Test results for amd64, comet, crypto_aead/aezv3
[Page version: 20241024 06:31:28]
Measurements for amd64, comet, crypto_aead
Test results for amd64, comet, crypto_aead
Test results for crypto_aead/aezv3
Computer: comet
Microarchitecture: amd64; Comet Lake (806ec)
Architecture: amd64
CPU ID: GenuineIntel-000806ec-bfebfbff
SUPERCOP version: 20241022
Operation: crypto_aead
Primitive: aezv3
| Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
|---|
| 3106 | 16535 0 0 | 39236 780 1088 | T:aesni | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall | 20240629 | 20240625 |
| 3115 | 9803 0 0 | 30596 780 1088 | T:aesni | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall | 20240629 | 20240625 |
| 3127 | 10844 0 0 | 34321 852 1056 | T:aesni | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20240629 | 20240625 |
| 3130 | 9539 0 0 | 30191 844 1088 | T:aesni | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20240629 | 20240625 |
| 3138 | 10436 0 0 | 29993 852 1024 | T:aesni | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20240629 | 20240625 |
| 3147 | 10876 0 0 | 34649 852 1088 | T:aesni | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20240629 | 20240625 |
| 3236 | 8428 0 0 | 26975 756 1056 | T:aesni | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall | 20240629 | 20240625 |
| 3270 | 10222 0 0 | 30379 772 1088 | T:aesni | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall | 20240629 | 20240625 |
| 787402 | 36127 0 0 | 60361 868 1088 | T:ref | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20240629 | 20240625 |
| 788604 | 33605 0 0 | 57537 868 1056 | T:ref | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20240629 | 20240625 |
| 812254 | 38063 0 0 | 60649 868 1024 | T:ref | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20240629 | 20240625 |
| 953957 | 22118 0 0 | 43063 860 1088 | T:ref | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20240629 | 20240625 |
| 986026 | 26290 0 0 | 47268 796 1088 | T:ref | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall | 20240629 | 20240625 |
| 1027846 | 55140 0 0 | 78124 796 1088 | T:ref | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall | 20240629 | 20240625 |
| 1065894 | 23348 0 0 | 43385 868 1024 | T:ref | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall | 20240629 | 20240625 |
| 1148393 | 24700 0 0 | 45084 796 1088 | T:ref | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall | 20240629 | 20240625 |
| 1402082 | 22063 0 0 | 40735 772 1056 | T:ref | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall | 20240629 | 20240625 |
Compiler output
aez_ni.c: aez_ni.c:146:22: error: '__builtin_ia32_vec_set_v16qi' needs target feature sse4.1
aez_ni.c: __m128i i1 = _mm_insert_epi8(zero, 1, 7);
aez_ni.c: ^
aez_ni.c: /usr/lib/llvm-14/lib/clang/14.0.6/include/smmintrin.h:930:13: note: expanded from macro '_mm_insert_epi8'
aez_ni.c: ((__m128i)__builtin_ia32_vec_set_v16qi((__v16qi)(__m128i)(X), \
aez_ni.c: ^
aez_ni.c: aez_ni.c:147:22: error: '__builtin_ia32_vec_set_v16qi' needs target feature sse4.1
aez_ni.c: __m128i i2 = _mm_insert_epi8(zero, 2, 7);
aez_ni.c: ^
aez_ni.c: /usr/lib/llvm-14/lib/clang/14.0.6/include/smmintrin.h:930:13: note: expanded from macro '_mm_insert_epi8'
aez_ni.c: ((__m128i)__builtin_ia32_vec_set_v16qi((__v16qi)(__m128i)(X), \
aez_ni.c: ^
aez_ni.c: aez_ni.c:148:22: error: '__builtin_ia32_vec_set_v16qi' needs target feature sse4.1
aez_ni.c: __m128i i3 = _mm_insert_epi8(zero, 3, 7);
aez_ni.c: ^
aez_ni.c: /usr/lib/llvm-14/lib/clang/14.0.6/include/smmintrin.h:930:13: note: expanded from macro '_mm_insert_epi8'
aez_ni.c: ((__m128i)__builtin_ia32_vec_set_v16qi((__v16qi)(__m128i)(X), \
aez_ni.c: ^
aez_ni.c: aez_ni.c:149:26: error: '__builtin_ia32_vec_set_v16qi' needs target feature sse4.1
aez_ni.c: __m128i j, one = _mm_insert_epi8(zero, 1, 15);
aez_ni.c: ^
aez_ni.c: /usr/lib/llvm-14/lib/clang/14.0.6/include/smmintrin.h:930:13: note: expanded from macro '_mm_insert_epi8'
aez_ni.c: ((__m128i)__builtin_ia32_vec_set_v16qi((__v16qi)(__m128i)(X), \
aez_ni.c: ^
aez_ni.c: 4 errors generated.
Number of similar (implementation,compiler) pairs: 1, namely:
| Implementation | Compiler |
| T:aesni | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6) |
Compiler output
aez_ni.c: In function 'load_partial',
aez_ni.c: inlined from 'load_partial' at aez_ni.c:119:16,
aez_ni.c: inlined from 'cipher_aez_tiny' at aez_ni.c:498:18,
aez_ni.c: inlined from 'aez_encrypt' at aez_ni.c:588:9,
aez_ni.c: inlined from 'crypto_aead_aezv3_aesni_timingleaks_encrypt' at aez_ni.c:637:5:
aez_ni.c: aez_ni.c:123:46: warning: '__builtin_memcpy' forming offset [16, 4294967263] is out of the bounds [0, 16] of object 'tmp' with type '__m128i' [-Warray-bounds]
aez_ni.c: 123 | for (i=0; i<n; i++) ((char*)&tmp)[i] = ((char*)p)[i];
aez_ni.c: | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~
aez_ni.c: aez_ni.c: In function 'crypto_aead_aezv3_aesni_timingleaks_encrypt':
aez_ni.c: aez_ni.c:122:17: note: 'tmp' declared here
aez_ni.c: 122 | __m128i tmp; unsigned i;
aez_ni.c: | ^~~
Number of similar (implementation,compiler) pairs: 1, namely:
| Implementation | Compiler |
| T:aesni | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0) |