Implementation notes: amd64, h3neo, crypto_core/inv3sntrup953

Computer: h3neo
Microarchitecture: amd64; K10 45nm (100f63)
Architecture: amd64
CPU ID: AuthenticAMD-00100f63-078bfbff
SUPERCOP version: 20240808
Operation: crypto_core
Primitive: inv3sntrup953
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
9845826746 0 020147 844 928bits64clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
10068399944 0 024453 804 992bits64gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
10642066586 0 020443 844 928bits64clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
12816354619 0 017083 844 928bits64clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
14703452013 0 013507 844 928bits64clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
15945152129 0 013021 836 928bits64clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
16779731458 0 012752 780 960bits64gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
17428871883 0 015069 804 992bits64gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
17473121653 0 014116 796 992bits64gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
83696954036 0 018631 812 992bitsgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
119410593269 0 016733 852 928bitsclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
120363243273 0 017189 852 928bitsclang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
121030383269 0 015813 852 928bitsclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
166411246063 0 020639 812 992refgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
403585862602 0 015157 852 928refclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024081120240808
403587282602 0 016077 852 928refclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
408516332542 0 016469 852 928refclang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024081120240808
44387854757 0 012333 852 928refclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024081120240808
44641031728 0 011687 844 928refclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
63115317924 0 014183 812 992refgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
642012511158 0 012717 852 928bitsclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
646403091174 0 012135 844 928bitsclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
66454304782 0 012106 788 960refgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
704117471111 0 012474 788 960bitsgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
72468258879 0 013308 796 992refgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
761642541394 0 014655 812 992bitsgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808
945049471230 0 013700 796 992bitsgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024081020240808

Compiler output


r3_recip.c: r3_recip.c:415:11: error: always_inline function '_mm256_set_epi32' requires target feature 'avx', but would be inlined into function 'crypto_core_inv3sntrup953_avx_constbranchindex' that is compiled without support for 'avx'
r3_recip.c:   F0[0] = _mm256_set_epi32(0,0,0,0,0,0,0,1);
r3_recip.c:           ^
r3_recip.c: r3_recip.c:415:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
r3_recip.c: r3_recip.c:416:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'avx', but would be inlined into function 'crypto_core_inv3sntrup953_avx_constbranchindex' that is compiled without support for 'avx'
r3_recip.c:   F0[1] = _mm256_set1_epi32(0);
r3_recip.c:           ^
r3_recip.c: r3_recip.c:416:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
r3_recip.c: r3_recip.c:417:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'avx', but would be inlined into function 'crypto_core_inv3sntrup953_avx_constbranchindex' that is compiled without support for 'avx'
r3_recip.c:   F0[2] = _mm256_set1_epi32(0);
r3_recip.c:           ^
r3_recip.c: r3_recip.c:417:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
r3_recip.c: r3_recip.c:418:11: error: always_inline function '_mm256_set_epi32' requires target feature 'avx', but would be inlined into function 'crypto_core_inv3sntrup953_avx_constbranchindex' that is compiled without support for 'avx'
r3_recip.c:   F0[3] = _mm256_set_epi32(0,0,0,0,16384,0,16384,0);
r3_recip.c:           ^
r3_recip.c: r3_recip.c:418:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
r3_recip.c: r3_recip.c:419:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'avx', but would be inlined into function 'crypto_core_inv3sntrup953_avx_constbranchindex' that is compiled without support for 'avx'
r3_recip.c:   F1[0] = _mm256_set1_epi32(0);
r3_recip.c:           ^
r3_recip.c: r3_recip.c:419:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
r3_recip.c: r3_recip.c:420:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'avx', but would be inlined into function 'crypto_core_inv3sntrup953_avx_constbranchindex' that is compiled without support for 'avx'
r3_recip.c:   F1[1] = _mm256_set1_epi32(0);
r3_recip.c:           ^
r3_recip.c: r3_recip.c:420:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
r3_recip.c: r3_recip.c:421:11: error: always_inline function '_mm256_set1_epi32' requires target feature 'avx', but would be inlined into function 'crypto_core_inv3sntrup953_avx_constbranchindex' that is compiled without support for 'avx'
r3_recip.c: ...

Number of similar (implementation,compiler) pairs: 5, namely:
ImplementationCompiler
avxclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
avxclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
avxclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
avxclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
avxclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)

Compiler output


r3_recip.c: r3_recip.c: In function 'crypto_core_inv3sntrup953_avx_constbranchindex':
r3_recip.c: r3_recip.c:415:9: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
r3_recip.c:   415 |   F0[0] = _mm256_set_epi32(0,0,0,0,0,0,0,1);
r3_recip.c:       |   ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c: In function 'vec256_swap':
r3_recip.c: r3_recip.c:175:20: note: the ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
r3_recip.c:   175 | static inline void vec256_swap(vec256 *f,vec256 *g,int len,vec256 mask)
r3_recip.c:       |                    ^~~~~~~~~~~
r3_recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
r3_recip.c:                  from r3_recip.c:3:
r3_recip.c: r3_recip.c: In function 'vec256_frombits':
r3_recip.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:597:1: error: inlining failed in call to 'always_inline' '_mm256_shuffle_epi32': target specific option mismatch
r3_recip.c:   597 | _mm256_shuffle_epi32 (__m256i __A, const int __mask)
r3_recip.c:       | ^~~~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c:71:9: note: called from here
r3_recip.c:    71 |     h = _mm256_shuffle_epi32(h,0xd8);
r3_recip.c:       |         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
r3_recip.c:                  from r3_recip.c:3:
r3_recip.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:1071:1: error: inlining failed in call to 'always_inline' '_mm256_permute4x64_epi64': target specific option mismatch
r3_recip.c:  1071 | _mm256_permute4x64_epi64 (__m256i __X, const int __M)
r3_recip.c:       | ^~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: r3_recip.c:70:9: note: called from here
r3_recip.c:    70 |     h = _mm256_permute4x64_epi64(h,0xd8);
r3_recip.c:       |         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
r3_recip.c: ...

Number of similar (implementation,compiler) pairs: 4, namely:
ImplementationCompiler
avxgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
avxgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
avxgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
avxgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)

Passed TIMECOP


TIMECOP iterations: 1

Number of similar (implementation,compiler) pairs: 27, namely:
ImplementationCompiler
bitsclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
bitsclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
bitsclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
bitsclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
bitsclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
bitsgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
bitsgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
bitsgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
bitsgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
bits64clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
bits64clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
bits64clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
bits64clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
bits64clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
bits64gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
bits64gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
bits64gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
bits64gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
refclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
refclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
refclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
refclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
refclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
refgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
refgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
refgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
refgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)