Implementation notes: amd64, rumba5, crypto_core/multsntrup761
Computer: rumba5
Microarchitecture: amd64; Zen (800f11)
Architecture: amd64
CPU ID: AuthenticAMD-00800f11-178bfbff
SUPERCOP version: 20240625
Operation: crypto_core
Primitive: multsntrup761
| Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
|---|
| 29813 | 19020 0 0 | 33787 844 960 | avx800 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 30001 | 20406 0 0 | 35555 844 960 | avx800 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 30122 | 20750 0 0 | 35899 844 960 | avx | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 30159 | 19364 0 0 | 34131 844 960 | avx | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 30277 | 19009 0 0 | 33037 804 992 | avx800 | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 31222 | 17544 0 0 | 29973 836 1024 | avx800 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 31662 | 19815 0 0 | 31571 844 928 | avx800 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 31731 | 17787 0 0 | 30205 836 1024 | avx | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 31806 | 19674 0 0 | 31427 844 928 | avx | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 32014 | 20485 0 0 | 34933 804 992 | avx | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 32161 | 18627 0 0 | 30884 796 992 | avx800 | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 33264 | 18162 0 0 | 29428 788 960 | avx800 | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 33384 | 18368 0 0 | 31149 804 992 | avx800 | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 33688 | 20128 0 0 | 32796 796 992 | avx | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 34768 | 18772 0 0 | 30436 788 960 | avx | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 34937 | 19844 0 0 | 33045 804 992 | avx | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 44677 | 12726 0 0 | 27939 844 960 | round1 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 45324 | 11186 0 0 | 26035 844 960 | round1 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 50813 | 9170 0 0 | 20931 844 928 | round1 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 50907 | 8664 0 0 | 21189 836 1024 | round1 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 186248 | 3299 0 0 | 17693 804 992 | ref | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 416762 | 2541 0 0 | 17355 844 960 | ref | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 417223 | 2541 0 0 | 17731 844 960 | ref | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 443974 | 1787 0 0 | 15923 844 928 | ref | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 1413290 | 591 0 0 | 13069 836 1024 | ref | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 1461784 | 634 0 0 | 12355 844 928 | ref | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 1545081 | 646 0 0 | 13284 796 992 | ref | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 1570422 | 697 0 0 | 13861 804 992 | ref | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
| 1581082 | 556 0 0 | 12180 788 960 | ref | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
Compiler output
mult768.c: mult768.c:265:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup761_avx_constbranchindex' that is compiled without support for 'avx'
mult768.c: x = const_x16(0);
mult768.c: ^
mult768.c: mult768.c:10:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c: ^
mult768.c: mult768.c:265:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:10:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c: ^
mult768.c: mult768.c:266:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup761_avx_constbranchindex' that is compiled without support for 'avx'
mult768.c: for (i = p&~15;i < 768;i += 16) store_x16(&f[i],x);
mult768.c: ^
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c: ^
mult768.c: mult768.c:266:35: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c: ^
mult768.c: mult768.c:267:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup761_avx_constbranchindex' that is compiled without support for 'avx'
mult768.c: for (i = p&~15;i < 768;i += 16) store_x16(&g[i],x);
mult768.c: ^
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c: ...
Number of similar (implementation,compiler) pairs: 1, namely:
| Implementation | Compiler |
| avx | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
Compiler output
mult768.c: mult768.c:265:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup761_avx800_constbranchindex' that is compiled without support for 'avx'
mult768.c: x = const_x16(0);
mult768.c: ^
mult768.c: mult768.c:10:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c: ^
mult768.c: mult768.c:265:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:10:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c: ^
mult768.c: mult768.c:266:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup761_avx800_constbranchindex' that is compiled without support for 'avx'
mult768.c: for (i = p&~15;i < 768;i += 16) store_x16(&f[i],x);
mult768.c: ^
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c: ^
mult768.c: mult768.c:266:35: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c: ^
mult768.c: mult768.c:267:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup761_avx800_constbranchindex' that is compiled without support for 'avx'
mult768.c: for (i = p&~15;i < 768;i += 16) store_x16(&g[i],x);
mult768.c: ^
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c: ...
Number of similar (implementation,compiler) pairs: 1, namely:
| Implementation | Compiler |
| avx800 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
Compiler output
mult.c: mult.c:146:22: error: invalid output size for constraint '=&x'
mult.c: MULSTEP_fromzero(0,h0,h1,h2,h3,h4)
mult.c: ^
mult.c: mult.c:148:26: error: invalid output size for constraint '+x'
mult.c: MULSTEP_noload(j + 1,h1,h2,h3,h4,h0)
mult.c: ^
mult.c: mult.c:149:26: error: invalid output size for constraint '+x'
mult.c: MULSTEP_noload(j + 2,h2,h3,h4,h0,h1)
mult.c: ^
mult.c: mult.c:150:26: error: invalid output size for constraint '+x'
mult.c: MULSTEP_noload(j + 3,h3,h4,h0,h1,h2)
mult.c: ^
mult.c: mult.c:151:26: error: invalid output size for constraint '+x'
mult.c: MULSTEP_noload(j + 4,h4,h0,h1,h2,h3)
mult.c: ^
mult.c: mult.c:152:26: error: invalid output size for constraint '+x'
mult.c: MULSTEP_noload(j + 5,h0,h1,h2,h3,h4)
mult.c: ^
mult.c: mult.c:154:24: error: invalid output size for constraint '+x'
mult.c: MULSTEP_noload(j + 1,h1,h2,h3,h4,h0)
mult.c: ^
mult.c: mult.c:155:24: error: invalid output size for constraint '+x'
mult.c: MULSTEP_noload(j + 2,h2,h3,h4,h0,h1)
mult.c: ^
mult.c: mult.c:156:24: error: invalid output size for constraint '+x'
mult.c: ...
Number of similar (implementation,compiler) pairs: 1, namely:
| Implementation | Compiler |
| round1 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
Compiler output
mult.c: In function 'mult768_mix2_m256i',
mult.c: inlined from 'crypto_core_multsntrup761_round1_constbranchindex' at mult.c:755:3:
mult.c: mult.c:567:3: warning: 'mult96x16' accessing 6144 bytes in a region of size 512 [-Wstringop-overflow=]
mult.c: 567 | mult96x16(hkara[12],fkara[6],(__m256i *) (1 + (__m128i *) gkara));
mult.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: mult.c: In function 'crypto_core_multsntrup761_round1_constbranchindex':
mult.c: mult.c:567:3: note: referencing argument 1 of type '__m256i *'
mult.c: In function 'mult768_mix2_m256i',
mult.c: inlined from 'crypto_core_multsntrup761_round1_constbranchindex' at mult.c:755:3:
mult.c: mult.c:567:3: warning: 'mult96x16' reading 3072 bytes from a region of size 512 [-Wstringop-overread]
mult.c: mult.c: In function 'crypto_core_multsntrup761_round1_constbranchindex':
mult.c: mult.c:567:3: note: referencing argument 2 of type 'const __m256i *'
mult.c: In function 'mult768_mix2_m256i',
mult.c: inlined from 'crypto_core_multsntrup761_round1_constbranchindex' at mult.c:755:3:
mult.c: mult.c:567:3: warning: 'mult96x16' reading 3072 bytes from a region of size 3056 [-Wstringop-overread]
mult.c: mult.c: In function 'crypto_core_multsntrup761_round1_constbranchindex':
mult.c: mult.c:567:3: note: referencing argument 3 of type 'const __m256i *'
mult.c: mult.c:278:13: note: in a call to function 'mult96x16'
mult.c: 278 | static void mult96x16(__m256i h[192],const __m256i f[96],const __m256i g[96])
mult.c: | ^~~~~~~~~
mult.c: In function 'mult768_mix2_m256i',
mult.c: inlined from 'crypto_core_multsntrup761_round1_constbranchindex' at mult.c:755:3:
mult.c: mult.c:568:3: warning: 'mult96x16' accessing 6144 bytes in a region of size 512 [-Wstringop-overflow=]
mult.c: 568 | mult96x16(hkara[0],fkara[0],gkara[0]);
mult.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: ...
Number of similar (implementation,compiler) pairs: 4, namely:
| Implementation | Compiler |
| round1 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
| round1 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
| round1 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
| round1 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
Compiler output
ntt.c: ntt.c:562:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:562:44: warning: unused variable 'h3' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:562:35: warning: unused variable 'h0' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:562:38: warning: unused variable 'h1' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:865:10: warning: unused variable 'origf' [-Wunused-variable]
ntt.c: int16 *origf = f;
ntt.c: ^
ntt.c: ntt.c:864:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:864:44: warning: unused variable 'h3' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:864:35: warning: unused variable 'h0' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:864:38: warning: unused variable 'h1' [-Wunused-variable]
ntt.c: ...
Number of similar (implementation,compiler) pairs: 1, namely:
| Implementation | Compiler |
| round2 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
Compiler output
ntt.c: ntt.c:562:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:562:38: warning: unused variable 'h1' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:562:35: warning: unused variable 'h0' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:562:44: warning: unused variable 'h3' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:864:35: warning: unused variable 'h0' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:864:44: warning: unused variable 'h3' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:864:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:865:10: warning: unused variable 'origf' [-Wunused-variable]
ntt.c: int16 *origf = f;
ntt.c: ^
ntt.c: ntt.c:864:38: warning: unused variable 'h1' [-Wunused-variable]
ntt.c: ...
Number of similar (implementation,compiler) pairs: 1, namely:
| Implementation | Compiler |
| round2 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
Compiler output
ntt.c: ntt.c:562:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:562:38: warning: unused variable 'h1' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:562:35: warning: unused variable 'h0' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:562:44: warning: unused variable 'h3' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:864:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:864:44: warning: unused variable 'h3' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:864:35: warning: unused variable 'h0' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:864:38: warning: unused variable 'h1' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:865:10: warning: unused variable 'origf' [-Wunused-variable]
ntt.c: ...
Number of similar (implementation,compiler) pairs: 1, namely:
| Implementation | Compiler |
| round2 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
Compiler output
ntt.c: ntt.c:562:44: warning: unused variable 'h3' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:562:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:562:38: warning: unused variable 'h1' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:562:35: warning: unused variable 'h0' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:864:38: warning: unused variable 'h1' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:864:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:864:44: warning: unused variable 'h3' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:864:35: warning: unused variable 'h0' [-Wunused-variable]
ntt.c: __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ^
ntt.c: ntt.c:865:10: warning: unused variable 'origf' [-Wunused-variable]
ntt.c: ...
Number of similar (implementation,compiler) pairs: 1, namely:
| Implementation | Compiler |
| round2 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
Compiler output
mult768.c: mult768.c:266:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup761_round2_constbranchindex' that is compiled without support for 'avx'
mult768.c: x = const_x16(0);
mult768.c: ^
mult768.c: mult768.c:10:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c: ^
mult768.c: mult768.c:266:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:10:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c: ^
mult768.c: mult768.c:267:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup761_round2_constbranchindex' that is compiled without support for 'avx'
mult768.c: for (i = p&~15;i < 768;i += 16) store_x16(&f[i],x);
mult768.c: ^
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c: ^
mult768.c: mult768.c:267:35: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c: ^
mult768.c: mult768.c:268:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup761_round2_constbranchindex' that is compiled without support for 'avx'
mult768.c: for (i = p&~15;i < 768;i += 16) store_x16(&g[i],x);
mult768.c: ^
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c: ...
Number of similar (implementation,compiler) pairs: 1, namely:
| Implementation | Compiler |
| round2 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
Compiler output
ntt.c: ntt.c: In function 'ntt512':
ntt.c: ntt.c:562:44: warning: unused variable 'h3' [-Wunused-variable]
ntt.c: 562 | __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: | ^~
ntt.c: ntt.c:562:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c: 562 | __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: | ^~
ntt.c: ntt.c:562:38: warning: unused variable 'h1' [-Wunused-variable]
ntt.c: 562 | __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: | ^~
ntt.c: ntt.c:562:35: warning: unused variable 'h0' [-Wunused-variable]
ntt.c: 562 | __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: | ^~
ntt.c: ntt.c: In function 'invntt512':
ntt.c: ntt.c:865:10: warning: unused variable 'origf' [-Wunused-variable]
ntt.c: 865 | int16 *origf = f;
ntt.c: | ^~~~~
ntt.c: ntt.c:864:44: warning: unused variable 'h3' [-Wunused-variable]
ntt.c: 864 | __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: | ^~
ntt.c: ntt.c:864:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c: 864 | __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: | ^~
ntt.c: ntt.c:864:38: warning: unused variable 'h1' [-Wunused-variable]
ntt.c: 864 | __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ...
Number of similar (implementation,compiler) pairs: 4, namely:
| Implementation | Compiler |
| round2 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
| round2 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
| round2 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
| round2 | gcc -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: 29, namely:
| Implementation | Compiler |
| avx | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
| avx | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
| avx | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
| avx | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
| avx | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
| avx | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
| avx | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
| avx | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
| avx800 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
| avx800 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
| avx800 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
| avx800 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
| avx800 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
| avx800 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
| avx800 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
| avx800 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
| ref | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
| ref | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
| ref | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
| ref | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
| ref | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
| ref | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
| ref | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
| ref | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
| ref | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
| round1 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
| round1 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
| round1 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
| round1 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |