ^
decrypt.c: In file included from decrypt.c:15:
decrypt.c: In file included from ./fft_tr.h:11:
decrypt.c: ./vec256.h:74:9: error: always_inline function '_mm256_and_si256' requires target feature 'avx2', but would be inlined into function 'vec256_and' that is compiled without support for 'avx2'
decrypt.c:         return _mm256_and_si256(a, b);
decrypt.c: ...

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

Implementation	Compiler
`avx`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`

Compiler output

decrypt.c: In file included from decrypt.c:9:
decrypt.c: In file included from ./vec128_gf.h:10:
decrypt.c: ./vec128.h:33:9: error: always_inline function '_mm_testz_si128' requires target feature 'sse4.1', but would be inlined into function 'vec128_testz' that is compiled without support for 'sse4.1'
decrypt.c:         return _mm_testz_si128(a, a);
decrypt.c:                ^
decrypt.c: 1 error generated.

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

Implementation	Compiler
`sse`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`

Compiler output

bm.c: bm.c:120:18: warning: argument 1 of type 'uint64_t[12]' {aka 'long unsigned int[12]'} with mismatched bound [-Warray-parameter=]
bm.c:   120 | void bm(uint64_t out[ GFBITS ], vec128 in[ GFBITS ])
bm.c:       |         ~~~~~~~~~^~~~~~~~~~~~~
bm.c: In file included from bm.c:15:
bm.c: bm.h:15:19: note: previously declared as 'uint64_t *' {aka 'long unsigned int *'}
bm.c:    15 | void bm(uint64_t *out, vec128 *in);
bm.c:       |         ~~~~~~~~~~^~~
bm.c: bm.c:120:40: warning: argument 2 of type 'vec128[12]' {aka '__m128i[12]'} with mismatched bound [-Warray-parameter=]
bm.c:   120 | void bm(uint64_t out[ GFBITS ], vec128 in[ GFBITS ])
bm.c:       |                                 ~~~~~~~^~~~~~~~~~~~
bm.c: bm.h:15:32: note: previously declared as 'vec128 *' {aka '__m128i *'}
bm.c:    15 | void bm(uint64_t *out, vec128 *in);
bm.c:       |                        ~~~~~~~~^~
vec.c: vec.c:12:21: warning: argument 1 of type 'vec[12]' {aka 'long unsigned int[12]'} with mismatched bound [-Warray-parameter=]
vec.c:    12 | void vec_GF_mul(vec out[ GFBITS ], vec v[ GFBITS ], gf a[ SYS_T ])
vec.c:       |                 ~~~~^~~~~~~~~~~~~
vec.c: In file included from vec.c:7:
vec.c: vec.h:42:17: note: previously declared as 'vec[]' {aka 'long unsigned int[]'}
vec.c:    42 | void vec_GF_mul(vec [], vec [], gf []);
vec.c:       |                 ^~~~~~
vec.c: vec.c:12:40: warning: argument 2 of type 'vec[12]' {aka 'long unsigned int[12]'} with mismatched bound [-Warray-parameter=]
vec.c:    12 | void vec_GF_mul(vec out[ GFBITS ], vec v[ GFBITS ], gf a[ SYS_T ])
vec.c:       |                                    ~~~~^~~~~~~~~~~
vec.c: vec.h:42:25: note: previously declared as 'vec[]' {aka 'long unsigned int[]'}
vec.c:    42 | void vec_GF_mul(vec [], vec [], gf []);
vec.c:       |                         ^~~~~~
vec.c: vec.c:12:56: warning: argument 3 of type 'gf[64]' {aka 'short unsigned int[64]'} with mismatched bound [-Warray-parameter=]
vec.c:    12 | void vec_GF_mul(vec out[ GFBITS ], vec v[ GFBITS ], gf a[ SYS_T ])
vec.c:       |                                                     ~~~^~~~~~~~~~
vec.c: vec.h:42:33: note: previously declared as 'gf[]' {aka 'short unsigned int[]'}
vec.c:    42 | void vec_GF_mul(vec [], vec [], gf []);
vec.c:       |                                 ^~~~~

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

Implementation	Compiler
`sse`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`sse`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`sse`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`sse`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`

Passed TIMECOP

TIMECOP iterations: 1

Number of similar (implementation,compiler) pairs: 34, namely:

Implementation	Compiler
`avx`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`avx`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`avx`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`avx`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`avx`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`avx`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`avx`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`avx`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`ref`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`ref`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`ref`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`ref`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`ref`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`sse`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`sse`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`sse`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`sse`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`sse`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`sse`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`sse`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`sse`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`vec`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`vec`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`vec`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`vec`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`vec`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`vec`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`vec`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`vec`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`vec`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`