Implementation notes: amd64, saber214, crypto_decode/1013x2393
Computer: saber214
Microarchitecture: amd64; Bulldozer (600f20)
Architecture: amd64
CPU ID: AuthenticAMD-00600f20-1789c3f5
SUPERCOP version: 20240808
Operation: crypto_decode
Primitive: 1013x2393
Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
23067 | 2828 0 0 | 13652 816 728 | int16 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
23163 | 3260 0 0 | 16476 816 744 | int16 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
23394 | 2390 0 0 | 11558 808 728 | int16 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
24921 | 2585 0 0 | 12164 816 728 | int16 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
25168 | 2675 0 0 | 12941 768 800 | int16 | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
25633 | 3277 0 0 | 15212 816 728 | int16 | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
27870 | 3603 0 0 | 15566 776 800 | int16 | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
27958 | 2574 0 0 | 13062 776 800 | int16 | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
28565 | 2515 0 0 | 11833 752 768 | int16 | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
35987 | 4103 0 0 | 17308 816 744 | portable | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
36117 | 3442 0 0 | 14260 816 728 | portable | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
36780 | 3014 0 0 | 12182 808 728 | portable | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
37629 | 3173 0 0 | 12748 816 728 | portable | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
39258 | 3345 0 0 | 13838 776 800 | portable | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
39295 | 4626 0 0 | 16582 776 800 | portable | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
40945 | 4337 0 0 | 16268 816 728 | portable | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
77645 | 2358 0 0 | 14292 816 728 | ref | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
78722 | 1887 0 0 | 13798 776 800 | ref | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
78904 | 2325 0 0 | 15556 816 744 | ref | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
78999 | 2325 0 0 | 13164 816 728 | ref | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
82681 | 1618 0 0 | 12062 776 800 | ref | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
83750 | 1970 0 0 | 12245 768 800 | portable | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
84466 | 1162 0 0 | 10310 808 728 | ref | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
85698 | 1897 0 0 | 11225 752 768 | portable | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
87307 | 1169 0 0 | 10740 816 728 | ref | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
100251 | 1673 0 0 | 11853 768 800 | ref | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
107243 | 1530 0 0 | 10729 752 768 | ref | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240808 | 20240808 |
Compiler output
decode.c: decode.c:270:10: error: always_inline function '_mm256_srli_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_1013x2393_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: S1 = _mm256_srli_epi16(S0,8);
decode.c: ^
decode.c: decode.c:285:10: error: always_inline function '_mm256_unpacklo_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_1013x2393_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: B0 = _mm256_unpacklo_epi16(A0,A1);
decode.c: ^
decode.c: decode.c:286:10: error: always_inline function '_mm256_unpackhi_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_1013x2393_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: B1 = _mm256_unpackhi_epi16(A0,A1);
decode.c: ^
decode.c: decode.c:289:10: error: '__builtin_ia32_permti256' needs target feature avx2
decode.c: C0 = _mm256_permute2x128_si256(B0,B1,0x20);
decode.c: ^
decode.c: /usr/lib/llvm-14/lib/clang/14.0.0/include/avx2intrin.h:821:13: note: expanded from macro '_mm256_permute2x128_si256'
decode.c: ((__m256i)__builtin_ia32_permti256((__m256i)(V1), (__m256i)(V2), (int)(M)))
decode.c: ^
decode.c: decode.c:290:10: error: '__builtin_ia32_permti256' needs target feature avx2
decode.c: C1 = _mm256_permute2x128_si256(B0,B1,0x31);
decode.c: ^
decode.c: /usr/lib/llvm-14/lib/clang/14.0.0/include/avx2intrin.h:821:13: note: expanded from macro '_mm256_permute2x128_si256'
decode.c: ((__m256i)__builtin_ia32_permti256((__m256i)(V1), (__m256i)(V2), (int)(M)))
decode.c: ^
decode.c: decode.c:306:10: error: always_inline function '_mm256_cvtepu8_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_1013x2393_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: S0 = _mm256_cvtepu8_epi16(_mm_loadu_si128((__m128i *) (s+i)));
decode.c: ^
decode.c: decode.c:318:10: error: always_inline function '_mm256_unpacklo_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_1013x2393_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: ...
Number of similar (implementation,compiler) pairs: 4, 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) |
Compiler output
decode.c: decode.c:268:15: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'crypto_decode_1013x2393_avx_constbranchindex' that is compiled without support for 'avx'
decode.c: A2 = A0 = _mm256_loadu_si256((__m256i *) &R5[i]);
decode.c: ^
decode.c: decode.c:268:15: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decode.c: decode.c:269:10: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'crypto_decode_1013x2393_avx_constbranchindex' that is compiled without support for 'avx'
decode.c: S0 = _mm256_loadu_si256((__m256i *) (s+2*i));
decode.c: ^
decode.c: decode.c:269:10: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decode.c: decode.c:270:10: error: always_inline function '_mm256_srli_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_1013x2393_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: S1 = _mm256_srli_epi16(S0,8);
decode.c: ^
decode.c: decode.c:270:10: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decode.c: decode.c:271:11: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_decode_1013x2393_avx_constbranchindex' that is compiled without support for 'avx'
decode.c: S0 &= _mm256_set1_epi16(255);
decode.c: ^
decode.c: decode.c:271:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decode.c: decode.c:272:14: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
decode.c: A0 = sub(mulhiconst(A0,412),mulhiconst(mulloconst(A0,-5118),3278)); /* -1639...1742 */
decode.c: ^
decode.c: decode.c:272:44: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
decode.c: A0 = sub(mulhiconst(A0,412),mulhiconst(mulloconst(A0,-5118),3278)); /* -1639...1742 */
decode.c: ^
decode.c: decode.c:272:33: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
decode.c: A0 = sub(mulhiconst(A0,412),mulhiconst(mulloconst(A0,-5118),3278)); /* -1639...1742 */
decode.c: ^
decode.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
decode.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
decode.c: from decode.c:3:
decode.c: decode.c: In function 'add':
decode.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:112:1: error: inlining failed in call to 'always_inline' '_mm256_add_epi16': target specific option mismatch
decode.c: 112 | _mm256_add_epi16 (__m256i __A, __m256i __B)
decode.c: | ^~~~~~~~~~~~~~~~
decode.c: decode.c:22:10: note: called from here
decode.c: 22 | return _mm256_add_epi16(x,y);
decode.c: | ^~~~~~~~~~~~~~~~~~~~~
Number of similar (implementation,compiler) pairs: 4, namely:
Implementation | Compiler |
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) |
TIMECOP error (can be valgrind bug)
error 111
Process terminating with default action of signal 4 (SIGILL)
Illegal opcode at address 0x109C3D
at 0x...: salsa20.part.0 (try-anything.c:102)
by 0x...: salsa20 (try-anything.c:85)
by 0x...: testvector (try-anything.c:124)
by 0x...: input_prepare (try-anything.c:162)
by 0x...: test (try.c:95)
by 0x...: main (try-anything.c:345)
Number of similar (implementation,compiler) pairs: 3, namely:
Implementation | Compiler |
int16 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
portable | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
ref | gcc -march=native -mtune=native -O2 -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 0x10988A
at 0x...: core (try-anything.c:53)
by 0x...: salsa20.part.0 (try-anything.c:89)
by 0x...: salsa20 (try-anything.c:85)
by 0x...: testvector (try-anything.c:124)
by 0x...: input_prepare (try-anything.c:162)
by 0x...: test (try.c:95)
by 0x...: main (try-anything.c:345)
Number of similar (implementation,compiler) pairs: 3, namely:
Implementation | Compiler |
int16 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
portable | gcc -march=native -mtune=native -O3 -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) |
TIMECOP error (can be valgrind bug)
error 111
Process terminating with default action of signal 4 (SIGILL)
Illegal opcode at address 0x10A770
at 0x...: crypto_decode_1013x2393_ref_constbranchindex (wrapper.c:17)
by 0x...: test (try.c:99)
by 0x...: main (try-anything.c:345)
Number of similar (implementation,compiler) pairs: 1, namely:
Implementation | Compiler |
ref | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
TIMECOP error (can be valgrind bug)
error 111
Process terminating with default action of signal 4 (SIGILL)
Illegal opcode at address 0x10A810
at 0x...: crypto_decode_1013x2393_ref_constbranchindex (wrapper.c:17)
by 0x...: test (try.c:99)
by 0x...: main (try-anything.c:345)
Number of similar (implementation,compiler) pairs: 1, namely:
Implementation | Compiler |
ref | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
TIMECOP error (can be valgrind bug)
error 111
Process terminating with default action of signal 4 (SIGILL)
Illegal opcode at address 0x109E14
at 0x...: crypto_decode_1013x2393_ref_constbranchindex (wrapper.c:10)
by 0x...: test (try.c:99)
by 0x...: main (try-anything.c:345)
Number of similar (implementation,compiler) pairs: 1, namely:
Implementation | Compiler |
ref | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
TIMECOP error (can be valgrind bug)
error 111
Process terminating with default action of signal 4 (SIGILL)
Illegal opcode at address 0x10A277
at 0x...: crypto_decode_1013x2393_ref_constbranchindex_Decode (Decode.c:32)
by 0x...: crypto_decode_1013x2393_ref_constbranchindex (wrapper.c:16)
by 0x...: test (try.c:99)
by 0x...: main (try-anything.c:345)
Number of similar (implementation,compiler) pairs: 1, namely:
Implementation | Compiler |
ref | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
Passed TIMECOP
TIMECOP iterations: 10
Number of similar (implementation,compiler) pairs: 17, namely:
Implementation | Compiler |
int16 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
int16 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
int16 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
int16 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
int16 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
int16 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
int16 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
portable | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
portable | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
portable | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
portable | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
portable | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
portable | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
portable | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
ref | clang -march=native -O -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 -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |