Implementation notes: amd64, speed2supercop, crypto_aead/grain128aeadv2
Computer: speed2supercop
Microarchitecture: amd64; Haswell+AES (306c3)
Architecture: amd64
CPU ID: GenuineIntel-000306c3-1fc9cbf5
SUPERCOP version: 20240625
Operation: crypto_aead
Primitive: grain128aeadv2
| Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
|---|
| 159056 | 10458 0 0 | 23747 824 856 | T:sse | clang++_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 159396 | 10576 0 0 | 24716 816 920 | T:sse | clang++_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 160156 | 18362 0 0 | 35611 824 872 | T:sse | clang++_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 160452 | 18362 0 0 | 35787 824 872 | T:sse | clang++_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 170060 | 12041 0 0 | 25436 744 944 | T:sse | g++_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 170788 | 4083 0 0 | 16288 728 912 | T:sse | g++_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 171184 | 13412 0 0 | 27093 752 944 | T:sse | g++_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 171244 | 17331 0 0 | 32981 752 944 | T:sse | g++_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 318116 | 9997 0 0 | 27475 824 872 | T:x64 | clang++_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 322488 | 5247 0 0 | 19404 816 920 | T:x64 | clang++_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 323592 | 6478 0 0 | 19852 744 944 | T:x64 | g++_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 324956 | 11406 0 0 | 28683 824 872 | T:x64 | clang++_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 352344 | 6941 0 0 | 20613 752 944 | T:x64 | g++_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 378016 | 2434 0 0 | 14616 728 912 | T:x64 | g++_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 609224 | 5523 0 0 | 18867 824 856 | T:x64 | clang++_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
Checksum failure
d0dd6234d89dbd95039a8c1c4e9e8f6fa0d58228afa4fda263447f76c3102a36
Number of similar (implementation,compiler) pairs: 1, namely:
| Implementation | Compiler |
| T:x64 | g++ -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
Compiler output
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp:236:6: error: '__builtin_ia32_pternlogq128_mask' needs target feature avx512vl
grain128aead-v2_opt.cpp: T = _xorand3(_mm_srli_epi16(X, 1), X, _mm_set1_epi16(0x2222));
grain128aead-v2_opt.cpp: ^
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp:125:27: note: expanded from macro '_xorand3'
grain128aead-v2_opt.cpp: #define _xorand3(a, b, c) _mm_ternarylogic_epi64(a, b, c, 0x28)
grain128aead-v2_opt.cpp: ^
grain128aead-v2_opt.cpp: /usr/lib/llvm-16/lib/clang/16/include/avx512vlintrin.h:6559:13: note: expanded from macro '_mm_ternarylogic_epi64'
grain128aead-v2_opt.cpp: ((__m128i)__builtin_ia32_pternlogq128_mask( \
grain128aead-v2_opt.cpp: ^
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp:237:6: error: '__builtin_ia32_pternlogq128_mask' needs target feature avx512vl
grain128aead-v2_opt.cpp: X = _xor3(_mm_slli_epi16(T, 1), X, T);
grain128aead-v2_opt.cpp: ^
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp:122:25: note: expanded from macro '_xor3'
grain128aead-v2_opt.cpp: #define _xor3(a, b, c) _mm_ternarylogic_epi64(a, b, c, 0x96)
grain128aead-v2_opt.cpp: ^
grain128aead-v2_opt.cpp: /usr/lib/llvm-16/lib/clang/16/include/avx512vlintrin.h:6559:13: note: expanded from macro '_mm_ternarylogic_epi64'
grain128aead-v2_opt.cpp: ((__m128i)__builtin_ia32_pternlogq128_mask( \
grain128aead-v2_opt.cpp: ^
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp:238:6: error: '__builtin_ia32_pternlogq128_mask' needs target feature avx512vl
grain128aead-v2_opt.cpp: T = _xorand3(_mm_srli_epi16(X, 2), X, _mm_set1_epi16(0x0c0c));
grain128aead-v2_opt.cpp: ^
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp:125:27: note: expanded from macro '_xorand3'
grain128aead-v2_opt.cpp: #define _xorand3(a, b, c) _mm_ternarylogic_epi64(a, b, c, 0x28)
grain128aead-v2_opt.cpp: ^
grain128aead-v2_opt.cpp: /usr/lib/llvm-16/lib/clang/16/include/avx512vlintrin.h:6559:13: note: expanded from macro '_mm_ternarylogic_epi64'
grain128aead-v2_opt.cpp: ...
Number of similar (implementation,compiler) pairs: 4, namely:
| Implementation | Compiler |
| T:avx512 | clang++ -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| T:avx512 | clang++ -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| T:avx512 | clang++ -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| T:avx512 | clang++ -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall |
Compiler output
grain128aead-v2_opt.cpp: In file included from /usr/lib/gcc/x86_64-linux-gnu/13/include/immintrin.h:61,
grain128aead-v2_opt.cpp: from /usr/lib/gcc/x86_64-linux-gnu/13/include/x86intrin.h:32,
grain128aead-v2_opt.cpp: from grain128aead-v2_opt.h:41,
grain128aead-v2_opt.cpp: from grain128aead-v2_opt.cpp:10:
grain128aead-v2_opt.cpp: /usr/lib/gcc/x86_64-linux-gnu/13/include/avx512vlintrin.h: In function 'u64 grain_keystream64(grain_ctx*)':
grain128aead-v2_opt.cpp: /usr/lib/gcc/x86_64-linux-gnu/13/include/avx512vlintrin.h:10657:1: error: inlining failed in call to 'always_inline' '__m128i _mm_ternarylogic_epi64(__m128i, __m128i, __m128i, int)': target specific option mismatch
grain128aead-v2_opt.cpp: 10657 | _mm_ternarylogic_epi64 (__m128i __A, __m128i __B, __m128i __C,
grain128aead-v2_opt.cpp: | ^~~~~~~~~~~~~~~~~~~~~~
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp:207:39: note: called from here
grain128aead-v2_opt.cpp: 207 | u64 y = ys ^ _mm_cvtsi128_si64(_xor2(shr8(_xor3(_andxor3(s4, s7, s5), _and3(ts, b7, s6), b1), 7), shr8(_andxor3(shr8(b7, 2), s2, b1), 5)));
grain128aead-v2_opt.cpp: | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
grain128aead-v2_opt.cpp: /usr/lib/gcc/x86_64-linux-gnu/13/include/avx512vlintrin.h:10657:1: error: inlining failed in call to 'always_inline' '__m128i _mm_ternarylogic_epi64(__m128i, __m128i, __m128i, int)': target specific option mismatch
grain128aead-v2_opt.cpp: 10657 | _mm_ternarylogic_epi64 (__m128i __A, __m128i __B, __m128i __C,
grain128aead-v2_opt.cpp: | ^~~~~~~~~~~~~~~~~~~~~~
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp:207:39: note: called from here
grain128aead-v2_opt.cpp: 207 | u64 y = ys ^ _mm_cvtsi128_si64(_xor2(shr8(_xor3(_andxor3(s4, s7, s5), _and3(ts, b7, s6), b1), 7), shr8(_andxor3(shr8(b7, 2), s2, b1), 5)));
grain128aead-v2_opt.cpp: | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
grain128aead-v2_opt.cpp: /usr/lib/gcc/x86_64-linux-gnu/13/include/avx512vlintrin.h:10657:1: error: inlining failed in call to 'always_inline' '__m128i _mm_ternarylogic_epi64(__m128i, __m128i, __m128i, int)': target specific option mismatch
grain128aead-v2_opt.cpp: 10657 | _mm_ternarylogic_epi64 (__m128i __A, __m128i __B, __m128i __C,
grain128aead-v2_opt.cpp: | ^~~~~~~~~~~~~~~~~~~~~~
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp:207:39: note: called from here
grain128aead-v2_opt.cpp: 207 | u64 y = ys ^ _mm_cvtsi128_si64(_xor2(shr8(_xor3(_andxor3(s4, s7, s5), _and3(ts, b7, s6), b1), 7), shr8(_andxor3(shr8(b7, 2), s2, b1), 5)));
grain128aead-v2_opt.cpp: | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
grain128aead-v2_opt.cpp: /usr/lib/gcc/x86_64-linux-gnu/13/include/avx512vlintrin.h:10657:1: error: inlining failed in call to 'always_inline' '__m128i _mm_ternarylogic_epi64(__m128i, __m128i, __m128i, int)': target specific option mismatch
grain128aead-v2_opt.cpp: 10657 | _mm_ternarylogic_epi64 (__m128i __A, __m128i __B, __m128i __C,
grain128aead-v2_opt.cpp: ...
Number of similar (implementation,compiler) pairs: 8, namely:
| Implementation | Compiler |
| T:avx512 | g++ -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| T:avx512 | g++ -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| T:avx512 | g++ -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| T:avx512 | g++ -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall |
| T:gf2 | g++ -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| T:gf2 | g++ -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| T:gf2 | g++ -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| T:gf2 | g++ -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall |
Compiler output
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp:234:6: error: '__builtin_ia32_vgf2p8affineqb_v16qi' needs target feature gfni
grain128aead-v2_opt.cpp: X = _mm_gf2p8affine_epi64_epi8(X, _mm_set1_epi64x(0x0104104002082080ULL), 0);
grain128aead-v2_opt.cpp: ^
grain128aead-v2_opt.cpp: /usr/lib/llvm-16/lib/clang/16/include/gfniintrin.h:38:13: note: expanded from macro '_mm_gf2p8affine_epi64_epi8'
grain128aead-v2_opt.cpp: ((__m128i)__builtin_ia32_vgf2p8affineqb_v16qi((__v16qi)(__m128i)(A), \
grain128aead-v2_opt.cpp: ^
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp:241:6: error: '__builtin_ia32_pternlogq128_mask' needs target feature avx512vl
grain128aead-v2_opt.cpp: T = _xorand3(_mm_srli_epi16(X, 4), X, _mm_set1_epi16(0x00f0));
grain128aead-v2_opt.cpp: ^
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp:125:27: note: expanded from macro '_xorand3'
grain128aead-v2_opt.cpp: #define _xorand3(a, b, c) _mm_ternarylogic_epi64(a, b, c, 0x28)
grain128aead-v2_opt.cpp: ^
grain128aead-v2_opt.cpp: /usr/lib/llvm-16/lib/clang/16/include/avx512vlintrin.h:6559:13: note: expanded from macro '_mm_ternarylogic_epi64'
grain128aead-v2_opt.cpp: ((__m128i)__builtin_ia32_pternlogq128_mask( \
grain128aead-v2_opt.cpp: ^
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp:242:6: error: '__builtin_ia32_pternlogq128_mask' needs target feature avx512vl
grain128aead-v2_opt.cpp: X = _xor3(_mm_slli_epi16(T, 4), X, T);
grain128aead-v2_opt.cpp: ^
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp:122:25: note: expanded from macro '_xor3'
grain128aead-v2_opt.cpp: #define _xor3(a, b, c) _mm_ternarylogic_epi64(a, b, c, 0x96)
grain128aead-v2_opt.cpp: ^
grain128aead-v2_opt.cpp: /usr/lib/llvm-16/lib/clang/16/include/avx512vlintrin.h:6559:13: note: expanded from macro '_mm_ternarylogic_epi64'
grain128aead-v2_opt.cpp: ((__m128i)__builtin_ia32_pternlogq128_mask( \
grain128aead-v2_opt.cpp: ^
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp:155:30: error: '__builtin_ia32_pternlogq128_mask' needs target feature avx512vl
grain128aead-v2_opt.cpp: ...
Number of similar (implementation,compiler) pairs: 4, namely:
| Implementation | Compiler |
| T:gf2 | clang++ -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| T:gf2 | clang++ -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| T:gf2 | clang++ -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| T:gf2 | clang++ -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall |
Compiler output
grain128aead-v2.c: grain128aead-v2.c:150:31: warning: argument 'sr' of type 'unsigned char[64]' with mismatched bound [-Warray-parameter]
grain128aead-v2.c: void auth_shift(unsigned char sr[64], unsigned char fb)
grain128aead-v2.c: ^
grain128aead-v2.c: ./grain128aead-v2.h:26:31: note: previously declared as 'unsigned char[32]' here
grain128aead-v2.c: void auth_shift(unsigned char sr[32], unsigned char fb);
grain128aead-v2.c: ^
grain128aead-v2.c: grain128aead-v2.c:426:21: warning: variable 'ac_cnt' set but not used [-Wunused-but-set-variable]
grain128aead-v2.c: unsigned long long ac_cnt = 0;
grain128aead-v2.c: ^
grain128aead-v2.c: 2 warnings generated.
Number of similar (implementation,compiler) pairs: 5, namely:
| Implementation | Compiler |
| T:ref | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| T:ref | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| T:ref | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| T:ref | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| T:ref | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
Compiler output
grain128aead-v2.c: grain128aead-v2.c:150:31: warning: argument 1 of type 'unsigned char[64]' with mismatched bound [-Warray-parameter=]
grain128aead-v2.c: 150 | void auth_shift(unsigned char sr[64], unsigned char fb)
grain128aead-v2.c: | ~~~~~~~~~~~~~~^~~~~~
grain128aead-v2.c: In file included from grain128aead-v2.c:20:
grain128aead-v2.c: grain128aead-v2.h:26:31: note: previously declared as 'unsigned char[32]'
grain128aead-v2.c: 26 | void auth_shift(unsigned char sr[32], unsigned char fb);
grain128aead-v2.c: | ~~~~~~~~~~~~~~^~~~~~
grain128aead-v2.c: grain128aead-v2.c: In function 'auth_shift':
grain128aead-v2.c: grain128aead-v2.c:155:11: warning: array subscript 63 is outside array bounds of 'unsigned char[32]' [-Warray-bounds=]
grain128aead-v2.c: 155 | sr[63] = fb;
grain128aead-v2.c: | ~~^~~~
grain128aead-v2.c: grain128aead-v2.c:150:31: note: at offset 63 into object 'sr' of size [0, 32]
grain128aead-v2.c: 150 | void auth_shift(unsigned char sr[64], unsigned char fb)
grain128aead-v2.c: | ~~~~~~~~~~~~~~^~~~~~
grain128aead-v2.c: grain128aead-v2.c:153:23: warning: '__builtin_memmove' forming offset [32, 62] is out of the bounds [0, 32] [-Warray-bounds=]
grain128aead-v2.c: 153 | sr[i] = sr[i+1];
grain128aead-v2.c: | ~~~~~~^~~~~~~~~
Number of similar (implementation,compiler) pairs: 3, namely:
| Implementation | Compiler |
| T:ref | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| T:ref | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| T:ref | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
Compiler output
grain128aead-v2.c: grain128aead-v2.c:150:31: warning: argument 1 of type 'unsigned char[64]' with mismatched bound [-Warray-parameter=]
grain128aead-v2.c: 150 | void auth_shift(unsigned char sr[64], unsigned char fb)
grain128aead-v2.c: | ~~~~~~~~~~~~~~^~~~~~
grain128aead-v2.c: In file included from grain128aead-v2.c:20:
grain128aead-v2.c: grain128aead-v2.h:26:31: note: previously declared as 'unsigned char[32]'
grain128aead-v2.c: 26 | void auth_shift(unsigned char sr[32], unsigned char fb);
grain128aead-v2.c: | ~~~~~~~~~~~~~~^~~~~~
Number of similar (implementation,compiler) pairs: 1, namely:
| Implementation | Compiler |
| T:ref | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
Compiler output
grain128aead-v2_opt.cpp: In function 'void grain_auth(grain_ctx*, u8*, int)',
grain128aead-v2_opt.cpp: inlined from 'void grain_auth(grain_ctx*, u8*, int)' at grain128aead-v2_opt.cpp:248:20,
grain128aead-v2_opt.cpp: inlined from 'int grain_aead_encdec(unsigned char*, long long unsigned int*, const unsigned char*, long long unsigned int, const unsigned char*, long long unsigned int, const unsigned char*, const unsigned char*) [with int to_decrypt = 0]' at grain128aead-v2_opt.cpp:413:12,
grain128aead-v2_opt.cpp: inlined from 'int crypto_aead_grain128aeadv2_sse_timingleaks_encrypt(unsigned char*, long long unsigned int*, const unsigned char*, long long unsigned int, const unsigned char*, long long unsigned int, const unsigned char*, const unsigned char*, const unsigned char*)' at grain128aead-v2_opt.cpp:504:29:
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp:294:16: warning: 'grain.grain_ctx::A' is used uninitialized [-Wuninitialized]
grain128aead-v2_opt.cpp: 294 | grain->A ^= ((*(u64*)(tmp + bytes)) << 1) ^ ((u64)tmp[bytes - 1] >> 7) ^ (((u64)_mm_cvtsi128_si64(reg)) << (65 - bits));
grain128aead-v2_opt.cpp: | ~~~~~~~^
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp: In function 'int crypto_aead_grain128aeadv2_sse_timingleaks_encrypt(unsigned char*, long long unsigned int*, const unsigned char*, long long unsigned int, const unsigned char*, long long unsigned int, const unsigned char*, const unsigned char*, const unsigned char*)':
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp:383:19: note: 'grain' declared here
grain128aead-v2_opt.cpp: 383 | grain_ctx grain;
grain128aead-v2_opt.cpp: | ^~~~~
grain128aead-v2_opt.cpp: In function 'void grain_auth(grain_ctx*, u8*, int)',
grain128aead-v2_opt.cpp: inlined from 'void grain_auth(grain_ctx*, u8*, int)' at grain128aead-v2_opt.cpp:248:20,
grain128aead-v2_opt.cpp: inlined from 'int grain_aead_encdec(unsigned char*, long long unsigned int*, const unsigned char*, long long unsigned int, const unsigned char*, long long unsigned int, const unsigned char*, const unsigned char*) [with int to_decrypt = 1]' at grain128aead-v2_opt.cpp:413:12,
grain128aead-v2_opt.cpp: inlined from 'int crypto_aead_grain128aeadv2_sse_timingleaks_decrypt(unsigned char*, long long unsigned int*, unsigned char*, const unsigned char*, long long unsigned int, const unsigned char*, long long unsigned int, const unsigned char*, const unsigned char*)' at grain128aead-v2_opt.cpp:518:29:
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp:294:16: warning: 'grain.grain_ctx::A' may be used uninitialized [-Wmaybe-uninitialized]
grain128aead-v2_opt.cpp: 294 | grain->A ^= ((*(u64*)(tmp + bytes)) << 1) ^ ((u64)tmp[bytes - 1] >> 7) ^ (((u64)_mm_cvtsi128_si64(reg)) << (65 - bits));
grain128aead-v2_opt.cpp: | ~~~~~~~^
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp: In function 'int crypto_aead_grain128aeadv2_sse_timingleaks_decrypt(unsigned char*, long long unsigned int*, unsigned char*, const unsigned char*, long long unsigned int, const unsigned char*, long long unsigned int, const unsigned char*, const unsigned char*)':
grain128aead-v2_opt.cpp: grain128aead-v2_opt.cpp:383:19: note: 'grain' declared here
grain128aead-v2_opt.cpp: 383 | grain_ctx grain;
grain128aead-v2_opt.cpp: | ^~~~~
Number of similar (implementation,compiler) pairs: 2, namely:
| Implementation | Compiler |
| T:sse | g++ -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| T:sse | g++ -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |