Test results for amd64, h2atom, crypto_core/multsntrup953

[Page version: 20260919 18:54:16]

Measurements for amd64, h2atom, crypto_core Test results for amd64, h2atom, crypto_core Test results for crypto_core/multsntrup953

Computer: h2atom
Microarchitecture: amd64; Bonnell (106ca)
Architecture: amd64
CPU ID: GenuineIntel-000106ca-bfe9fbff
SUPERCOP version: 20260330
Operation: crypto_core
Primitive: multsntrup953

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
1621386	4928 0 0	29267 1224 1608	`ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260510	20260330
3978260	2321 0 0	26628 1240 1512	`ref`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260510	20260330
4256804	2213 0 0	26484 1240 1512	`ref`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260510	20260330
4269630	2213 0 0	25292 1240 1512	`ref`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260510	20260330
4393039	1913 0 0	26267 1224 1608	`compact`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260510	20260330
5438330	1007 0 0	24092 1240 1512	`compact`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260510	20260330
5438910	1007 0 0	25284 1240 1512	`compact`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260510	20260330
6011150	1183 0 0	25492 1240 1512	`compact`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260510	20260330
8289231	591 0 0	23162 1216 1608	`compact`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260510	20260330
8776981	1501 0 0	24779 1224 1608	`ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260510	20260330
9191645	465 0 0	21670 1232 1512	`compact`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260510	20260330
9195372	466 0 0	22252 1240 1512	`compact`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260510	20260330
9237372	1424 0 0	22638 1232 1512	`ref`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260510	20260330
10105608	630 0 0	23899 1224 1608	`compact`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260510	20260330
10109690	536 0 0	21589 1208 1576	`compact`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260510	20260330
10195565	712 0 0	23282 1216 1608	`ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260510	20260330
10195590	565 0 0	21613 1208 1576	`ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260510	20260330
10622702	683 0 0	22468 1240 1512	`ref`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260510	20260330

Compiler output

mult1024.c: mult1024.c:309:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup953_avx_constbranchindex' that is compiled without support for 'avx'
mult1024.c:   309 |   x = const_x16(0);
mult1024.c:       |       ^
mult1024.c: mult1024.c:12:19: note: expanded from macro 'const_x16'
mult1024.c:    12 | #define const_x16 _mm256_set1_epi16
mult1024.c:       |                   ^
mult1024.c: mult1024.c:309:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult1024.c: mult1024.c:12:19: note: expanded from macro 'const_x16'
mult1024.c:    12 | #define const_x16 _mm256_set1_epi16
mult1024.c:       |                   ^
mult1024.c: mult1024.c:310:36: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup953_avx_constbranchindex' that is compiled without support for 'avx'
mult1024.c:   310 |   for (i = p&~15;i < 1024;i += 16) store_x16(&f[i],x);
mult1024.c:       |                                    ^
mult1024.c: mult1024.c:11:24: note: expanded from macro 'store_x16'
mult1024.c:    11 | #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1024.c:       |                        ^
mult1024.c: mult1024.c:310:36: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult1024.c: mult1024.c:11:24: note: expanded from macro 'store_x16'
mult1024.c:    11 | #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1024.c:       |                        ^
mult1024.c: mult1024.c:311:36: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup953_avx_constbranchindex' that is compiled without support for 'avx'
mult1024.c:   311 |   for (i = p&~15;i < 1024;i += 16) store_x16(&g[i],x);
mult1024.c:       |                                    ^
mult1024.c: mult1024.c:11:24: note: expanded from macro 'store_x16'
mult1024.c:    11 | #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1024.c: ...

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

Implementation	Compiler
`avx`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_18.1.3_(1ubuntu1))`
`avx`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_18.1.3_(1ubuntu1))`
`avx`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_18.1.3_(1ubuntu1))`
`avx`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_18.1.3_(1ubuntu1))`
`avx`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_18.1.3_(1ubuntu1))`

Compiler output

mult1024.c: mult1024.c: In function 'squeeze_6343_x16':
mult1024.c: mult1024.c:21:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult1024.c:    21 | {
mult1024.c:       | ^
mult1024.c: mult1024.c: In function 'squeeze_7681_x16':
mult1024.c: mult1024.c:25:24: note: the ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
mult1024.c:    25 | static inline int16x16 squeeze_7681_x16(int16x16 x)
mult1024.c:       |                        ^~~~~~~~~~~~~~~~
mult1024.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/13/include/immintrin.h:51,
mult1024.c:                  from mult1024.c:3:
mult1024.c: /usr/lib/gcc/x86_64-linux-gnu/13/include/avx2intrin.h: In function 'squeeze_6343_x16':
mult1024.c: /usr/lib/gcc/x86_64-linux-gnu/13/include/avx2intrin.h:808:1: error: inlining failed in call to 'always_inline' '_mm256_sub_epi16': target specific option mismatch
mult1024.c:   808 | _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult1024.c:       | ^~~~~~~~~~~~~~~~
mult1024.c: mult1024.c:14:17: note: called from here
mult1024.c:    14 | #define sub_x16 _mm256_sub_epi16
mult1024.c:       |                 ^
mult1024.c: mult1024.c:22:10: note: in expansion of macro 'sub_x16'
mult1024.c:    22 |   return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(5)),const_x16(6343)));
mult1024.c:       |          ^~~~~~~
mult1024.c: /usr/lib/gcc/x86_64-linux-gnu/13/include/avx2intrin.h:553:1: error: inlining failed in call to 'always_inline' '_mm256_mullo_epi16': target specific option mismatch
mult1024.c:   553 | _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult1024.c:       | ^~~~~~~~~~~~~~~~~~
mult1024.c: mult1024.c:14:17: note: called from here
mult1024.c:    14 | #define sub_x16 _mm256_sub_epi16
mult1024.c: ...

Number of similar (implementation,compiler) pairs: 8, namely:

Implementation	Compiler
`avx`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`avx`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`avx`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`avx`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`avx800`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`avx800`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`avx800`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`avx800`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`

Compiler output

mult1024.c: mult1024.c:309:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup953_avx800_constbranchindex' that is compiled without support for 'avx'
mult1024.c:   309 |   x = const_x16(0);
mult1024.c:       |       ^
mult1024.c: mult1024.c:12:19: note: expanded from macro 'const_x16'
mult1024.c:    12 | #define const_x16 _mm256_set1_epi16
mult1024.c:       |                   ^
mult1024.c: mult1024.c:309:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult1024.c: mult1024.c:12:19: note: expanded from macro 'const_x16'
mult1024.c:    12 | #define const_x16 _mm256_set1_epi16
mult1024.c:       |                   ^
mult1024.c: mult1024.c:310:36: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup953_avx800_constbranchindex' that is compiled without support for 'avx'
mult1024.c:   310 |   for (i = p&~15;i < 1024;i += 16) store_x16(&f[i],x);
mult1024.c:       |                                    ^
mult1024.c: mult1024.c:11:24: note: expanded from macro 'store_x16'
mult1024.c:    11 | #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1024.c:       |                        ^
mult1024.c: mult1024.c:310:36: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult1024.c: mult1024.c:11:24: note: expanded from macro 'store_x16'
mult1024.c:    11 | #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1024.c:       |                        ^
mult1024.c: mult1024.c:311:36: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup953_avx800_constbranchindex' that is compiled without support for 'avx'
mult1024.c:   311 |   for (i = p&~15;i < 1024;i += 16) store_x16(&g[i],x);
mult1024.c:       |                                    ^
mult1024.c: mult1024.c:11:24: note: expanded from macro 'store_x16'
mult1024.c:    11 | #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1024.c: ...

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

Implementation	Compiler
`avx800`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_18.1.3_(1ubuntu1))`
`avx800`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_18.1.3_(1ubuntu1))`
`avx800`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_18.1.3_(1ubuntu1))`
`avx800`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_18.1.3_(1ubuntu1))`
`avx800`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_18.1.3_(1ubuntu1))`

Passed TIMECOP

TIMECOP iterations: 1

Number of similar (implementation,compiler) pairs: 18, namely:

Implementation	Compiler
`compact`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_18.1.3_(1ubuntu1))`
`compact`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_18.1.3_(1ubuntu1))`
`compact`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_18.1.3_(1ubuntu1))`
`compact`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_18.1.3_(1ubuntu1))`
`compact`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_18.1.3_(1ubuntu1))`
`compact`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`compact`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`compact`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`compact`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`ref`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_18.1.3_(1ubuntu1))`
`ref`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_18.1.3_(1ubuntu1))`
`ref`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_18.1.3_(1ubuntu1))`
`ref`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_18.1.3_(1ubuntu1))`
`ref`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_18.1.3_(1ubuntu1))`
`ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`