Implementation notes: amd64, jasper2, crypto_core/inv3sntrup953

Computer: jasper2
Microarchitecture: amd64; Tremont (906c0)
Architecture: amd64
CPU ID: GenuineIntel-000906c0-20-bfebfbff
SUPERCOP version: 20240808
Operation: crypto_core
Primitive: inv3sntrup953
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
8603146042 0 021208 812 920bits64clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
9335854628 0 017480 812 920bits64clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
9659401400 0 011995 756 952bits64gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
10502279561 0 023040 780 984bits64gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
10658311779 0 014080 780 984bits64gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
11411441591 0 013455 772 984bits64gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
14552722119 0 013150 804 920bits64clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
14696196650 0 020432 812 920bits64clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
18526611970 0 013614 804 920bits64clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
33800742989 0 016538 788 984bitsgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
76850593164 0 016682 788 984refgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
103885959841 0 023616 812 920bitsclang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
109638493919 0 016784 812 920bitsclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
1141196610247 0 025416 812 920bitsclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
194769847108 0 022288 812 920refclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
195690982987 0 015856 812 920refclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
259455854350 0 018136 812 920refclang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
43130218708 0 011734 804 920refclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
47754783895 0 012446 804 920refclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
490646701323 0 013690 788 984bitsgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
624617081583 0 013190 804 920bitsclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
628924951152 0 013023 772 984bitsgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
656573071042 0 011701 764 952bitsgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
67088923842 0 013210 788 984refgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
73784660705 0 011317 764 952refgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
75384823819 0 012655 772 984refgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808
785020981165 0 012190 804 920bitsclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024080920240808

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 (Debian_Clang_11.0.1)
avxclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
avxclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
avxclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
avxclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)

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/10/include/immintrin.h:53,
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/10/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/10/include/immintrin.h:53,
r3_recip.c:                  from r3_recip.c:3:
r3_recip.c: /usr/lib/gcc/x86_64-linux-gnu/10/include/avx2intrin.h:1068:1: error: inlining failed in call to 'always_inline' '_mm256_permute4x64_epi64': target specific option mismatch
r3_recip.c:  1068 | _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 (10.2.1_20210110)
avxgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
avxgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
avxgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)

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 (Debian_Clang_11.0.1)
bitsclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
bitsclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
bitsclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
bitsclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
bitsgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
bitsgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
bitsgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
bitsgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
bits64clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
bits64clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
bits64clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
bits64clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
bits64clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
bits64gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
bits64gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
bits64gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
bits64gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
refclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
refclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
refclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
refclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
refclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)
refgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
refgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
refgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)
refgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)