Implementation notes: amd64, rumba7, crypto_kem/mceliece348864pcf

Computer: rumba7
Microarchitecture: amd64; Zen (800f11)
Architecture: amd64
CPU ID: AuthenticAMD-00800f11-178bfbff
SUPERCOP version: 20240625
Operation: crypto_kem
Primitive: mceliece348864pcf

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
225723	154949 0 0	199615 924 1728	`avx`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
226218	101982 0 0	145656 876 1760	`avx`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
226791	112944 0 0	157535 916 1728	`avx`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
237565	67939 0 0	110505 900 1792	`avx`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
240697	69934 0 0	112752 876 1760	`avx`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
244040	69668 0 0	111951 908 1728	`avx`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
244567	104812 0 0	148063 900 1728	`sse`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
244914	117821 0 0	160376 876 1760	`sse`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
245942	145642 0 0	188839 900 1728	`sse`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
247623	67857 0 0	110032 876 1760	`avx`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
248201	63661 0 0	104784 868 1728	`avx`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
262097	65349 0 0	106937 892 1792	`sse`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
263006	71770 0 0	113424 876 1760	`sse`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
268466	68278 0 0	109287 900 1728	`sse`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
273228	66382 0 0	107424 876 1760	`sse`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
284358	62018 0 0	101944 868 1728	`sse`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
678601	75611 0 0	120144 876 1760	`vec`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
728902	106548 0 0	152047 900 1728	`vec`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
789808	41604 0 0	85089 900 1792	`vec`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
814383	40614 0 0	83823 908 1728	`vec`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
845573	42649 0 0	86384 876 1760	`vec`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
966967	86567 0 0	132639 900 1728	`vec`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
971294	66911 0 0	112591 900 1728	`vec`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
1078324	41253 0 0	84368 876 1760	`vec`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
1098956	35097 0 0	77080 868 1728	`vec`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
60299638	28546 0 0	71450 884 1760	`ref`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
62166854	45838 0 0	90055 900 1728	`ref`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
62316183	31087 0 0	74911 900 1728	`ref`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
62502410	48521 0 0	91903 900 1728	`ref`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
65630621	15657 0 0	57201 892 1792	`ref`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
81991061	16303 0 0	58098 884 1760	`ref`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
82570700	12450 0 0	52394 876 1728	`ref`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
85597835	14790 0 0	55751 900 1728	`ref`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	20240625
86584679	15311 0 0	56288 876 1760	`ref`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240627	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 (Ubuntu_Clang_14.0.0)`

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 (Ubuntu_Clang_14.0.0)`

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: In file included from bm.c:15:
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: In file included from vec.c:7:
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: In file included from vec.c:7:
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 (11.4.0)`
`sse`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`sse`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`sse`	`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: 34, namely:

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