Implementation notes: amd64, bolero, crypto_kem/mceliece460896

Computer: bolero
Microarchitecture: amd64; Broadwell+AES (406f1)
Architecture: amd64
CPU ID: GenuineIntel-000406f1-1fc9cbf5
SUPERCOP version: 20240716
Operation: crypto_kem
Primitive: mceliece460896
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
324852135233 0 0185846 784 1608avxgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
325480147226 0 0199772 840 1576avxclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
331428129999 0 0182164 840 1576avxclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
35546083945 0 0133054 824 1640avxclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
35752488038 0 0137214 784 1608avxgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
36202488211 0 0136988 832 1576avxclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
47999686322 0 0135038 784 1608avxgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
49381682161 0 0129678 776 1576avxgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
511152138134 0 0185222 784 1608ssegcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
512360116167 0 0164452 824 1576sseclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
512952129986 0 0178636 824 1576sseclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
55212884456 0 0129966 784 1608ssegcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
55370074965 0 0120894 816 1640sseclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
56109278735 0 0123886 784 1608ssegcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
56875280164 0 0125124 824 1576sseclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
57993675016 0 0118878 776 1576ssegcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
1617512104631 0 0156404 824 1576vecclang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
161858490091 0 0141454 784 1608vecgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
222815647111 0 096780 832 1576vecclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
2256844101963 0 0155140 824 1576vecclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
231989284771 0 0137724 824 1576vecclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
246996450503 0 0100622 784 1608vecgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
286202847545 0 097310 824 1640vecclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
287447649232 0 098966 784 1608vecgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
290396440464 0 088934 776 1576vecgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
14644878015942 0 062968 824 1640refclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
15018814857707 0 0107892 824 1576refclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
15038108434732 0 084596 824 1576refclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
15593271244944 0 093646 832 1576refclang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
19436040014731 0 061164 824 1576refclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
20310979616897 0 063936 792 1608refgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
20458864832145 0 081080 792 1608refgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
20937934815676 0 062150 784 1608refgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716
23825101213234 0 058536 784 1576refgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024072020240716

Compiler output


bm.c: bm.c:78:37: warning: AVX vector return of type 'vec256' (aka '__m256i') without 'avx' enabled changes the ABI [-Wpsabi]
bm.c:         for (i = 13; i < 16; i++) buf[i] = vec256_setzero();
bm.c:                                            ^
bm.c: bm.c:80:15: warning: AVX vector return of type 'vec256' (aka '__m256i') without 'avx' enabled changes the ABI [-Wpsabi]
bm.c:         mask[0][0] = vec256_set1_16b(0x5555);
bm.c:                      ^
bm.c: bm.c:81:15: warning: AVX vector return of type 'vec256' (aka '__m256i') without 'avx' enabled changes the ABI [-Wpsabi]
bm.c:         mask[0][1] = vec256_set1_16b(0xAAAA);
bm.c:                      ^
bm.c: bm.c:82:15: warning: AVX vector return of type 'vec256' (aka '__m256i') without 'avx' enabled changes the ABI [-Wpsabi]
bm.c:         mask[1][0] = vec256_set1_16b(0x3333);
bm.c:                      ^
bm.c: bm.c:83:15: warning: AVX vector return of type 'vec256' (aka '__m256i') without 'avx' enabled changes the ABI [-Wpsabi]
bm.c:         mask[1][1] = vec256_set1_16b(0xCCCC);
bm.c:                      ^
bm.c: bm.c:84:15: warning: AVX vector return of type 'vec256' (aka '__m256i') without 'avx' enabled changes the ABI [-Wpsabi]
bm.c:         mask[2][0] = vec256_set1_16b(0x0F0F);
bm.c:                      ^
bm.c: bm.c:85:15: warning: AVX vector return of type 'vec256' (aka '__m256i') without 'avx' enabled changes the ABI [-Wpsabi]
bm.c:         mask[2][1] = vec256_set1_16b(0xF0F0);
bm.c:                      ^
bm.c: bm.c:86:15: warning: AVX vector return of type 'vec256' (aka '__m256i') without 'avx' enabled changes the ABI [-Wpsabi]
bm.c:         mask[3][0] = vec256_set1_16b(0x00FF);
bm.c:                      ^
bm.c: bm.c:87:15: warning: AVX vector return of type 'vec256' (aka '__m256i') without 'avx' enabled changes the ABI [-Wpsabi]
bm.c: ...

Number of similar (implementation,compiler) pairs: 1, namely:
ImplementationCompiler
avxclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)

Compiler output


pk_gen.c: pk_gen.c:211:12: warning: variable length array folded to constant array as an extension [-Wgnu-folding-constant]
pk_gen.c:                 uint64_t w[ PK_NROWS ][ nBlocks_I*2 ];
pk_gen.c:                          ^
pk_gen.c: pk_gen.c:212:12: warning: variable length array folded to constant array as an extension [-Wgnu-folding-constant]
pk_gen.c:                 vec128   v[ PK_NROWS ][ nBlocks_I ];
pk_gen.c:                          ^
pk_gen.c: 2 warnings generated.

Number of similar (implementation,compiler) pairs: 4, namely:
ImplementationCompiler
sseclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
sseclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
sseclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
sseclang -march=native -Os -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:
ImplementationCompiler
sseclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)

TIMECOP error (can be valgrind bug)


error 1
VEX temporary storage exhausted.
Pool = TEMP,  start 0x597c14a8 curr 0x59c6f8e8 end 0x59c85fe7 (size 5000000)
vex: the `impossible' happened:
VEX temporary storage exhausted.
Increase N_{TEMPORARY,PERMANENT}_BYTES and recompile.
vex storage: T total 310904280 bytes allocated
vex storage: P total 512 bytes allocated
valgrind: the 'impossible' happened:
LibVEX called failure_exit().
host stacktrace:
   at 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
sched status:
running_tid=1
Thread 1: status = VgTs_Runnable (lwpid 4172702)
   at 0x...: extract_gf (sk_gen.c:43)
   by 0x...: crypto_kem_mceliece460896_avx_constbranchindex_genpoly_gen (sk_gen.c:153)
   by 0x...: crypto_kem_mceliece460896_avx_constbranchindex_operation_keypair (kem_keypair.c:57)
   by 0x...: crypto_kem_mceliece460896_avx_constbranchindex_keypair (wrap_keypair.c:10)
   by 0x...: test (try.c:126)
   by 0x...: main (try-anything.c:345)
client stack range: [0x1FFEFDF000 0x1FFF000FFF] client SP: 0x1FFEFE0180
valgrind stack range: [0x1008CAE000 0x1008DADFFF] top usage: 18744 of 1048576
Note: see also the FAQ in the source distribution.
It contains workarounds to several common problems.
In particular, if Valgrind aborted or crashed after
identifying problems in your program, there's a good chance
that fixing those problems will prevent Valgrind aborting or
crashing, especially if it happened in m_mallocfree.c.
If that doesn't help, please report this bug to: www.valgrind.org
In the bug report, send all the above text, the valgrind
version, and what OS and version you are using.  Thanks.

Number of similar (implementation,compiler) pairs: 1, namely:
ImplementationCompiler
avxgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)

TIMECOP error (can be valgrind bug)


error 111

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x122637
   at 0x...: vec128_set2x (vec128.h:56)
   by 0x...: postprocess (fft_tr.c:283)
   by 0x...: crypto_kem_mceliece460896_sse_constbranchindex_fft_tr (fft_tr.c:292)
   by 0x...: crypto_kem_mceliece460896_sse_constbranchindex_decrypt (decrypt.c:175)
   by 0x...: crypto_kem_mceliece460896_sse_constbranchindex_operation_dec (kem_dec.c:36)
   by 0x...: test (try.c:160)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 1, namely:
ImplementationCompiler
sseclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)

TIMECOP error (can be valgrind bug)


error 1
VEX temporary storage exhausted.
Pool = TEMP,  start 0x597c14a8 curr 0x59c6f8e8 end 0x59c85fe7 (size 5000000)
vex: the `impossible' happened:
VEX temporary storage exhausted.
Increase N_{TEMPORARY,PERMANENT}_BYTES and recompile.
vex storage: T total 313910752 bytes allocated
vex storage: P total 512 bytes allocated
valgrind: the 'impossible' happened:
LibVEX called failure_exit().
host stacktrace:
   at 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
   by 0x...: ??? (in /usr/libexec/valgrind/memcheck-amd64-linux)
sched status:
running_tid=1
Thread 1: status = VgTs_Runnable (lwpid 4182219)
   at 0x...: extract_gf (sk_gen.c:43)
   by 0x...: crypto_kem_mceliece460896_sse_constbranchindex_genpoly_gen (sk_gen.c:153)
   by 0x...: crypto_kem_mceliece460896_sse_constbranchindex_operation_keypair (kem_keypair.c:57)
   by 0x...: crypto_kem_mceliece460896_sse_constbranchindex_keypair (wrap_keypair.c:10)
   by 0x...: test (try.c:126)
   by 0x...: main (try-anything.c:345)
client stack range: [0x1FFEFDF000 0x1FFF000FFF] client SP: 0x1FFEFE0180
valgrind stack range: [0x1008CAE000 0x1008DADFFF] top usage: 18744 of 1048576
Note: see also the FAQ in the source distribution.
It contains workarounds to several common problems.
In particular, if Valgrind aborted or crashed after
identifying problems in your program, there's a good chance
that fixing those problems will prevent Valgrind aborting or
crashing, especially if it happened in m_mallocfree.c.
If that doesn't help, please report this bug to: www.valgrind.org
In the bug report, send all the above text, the valgrind
version, and what OS and version you are using.  Thanks.

Number of similar (implementation,compiler) pairs: 1, namely:
ImplementationCompiler
ssegcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)

Passed TIMECOP


TIMECOP iterations: 1

Number of similar (implementation,compiler) pairs: 31, namely:
ImplementationCompiler
avxclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
avxclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
avxclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
avxclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
avxgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
avxgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
avxgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
refclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
refclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
refclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
refclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
refclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
refgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
refgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
refgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
refgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
sseclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
sseclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
sseclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
ssegcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
ssegcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
ssegcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
vecclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
vecclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
vecclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
vecclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
vecclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
vecgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
vecgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
vecgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
vecgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)