Implementation notes: amd64, wolfdale, crypto_core/multsntrup1013
Computer: wolfdale
Microarchitecture: amd64; Core 2 45nm (1067a)
Architecture: amd64
CPU ID: GenuineIntel-0001067a-bfebfbff
SUPERCOP version: 20240808
Operation: crypto_core
Primitive: multsntrup1013
Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
893964 | 3657 0 0 | 16784 780 984 | ref | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
1563294 | 1717 0 0 | 15656 812 920 | ref | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
1727831 | 1604 0 0 | 15000 812 920 | ref | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
1757287 | 1604 0 0 | 15816 812 920 | ref | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
2505215 | 606 0 0 | 11774 804 920 | ref | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
2548005 | 615 0 0 | 12302 804 920 | ref | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
2634638 | 456 0 0 | 11614 804 920 | compact | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
2641631 | 511 0 0 | 12198 804 920 | compact | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
2943856 | 538 0 0 | 12303 772 984 | ref | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
2949880 | 1568 0 0 | 15784 812 920 | compact | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
2950366 | 1568 0 0 | 14968 812 920 | compact | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
3021704 | 1703 0 0 | 15640 812 920 | compact | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
3057634 | 620 0 0 | 12824 780 984 | ref | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
3159448 | 409 0 0 | 11183 764 952 | compact | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
3262581 | 451 0 0 | 12207 772 984 | compact | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
3342760 | 451 0 0 | 12656 780 984 | compact | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
3589274 | 456 0 0 | 11239 764 952 | ref | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
3861695 | 1510 0 0 | 14640 780 984 | compact | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
Compiler output
mult1024.c: mult1024.c:308:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup1013_avx_constbranchindex' that is compiled without support for 'avx'
mult1024.c: x = const_x16(0);
mult1024.c: ^
mult1024.c: mult1024.c:11:19: note: expanded from macro 'const_x16'
mult1024.c: #define const_x16 _mm256_set1_epi16
mult1024.c: ^
mult1024.c: mult1024.c:308:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult1024.c: mult1024.c:11:19: note: expanded from macro 'const_x16'
mult1024.c: #define const_x16 _mm256_set1_epi16
mult1024.c: ^
mult1024.c: mult1024.c:309:36: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup1013_avx_constbranchindex' that is compiled without support for 'avx'
mult1024.c: for (i = p&~15;i < 1024;i += 16) store_x16(&f[i],x);
mult1024.c: ^
mult1024.c: mult1024.c:10:24: note: expanded from macro 'store_x16'
mult1024.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1024.c: ^
mult1024.c: mult1024.c:309:36: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult1024.c: mult1024.c:10:24: note: expanded from macro 'store_x16'
mult1024.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
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_multsntrup1013_avx_constbranchindex' that is compiled without support for 'avx'
mult1024.c: for (i = p&~15;i < 1024;i += 16) store_x16(&g[i],x);
mult1024.c: ^
mult1024.c: mult1024.c:10:24: note: expanded from macro 'store_x16'
mult1024.c: #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 (Debian_Clang_11.0.1) |
avx | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
avx | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
avx | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
avx | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
Compiler output
mult1024.c: mult1024.c: In function 'squeeze_7177_x16':
mult1024.c: mult1024.c:20:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
mult1024.c: 20 | {
mult1024.c: | ^
mult1024.c: mult1024.c: In function 'squeeze_7681_x16':
mult1024.c: mult1024.c:24:24: note: the ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
mult1024.c: 24 | static inline int16x16 squeeze_7681_x16(int16x16 x)
mult1024.c: | ^~~~~~~~~~~~~~~~
mult1024.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:53,
mult1024.c: from mult1024.c:2:
mult1024.c: mult1024.c: In function 'squeeze_7177_x16':
mult1024.c: /usr/lib/gcc/x86_64-linux-gnu/10/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:13:17: note: called from here
mult1024.c: 13 | #define sub_x16 _mm256_sub_epi16
mult1024.c: | ^
mult1024.c: mult1024.c:21:10: note: in expansion of macro 'sub_x16'
mult1024.c: 21 | return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(4)),const_x16(7177)));
mult1024.c: | ^~~~~~~
mult1024.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:53,
mult1024.c: from mult1024.c:2:
mult1024.c: /usr/lib/gcc/x86_64-linux-gnu/10/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: ...
Number of similar (implementation,compiler) pairs: 8, namely:
Implementation | Compiler |
avx | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
avx | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
avx | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
avx | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
avx800 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
avx800 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
avx800 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
avx800 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
Compiler output
mult1024.c: mult1024.c:308:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup1013_avx800_constbranchindex' that is compiled without support for 'avx'
mult1024.c: x = const_x16(0);
mult1024.c: ^
mult1024.c: mult1024.c:11:19: note: expanded from macro 'const_x16'
mult1024.c: #define const_x16 _mm256_set1_epi16
mult1024.c: ^
mult1024.c: mult1024.c:308:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult1024.c: mult1024.c:11:19: note: expanded from macro 'const_x16'
mult1024.c: #define const_x16 _mm256_set1_epi16
mult1024.c: ^
mult1024.c: mult1024.c:309:36: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup1013_avx800_constbranchindex' that is compiled without support for 'avx'
mult1024.c: for (i = p&~15;i < 1024;i += 16) store_x16(&f[i],x);
mult1024.c: ^
mult1024.c: mult1024.c:10:24: note: expanded from macro 'store_x16'
mult1024.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1024.c: ^
mult1024.c: mult1024.c:309:36: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult1024.c: mult1024.c:10:24: note: expanded from macro 'store_x16'
mult1024.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
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_multsntrup1013_avx800_constbranchindex' that is compiled without support for 'avx'
mult1024.c: for (i = p&~15;i < 1024;i += 16) store_x16(&g[i],x);
mult1024.c: ^
mult1024.c: mult1024.c:10:24: note: expanded from macro 'store_x16'
mult1024.c: #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 (Debian_Clang_11.0.1) |
avx800 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
avx800 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
avx800 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
avx800 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
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 (Debian_Clang_11.0.1) |
compact | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
compact | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
compact | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
compact | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
compact | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
compact | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
compact | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
compact | 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) |