Test results for amd64, hydra5, crypto_core/mult3sntrup1277

[Page version: 20260409 06:44:40]

Measurements for amd64, hydra5, crypto_core Test results for amd64, hydra5, crypto_core Test results for crypto_core/mult3sntrup1277

Computer: hydra5
Microarchitecture: amd64; K10 32nm (300f10)
Architecture: amd64
CPU ID: AuthenticAMD-00300f10-178bfbff
SUPERCOP version: 20260330
Operation: crypto_core
Primitive: mult3sntrup1277

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
1109220	3323 0 0	29469 1224 1608	`compact`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260303	20260217
1454092	2991 0 0	27970 1272 1512	`ref`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260303	20260217
1455318	2237 0 0	26282 1272 1512	`ref`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260304	20260217
1457764	2991 0 0	27970 1272 1512	`ref`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260304	20260217
1615885	1850 0 0	26818 1272 1512	`compact`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260303	20260217
1615979	1850 0 0	26818 1272 1512	`compact`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260303	20260217
1618877	1850 0 0	25898 1272 1512	`compact`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260303	20260217
3770881	372 0 0	22164 1264 1512	`compact`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260303	20260217
5761268	420 0 0	22523 1200 1576	`compact`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260303	20260217
6441453	752 0 0	24925 1224 1608	`ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260303	20260217
6450157	1010 0 0	27181 1224 1608	`ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260303	20260217
6577996	412 0 0	22698 1272 1512	`compact`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260303	20260217
6596013	563 0 0	22834 1272 1512	`ref`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260304	20260217
6598514	499 0 0	22268 1264 1512	`ref`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260304	20260217
6682444	505 0 0	24685 1224 1608	`compact`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260303	20260217
7439844	713 0 0	24092 1216 1608	`ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260303	20260217
8203770	497 0 0	23868 1216 1608	`compact`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260303	20260217
8245482	586 0 0	22699 1200 1576	`ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260303	20260217

Compiler output

mult1280.c: mult1280.c:345:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup1277_avx_constbranchindex' that is compiled without support for 'avx'
mult1280.c:   345 |   x = const_x16(0);
mult1280.c:       |       ^
mult1280.c: mult1280.c:12:19: note: expanded from macro 'const_x16'
mult1280.c:    12 | #define const_x16 _mm256_set1_epi16
mult1280.c:       |                   ^
mult1280.c: mult1280.c:345:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult1280.c: mult1280.c:12:19: note: expanded from macro 'const_x16'
mult1280.c:    12 | #define const_x16 _mm256_set1_epi16
mult1280.c:       |                   ^
mult1280.c: mult1280.c:346:36: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup1277_avx_constbranchindex' that is compiled without support for 'avx'
mult1280.c:   346 |   for (i = p&~15;i < 1280;i += 16) store_x16(&f[i],x);
mult1280.c:       |                                    ^
mult1280.c: mult1280.c:11:24: note: expanded from macro 'store_x16'
mult1280.c:    11 | #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1280.c:       |                        ^
mult1280.c: mult1280.c:346:36: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult1280.c: mult1280.c:11:24: note: expanded from macro 'store_x16'
mult1280.c:    11 | #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1280.c:       |                        ^
mult1280.c: mult1280.c:347:36: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup1277_avx_constbranchindex' that is compiled without support for 'avx'
mult1280.c:   347 |   for (i = p&~15;i < 1280;i += 16) store_x16(&g[i],x);
mult1280.c:       |                                    ^
mult1280.c: mult1280.c:11:24: note: expanded from macro 'store_x16'
mult1280.c:    11 | #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1280.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

mult1280.c: mult1280.c: In function 'squeeze_3_x16':
mult1280.c: mult1280.c:21:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult1280.c:    21 | {
mult1280.c:       | ^
mult1280.c: mult1280.c: In function 'squeeze_7681_x16':
mult1280.c: mult1280.c:25:17: note: the ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
mult1280.c:    25 | static int16x16 squeeze_7681_x16(int16x16 x)
mult1280.c:       |                 ^~~~~~~~~~~~~~~~
mult1280.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/13/include/immintrin.h:51,
mult1280.c:                  from mult1280.c:3:
mult1280.c: /usr/lib/gcc/x86_64-linux-gnu/13/include/avx2intrin.h: In function 'squeeze_3_x16':
mult1280.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
mult1280.c:   808 | _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult1280.c:       | ^~~~~~~~~~~~~~~~
mult1280.c: mult1280.c:14:17: note: called from here
mult1280.c:    14 | #define sub_x16 _mm256_sub_epi16
mult1280.c:       |                 ^
mult1280.c: mult1280.c:22:10: note: in expansion of macro 'sub_x16'
mult1280.c:    22 |   return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(10923)),const_x16(3)));
mult1280.c:       |          ^~~~~~~
mult1280.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
mult1280.c:   553 | _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult1280.c:       | ^~~~~~~~~~~~~~~~~~
mult1280.c: mult1280.c:14:17: note: called from here
mult1280.c:    14 | #define sub_x16 _mm256_sub_epi16
mult1280.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

mult1280.c: mult1280.c:345:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup1277_avx800_constbranchindex' that is compiled without support for 'avx'
mult1280.c:   345 |   x = const_x16(0);
mult1280.c:       |       ^
mult1280.c: mult1280.c:12:19: note: expanded from macro 'const_x16'
mult1280.c:    12 | #define const_x16 _mm256_set1_epi16
mult1280.c:       |                   ^
mult1280.c: mult1280.c:345:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult1280.c: mult1280.c:12:19: note: expanded from macro 'const_x16'
mult1280.c:    12 | #define const_x16 _mm256_set1_epi16
mult1280.c:       |                   ^
mult1280.c: mult1280.c:346:36: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup1277_avx800_constbranchindex' that is compiled without support for 'avx'
mult1280.c:   346 |   for (i = p&~15;i < 1280;i += 16) store_x16(&f[i],x);
mult1280.c:       |                                    ^
mult1280.c: mult1280.c:11:24: note: expanded from macro 'store_x16'
mult1280.c:    11 | #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1280.c:       |                        ^
mult1280.c: mult1280.c:346:36: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult1280.c: mult1280.c:11:24: note: expanded from macro 'store_x16'
mult1280.c:    11 | #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1280.c:       |                        ^
mult1280.c: mult1280.c:347:36: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup1277_avx800_constbranchindex' that is compiled without support for 'avx'
mult1280.c:   347 |   for (i = p&~15;i < 1280;i += 16) store_x16(&g[i],x);
mult1280.c:       |                                    ^
mult1280.c: mult1280.c:11:24: note: expanded from macro 'store_x16'
mult1280.c:    11 | #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1280.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)`