Implementation notes: amd64, speed2supercop, crypto_stream/simon128256ctr
Computer: speed2supercop
Microarchitecture: amd64; Haswell+AES (306c3)
Architecture: amd64
CPU ID: GenuineIntel-000306c3-1fc9cbf5
SUPERCOP version: 20240625
Operation: crypto_stream
Primitive: simon128256ctr
| Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
|---|
| 5400 | 128381 0 0 | 144333 792 808 | T:avx2 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 5424 | 127597 0 0 | 143341 792 808 | T:avx2 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 6188 | 146603 0 0 | 161301 752 864 | T:avx2 | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 8236 | 127911 0 0 | 140631 784 856 | T:avx2 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 8720 | 141090 0 0 | 153733 752 864 | T:avx2 | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 8884 | 138561 0 0 | 149728 728 832 | T:avx2 | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 9160 | 163578 0 0 | 175549 792 792 | T:avx2 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 9376 | 124420 0 0 | 140430 792 808 | T:sse4 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 9380 | 123812 0 0 | 139630 792 808 | T:sse4 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 9564 | 141852 0 0 | 156509 752 864 | T:sse4 | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 14256 | 142338 0 0 | 154596 744 864 | T:sse4 | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 14312 | 123177 0 0 | 136039 784 856 | T:sse4 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 14508 | 139088 0 0 | 150208 728 832 | T:sse4 | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 14784 | 140554 0 0 | 153165 752 864 | T:sse4 | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
| 15356 | 131579 0 0 | 143470 792 792 | T:sse4 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240703 | 20240625 |
Compiler output
stream.c: stream.c:128:3: error: always_inline function '_mm256_set_epi64x' requires target feature 'avx', but would be inlined into function 'Encrypt' that is compiled without support for 'avx'
stream.c: SET1(X[0],nonce[1]); SET4(Y[0],nonce[0]);
stream.c: ^
stream.c: ./Intrinsics_AVX2_128block.h:25:22: note: expanded from macro 'SET1'
stream.c: #define SET1(X,c) (X=SET(c,c,c,c))
stream.c: ^
stream.c: ./Intrinsics_AVX2_128block.h:24:13: note: expanded from macro 'SET'
stream.c: #define SET _mm256_set_epi64x
stream.c: ^
stream.c: stream.c:128:3: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
stream.c: ./Intrinsics_AVX2_128block.h:25:22: note: expanded from macro 'SET1'
stream.c: #define SET1(X,c) (X=SET(c,c,c,c))
stream.c: ^
stream.c: ./Intrinsics_AVX2_128block.h:24:13: note: expanded from macro 'SET'
stream.c: #define SET _mm256_set_epi64x
stream.c: ^
stream.c: stream.c:128:24: error: always_inline function '_mm256_set_epi64x' requires target feature 'avx', but would be inlined into function 'Encrypt' that is compiled without support for 'avx'
stream.c: SET1(X[0],nonce[1]); SET4(Y[0],nonce[0]);
stream.c: ^
stream.c: ./Intrinsics_AVX2_128block.h:26:22: note: expanded from macro 'SET4'
stream.c: #define SET4(X,c) (X=SET(c,c,c,c), X=ADD(X,_q))
stream.c: ^
stream.c: ./Intrinsics_AVX2_128block.h:24:13: note: expanded from macro 'SET'
stream.c: #define SET _mm256_set_epi64x
stream.c: ^
stream.c: ...
Number of similar (implementation,compiler) pairs: 1, namely:
| Implementation | Compiler |
| T:avx2 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
Compiler output
stream.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/13/include/immintrin.h:51,
stream.c: from Intrinsics_AVX2_128block.h:5,
stream.c: from Simon128256AVX2.h:17,
stream.c: from stream.c:20:
stream.c: In function '_mm256_unpackhi_epi64',
stream.c: inlined from 'Encrypt' at stream.c:163:22:
stream.c: /usr/lib/gcc/x86_64-linux-gnu/13/include/avx2intrin.h:880:19: warning: 'X[1]' may be used uninitialized [-Wmaybe-uninitialized]
stream.c: 880 | return (__m256i)__builtin_ia32_punpckhqdq256 ((__v4di)__A, (__v4di)__B);
stream.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stream.c: stream.c: In function 'Encrypt':
stream.c: stream.c:108:8: note: 'X[1]' was declared here
stream.c: 108 | u256 X[8],Y[8];
stream.c: | ^
stream.c: In function '_mm256_unpackhi_epi64',
stream.c: inlined from 'Encrypt' at stream.c:164:22:
stream.c: /usr/lib/gcc/x86_64-linux-gnu/13/include/avx2intrin.h:880:19: warning: 'X[2]' may be used uninitialized [-Wmaybe-uninitialized]
stream.c: 880 | return (__m256i)__builtin_ia32_punpckhqdq256 ((__v4di)__A, (__v4di)__B);
stream.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stream.c: stream.c: In function 'Encrypt':
stream.c: stream.c:108:8: note: 'X[2]' was declared here
stream.c: 108 | u256 X[8],Y[8];
stream.c: | ^
stream.c: In function '_mm256_unpackhi_epi64',
stream.c: inlined from 'Encrypt' at stream.c:165:22:
stream.c: /usr/lib/gcc/x86_64-linux-gnu/13/include/avx2intrin.h:880:19: warning: 'X[3]' may be used uninitialized [-Wmaybe-uninitialized]
stream.c: ...
Number of similar (implementation,compiler) pairs: 1, namely:
| Implementation | Compiler |
| T:avx2 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
Compiler output
try.c: /usr/bin/ld: libcrypto_stream_simon128256ctr.a(stream.o): in function `Encrypt':
try.c: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_stream/simon128256ctr/avx2/work/stream.c:145:(.text+0x...): undefined reference to `Transpose'
try.c: /usr/bin/ld: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_stream/simon128256ctr/avx2/work/stream.c:145:(.text+0x...): undefined reference to `Transpose'
try.c: /usr/bin/ld: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_stream/simon128256ctr/avx2/work/stream.c:154:(.text+0x...): undefined reference to `Transpose'
try.c: /usr/bin/ld: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_stream/simon128256ctr/avx2/work/stream.c:154:(.text+0x...): undefined reference to `Transpose'
try.c: /usr/bin/ld: libcrypto_stream_simon128256ctr.a(stream.o): in function `Encrypt_Xor':
try.c: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_stream/simon128256ctr/avx2/work/stream.c:294:(.text+0x...): undefined reference to `Transpose'
try.c: /usr/bin/ld: libcrypto_stream_simon128256ctr.a(stream.o):.../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_stream/simon128256ctr/avx2/work/stream.c:294: more undefined references to `Transpose' follow
try.c: collect2: error: ld returned 1 exit status
Number of similar (implementation,compiler) pairs: 1, namely:
| Implementation | Compiler |
| T:avx2 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
Compiler output
stream.c: stream.c:325:58: warning: argument 'T' of type '__m128i[8]' with mismatched bound [-Warray-parameter]
stream.c: inline __attribute__((always_inline)) int Transpose(u128 T[8])
stream.c: ^
stream.c: stream.c:29:58: note: previously declared as '__m128i[]' here
stream.c: inline __attribute__((always_inline)) int Transpose(u128 M[]);
stream.c: ^
stream.c: 1 warning generated.
Number of similar (implementation,compiler) pairs: 4, namely:
| Implementation | Compiler |
| T:sse4 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| T:sse4 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| T:sse4 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
| T:sse4 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
Compiler output
stream.c: stream.c:307:3: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'ExpandKeyBS' that is compiled without support for 'ssse3'
stream.c: EKBS(rk);
stream.c: ^
stream.c: ./Simon128256SSE4.h:67:19: note: expanded from macro 'EKBS'
stream.c: #define EKBS(rk) (RKBS(rk,4,_D), RKBS(rk,5,_D), RKBS(rk,6,_C), RKBS(rk,7,_D), RKBS(rk,8,_C), RKBS(rk,9,_C), RKBS(rk,10,_C), RKBS(rk,11,_D), \
stream.c: ^
stream.c: ./Simon128256SSE4.h:57:52: note: expanded from macro 'RKBS'
stream.c: #define RKBS(rk,r,_V) (rk[r][7]= _D ^ rk[r-4][7] ^ ROR8(rk[r-1][2]) ^ rk[r-3][7] ^ ROR8(rk[r-1][3]) ^ ROR8(rk[r-3][0]), \
stream.c: ^
stream.c: ./Intrinsics_SSE4_128block.h:39:19: note: expanded from macro 'ROR8'
stream.c: #define ROR8(X) (SHFL(X,R8))
stream.c: ^
stream.c: ./Intrinsics_SSE4_128block.h:35:14: note: expanded from macro 'SHFL'
stream.c: #define SHFL _mm_shuffle_epi8
stream.c: ^
stream.c: stream.c:307:3: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'ExpandKeyBS' that is compiled without support for 'ssse3'
stream.c: ./Simon128256SSE4.h:67:19: note: expanded from macro 'EKBS'
stream.c: #define EKBS(rk) (RKBS(rk,4,_D), RKBS(rk,5,_D), RKBS(rk,6,_C), RKBS(rk,7,_D), RKBS(rk,8,_C), RKBS(rk,9,_C), RKBS(rk,10,_C), RKBS(rk,11,_D), \
stream.c: ^
stream.c: ./Simon128256SSE4.h:57:85: note: expanded from macro 'RKBS'
stream.c: #define RKBS(rk,r,_V) (rk[r][7]= _D ^ rk[r-4][7] ^ ROR8(rk[r-1][2]) ^ rk[r-3][7] ^ ROR8(rk[r-1][3]) ^ ROR8(rk[r-3][0]), \
stream.c: ^
stream.c: ./Intrinsics_SSE4_128block.h:39:19: note: expanded from macro 'ROR8'
stream.c: #define ROR8(X) (SHFL(X,R8))
stream.c: ^
stream.c: ...
Number of similar (implementation,compiler) pairs: 1, namely:
| Implementation | Compiler |
| T:sse4 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1)) |
Compiler output
stream.c: stream.c:325:58: warning: argument 1 of type '__m128i[8]' with mismatched bound [-Warray-parameter=]
stream.c: 325 | inline __attribute__((always_inline)) int Transpose(u128 T[8])
stream.c: stream.c:29:58: note: previously declared as '__m128i[]'
stream.c: 29 | inline __attribute__((always_inline)) int Transpose(u128 M[]);
Number of similar (implementation,compiler) pairs: 4, namely:
| Implementation | Compiler |
| T:sse4 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| T:sse4 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| T:sse4 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |
| T:sse4 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0) |