Implementation notes: amd64, lucienne, crypto_core/mult3sntrup653

Computer: lucienne
Microarchitecture: amd64; Zen 2 (860f81)
Architecture: amd64
CPU ID: AuthenticAMD-00860f81-178bfbff
SUPERCOP version: 20240808
Operation: crypto_core
Primitive: mult3sntrup653

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
11177	18913 0 0	30216 812 952	`avx`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
11224	16290 0 0	29952 812 952	`avx800`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
11249	15352 0 0	28896 812 952	`avx800`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
11278	17959 0 0	29144 812 952	`avx`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
11656	15603 0 0	27808 812 952	`round2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
11722	15609 0 0	29408 780 984	`avx`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
11738	14416 0 0	28264 780 984	`avx800`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
11813	16541 0 0	28864 812 952	`round2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
12243	15591 0 0	29448 780 984	`round2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
12289	13699 0 0	25455 772 984	`avx800`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
12398	13718 0 0	25912 780 984	`avx800`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
12409	13269 0 0	24494 804 920	`avx800`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
12462	14911 0 0	27056 780 984	`avx`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
12537	15180 0 0	24382 804 920	`avx`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
12538	14789 0 0	26487 772 984	`avx`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
12624	11081 0 0	21758 804 920	`round2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
13033	10749 0 0	22527 772 984	`round2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
13125	12797 0 0	24984 780 984	`round2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
13302	13365 0 0	24051 756 952	`avx800`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
13309	11132 0 0	21827 756 952	`round2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
13459	14110 0 0	24739 756 952	`avx`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
17313	13923 0 0	25374 804 920	`avx800`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
38390	16052 0 0	27198 804 920	`round2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
40343	26324 0 0	35654 804 920	`avx`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
70058	5443 0 0	19176 812 952	`compact`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
73727	4044 0 0	17640 812 952	`compact`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
81897	1821 0 0	15672 780 984	`compact`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
117032	1906 0 0	15808 812 920	`compact`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
125222	4563 0 0	18432 780 984	`ref`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
179211	1248 0 0	14872 812 952	`ref`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
179733	1248 0 0	15000 812 952	`ref`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
225774	1118 0 0	15008 812 920	`ref`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
928788	511 0 0	12046 804 920	`compact`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
929286	363 0 0	11646 804 920	`compact`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1015550	471 0 0	11750 804 920	`ref`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1068523	607 0 0	12142 804 920	`ref`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1123651	589 0 0	12744 780 984	`ref`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1125020	476 0 0	11131 756 952	`ref`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1520644	607 0 0	12327 772 984	`ref`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1718560	422 0 0	12584 780 984	`compact`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1724714	342 0 0	11003 756 952	`compact`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
2011983	412 0 0	12135 772 984	`compact`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808

Compiler output

mult768.c: mult768.c:209:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup653_avx_constbranchindex' that is compiled without support for 'avx'
mult768.c:   x = const_x16(0);
mult768.c:       ^
mult768.c: mult768.c:11:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:209:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:11:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:210:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup653_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:10:24: 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:210:35: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:10:24: 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:211:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup653_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:10:24: 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 (Debian_Clang_11.0.1)`

Compiler output

mult768.c: mult768.c:209:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup653_avx800_constbranchindex' that is compiled without support for 'avx'
mult768.c:   x = const_x16(0);
mult768.c:       ^
mult768.c: mult768.c:11:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:209:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:11:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:210:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup653_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:10:24: 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:210:35: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:10:24: 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:211:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup653_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:10:24: 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 (Debian_Clang_11.0.1)`

Compiler output

ntt.c: ntt.c:444:38: 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:444:35: 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:444:44: 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:444:41: 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:741:41: 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:742:10: warning: unused variable 'origf' [-Wunused-variable]
ntt.c:   int16 *origf = f;
ntt.c:          ^
ntt.c: ntt.c:741:38: 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:741:35: 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:741:44: warning: unused variable 'h3' [-Wunused-variable]
ntt.c: ...

Number of similar (implementation,compiler) pairs: 2, namely:

Implementation	Compiler
`round2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`round2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

Compiler output

ntt.c: ntt.c:444:35: 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:444:41: 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:444:44: 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:444:38: 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:741:35: 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:741:44: 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:741:41: 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:741:38: 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:742:10: 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 (Debian_Clang_11.0.1)`

Compiler output

ntt.c: ntt.c:444:38: 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:444:35: 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:444:44: 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:444:41: 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:741:35: 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:742:10: warning: unused variable 'origf' [-Wunused-variable]
ntt.c:   int16 *origf = f;
ntt.c:          ^
ntt.c: ntt.c:741:41: 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:741:44: 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:741:38: warning: unused variable 'h1' [-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 (Debian_Clang_11.0.1)`

Compiler output

mult768.c: mult768.c:210:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup653_round2_constbranchindex' that is compiled without support for 'avx'
mult768.c:   x = const_x16(0);
mult768.c:       ^
mult768.c: mult768.c:11:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:210:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:11:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:211:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup653_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:10:24: 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:211:35: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:10:24: 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:212:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup653_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:10:24: 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 (Debian_Clang_11.0.1)`

Compiler output

ntt.c: ntt.c: In function 'ntt512':
ntt.c: ntt.c:444:44: warning: unused variable 'h3' [-Wunused-variable]
ntt.c:   444 |   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:       |                                            ^~
ntt.c: ntt.c:444:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c:   444 |   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:       |                                         ^~
ntt.c: ntt.c:444:38: warning: unused variable 'h1' [-Wunused-variable]
ntt.c:   444 |   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:       |                                      ^~
ntt.c: ntt.c:444:35: warning: unused variable 'h0' [-Wunused-variable]
ntt.c:   444 |   __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:742:10: warning: unused variable 'origf' [-Wunused-variable]
ntt.c:   742 |   int16 *origf = f;
ntt.c:       |          ^~~~~
ntt.c: ntt.c:741:44: warning: unused variable 'h3' [-Wunused-variable]
ntt.c:   741 |   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:       |                                            ^~
ntt.c: ntt.c:741:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c:   741 |   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:       |                                         ^~
ntt.c: ntt.c:741:38: warning: unused variable 'h1' [-Wunused-variable]
ntt.c:   741 |   __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 (10.2.1_20210110)`
`round2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`round2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`round2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`

Passed TIMECOP

TIMECOP iterations: 1

Number of similar (implementation,compiler) pairs: 42, 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`	`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`	`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`	`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)`
`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)`
`round2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`round2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`round2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`round2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`round2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`round2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`round2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`round2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`