Implementation notes: amd64, panther, crypto_hash/lsh256

Computer: panther
Microarchitecture: amd64; Tiger Lake (806c1)
Architecture: amd64
CPU ID: GenuineIntel-000806c1-00-bfebfbff
SUPERCOP version: 20240625
Operation: crypto_hash
Primitive: lsh256

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
3672	9665 0 0	15027 820 888	`ssse3`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
3674	11075 0 0	18645 828 920	`ssse3`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
3686	11133 0 0	18685 828 920	`ssse3`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
3688	9786 0 0	15267 820 888	`ssse3`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
4416	8605 0 0	17413 828 920	`avx2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
4420	8605 0 0	17429 828 920	`avx2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
4420	7559 0 0	13923 820 888	`avx2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
4425	7706 0 0	14211 820 888	`avx2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
5546	12660 0 0	16887 772 952	`ssse3`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
5548	13731 0 0	17904 780 952	`ssse3`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
5607	9298 0 0	15207 772 952	`avx2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
5613	13655 0 0	19952 780 952	`ssse3`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
5637	10047 0 0	18136 780 952	`avx2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
5640	10263 0 0	16152 780 952	`avx2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
5668	7755 0 0	13475 756 920	`avx2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
5673	11171 0 0	15179 756 920	`ssse3`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
5753	2341 336 0	1424425 144916 10296	`cryptopp`	`clang++_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
5753	2341 336 0	1424441 144916 10296	`cryptopp`	`clang++_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
5755	1879 336 0	1713758 144908 10328	`cryptopp`	`g++_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
5759	2598 336 0	1421726 144908 10264	`cryptopp`	`clang++_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
5762	2807 336 0	1715594 144908 10360	`cryptopp`	`g++_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
5766	2423 336 0	1714962 144908 10360	`cryptopp`	`g++_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
5768	2609 336 0	1717912 144900 10360	`cryptopp`	`g++_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
5817	4649 336 0	1426731 145020 10264	`cryptopp`	`clang++_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
6913	13402 0 0	17139 820 888	`sse2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
6922	13399 0 0	20085 828 920	`sse2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
6928	13399 0 0	20101 828 920	`sse2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
6976	13101 0 0	16803 820 888	`sse2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
9925	19379 0 0	20728 780 952	`sse2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
9934	19287 0 0	22768 780 952	`sse2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
9999	18002 0 0	19559 772 952	`sse2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
10086	16351 0 0	17771 756 920	`sse2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
10220	18967 0 0	22181 828 888	`sse2`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
12151	19223 0 0	22981 828 920	`ref`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
12153	19223 0 0	22965 828 920	`ref`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
12411	20255 0 0	20323 820 888	`ref`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
14623	28766 0 0	24935 772 952	`ref`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
14813	32141 0 0	27104 780 952	`ref`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
15173	23479 0 0	21339 756 920	`ref`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
15215	32785 0 0	29520 780 952	`ref`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
15855	24983 0 0	25365 828 888	`ref`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
33317	37098 0 0	29067 820 888	`ref`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625

Compiler output

lsh-impl.c: lsh-impl.c:367:10: error: always_inline function '_mm256_set_epi32' requires target feature 'avx', but would be inlined into function 'lsh256_init' that is compiled without support for 'avx'
lsh-impl.c:         *cv_l = _mm256_set_epi32(0, 0, 0, 0, 0, 0, LSH_GET_HASHBIT(algtype), LSH256_HASH_VAL_MAX_BYTE_LEN);
lsh-impl.c:                 ^
lsh-impl.c: lsh-impl.c:367:10: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
lsh-impl.c: lsh-impl.c:368:10: error: always_inline function '_mm256_setzero_si256' requires target feature 'avx', but would be inlined into function 'lsh256_init' that is compiled without support for 'avx'
lsh-impl.c:         *cv_r = _mm256_setzero_si256();
lsh-impl.c:                 ^
lsh-impl.c: lsh-impl.c:368:10: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
lsh-impl.c: lsh-impl.c:369:19: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'lsh256_init' that is compiled without support for 'avx'
lsh-impl.c:         byte_perm_step = LOAD(g_BytePermInfo);
lsh-impl.c:                          ^
lsh-impl.c: lsh-impl.c:145:17: note: expanded from macro 'LOAD'
lsh-impl.c: #define LOAD(x) _mm256_loadu_si256((__m256i*)x)
lsh-impl.c:                 ^
lsh-impl.c: lsh-impl.c:369:19: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
lsh-impl.c: lsh-impl.c:145:17: note: expanded from macro 'LOAD'
lsh-impl.c: #define LOAD(x) _mm256_loadu_si256((__m256i*)x)
lsh-impl.c:                 ^
lsh-impl.c: lsh-impl.c:375:3: warning: AVX vector argument of type 'const __m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
lsh-impl.c:                 mix_even(cv_l, cv_r, const_v, byte_perm_step);
lsh-impl.c:                 ^
lsh-impl.c: lsh-impl.c:379:3: warning: AVX vector argument of type 'const __m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
lsh-impl.c:                 mix_odd(cv_l, cv_r, const_v, byte_perm_step);
lsh-impl.c:                 ^
lsh-impl.c: 2 warnings and 6 errors generated.

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`avx2`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

Compiler output

lsh-impl.c: lsh-impl.c:126:39: warning: unused variable 'g_MsgWordPermInfo' [-Wunused-const-variable]
lsh-impl.c: static const LSH_ALIGNED_(32) lsh_u32 g_MsgWordPermInfo[8] = {
lsh-impl.c:                                       ^
lsh-impl.c: 1 warning generated.
lsh.c: lsh.c:126:39: warning: unused variable 'g_MsgWordPermInfo' [-Wunused-const-variable]
lsh.c: static const LSH_ALIGNED_(32) lsh_u32 g_MsgWordPermInfo[8] = {
lsh.c:                                       ^
lsh.c: 1 warning generated.

Number of similar (implementation,compiler) pairs: 4, namely:

Implementation	Compiler
`ssse3`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`ssse3`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`ssse3`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`ssse3`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

Compiler output

lsh-impl.c: lsh-impl.c:126:39: warning: unused variable 'g_MsgWordPermInfo' [-Wunused-const-variable]
lsh-impl.c: static const LSH_ALIGNED_(32) lsh_u32 g_MsgWordPermInfo[8] = {
lsh-impl.c:                                       ^
lsh-impl.c: lsh-impl.c:221:12: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'rotate_msg_gamma' that is compiled without support for 'ssse3'
lsh-impl.c:         cv_r[0] = SHUFFLE8(cv_r[0], perm_step[0]);
lsh-impl.c:                   ^
lsh-impl.c: lsh-impl.c:143:23: note: expanded from macro 'SHUFFLE8'
lsh-impl.c: #define SHUFFLE8(x,y) _mm_shuffle_epi8(x,y)
lsh-impl.c:                       ^
lsh-impl.c: lsh-impl.c:222:12: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'rotate_msg_gamma' that is compiled without support for 'ssse3'
lsh-impl.c:         cv_r[1] = SHUFFLE8(cv_r[1], perm_step[1]);
lsh-impl.c:                   ^
lsh-impl.c: lsh-impl.c:143:23: note: expanded from macro 'SHUFFLE8'
lsh-impl.c: #define SHUFFLE8(x,y) _mm_shuffle_epi8(x,y)
lsh-impl.c:                       ^
lsh-impl.c: 1 warning and 2 errors generated.

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`ssse3`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

Compiler output

lsh-impl.c: lsh-impl.c:126:39: warning: 'g_MsgWordPermInfo' defined but not used [-Wunused-const-variable=]
lsh-impl.c:   126 | static const LSH_ALIGNED_(32) lsh_u32 g_MsgWordPermInfo[8] = {
lsh-impl.c:       |                                       ^~~~~~~~~~~~~~~~~
lsh.c: lsh.c:126:39: warning: 'g_MsgWordPermInfo' defined but not used [-Wunused-const-variable=]
lsh.c:   126 | static const LSH_ALIGNED_(32) lsh_u32 g_MsgWordPermInfo[8] = {
lsh.c:       |                                       ^~~~~~~~~~~~~~~~~

Number of similar (implementation,compiler) pairs: 4, namely:

Implementation	Compiler
`ssse3`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`ssse3`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`ssse3`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`ssse3`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`

Compiler output

lsh-impl.c: lsh-impl.c:125:39: warning: unused variable 'g_MsgWordPermInfo' [-Wunused-const-variable]
lsh-impl.c: static const LSH_ALIGNED_(32) lsh_u32 g_MsgWordPermInfo[8] = {
lsh-impl.c:                                       ^
lsh-impl.c: lsh-impl.c:203:10: error: '__builtin_ia32_vprotdi' needs target feature xop
lsh-impl.c:         cv[0] = _mm_roti_epi32(cv[0], ROT_EVEN_ALPHA);
lsh-impl.c:                 ^
lsh-impl.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/xopintrin.h:234:12: note: expanded from macro '_mm_roti_epi32'
lsh-impl.c:   (__m128i)__builtin_ia32_vprotdi((__v4si)(__m128i)(A), (N))
lsh-impl.c:            ^
lsh-impl.c: lsh-impl.c:204:10: error: '__builtin_ia32_vprotdi' needs target feature xop
lsh-impl.c:         cv[1] = _mm_roti_epi32(cv[1], ROT_EVEN_ALPHA);
lsh-impl.c:                 ^
lsh-impl.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/xopintrin.h:234:12: note: expanded from macro '_mm_roti_epi32'
lsh-impl.c:   (__m128i)__builtin_ia32_vprotdi((__v4si)(__m128i)(A), (N))
lsh-impl.c:            ^
lsh-impl.c: lsh-impl.c:207:10: error: '__builtin_ia32_vprotdi' needs target feature xop
lsh-impl.c:         cv[0] = _mm_roti_epi32(cv[0], ROT_EVEN_BETA);
lsh-impl.c:                 ^
lsh-impl.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/xopintrin.h:234:12: note: expanded from macro '_mm_roti_epi32'
lsh-impl.c:   (__m128i)__builtin_ia32_vprotdi((__v4si)(__m128i)(A), (N))
lsh-impl.c:            ^
lsh-impl.c: lsh-impl.c:208:10: error: '__builtin_ia32_vprotdi' needs target feature xop
lsh-impl.c:         cv[1] = _mm_roti_epi32(cv[1], ROT_EVEN_BETA);
lsh-impl.c:                 ^
lsh-impl.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/xopintrin.h:234:12: note: expanded from macro '_mm_roti_epi32'
lsh-impl.c: ...

Number of similar (implementation,compiler) pairs: 5, namely:

Implementation	Compiler
`xop`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`xop`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`xop`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`xop`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`xop`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

Compiler output

lsh-impl.c: lsh-impl.c:125:39: warning: 'g_MsgWordPermInfo' defined but not used [-Wunused-const-variable=]
lsh-impl.c:   125 | static const LSH_ALIGNED_(32) lsh_u32 g_MsgWordPermInfo[8] = {
lsh-impl.c:       |                                       ^~~~~~~~~~~~~~~~~
lsh-impl.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/x86intrin.h:38,
lsh-impl.c:                  from lsh-impl.c:34:
lsh-impl.c: lsh-impl.c: In function 'rotate_blk_even_alpha':
lsh-impl.c: /usr/lib/gcc/x86_64-linux-gnu/10/include/xopintrin.h:266:1: error: inlining failed in call to 'always_inline' '_mm_roti_epi32': target specific option mismatch
lsh-impl.c:   266 | _mm_roti_epi32(__m128i __A, const int __B)
lsh-impl.c:       | ^~~~~~~~~~~~~~
lsh-impl.c: lsh-impl.c:204:10: note: called from here
lsh-impl.c:   204 |  cv[1] = _mm_roti_epi32(cv[1], ROT_EVEN_ALPHA);
lsh-impl.c:       |          ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
lsh-impl.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/x86intrin.h:38,
lsh-impl.c:                  from lsh-impl.c:34:
lsh-impl.c: /usr/lib/gcc/x86_64-linux-gnu/10/include/xopintrin.h:266:1: error: inlining failed in call to 'always_inline' '_mm_roti_epi32': target specific option mismatch
lsh-impl.c:   266 | _mm_roti_epi32(__m128i __A, const int __B)
lsh-impl.c:       | ^~~~~~~~~~~~~~
lsh-impl.c: lsh-impl.c:203:10: note: called from here
lsh-impl.c:   203 |  cv[0] = _mm_roti_epi32(cv[0], ROT_EVEN_ALPHA);
lsh-impl.c:       |          ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Number of similar (implementation,compiler) pairs: 4, namely:

Implementation	Compiler
`xop`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`xop`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`xop`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`xop`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x402010
   at 0x...: st32 (try-anything.c:47)
   by 0x...: core (try-anything.c:78)
   by 0x...: salsa20 (try-anything.c:101)
   by 0x...: testvector (try-anything.c:124)
   by 0x...: myrandom (try-anything.c:132)
   by 0x...: test (try.c:85)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 4, namely:

Implementation	Compiler
`avx2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`ref`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`sse2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`ssse3`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x402E25
   at 0x...: rotate_blk_even_alpha (lsh-impl.c:194)
   by 0x...: mix_even (lsh-impl.c:229)
   by 0x...: compress (lsh-impl.c:268)
   by 0x...: lsh256_update (lsh-impl.c:443)
   by 0x...: lsh256_digest (lsh-impl.c:514)
   by 0x...: test (try.c:90)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`avx2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x4024E5
   at 0x...: rotate_blk_even_alpha (lsh-impl.c:194)
   by 0x...: mix_even (lsh-impl.c:229)
   by 0x...: compress (lsh-impl.c:268)
   by 0x...: lsh256_update (lsh-impl.c:443)
   by 0x...: lsh256_digest (lsh-impl.c:514)
   by 0x...: crypto_hash_lsh256_avx2_constbranchindex (wrapper.c:10)
   by 0x...: test (try.c:90)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`avx2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x401A5E
   at 0x...: core (try-anything.c:73)
   by 0x...: salsa20 (try-anything.c:101)
   by 0x...: testvector (try-anything.c:124)
   by 0x...: myrandom (try-anything.c:132)
   by 0x...: test (try.c:85)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 4, namely:

Implementation	Compiler
`avx2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`ref`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`sse2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`ssse3`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x109C49
   at 0x...: salsa20.part.0 (try-anything.c:102)
   by 0x...: salsa20 (try-anything.c:85)
   by 0x...: canary (try-anything.c:148)
   by 0x...: input_prepare (try-anything.c:163)
   by 0x...: test (try.c:88)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 4, namely:

Implementation	Compiler
`avx2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`sse2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`ssse3`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x109B0A
   at 0x...: st32 (try-anything.c:47)
   by 0x...: core (try-anything.c:78)
   by 0x...: salsa20 (try-anything.c:101)
   by 0x...: salsa20 (try-anything.c:81)
   by 0x...: testvector (try-anything.c:124)
   by 0x...: myrandom (try-anything.c:132)
   by 0x...: test (try.c:85)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 4, namely:

Implementation	Compiler
`avx2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`sse2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`ssse3`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x10A47F
   at 0x...: _mm256_add_epi32 (avx2intrin.h:121)
   by 0x...: msg_exp_odd (lsh-impl.c:175)
   by 0x...: compress (lsh-impl.c:283)
   by 0x...: lsh256_update (lsh-impl.c:443)
   by 0x...: lsh256_digest (lsh-impl.c:514)
   by 0x...: crypto_hash_lsh256_avx2_constbranchindex (wrapper.c:10)
   by 0x...: test (try.c:90)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`avx2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x4224F0
   at 0x...: st32 (try-anything.cpp:47)
   by 0x...: core(unsigned char*, unsigned char const*, unsigned char const*) (try-anything.cpp:78)
   by 0x...: salsa20 (try-anything.cpp:101)
   by 0x...: testvector (try-anything.cpp:124)
   by 0x...: myrandom() (try-anything.cpp:132)
   by 0x...: test() (try.cpp:85)
   by 0x...: main (try-anything.cpp:345)

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`cryptopp`	`clang++ -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x4CE1E9
   at 0x...: SecureWipeBuffer<long unsigned int> (misc.h:1652)
   by 0x...: SecureWipeArray<long unsigned int> (misc.h:1703)
   by 0x...: deallocate (secblock.h:235)
   by 0x...: ~SecBlock (secblock.h:799)
   by 0x...: CryptoPP::PolynomialMod2::~PolynomialMod2() (gf2n.h:26)
   by 0x...: __run_exit_handlers (exit.c:108)
   by 0x...: exit (exit.c:139)
   by 0x...: (below main) (libc-start.c:342)

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`cryptopp`	`clang++ -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x4CDE39
   at 0x...: SecureWipeBuffer<long unsigned int> (misc.h:1652)
   by 0x...: SecureWipeArray<long unsigned int> (misc.h:1703)
   by 0x...: deallocate (secblock.h:235)
   by 0x...: ~SecBlock (secblock.h:799)
   by 0x...: CryptoPP::PolynomialMod2::~PolynomialMod2() (gf2n.h:26)
   by 0x...: __run_exit_handlers (exit.c:108)
   by 0x...: exit (exit.c:139)
   by 0x...: (below main) (libc-start.c:342)

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`cryptopp`	`clang++ -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x421F3E
   at 0x...: core(unsigned char*, unsigned char const*, unsigned char const*) (try-anything.cpp:73)
   by 0x...: salsa20 (try-anything.cpp:101)
   by 0x...: testvector (try-anything.cpp:124)
   by 0x...: myrandom() (try-anything.cpp:132)
   by 0x...: test() (try.cpp:85)
   by 0x...: main (try-anything.cpp:345)

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`cryptopp`	`clang++ -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x1721D9
   at 0x...: salsa20(unsigned char*, unsigned long, unsigned char const*, unsigned char const*) [clone .part.0] (try-anything.cpp:102)
   by 0x...: salsa20 (try-anything.cpp:85)
   by 0x...: canary (try-anything.cpp:148)
   by 0x...: input_prepare(unsigned char*, unsigned char*, unsigned long long) (try-anything.cpp:163)
   by 0x...: test() (try.cpp:88)
   by 0x...: main (try-anything.cpp:345)

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`cryptopp`	`g++ -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x1721AA
   at 0x...: st32 (try-anything.cpp:47)
   by 0x...: core(unsigned char*, unsigned char const*, unsigned char const*) (try-anything.cpp:78)
   by 0x...: salsa20 (try-anything.cpp:101)
   by 0x...: salsa20 (try-anything.cpp:81)
   by 0x...: testvector (try-anything.cpp:124)
   by 0x...: myrandom() (try-anything.cpp:132)
   by 0x...: test() (try.cpp:85)
   by 0x...: main (try-anything.cpp:345)

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`cryptopp`	`g++ -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x21D789
   at 0x...: SecureWipeBuffer<long unsigned int> (misc.h:1652)
   by 0x...: SecureWipeArray<long unsigned int> (misc.h:1703)
   by 0x...: deallocate (secblock.h:235)
   by 0x...: ~SecBlock (secblock.h:799)
   by 0x...: CryptoPP::PolynomialMod2::~PolynomialMod2() (gf2n.h:26)
   by 0x...: __run_exit_handlers (exit.c:108)
   by 0x...: exit (exit.c:139)
   by 0x...: (below main) (libc-start.c:342)

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`cryptopp`	`g++ -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x1726A4
   at 0x...: SecureWipeBuffer<unsigned int> (misc.h:1636)
   by 0x...: SecureWipeArray<unsigned int> (misc.h:1705)
   by 0x...: deallocate (secblock.h:654)
   by 0x...: ~SecBlock (secblock.h:799)
   by 0x...: ~FixedSizeSecBlock (secblock.h:1245)
   by 0x...: CryptoPP::LSH256_Base::~LSH256_Base() (lsh.h:41)
   by 0x...: crypto_hash_lsh256_cryptopp_constbranchindex (hash.cpp:6)
   by 0x...: test() (try.cpp:90)
   by 0x...: main (try-anything.cpp:345)

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`cryptopp`	`g++ -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x4037CF
   at 0x...: load_msg_blk (lsh-impl.c:142)
   by 0x...: compress (lsh-impl.c:315)
   by 0x...: lsh256_update (lsh-impl.c:526)
   by 0x...: lsh256_digest (lsh-impl.c:586)
   by 0x...: test (try.c:90)
   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 (Debian_Clang_11.0.1)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x4032D5
   at 0x...: lsh256_update (lsh-impl.c:0)
   by 0x...: lsh256_digest (lsh-impl.c:534)
   by 0x...: test (try.c:90)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`sse2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x402980
   at 0x...: lsh256_update (lsh-impl.c:0)
   by 0x...: lsh256_digest (lsh-impl.c:534)
   by 0x...: crypto_hash_lsh256_sse2_constbranchindex (wrapper.c:10)
   by 0x...: test (try.c:90)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`sse2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x10A53D
   at 0x...: _mm_xor_si128 (emmintrin.h:1305)
   by 0x...: xor_with_const (lsh-impl.c:204)
   by 0x...: mix_odd (lsh-impl.c:263)
   by 0x...: compress (lsh-impl.c:289)
   by 0x...: lsh256_update (lsh-impl.c:463)
   by 0x...: lsh256_digest (lsh-impl.c:534)
   by 0x...: crypto_hash_lsh256_sse2_constbranchindex (wrapper.c:10)
   by 0x...: test (try.c:90)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`sse2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x10A972
   at 0x...: _mm_and_si128 (emmintrin.h:1287)
   by 0x...: rotate_msg_gamma (lsh-impl.c:212)
   by 0x...: mix_even (lsh-impl.c:257)
   by 0x...: compress (lsh-impl.c:284)
   by 0x...: lsh256_update (lsh-impl.c:463)
   by 0x...: lsh256_digest (lsh-impl.c:534)
   by 0x...: test (try.c:90)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`sse2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x403000
   at 0x...: load_blk (lsh-impl.c:154)
   by 0x...: load_msg_blk (lsh-impl.c:164)
   by 0x...: compress (lsh-impl.c:266)
   by 0x...: lsh256_update (lsh-impl.c:453)
   by 0x...: lsh256_digest (lsh-impl.c:523)
   by 0x...: test (try.c:90)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`ssse3`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x4026B0
   at 0x...: load_blk (lsh-impl.c:154)
   by 0x...: load_msg_blk (lsh-impl.c:164)
   by 0x...: compress (lsh-impl.c:266)
   by 0x...: lsh256_update (lsh-impl.c:453)
   by 0x...: lsh256_digest (lsh-impl.c:523)
   by 0x...: crypto_hash_lsh256_ssse3_constbranchindex (wrapper.c:10)
   by 0x...: test (try.c:90)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`ssse3`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x10A393
   at 0x...: _mm_loadu_si128 (emmintrin.h:703)
   by 0x...: load_blk (lsh-impl.c:155)
   by 0x...: lsh256_update (lsh-impl.c:438)
   by 0x...: lsh256_digest (lsh-impl.c:523)
   by 0x...: crypto_hash_lsh256_ssse3_constbranchindex (wrapper.c:10)
   by 0x...: test (try.c:90)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`ssse3`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`

TIMECOP error (can be valgrind bug)

Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x10A103
   at 0x...: _mm_loadu_si128 (emmintrin.h:703)
   by 0x...: load_blk (lsh-impl.c:154)
   by 0x...: lsh256_update (lsh-impl.c:439)
   by 0x...: lsh256_digest (lsh-impl.c:523)
   by 0x...: test (try.c:90)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`ssse3`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`

Passed TIMECOP

TIMECOP iterations: 10

Number of similar (implementation,compiler) pairs: 6, namely:

Implementation	Compiler
`avx2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`ref`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`ref`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`sse2`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`