Implementation notes: amd64, comet, crypto_kem/mceliece8192128pcf

Computer: comet
Microarchitecture: amd64; Comet Lake (806ec)
Architecture: amd64
CPU ID: GenuineIntel-000806ec-bfebfbff
SUPERCOP version: 20240625
Operation: crypto_kem
Primitive: mceliece8192128pcf
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
422137148050 0 0201788 788 1760avxgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
431101166644 0 0221673 876 1792avxclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
432288150028 0 0204681 876 1728avxclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
451884100961 0 0152892 788 1760avxgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
45912399284 0 0150911 860 1792avxclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
467933102271 0 0153665 868 1728avxclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
46836298677 0 0150124 788 1760avxgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
48252193581 0 0143588 780 1728avxgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
715726188489 0 0239332 788 1760ssegcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
716627130445 0 0180929 860 1728sseclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
717421145516 0 0196289 860 1792sseclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
76021897164 0 0146084 788 1760ssegcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
78478687372 0 0135551 852 1792sseclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
79067691532 0 0138761 860 1728sseclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
80301788204 0 0136548 788 1760ssegcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
81765683508 0 0130492 780 1728ssegcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
157179099503 0 0153556 788 1760vecgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
2109108117283 0 0171265 860 1728vecclang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
2149469100530 0 0155545 860 1728vecclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
2199930127713 0 0182081 860 1792vecclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
251775061595 0 0113535 860 1792vecclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
275195460977 0 0112881 868 1728vecclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
284354164434 0 0116668 788 1760vecgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
373767151962 0 0102556 780 1728vecgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
411102361910 0 0113924 788 1760vecgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
33321598446845 0 098111 868 1728refclang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
35580276817295 0 066845 860 1792refclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
36436075162902 0 0115513 860 1792refclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
36444562639642 0 091993 860 1728refclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
43319019433636 0 085190 796 1760refgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
45499680615696 0 064721 860 1728refclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
48292546517288 0 066982 796 1760refgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
49125408715155 0 064220 788 1760refgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625
55191257911861 0 059574 788 1728refgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071120240625

Compiler output


bm.c: bm.c:80:37: 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:82:15: 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:83:15: 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:84:15: 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:85:15: 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:86:15: 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:87:15: 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:88:15: 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:89:15: 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 (Debian_Clang_14.0.6)

Compiler output


encrypt.c: encrypt.c:38:16: warning: unused variable 'mask' [-Wunused-variable]
encrypt.c:         unsigned char mask;
encrypt.c:                       ^
encrypt.c: 1 warning generated.

Number of similar (implementation,compiler) pairs: 5, namely:
ImplementationCompiler
refclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
refclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
refclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
refclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
refclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)

Compiler output


encrypt.c: encrypt.c: In function 'gen_e':
encrypt.c: encrypt.c:38:23: warning: unused variable 'mask' [-Wunused-variable]
encrypt.c:    38 |         unsigned char mask;
encrypt.c:       |                       ^~~~

Number of similar (implementation,compiler) pairs: 4, namely:
ImplementationCompiler
refgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)
refgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)
refgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)
refgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)

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:38:9: 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 (Debian_Clang_14.0.6)

TIMECOP error (can be valgrind bug)


error 1
VEX temporary storage exhausted.
Pool = TEMP,  start 0x597c5528 curr 0x59c787f8 end 0x59c8a067 (size 5000000)
vex: the `impossible' happened:
VEX temporary storage exhausted.
Increase N_{TEMPORARY,PERMANENT}_BYTES and recompile.
vex storage: T total 302317240 bytes allocated
vex storage: P total 512 bytes allocated
valgrind: the 'impossible' happened:
LibVEX called failure_exit().
host stacktrace:
   at 0x...: show_sched_status_wrk (m_libcassert.c:406)
   by 0x...: report_and_quit (m_libcassert.c:477)
   by 0x...: panic (m_libcassert.c:553)
   by 0x...: vgPlain_core_panic_at (m_libcassert.c:558)
   by 0x...: vgPlain_core_panic (m_libcassert.c:563)
   by 0x...: failure_exit (m_translate.c:761)
   by 0x...: vpanic (main_util.c:253)
   by 0x...: private_LibVEX_alloc_OOM (main_util.c:181)
   by 0x...: LibVEX_Alloc_inline (main_util.h:176)
   by 0x...: addHInstr_SLOW (host_generic_regs.c:332)
   by 0x...: emit_instr (host_generic_reg_alloc3.c:301)
   by 0x...: doRegisterAllocation_v3 (host_generic_reg_alloc3.c:1320)
   by 0x...: libvex_BackEnd (main_main.c:1133)
   by 0x...: LibVEX_Translate (main_main.c:1236)
   by 0x...: vgPlain_translate (m_translate.c:1831)
   by 0x...: handle_chain_me (scheduler.c:1169)
   by 0x...: vgPlain_scheduler (scheduler.c:1514)
   by 0x...: thread_wrapper (syswrap-linux.c:101)
   by 0x...: run_a_thread_NORETURN (syswrap-linux.c:154)
sched status:
running_tid=1
Thread 1: status = VgTs_Runnable (lwpid 3087291)
   at 0x...: extract_gf (sk_gen.c:43)
   by 0x...: crypto_kem_mceliece8192128pcf_avx_constbranchindex_genpoly_gen (sk_gen.c:153)
   by 0x...: crypto_kem_mceliece8192128pcf_avx_constbranchindex_operation_keypair (kem_keypair.c:59)
   by 0x...: crypto_kem_mceliece8192128pcf_avx_constbranchindex_keypair (wrap_keypair.c:10)
   by 0x...: test (try.c:126)
   by 0x...: main (try-anything.c:345)
client stack range: [0x1FFEFDD000 0x1FFF000FFF] client SP: 0x1FFEFDE4C0
valgrind stack range: [0x1008BAE000 0x1008CADFFF] top usage: 18792 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 (12.2.0)

TIMECOP error (can be valgrind bug)


error 1
VEX temporary storage exhausted.
Pool = TEMP,  start 0x597c5528 curr 0x59c787f8 end 0x59c8a067 (size 5000000)
vex: the `impossible' happened:
VEX temporary storage exhausted.
Increase N_{TEMPORARY,PERMANENT}_BYTES and recompile.
vex storage: T total 305343688 bytes allocated
vex storage: P total 512 bytes allocated
valgrind: the 'impossible' happened:
LibVEX called failure_exit().
host stacktrace:
   at 0x...: show_sched_status_wrk (m_libcassert.c:406)
   by 0x...: report_and_quit (m_libcassert.c:477)
   by 0x...: panic (m_libcassert.c:553)
   by 0x...: vgPlain_core_panic_at (m_libcassert.c:558)
   by 0x...: vgPlain_core_panic (m_libcassert.c:563)
   by 0x...: failure_exit (m_translate.c:761)
   by 0x...: vpanic (main_util.c:253)
   by 0x...: private_LibVEX_alloc_OOM (main_util.c:181)
   by 0x...: LibVEX_Alloc_inline (main_util.h:176)
   by 0x...: addHInstr_SLOW (host_generic_regs.c:332)
   by 0x...: emit_instr (host_generic_reg_alloc3.c:301)
   by 0x...: doRegisterAllocation_v3 (host_generic_reg_alloc3.c:1320)
   by 0x...: libvex_BackEnd (main_main.c:1133)
   by 0x...: LibVEX_Translate (main_main.c:1236)
   by 0x...: vgPlain_translate (m_translate.c:1831)
   by 0x...: handle_chain_me (scheduler.c:1169)
   by 0x...: vgPlain_scheduler (scheduler.c:1514)
   by 0x...: thread_wrapper (syswrap-linux.c:101)
   by 0x...: run_a_thread_NORETURN (syswrap-linux.c:154)
sched status:
running_tid=1
Thread 1: status = VgTs_Runnable (lwpid 3100069)
   at 0x...: extract_gf (sk_gen.c:43)
   by 0x...: crypto_kem_mceliece8192128pcf_sse_constbranchindex_genpoly_gen (sk_gen.c:153)
   by 0x...: crypto_kem_mceliece8192128pcf_sse_constbranchindex_operation_keypair (kem_keypair.c:59)
   by 0x...: crypto_kem_mceliece8192128pcf_sse_constbranchindex_keypair (wrap_keypair.c:10)
   by 0x...: test (try.c:126)
   by 0x...: main (try-anything.c:345)
client stack range: [0x1FFEFDD000 0x1FFF000FFF] client SP: 0x1FFEFDE4C0
valgrind stack range: [0x1008BAE000 0x1008CADFFF] top usage: 18792 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 (12.2.0)

Passed TIMECOP


TIMECOP iterations: 1

Number of similar (implementation,compiler) pairs: 32, namely:
ImplementationCompiler
avxclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
avxclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
avxclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
avxclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
avxgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)
avxgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)
avxgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)
refclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
refclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
refclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
refclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
refclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
refgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)
refgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)
refgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)
refgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)
sseclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
sseclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
sseclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
sseclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
ssegcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)
ssegcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)
ssegcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)
vecclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
vecclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
vecclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
vecclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
vecclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)
vecgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)
vecgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)
vecgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)
vecgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)