Implementation notes: amd64, renoir, crypto_sign/aimer128s
Computer: renoir
Microarchitecture: amd64; Zen 2 (860f01)
Architecture: amd64
CPU ID: AuthenticAMD-00860f01-178bfbff
SUPERCOP version: 20240808
Operation: crypto_sign
Primitive: aimer128s
Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
20705043 | 132165 0 0 | 145270 812 1720 | avx2 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
20906842 | 130537 0 0 | 143886 812 1720 | avx2 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
20916947 | 141353 0 0 | 154688 820 1752 | avx2 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
20953383 | 141049 0 0 | 152168 820 1752 | avx2 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
21331477 | 130877 0 0 | 145072 788 1784 | avx2 | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
21457384 | 132119 0 0 | 146320 788 1784 | avx2 | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
21540139 | 152527 0 0 | 152760 788 1784 | avx2 | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
22438258 | 128462 0 0 | 142072 780 1752 | avx2 | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
57834190 | 44843 0 0 | 58904 836 1752 | ref | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
57958427 | 43291 0 0 | 55168 836 1752 | ref | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
58406326 | 33533 0 0 | 47574 828 1720 | ref | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
60114679 | 36978 0 0 | 51368 804 1784 | ref | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
60508432 | 70936 0 0 | 71312 804 1784 | ref | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
61928916 | 35262 0 0 | 49664 804 1784 | ref | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
64203286 | 32722 0 0 | 46576 796 1752 | ref | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
65423519 | 45850 0 0 | 59784 836 1720 | ref | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
76278276 | 44003 0 0 | 55888 836 1752 | mem_opt | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
77164355 | 45555 0 0 | 59624 836 1752 | mem_opt | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
77324178 | 34453 0 0 | 48534 828 1720 | mem_opt | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
77514149 | 38418 0 0 | 52832 804 1784 | mem_opt | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
79013301 | 72456 0 0 | 72840 804 1784 | mem_opt | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
80544546 | 36574 0 0 | 50992 804 1784 | mem_opt | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
83545878 | 33666 0 0 | 47552 796 1752 | mem_opt | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
87171302 | 46618 0 0 | 60560 836 1720 | mem_opt | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
104956673 | 35726 0 0 | 49686 828 1720 | ref | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
124481325 | 36582 0 0 | 50534 828 1720 | mem_opt | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
Compiler output
fips202.c: In file included from fips202.c:11:
fips202.c: ./KeccakP-1600-SnP.h:41:82: warning: multi-line // comment [-Wcomment]
fips202.c: //#define KeccakP1600_StaticInitialize \
fips202.c: ^
fips202.c: ./KeccakP-1600-SnP.h:56:82: warning: multi-line // comment [-Wcomment]
fips202.c: //#define KeccakP1600_OverwriteBytes \
fips202.c: ^
fips202.c: ./KeccakP-1600-SnP.h:63:82: warning: multi-line // comment [-Wcomment]
fips202.c: //#define KeccakP1600_OverwriteWithZeroes \
fips202.c: ^
fips202.c: ./KeccakP-1600-SnP.h:68:82: warning: multi-line // comment [-Wcomment]
fips202.c: //#define KeccakP1600_Permute_Nrounds \
fips202.c: ^
fips202.c: ./KeccakP-1600-SnP.h:72:82: warning: multi-line // comment [-Wcomment]
fips202.c: //#define KeccakP1600_Permute_12rounds \
fips202.c: ^
fips202.c: ./KeccakP-1600-SnP.h:76:82: warning: multi-line // comment [-Wcomment]
fips202.c: //#define KeccakP1600_Permute_24rounds \
fips202.c: ^
fips202.c: ./KeccakP-1600-SnP.h:85:82: warning: multi-line // comment [-Wcomment]
fips202.c: //#define KeccakP1600_ExtractAndAddBytes \
fips202.c: ^
fips202.c: ./KeccakP-1600-SnP.h:93:82: warning: multi-line // comment [-Wcomment]
fips202.c: //#define KeccakF1600_FastLoop_Absorb \
fips202.c: ^
fips202.c: ...
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) |
avx2 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
avx2 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
avx2 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
Compiler output
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'KeccakP1600times4_AddLanesAll' that is compiled without support for 'avx'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:138:38: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: #define Xor_In4( argIndex ) lanes0 = LOAD256u( curData0[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:49:33: note: expanded from macro 'LOAD256u'
KeccakP-1600-times4-SIMD256.c: #define LOAD256u(a) _mm256_loadu_si256((const V256 *)&(a))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:138:38: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: #define Xor_In4( argIndex ) lanes0 = LOAD256u( curData0[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:49:33: note: expanded from macro 'LOAD256u'
KeccakP-1600-times4-SIMD256.c: #define LOAD256u(a) _mm256_loadu_si256((const V256 *)&(a))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'KeccakP1600times4_AddLanesAll' that is compiled without support for 'avx'
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:139:47: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: lanes1 = LOAD256u( curData1[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:49:33: note: expanded from macro 'LOAD256u'
KeccakP-1600-times4-SIMD256.c: #define LOAD256u(a) _mm256_loadu_si256((const V256 *)&(a))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:139:47: note: expanded from macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: ...
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
fips202.c: In file included from fips202.c:11:
fips202.c: KeccakP-1600-SnP.h:41:1: warning: multi-line comment [-Wcomment]
fips202.c: 41 | //#define KeccakP1600_StaticInitialize \
fips202.c: | ^
fips202.c: KeccakP-1600-SnP.h:56:1: warning: multi-line comment [-Wcomment]
fips202.c: 56 | //#define KeccakP1600_OverwriteBytes \
fips202.c: | ^
fips202.c: KeccakP-1600-SnP.h:63:1: warning: multi-line comment [-Wcomment]
fips202.c: 63 | //#define KeccakP1600_OverwriteWithZeroes \
fips202.c: | ^
fips202.c: KeccakP-1600-SnP.h:68:1: warning: multi-line comment [-Wcomment]
fips202.c: 68 | //#define KeccakP1600_Permute_Nrounds \
fips202.c: | ^
fips202.c: KeccakP-1600-SnP.h:72:1: warning: multi-line comment [-Wcomment]
fips202.c: 72 | //#define KeccakP1600_Permute_12rounds \
fips202.c: | ^
fips202.c: KeccakP-1600-SnP.h:76:1: warning: multi-line comment [-Wcomment]
fips202.c: 76 | //#define KeccakP1600_Permute_24rounds \
fips202.c: | ^
fips202.c: KeccakP-1600-SnP.h:85:1: warning: multi-line comment [-Wcomment]
fips202.c: 85 | //#define KeccakP1600_ExtractAndAddBytes \
fips202.c: | ^
fips202.c: KeccakP-1600-SnP.h:93:1: warning: multi-line comment [-Wcomment]
fips202.c: 93 | //#define KeccakF1600_FastLoop_Absorb \
fips202.c: | ^
fips202.c: ...
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) |
avx2 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
avx2 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
avx2 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
Namespace violations
KeccakP-1600-AVX2.o ALLON a
KeccakP-1600-AVX2.o KeccakF1600_FastLoop_Absorb T
KeccakP-1600-AVX2.o KeccakP1600_12rounds_FastLoop_Absorb T
KeccakP-1600-AVX2.o KeccakP1600_AddByte T
KeccakP-1600-AVX2.o KeccakP1600_AddBytes T
KeccakP-1600-AVX2.o KeccakP1600_ExtractAndAddBytes T
KeccakP-1600-AVX2.o KeccakP1600_ExtractBytes T
KeccakP-1600-AVX2.o KeccakP1600_Initialize T
KeccakP-1600-AVX2.o KeccakP1600_OverwriteBytes T
KeccakP-1600-AVX2.o KeccakP1600_OverwriteWithZeroes T
KeccakP-1600-AVX2.o KeccakP1600_Permute_12rounds T
KeccakP-1600-AVX2.o KeccakP1600_Permute_24rounds T
KeccakP-1600-AVX2.o KeccakP1600_Permute_Nrounds T
KeccakP-1600-AVX2.o _KeccakF1600_FastLoop_Absorb T
KeccakP-1600-AVX2.o _KeccakP1600_12rounds_FastLoop_Absorb T
KeccakP-1600-AVX2.o _KeccakP1600_AddByte T
KeccakP-1600-AVX2.o _KeccakP1600_AddBytes T
KeccakP-1600-AVX2.o _KeccakP1600_ExtractAndAddBytes T
KeccakP-1600-AVX2.o _KeccakP1600_ExtractBytes T
KeccakP-1600-AVX2.o _KeccakP1600_Initialize T
KeccakP-1600-AVX2.o _KeccakP1600_OverwriteBytes T
KeccakP-1600-AVX2.o _KeccakP1600_OverwriteWithZeroes T
KeccakP-1600-AVX2.o _KeccakP1600_Permute_12rounds T
KeccakP-1600-AVX2.o _KeccakP1600_Permute_24rounds T
KeccakP-1600-AVX2.o _KeccakP1600_Permute_Nrounds T
KeccakP-1600-times4-SIMD256.o KeccakF1600times4_FastLoop_Absorb T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_12rounds_FastLoop_Absorb T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_AddBytes T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_AddLanesAll T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_ExtractAndAddBytes T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_ExtractAndAddLanesAll T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_ExtractBytes T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_ExtractLanesAll T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_InitializeAll T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_OverwriteBytes T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_OverwriteLanesAll T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_OverwriteWithZeroes T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_PermuteAll_12rounds T
KeccakP-1600-times4-SIMD256.o KeccakP1600times4_PermuteAll_24rounds T
aes.o aes128_ctr T
aes.o aes128_ctr_keyexp T
aes.o aes128_ctx_release T
aes.o aes128_ecb T
aes.o aes128_ecb_keyexp T
aes.o aes192_ctr T
aes.o aes192_ctr_keyexp T
aes.o aes192_ctx_release T
aes.o aes192_ecb T
aes.o aes192_ecb_keyexp T
aes.o aes256_ctr T
aes.o aes256_ctr_keyexp T
aes.o aes256_ctx_release T
aes.o aes256_ecb T
aes.o aes256_ecb_keyexp T
aim2.o samsungsds_aimer128s_avx2_GF_exp_invmer_e_1 T
aim2.o samsungsds_aimer128s_avx2_GF_exp_invmer_e_2 T
aim2.o samsungsds_aimer128s_avx2_GF_exp_mer_e_star T
aim2.o samsungsds_aimer128s_avx2_aim2 T
aim2.o samsungsds_aimer128s_avx2_aim2_sbox_outputs T
aim2.o samsungsds_aimer128s_avx2_generate_matrices_L_and_U T
aim2.o samsungsds_aimer128s_avx2_generate_matrix_LU T
field.o samsungsds_aimer128s_avx2_GF_add T
field.o samsungsds_aimer128s_avx2_GF_copy T
field.o samsungsds_aimer128s_avx2_GF_from_bytes T
field.o samsungsds_aimer128s_avx2_GF_mul T
field.o samsungsds_aimer128s_avx2_GF_mul_N T
field.o samsungsds_aimer128s_avx2_GF_mul_add T
field.o samsungsds_aimer128s_avx2_GF_mul_add_N T
field.o samsungsds_aimer128s_avx2_GF_set0 T
field.o samsungsds_aimer128s_avx2_GF_sqr T
field.o samsungsds_aimer128s_avx2_GF_sqr_N T
field.o samsungsds_aimer128s_avx2_GF_to_bytes T
field.o samsungsds_aimer128s_avx2_GF_transposed_matmul T
field.o samsungsds_aimer128s_avx2_GF_transposed_matmul_add_N T
field.o samsungsds_aimer128s_avx2_POLY_mul_add_N T
field.o samsungsds_aimer128s_avx2_POLY_red_N T
fips202.o fips202avx_sha3_256 T
fips202.o fips202avx_sha3_256_absorb T
fips202.o fips202avx_sha3_256_finalize T
fips202.o fips202avx_sha3_256_init T
fips202.o fips202avx_shake128 T
fips202.o fips202avx_shake128_absorb T
fips202.o fips202avx_shake128_finalize T
fips202.o fips202avx_shake128_init T
fips202.o fips202avx_shake128_squeeze T
fips202.o fips202avx_shake256 T
fips202.o fips202avx_shake256_absorb T
fips202.o fips202avx_shake256_finalize T
fips202.o fips202avx_shake256_init T
fips202.o fips202avx_shake256_squeeze T
hash.o samsungsds_aimer128s_avx2_hash_final T
hash.o samsungsds_aimer128s_avx2_hash_final_x4 T
hash.o samsungsds_aimer128s_avx2_hash_init T
hash.o samsungsds_aimer128s_avx2_hash_init_prefix T
hash.o samsungsds_aimer128s_avx2_hash_init_prefix_x4 T
hash.o samsungsds_aimer128s_avx2_hash_init_x4 T
hash.o samsungsds_aimer128s_avx2_hash_squeeze T
hash.o samsungsds_aimer128s_avx2_hash_squeeze_x4 T
hash.o samsungsds_aimer128s_avx2_hash_update T
hash.o samsungsds_aimer128s_avx2_hash_update_x4 T
hash.o samsungsds_aimer128s_avx2_hash_update_x4_1 T
sign.o samsungsds_aimer128s_avx2_aim2_mpc_N T
sign.o samsungsds_aimer128s_avx2_commit_and_expand_tape_x4 T
sign.o samsungsds_aimer128s_avx2_crypto_sign_signature T
sign.o samsungsds_aimer128s_avx2_crypto_sign_verify T
sign.o samsungsds_aimer128s_avx2_run_phase_1 T
sign.o samsungsds_aimer128s_avx2_run_phase_2_and_3 T
tree.o samsungsds_aimer128s_avx2_expand_trees T
tree.o samsungsds_aimer128s_avx2_reconstruct_tree T
tree.o samsungsds_aimer128s_avx2_reveal_all_but T
Number of similar (implementation,compiler) pairs: 8, namely:
Implementation | Compiler |
avx2 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
avx2 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
avx2 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
avx2 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
avx2 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
avx2 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
avx2 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
avx2 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
Namespace violations
aes.o aes128_ctr T
aes.o aes128_ctr_keyexp T
aes.o aes128_ctx_release T
aes.o aes128_ecb T
aes.o aes128_ecb_keyexp T
aes.o aes192_ctr T
aes.o aes192_ctr_keyexp T
aes.o aes192_ctx_release T
aes.o aes192_ecb T
aes.o aes192_ecb_keyexp T
aes.o aes256_ctr T
aes.o aes256_ctr_keyexp T
aes.o aes256_ctx_release T
aes.o aes256_ecb T
aes.o aes256_ecb_keyexp T
aim2.o samsungsds_aimer128s_mem_opt_GF_exp_invmer_e_1 T
aim2.o samsungsds_aimer128s_mem_opt_GF_exp_invmer_e_2 T
aim2.o samsungsds_aimer128s_mem_opt_GF_exp_mer_e_star T
aim2.o samsungsds_aimer128s_mem_opt_aim2 T
aim2.o samsungsds_aimer128s_mem_opt_aim2_sbox_outputs T
aim2.o samsungsds_aimer128s_mem_opt_generate_matrices_L_and_U T
aim2.o samsungsds_aimer128s_mem_opt_generate_matrix_LU T
field.o samsungsds_aimer128s_mem_opt_GF_add T
field.o samsungsds_aimer128s_mem_opt_GF_copy T
field.o samsungsds_aimer128s_mem_opt_GF_from_bytes T
field.o samsungsds_aimer128s_mem_opt_GF_mul T
field.o samsungsds_aimer128s_mem_opt_GF_mul_add T
field.o samsungsds_aimer128s_mem_opt_GF_mul_add_s T
field.o samsungsds_aimer128s_mem_opt_GF_mul_s T
field.o samsungsds_aimer128s_mem_opt_GF_set0 T
field.o samsungsds_aimer128s_mem_opt_GF_sqr_s T
field.o samsungsds_aimer128s_mem_opt_GF_to_bytes T
field.o samsungsds_aimer128s_mem_opt_GF_transposed_matmul T
field.o samsungsds_aimer128s_mem_opt_GF_transposed_matmul_add T
fips202.o sha3_256 T
fips202.o sha3_256_inc_absorb T
fips202.o sha3_256_inc_ctx_clone T
fips202.o sha3_256_inc_ctx_release T
fips202.o sha3_256_inc_finalize T
fips202.o sha3_256_inc_init T
fips202.o sha3_384 T
fips202.o sha3_384_inc_absorb T
fips202.o sha3_384_inc_ctx_clone T
fips202.o sha3_384_inc_ctx_release T
fips202.o sha3_384_inc_finalize T
fips202.o sha3_384_inc_init T
fips202.o sha3_512 T
fips202.o sha3_512_inc_absorb T
fips202.o sha3_512_inc_ctx_clone T
fips202.o sha3_512_inc_ctx_release T
fips202.o sha3_512_inc_finalize T
fips202.o sha3_512_inc_init T
fips202.o shake128 T
fips202.o shake128_absorb T
fips202.o shake128_ctx_clone T
fips202.o shake128_ctx_release T
fips202.o shake128_inc_absorb T
fips202.o shake128_inc_ctx_clone T
fips202.o shake128_inc_ctx_release T
fips202.o shake128_inc_finalize T
fips202.o shake128_inc_init T
fips202.o shake128_inc_squeeze T
fips202.o shake128_squeezeblocks T
fips202.o shake256 T
fips202.o shake256_absorb T
fips202.o shake256_ctx_clone T
fips202.o shake256_ctx_release T
fips202.o shake256_inc_absorb T
fips202.o shake256_inc_ctx_clone T
fips202.o shake256_inc_ctx_release T
fips202.o shake256_inc_finalize T
fips202.o shake256_inc_init T
fips202.o shake256_inc_squeeze T
fips202.o shake256_squeezeblocks T
hash.o samsungsds_aimer128s_mem_opt_hash_ctx_clone T
hash.o samsungsds_aimer128s_mem_opt_hash_ctx_release T
hash.o samsungsds_aimer128s_mem_opt_hash_final T
hash.o samsungsds_aimer128s_mem_opt_hash_init T
hash.o samsungsds_aimer128s_mem_opt_hash_init_prefix T
hash.o samsungsds_aimer128s_mem_opt_hash_squeeze T
hash.o samsungsds_aimer128s_mem_opt_hash_update T
sign.o samsungsds_aimer128s_mem_opt_aim2_mpc T
sign.o samsungsds_aimer128s_mem_opt_commit_and_expand_tape T
sign.o samsungsds_aimer128s_mem_opt_crypto_sign_signature T
sign.o samsungsds_aimer128s_mem_opt_crypto_sign_verify T
sign.o samsungsds_aimer128s_mem_opt_run_phase_1 T
sign.o samsungsds_aimer128s_mem_opt_run_phase_1_to_3 T
sign.o samsungsds_aimer128s_mem_opt_run_phase_1_to_5 T
tree.o samsungsds_aimer128s_mem_opt_expand_tree T
tree.o samsungsds_aimer128s_mem_opt_reconstruct_tree T
tree.o samsungsds_aimer128s_mem_opt_reveal_all_but T
Number of similar (implementation,compiler) pairs: 9, namely:
Implementation | Compiler |
mem_opt | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
mem_opt | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
mem_opt | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
mem_opt | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
mem_opt | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
mem_opt | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
mem_opt | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
mem_opt | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
mem_opt | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
Namespace violations
aes.o aes128_ctr T
aes.o aes128_ctr_keyexp T
aes.o aes128_ctx_release T
aes.o aes128_ecb T
aes.o aes128_ecb_keyexp T
aes.o aes192_ctr T
aes.o aes192_ctr_keyexp T
aes.o aes192_ctx_release T
aes.o aes192_ecb T
aes.o aes192_ecb_keyexp T
aes.o aes256_ctr T
aes.o aes256_ctr_keyexp T
aes.o aes256_ctx_release T
aes.o aes256_ecb T
aes.o aes256_ecb_keyexp T
aim2.o samsungsds_aimer128s_ref_GF_exp_invmer_e_1 T
aim2.o samsungsds_aimer128s_ref_GF_exp_invmer_e_2 T
aim2.o samsungsds_aimer128s_ref_GF_exp_mer_e_star T
aim2.o samsungsds_aimer128s_ref_aim2 T
aim2.o samsungsds_aimer128s_ref_aim2_sbox_outputs T
aim2.o samsungsds_aimer128s_ref_generate_matrices_L_and_U T
aim2.o samsungsds_aimer128s_ref_generate_matrix_LU T
field.o samsungsds_aimer128s_ref_GF_add T
field.o samsungsds_aimer128s_ref_GF_copy T
field.o samsungsds_aimer128s_ref_GF_from_bytes T
field.o samsungsds_aimer128s_ref_GF_mul T
field.o samsungsds_aimer128s_ref_GF_mul_add T
field.o samsungsds_aimer128s_ref_GF_mul_add_s T
field.o samsungsds_aimer128s_ref_GF_mul_s T
field.o samsungsds_aimer128s_ref_GF_set0 T
field.o samsungsds_aimer128s_ref_GF_sqr_s T
field.o samsungsds_aimer128s_ref_GF_to_bytes T
field.o samsungsds_aimer128s_ref_GF_transposed_matmul T
field.o samsungsds_aimer128s_ref_GF_transposed_matmul_add T
fips202.o sha3_256 T
fips202.o sha3_256_inc_absorb T
fips202.o sha3_256_inc_ctx_clone T
fips202.o sha3_256_inc_ctx_release T
fips202.o sha3_256_inc_finalize T
fips202.o sha3_256_inc_init T
fips202.o sha3_384 T
fips202.o sha3_384_inc_absorb T
fips202.o sha3_384_inc_ctx_clone T
fips202.o sha3_384_inc_ctx_release T
fips202.o sha3_384_inc_finalize T
fips202.o sha3_384_inc_init T
fips202.o sha3_512 T
fips202.o sha3_512_inc_absorb T
fips202.o sha3_512_inc_ctx_clone T
fips202.o sha3_512_inc_ctx_release T
fips202.o sha3_512_inc_finalize T
fips202.o sha3_512_inc_init T
fips202.o shake128 T
fips202.o shake128_absorb T
fips202.o shake128_ctx_clone T
fips202.o shake128_ctx_release T
fips202.o shake128_inc_absorb T
fips202.o shake128_inc_ctx_clone T
fips202.o shake128_inc_ctx_release T
fips202.o shake128_inc_finalize T
fips202.o shake128_inc_init T
fips202.o shake128_inc_squeeze T
fips202.o shake128_squeezeblocks T
fips202.o shake256 T
fips202.o shake256_absorb T
fips202.o shake256_ctx_clone T
fips202.o shake256_ctx_release T
fips202.o shake256_inc_absorb T
fips202.o shake256_inc_ctx_clone T
fips202.o shake256_inc_ctx_release T
fips202.o shake256_inc_finalize T
fips202.o shake256_inc_init T
fips202.o shake256_inc_squeeze T
fips202.o shake256_squeezeblocks T
hash.o samsungsds_aimer128s_ref_hash_ctx_clone T
hash.o samsungsds_aimer128s_ref_hash_ctx_release T
hash.o samsungsds_aimer128s_ref_hash_final T
hash.o samsungsds_aimer128s_ref_hash_init T
hash.o samsungsds_aimer128s_ref_hash_init_prefix T
hash.o samsungsds_aimer128s_ref_hash_squeeze T
hash.o samsungsds_aimer128s_ref_hash_update T
sign.o samsungsds_aimer128s_ref_aim2_mpc T
sign.o samsungsds_aimer128s_ref_commit_and_expand_tape T
sign.o samsungsds_aimer128s_ref_crypto_sign_signature T
sign.o samsungsds_aimer128s_ref_crypto_sign_verify T
sign.o samsungsds_aimer128s_ref_run_phase_1 T
sign.o samsungsds_aimer128s_ref_run_phase_2_and_3 T
tree.o samsungsds_aimer128s_ref_expand_trees T
tree.o samsungsds_aimer128s_ref_reconstruct_tree T
tree.o samsungsds_aimer128s_ref_reveal_all_but T
Number of similar (implementation,compiler) pairs: 9, namely:
Implementation | Compiler |
ref | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
ref | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
ref | clang -march=native -O -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) |
ref | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
ref | gcc -march=native -mtune=native -O2 -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) |
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) |
TIMECOP error (can be valgrind bug)
error 1
VEX temporary storage exhausted.
Pool = TEMP, start 0x5965fbc8 curr 0x59b0bab0 end 0x59b24707 (size 5000000)
vex: the `impossible' happened:
VEX temporary storage exhausted.
Increase N_{TEMPORARY,PERMANENT}_BYTES and recompile.
vex storage: T total 332371696 bytes allocated
vex storage: P total 512 bytes allocated
valgrind: the 'impossible' happened:
LibVEX called failure_exit().
host stacktrace:
at 0x...: show_sched_status_wrk (m_libcassert.c:406)
by 0x...: report_and_quit (m_libcassert.c:477)
by 0x...: panic (m_libcassert.c:553)
by 0x...: vgPlain_core_panic_at (m_libcassert.c:558)
by 0x...: vgPlain_core_panic (m_libcassert.c:563)
by 0x...: failure_exit (m_translate.c:761)
by 0x...: vpanic (main_util.c:253)
by 0x...: private_LibVEX_alloc_OOM (main_util.c:181)
by 0x...: LibVEX_Alloc_inline (main_util.h:176)
by 0x...: addHInstr_SLOW (host_generic_regs.c:332)
by 0x...: emit_instr (host_generic_reg_alloc3.c:301)
by 0x...: doRegisterAllocation_v3 (host_generic_reg_alloc3.c:1320)
by 0x...: libvex_BackEnd (main_main.c:1133)
by 0x...: LibVEX_Translate (main_main.c:1236)
by 0x...: vgPlain_translate (m_translate.c:1828)
by 0x...: handle_tt_miss (scheduler.c:1138)
by 0x...: vgPlain_scheduler (scheduler.c:1500)
by 0x...: thread_wrapper (syswrap-linux.c:101)
by 0x...: run_a_thread_NORETURN (syswrap-linux.c:154)
sched status:
running_tid=1
Thread 1: status = VgTs_Runnable (lwpid 470327)
at 0x...: samsungsds_aimer128s_avx2_aim2 (aim2.c:431)
by 0x...: crypto_sign_aimer128s_avx2_constbranchindex_keypair (sign.c:292)
by 0x...: test (try.c:128)
by 0x...: main (try-anything.c:345)
client stack range: [0x1FFEFFE000 0x1FFF000FFF] client SP: 0x1FFEFFE4D0
valgrind stack range: [0x1008DAA000 0x1008EA9FFF] top usage: 18472 of 1048576
Note: see also the FAQ in the source distribution.
It contains workarounds to several common problems.
In particular, if Valgrind aborted or crashed after
identifying problems in your program, there's a good chance
that fixing those problems will prevent Valgrind aborting or
crashing, especially if it happened in m_mallocfree.c.
If that doesn't help, please report this bug to: www.valgrind.org
In the bug report, send all the above text, the valgrind
version, and what OS and version you are using. Thanks.
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) |
Passed TIMECOP
TIMECOP iterations: 10
Number of similar (implementation,compiler) pairs: 25, namely:
Implementation | Compiler |
avx2 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
avx2 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
avx2 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
avx2 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
avx2 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
avx2 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
avx2 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
mem_opt | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
mem_opt | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
mem_opt | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
mem_opt | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
mem_opt | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
mem_opt | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
mem_opt | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
mem_opt | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
mem_opt | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
ref | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
ref | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
ref | clang -march=native -O -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) |
ref | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
ref | gcc -march=native -mtune=native -O2 -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) |
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) |