Implementation notes: amd64, h3neo, crypto_scalarmult/kummer
Computer: h3neo
Microarchitecture: amd64; K10 45nm (100f63)
Architecture: amd64
CPU ID: AuthenticAMD-00100f63-078bfbff
SUPERCOP version: 20240625
Operation: crypto_scalarmult
Primitive: kummer
Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
1744801 | 6834 0 0 | 28757 812 1792 | ref5u | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240706 | 20240625 |
1821672 | 14185 0 0 | 35515 852 1728 | ref5u | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240706 | 20240625 |
1822105 | 14166 0 0 | 35059 852 1728 | ref5u | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240706 | 20240625 |
1827784 | 6591 0 0 | 28485 812 1792 | ref5 | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240706 | 20240625 |
1832255 | 13943 0 0 | 35299 852 1728 | ref5 | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240706 | 20240625 |
1833101 | 13924 0 0 | 34779 852 1728 | ref5 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240706 | 20240625 |
1879366 | 4999 0 0 | 25621 812 1792 | ref5u | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240706 | 20240625 |
1879521 | 12242 0 0 | 31123 852 1728 | ref5 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240706 | 20240625 |
1880413 | 4675 0 0 | 25293 812 1792 | ref5 | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240706 | 20240625 |
1882906 | 12045 0 0 | 31995 852 1728 | ref5 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240706 | 20240625 |
1884377 | 12423 0 0 | 32403 852 1728 | ref5u | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240706 | 20240625 |
1900503 | 4343 0 0 | 22717 844 1728 | ref5 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240706 | 20240625 |
1938755 | 12476 0 0 | 31355 852 1728 | ref5u | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240706 | 20240625 |
1940811 | 4644 0 0 | 23021 844 1728 | ref5u | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240706 | 20240625 |
2004313 | 4446 0 0 | 22773 804 1760 | ref5 | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240706 | 20240625 |
2012671 | 4747 0 0 | 23125 804 1760 | ref5u | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240706 | 20240625 |
2055272 | 4768 0 0 | 24461 812 1792 | ref5 | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240706 | 20240625 |
2123924 | 5078 0 0 | 24789 812 1792 | ref5u | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240706 | 20240625 |
Test failure
error 111
Number of similar (implementation,compiler) pairs: 18, 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 | clang -mcpu=native -O3 -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) |
avx2 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
avx2 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
avx2 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
avx2 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
avx2 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
avx2 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
avx2 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
avx2 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
avx2 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
Compiler output
gfe.c: gfe.c:59:30: warning: argument 1 of type 'unsigned char *' declared as a pointer [-Warray-parameter=]
gfe.c: 59 | void gfe_pack(unsigned char *r, const gfe *x)
gfe.c: | ~~~~~~~~~~~~~~~^
gfe.c: In file included from gfe.c:1:
gfe.c: gfe.h:49:15: note: previously declared as an array 'unsigned char[16]'
gfe.c: 49 | void gfe_pack(unsigned char[16], const gfe *x);
gfe.c: | ^~~~~~~~~~~~~~~~~
gfe.c: gfe.c: In function 'fromdouble':
gfe.c: gfe.c:71:11: warning: dereferencing type-punned pointer will break strict-aliasing rules [-Wstrict-aliasing]
gfe.c: 71 | return *(unsigned long long *) &d - 0x4338000000000000;
gfe.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~
gfe.c: gfe.c: In function 'todouble':
gfe.c: gfe.c:77:11: warning: dereferencing type-punned pointer will break strict-aliasing rules [-Wstrict-aliasing]
gfe.c: 77 | return *(double *) &l - 6755399441055744.0;
gfe.c: | ^~~~~~~~~~~~~
gfe.c: gfe.c: At top level:
gfe.c: gfe.c:80:28: warning: argument 1 of type 'gfe *' declared as a pointer [-Warray-parameter=]
gfe.c: 80 | void gfe4x3limb_split(gfe *r, const gfe4x *x)
gfe.c: | ~~~~~^
gfe.c: In file included from gfe.c:1:
gfe.c: gfe.h:53:27: note: previously declared as an array 'gfe[4]'
gfe.c: 53 | void gfe4x3limb_split(gfe r[4], const gfe4x *a);
gfe.c: | ~~~~^~~~
Number of similar (implementation,compiler) pairs: 6, namely:
Implementation | Compiler |
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 -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
avx2 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
avx2 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
avx2 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
Compiler output
gfe.c: gfe.c:59:30: warning: argument 1 of type 'unsigned char *' declared as a pointer [-Warray-parameter=]
gfe.c: 59 | void gfe_pack(unsigned char *r, const gfe *x)
gfe.c: | ~~~~~~~~~~~~~~~^
gfe.c: In file included from gfe.c:1:
gfe.c: gfe.h:49:15: note: previously declared as an array 'unsigned char[16]'
gfe.c: 49 | void gfe_pack(unsigned char[16], const gfe *x);
gfe.c: | ^~~~~~~~~~~~~~~~~
gfe.c: gfe.c:80:28: warning: argument 1 of type 'gfe *' declared as a pointer [-Warray-parameter=]
gfe.c: 80 | void gfe4x3limb_split(gfe *r, const gfe4x *x)
gfe.c: | ~~~~~^
gfe.c: In file included from gfe.c:1:
gfe.c: gfe.h:53:27: note: previously declared as an array 'gfe[4]'
gfe.c: 53 | void gfe4x3limb_split(gfe r[4], const gfe4x *a);
gfe.c: | ~~~~^~~~
Number of similar (implementation,compiler) pairs: 2, namely:
Implementation | Compiler |
avx | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
avx2 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
Compiler output
smult.c: smult.c:36:8: error: always_inline function '_mm256_mul_epi32' requires target feature 'avx2', but would be inlined into function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_mulconst' that is compiled without support for 'avx2'
smult.c: t0 = _mm256_mul_epi32(a->v[0],*b);
smult.c: ^
smult.c: smult.c:36:8: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
smult.c: smult.c:37:8: error: always_inline function '_mm256_mul_epi32' requires target feature 'avx2', but would be inlined into function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_mulconst' that is compiled without support for 'avx2'
smult.c: t1 = _mm256_mul_epi32(a->v[1],*b);
smult.c: ^
smult.c: smult.c:37:8: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
smult.c: smult.c:38:30: error: always_inline function '_mm256_srli_epi64' requires target feature 'avx2', but would be inlined into function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_mulconst' that is compiled without support for 'avx2'
smult.c: t1 = _mm256_add_epi64(t1,_mm256_srli_epi64(t0,26)); t0 &= mask26;
smult.c: ^
smult.c: smult.c:38:30: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
smult.c: smult.c:38:10: error: always_inline function '_mm256_add_epi64' requires target feature 'avx2', but would be inlined into function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_mulconst' that is compiled without support for 'avx2'
smult.c: t1 = _mm256_add_epi64(t1,_mm256_srli_epi64(t0,26)); t0 &= mask26;
smult.c: ^
smult.c: smult.c:38:10: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
smult.c: smult.c:39:8: error: always_inline function '_mm256_mul_epi32' requires target feature 'avx2', but would be inlined into function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_mulconst' that is compiled without support for 'avx2'
smult.c: t2 = _mm256_mul_epi32(a->v[2],*b);
smult.c: ^
smult.c: smult.c:39:8: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
smult.c: smult.c:40:8: error: always_inline function '_mm256_mul_epi32' requires target feature 'avx2', but would be inlined into function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_mulconst' that is compiled without support for 'avx2'
smult.c: t3 = _mm256_mul_epi32(a->v[3],*b);
smult.c: ^
smult.c: smult.c:40:8: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
smult.c: smult.c:41:8: error: always_inline function '_mm256_mul_epi32' requires target feature 'avx2', but would be inlined into function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_mulconst' that is compiled without support for 'avx2'
smult.c: ...
Number of similar (implementation,compiler) pairs: 5, namely:
Implementation | Compiler |
avx2int | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
avx2int | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
avx2int | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
avx2int | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
avx2int | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
Compiler output
smult.c: smult.c: In function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_from_gfe':
smult.c: smult.c:14:6: warning: dereferencing type-punned pointer will break strict-aliasing rules [-Wstrict-aliasing]
smult.c: 14 | 0[(crypto_uint64 *) &y->v[i]] = x[0].v[i];
smult.c: | ^
smult.c: smult.c: In function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_to_gfe':
smult.c: smult.c:26:18: warning: dereferencing type-punned pointer will break strict-aliasing rules [-Wstrict-aliasing]
smult.c: 26 | x[0].v[i] = 0[(crypto_uint64 *) &y->v[i]];
smult.c: | ^
smult.c: smult.c: In function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_mulconst':
smult.c: smult.c:36:6: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
smult.c: 36 | t0 = _mm256_mul_epi32(a->v[0],*b);
smult.c: | ~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
smult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
smult.c: from gfe4x.h:5,
smult.c: from smult.c:3:
smult.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:126:1: error: inlining failed in call to 'always_inline' '_mm256_add_epi64': target specific option mismatch
smult.c: 126 | _mm256_add_epi64 (__m256i __A, __m256i __B)
smult.c: | ^~~~~~~~~~~~~~~~
smult.c: smult.c:45:10: note: called from here
smult.c: 45 | t2 = _mm256_add_epi64(t2,_mm256_srli_epi64(t1,25)); t1 &= mask25;
smult.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
smult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
smult.c: from gfe4x.h:5,
smult.c: from smult.c:3:
smult.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:787:1: error: inlining failed in call to 'always_inline' '_mm256_srli_epi64': target specific option mismatch
smult.c: ...
Number of similar (implementation,compiler) pairs: 3, namely:
Implementation | Compiler |
avx2int | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
avx2int | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
avx2int | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
Compiler output
smult.c: smult.c: In function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_mulconst':
smult.c: smult.c:36:6: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
smult.c: 36 | t0 = _mm256_mul_epi32(a->v[0],*b);
smult.c: | ~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
smult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
smult.c: from gfe4x.h:5,
smult.c: from smult.c:3:
smult.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:126:1: error: inlining failed in call to 'always_inline' '_mm256_add_epi64': target specific option mismatch
smult.c: 126 | _mm256_add_epi64 (__m256i __A, __m256i __B)
smult.c: | ^~~~~~~~~~~~~~~~
smult.c: smult.c:45:10: note: called from here
smult.c: 45 | t2 = _mm256_add_epi64(t2,_mm256_srli_epi64(t1,25)); t1 &= mask25;
smult.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
smult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
smult.c: from gfe4x.h:5,
smult.c: from smult.c:3:
smult.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:787:1: error: inlining failed in call to 'always_inline' '_mm256_srli_epi64': target specific option mismatch
smult.c: 787 | _mm256_srli_epi64 (__m256i __A, int __B)
smult.c: | ^~~~~~~~~~~~~~~~~
smult.c: smult.c:45:10: note: called from here
smult.c: 45 | t2 = _mm256_add_epi64(t2,_mm256_srli_epi64(t1,25)); t1 &= mask25;
smult.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
smult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
smult.c: from gfe4x.h:5,
smult.c: from smult.c:3:
smult.c: ...
Number of similar (implementation,compiler) pairs: 1, namely:
Implementation | Compiler |
avx2int | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
Passed TIMECOP
TIMECOP iterations: 10
Number of similar (implementation,compiler) pairs: 18, namely:
Implementation | Compiler |
ref5 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
ref5 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
ref5 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
ref5 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
ref5 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
ref5 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
ref5 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
ref5 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
ref5 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
ref5u | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
ref5u | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
ref5u | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
ref5u | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
ref5u | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
ref5u | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
ref5u | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
ref5u | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |
ref5u | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0) |