Implementation notes: amd64, cubi10, crypto_kem/mceliece460896pcf

Computer: cubi10
Microarchitecture: amd64; Comet Lake (806ec)
Architecture: amd64
CPU ID: GenuineIntel-000806ec-bfebfbff
SUPERCOP version: 20240625
Operation: crypto_kem
Primitive: mceliece460896pcf
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
315098133784 0 0186072 788 1752avxgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
316424153463 0 0206376 836 1720avxclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
316651133856 0 0186392 836 1720avxclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
34296487458 0 0138392 788 1752avxgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
34654784869 0 0134374 828 1720avxclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
35088185571 0 0136024 788 1752avxgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
36389380793 0 0129888 780 1720avxgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
499660138579 0 0186960 788 1752ssegcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
502576120097 0 0168576 820 1720sseclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
502969131337 0 0179888 820 1720sseclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
53972383498 0 0130448 788 1752ssegcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
54632775695 0 0121726 812 1720sseclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
54817377974 0 0124448 788 1752ssegcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
57544996314 0 0147742 836 1720avxclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
58747473701 0 0118880 780 1720ssegcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
86971589396 0 0139134 812 1720sseclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
143416687379 0 0140032 788 1752vecgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
187184796085 0 0149400 828 1720vecclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
188013798540 0 0151464 828 1720vecclang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
191506286310 0 0139544 820 1720vecclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
233113749702 0 0101248 788 1752vecgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
234527745023 0 095150 820 1720vecclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
240841243907 0 095254 820 1720vecclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
278391338537 0 088320 780 1720vecgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
294226647564 0 098664 788 1752vecgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
14228404436142 0 086232 820 1720refclang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
14273013040599 0 091288 820 1720refclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
14312669236110 0 086688 820 1720refclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
15066551934007 0 084610 796 1752refgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
15214419117154 0 064374 812 1720refclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
19680895815815 0 064006 812 1720refclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
20593667217208 0 066018 796 1752refgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
20893710715385 0 063560 788 1752refgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625
23496986712233 0 059138 788 1720refgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024070620240625

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 (Debian_Clang_11.0.1)

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 (Debian_Clang_11.0.1)

TIMECOP error (can be valgrind bug)

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:1296)
   by 0x...: libvex_BackEnd (main_main.c:1133)
   by 0x...: LibVEX_Translate (main_main.c:1236)
   by 0x...: vgPlain_translate (m_translate.c:1828)
   by 0x...: handle_chain_me (scheduler.c:1166)
   by 0x...: vgPlain_scheduler (scheduler.c:1511)
   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 348267)
   at 0x...: extract_gf (sk_gen.c:43)
   by 0x...: crypto_kem_mceliece460896pcf_avx_constbranchindex_genpoly_gen (sk_gen.c:153)
   by 0x...: crypto_kem_mceliece460896pcf_avx_constbranchindex_operation_keypair (kem_keypair.c:59)
   by 0x...: crypto_kem_mceliece460896pcf_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: 0x1FFEFE0200
valgrind stack range: [0x1008DAA000 0x1008EA9FFF] top usage: 18472 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 (10.2.1_20210110)

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x419A2E
   at 0x...: vec128_set2x (vec128.h:56)
   by 0x...: postprocess (fft_tr.c:283)
   by 0x...: crypto_kem_mceliece460896pcf_sse_constbranchindex_fft_tr (fft_tr.c:292)
   by 0x...: crypto_kem_mceliece460896pcf_sse_constbranchindex_decrypt (decrypt.c:175)
   by 0x...: crypto_kem_mceliece460896pcf_sse_constbranchindex_operation_dec (kem_dec.c:39)
   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 (Debian_Clang_11.0.1)

TIMECOP error (can be valgrind bug)

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:1296)
   by 0x...: libvex_BackEnd (main_main.c:1133)
   by 0x...: LibVEX_Translate (main_main.c:1236)
   by 0x...: vgPlain_translate (m_translate.c:1828)
   by 0x...: handle_chain_me (scheduler.c:1166)
   by 0x...: vgPlain_scheduler (scheduler.c:1511)
   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 358320)
   at 0x...: extract_gf (sk_gen.c:43)
   by 0x...: crypto_kem_mceliece460896pcf_sse_constbranchindex_genpoly_gen (sk_gen.c:153)
   by 0x...: crypto_kem_mceliece460896pcf_sse_constbranchindex_operation_keypair (kem_keypair.c:59)
   by 0x...: crypto_kem_mceliece460896pcf_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: 0x1FFEFE0200
valgrind stack range: [0x1008DAA000 0x1008EA9FFF] top usage: 18472 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 (10.2.1_20210110)

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 (Debian_Clang_11.0.1)
avxclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
avxclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
avxclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
avxgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
avxgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
avxgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
refclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
refclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
refclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
refclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
refclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
refgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
refgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
refgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
refgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
sseclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
sseclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
sseclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
ssegcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
ssegcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
ssegcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
vecclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
vecclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
vecclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
vecclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
vecclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
vecgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
vecgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
vecgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
vecgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)