Implementation notes: amd64, jasper3, crypto_kem/lightsaber2
Computer: jasper3
Microarchitecture: amd64; Tremont (906c0)
Architecture: amd64
CPU ID: GenuineIntel-000906c0-20-bfebfbff
SUPERCOP version: 20240625
Operation: crypto_kem
Primitive: lightsaber2
| Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
|---|
| 250932 | 45422 0 0 | 63467 828 1720 | T:ref | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240702 | 20240625 |
| 266822 | 75026 0 0 | 94115 828 1720 | T:ref | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240702 | 20240625 |
| 268096 | 79659 0 0 | 100035 828 1720 | T:ref | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240702 | 20240625 |
| 583651 | 61548 0 0 | 81199 796 1752 | T:ref | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240702 | 20240625 |
| 793667 | 13802 0 0 | 30241 820 1720 | T:ref | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240702 | 20240625 |
| 824462 | 14817 0 0 | 31961 820 1720 | T:ref | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240702 | 20240625 |
| 937928 | 15681 0 0 | 34295 796 1752 | T:ref | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240702 | 20240625 |
| 969931 | 13154 0 0 | 31151 796 1752 | T:ref | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240702 | 20240625 |
| 984734 | 12468 0 0 | 28567 788 1720 | T:ref | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240702 | 20240625 |
Compiler output
SABER_indcpa.c: In file included from SABER_indcpa.c:9:
SABER_indcpa.c: In file included from ././polymul/toom-cook_4way.c:6:
SABER_indcpa.c: ././polymul/scm_avx.c:40:13: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
SABER_indcpa.c: c_avx[0] = mul_add(a0, b0, c_avx[0]);
SABER_indcpa.c: ^
SABER_indcpa.c: ././polymul/scm_avx.c:43:9: error: always_inline function '_mm256_mullo_epi16' requires target feature 'avx2', but would be inlined into function 'schoolbook_avx_new3_acc' that is compiled without support for 'avx2'
SABER_indcpa.c: temp = _mm256_mullo_epi16 (a0, b1);
SABER_indcpa.c: ^
SABER_indcpa.c: ././polymul/scm_avx.c:43:9: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
SABER_indcpa.c: ././polymul/scm_avx.c:44:7: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
SABER_indcpa.c: temp=mul_add(a1, b0, temp);
SABER_indcpa.c: ^
SABER_indcpa.c: ././polymul/scm_avx.c:45:13: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'schoolbook_avx_new3_acc' that is compiled without support for 'avx2'
SABER_indcpa.c: c_avx[1] = _mm256_add_epi16(temp, c_avx[1]);
SABER_indcpa.c: ^
SABER_indcpa.c: ././polymul/scm_avx.c:45:13: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
SABER_indcpa.c: ././polymul/scm_avx.c:48:9: error: always_inline function '_mm256_mullo_epi16' requires target feature 'avx2', but would be inlined into function 'schoolbook_avx_new3_acc' that is compiled without support for 'avx2'
SABER_indcpa.c: temp = _mm256_mullo_epi16 (a0, b2);
SABER_indcpa.c: ^
SABER_indcpa.c: ././polymul/scm_avx.c:48:9: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
SABER_indcpa.c: ././polymul/scm_avx.c:49:9: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
SABER_indcpa.c: temp = mul_add(a1, b1, temp);
SABER_indcpa.c: ^
SABER_indcpa.c: ././polymul/scm_avx.c:50:7: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
SABER_indcpa.c: temp=mul_add(a2, b0, temp);
SABER_indcpa.c: ...
Number of similar (implementation,compiler) pairs: 5, namely:
| Implementation | Compiler |
| T:avx2 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
| T:avx2 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
| T:avx2 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
| T:avx2 | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
| T:avx2 | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
Compiler output
SABER_indcpa.c: In file included from ./polymul/toom-cook_4way.c:6,
SABER_indcpa.c: from SABER_indcpa.c:9:
SABER_indcpa.c: ./polymul/scm_avx.c: In function 'mul_add':
SABER_indcpa.c: ./polymul/scm_avx.c:6:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
SABER_indcpa.c: 6 | inline __m256i mul_add(__m256i a, __m256i b, __m256i c) {
SABER_indcpa.c: | ^~~~~~
SABER_indcpa.c: SABER_indcpa.c: In function 'indcpa_kem_enc':
SABER_indcpa.c: SABER_indcpa.c:269:19: warning: unused variable 'CLOCK2' [-Wunused-variable]
SABER_indcpa.c: 269 | uint64_t CLOCK1, CLOCK2;
SABER_indcpa.c: | ^~~~~~
SABER_indcpa.c: SABER_indcpa.c:269:11: warning: unused variable 'CLOCK1' [-Wunused-variable]
SABER_indcpa.c: 269 | uint64_t CLOCK1, CLOCK2;
SABER_indcpa.c: | ^~~~~~
SABER_indcpa.c: SABER_indcpa.c: In function 'indcpa_kem_dec':
SABER_indcpa.c: SABER_indcpa.c:436:19: warning: unused variable 'CLOCK2' [-Wunused-variable]
SABER_indcpa.c: 436 | uint64_t CLOCK1, CLOCK2;
SABER_indcpa.c: | ^~~~~~
SABER_indcpa.c: SABER_indcpa.c:436:11: warning: unused variable 'CLOCK1' [-Wunused-variable]
SABER_indcpa.c: 436 | uint64_t CLOCK1, CLOCK2;
SABER_indcpa.c: | ^~~~~~
SABER_indcpa.c: In file included from ./polymul/toom-cook_4way.c:6,
SABER_indcpa.c: from SABER_indcpa.c:9:
SABER_indcpa.c: ./polymul/scm_avx.c: In function 'mul_add':
SABER_indcpa.c: ./polymul/scm_avx.c:6:16: note: the ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
SABER_indcpa.c: 6 | inline __m256i mul_add(__m256i a, __m256i b, __m256i c) {
SABER_indcpa.c: ...
Number of similar (implementation,compiler) pairs: 4, namely:
| Implementation | Compiler |
| T:avx2 | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
| T:avx2 | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
| T:avx2 | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
| T:avx2 | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
Compiler output
poly.c: poly.c:31:26: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'nttmul_poly_crt' that is compiled without support for 'avx'
poly.c: const __m256i u_pinv = _mm256_set1_epi16(CRT_U_PINV);
poly.c: ^
poly.c: poly.c:31:26: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
poly.c: poly.c:32:21: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'nttmul_poly_crt' that is compiled without support for 'avx'
poly.c: const __m256i u = _mm256_set1_epi16(CRT_U);
poly.c: ^
poly.c: poly.c:32:21: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
poly.c: poly.c:33:22: error: always_inline function '_mm256_load_si256' requires target feature 'avx', but would be inlined into function 'nttmul_poly_crt' that is compiled without support for 'avx'
poly.c: const __m256i p0 = _mm256_load_si256((__m256i *)&PDATA0[_16XP]);
poly.c: ^
poly.c: poly.c:33:22: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
poly.c: poly.c:34:22: error: always_inline function '_mm256_load_si256' requires target feature 'avx', but would be inlined into function 'nttmul_poly_crt' that is compiled without support for 'avx'
poly.c: const __m256i p1 = _mm256_load_si256((__m256i *)&PDATA1[_16XP]);
poly.c: ^
poly.c: poly.c:34:22: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
poly.c: poly.c:35:23: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'nttmul_poly_crt' that is compiled without support for 'avx'
poly.c: const __m256i mod = _mm256_set1_epi16(KEM_Q-1);
poly.c: ^
poly.c: poly.c:35:23: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
poly.c: poly.c:36:30: error: always_inline function '_mm256_load_si256' requires target feature 'avx', but would be inlined into function 'nttmul_poly_crt' that is compiled without support for 'avx'
poly.c: const __m256i mont0_pinv = _mm256_load_si256((__m256i *)&PDATA0[_16XMONT_PINV]);
poly.c: ^
poly.c: poly.c:36:30: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
poly.c: poly.c:37:25: error: always_inline function '_mm256_load_si256' requires target feature 'avx', but would be inlined into function 'nttmul_poly_crt' that is compiled without support for 'avx'
poly.c: ...
Number of similar (implementation,compiler) pairs: 5, namely:
| Implementation | Compiler |
| T:avx2_nttmul | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
| T:avx2_nttmul | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
| T:avx2_nttmul | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
| T:avx2_nttmul | clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
| T:avx2_nttmul | clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1) |
Compiler output
poly.c: poly.c: In function 'mulmod':
poly.c: poly.c:7:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
poly.c: 7 | static inline __m256i mulmod(const __m256i a, const __m256i b_pinv, const __m256i b, const __m256i p) {
poly.c: | ^~~~~~
poly.c: poly.c:7:23: note: the ABI for passing parameters with 32-byte alignment has changed in GCC 4.6
poly.c: 7 | static inline __m256i mulmod(const __m256i a, const __m256i b_pinv, const __m256i b, const __m256i p) {
poly.c: | ^~~~~~
poly.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:53,
poly.c: from poly.c:3:
poly.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
poly.c: 808 | _mm256_sub_epi16 (__m256i __A, __m256i __B)
poly.c: | ^~~~~~~~~~~~~~~~
poly.c: poly.c:12:7: note: called from here
poly.c: 12 | t = _mm256_sub_epi16(u,t);
poly.c: | ^~~~~~~~~~~~~~~~~~~~~
poly.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:53,
poly.c: from poly.c:3:
poly.c: /usr/lib/gcc/x86_64-linux-gnu/10/include/avx2intrin.h:546:1: error: inlining failed in call to 'always_inline' '_mm256_mulhi_epi16': target specific option mismatch
poly.c: 546 | _mm256_mulhi_epi16 (__m256i __A, __m256i __B)
poly.c: | ^~~~~~~~~~~~~~~~~~
poly.c: poly.c:11:7: note: called from here
poly.c: 11 | t = _mm256_mulhi_epi16(t,p);
poly.c: | ^~~~~~~~~~~~~~~~~~~~~~~
poly.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:53,
poly.c: from poly.c:3:
poly.c: ...
Number of similar (implementation,compiler) pairs: 4, namely:
| Implementation | Compiler |
| T:avx2_nttmul | gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
| T:avx2_nttmul | gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
| T:avx2_nttmul | gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |
| T:avx2_nttmul | gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110) |