Test results for amd64, h8atom, crypto_decode/761x4591

[Page version: 20240912 08:39:10]

Measurements for amd64, h8atom, crypto_decode Test results for amd64, h8atom, crypto_decode Test results for crypto_decode/761x4591
Computer: h8atom
Microarchitecture: amd64; Bonnell (30661)
Architecture: amd64
CPU ID: GenuineIntel-00030661-bfebfbff
SUPERCOP version: 20240909
Operation: crypto_decode
Primitive: 761x4591
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
418952427 0 012196 816 728int16clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
436102809 0 014772 816 728int16clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
438832846 0 014804 816 728int16clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
447652147 0 011158 808 728int16clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
448352934 0 014926 776 800int16gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
448842327 0 012974 776 800int16gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
452972398 0 013180 816 728int16clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
453322318 0 011617 752 768int16gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
487692394 0 012709 768 800int16gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
843083013 0 013654 776 800portablegcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
852254022 0 016006 776 800portablegcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
872063156 0 012948 816 728portableclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
886203918 0 015876 816 728portableclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
886693272 0 014052 816 728portableclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
891173956 0 015916 816 728portableclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
896982946 0 011974 808 728portableclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
1812301854 0 011201 752 768portablegcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
1846041894 0 012221 768 800portablegcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
1897561251 0 012036 816 728refclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
1900431686 0 013622 776 800refgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
1904631923 0 013884 816 728refclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
1927102112 0 014076 816 728refclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
2002141633 0 012214 776 800refgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
2030841178 0 010964 816 728refclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
2071301605 0 010622 808 728refclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
2203951524 0 010737 752 768refgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall2024080820240808
2251761648 0 011877 768 800refgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall2024080820240808

Compiler output


decode.c: decode.c:254:15: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'crypto_decode_761x4591_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:254:15: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decode.c: decode.c:255:10: error: always_inline function '_mm256_cvtepu8_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_761x4591_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:255:10: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decode.c: decode.c:256:14: 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,-134),mulhiconst(mulloconst(A0,-10350),1621)); /* -844...810 */
decode.c:              ^
decode.c: decode.c:256:45: 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,-134),mulhiconst(mulloconst(A0,-10350),1621)); /* -844...810 */
decode.c:                                             ^
decode.c: decode.c:256:34: 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,-134),mulhiconst(mulloconst(A0,-10350),1621)); /* -844...810 */
decode.c:                                  ^
decode.c: decode.c:256:10: 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,-134),mulhiconst(mulloconst(A0,-10350),1621)); /* -844...810 */
decode.c:          ^
decode.c: decode.c:257:10: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
decode.c:     A0 = add(A0,S0); /* -844...1065 */
decode.c:          ^
decode.c: decode.c:258:10: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
decode.c:     A0 = ifnegaddconst(A0,1621); /* 0...1620 */
decode.c: ...

Number of similar (implementation,compiler) pairs: 5, 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)
avxclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)

Compiler output


decode.c: decode.c: In function 'add':
decode.c: decode.c:21:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
decode.c:    21 | {
decode.c:       | ^
decode.c: decode.c: In function 'signedshiftrightconst':
decode.c: decode.c:35:23: note: the ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
decode.c:    35 | static inline __m256i signedshiftrightconst(__m256i x,int16 y)
decode.c:       |                       ^~~~~~~~~~~~~~~~~~~~~
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:
ImplementationCompiler
avxgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
avxgcc -march=native -mtune=native -O3 -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)

Passed TIMECOP


TIMECOP iterations: 10

Number of similar (implementation,compiler) pairs: 27, namely:
ImplementationCompiler
int16clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
int16clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
int16clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
int16clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
int16clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
int16gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
int16gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
int16gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
int16gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
portableclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
portableclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
portableclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
portableclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
portableclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
portablegcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
portablegcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
portablegcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
portablegcc -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)