Implementation notes: amd64, samba, crypto_scalarmult/kummer

Computer: samba
Microarchitecture: amd64; Skylake (506e3)
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20240107
Operation: crypto_scalarmult
Primitive: kummer

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
213152	18821 0 0	44547 852 1792	`avx2int`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
213253	21269 0 0	47291 852 1824	`avx2int`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
213933	15419 0 0	41117 812 1824	`avx2int`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
228315	17423 0 0	39467 852 1760	`avx2int`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
228930	8493 0 0	31365 844 1824	`avx2int`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
244298	9601 0 0	33141 812 1824	`avx2int`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
247779	9170 0 0	31853 812 1824	`avx2int`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
249112	6525 0 0	28013 804 1792	`avx2int`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
262903	8449 0 0	31429 844 1824	`avx2`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
263468	8934 0 0	32469 812 1824	`avx2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
263525	8587 0 0	30779 852 1760	`avx2`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
263555	9150 0 0	34821 812 1824	`avx2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
263890	8891 0 0	33347 852 1760	`avx2`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
264077	9083 0 0	35299 852 1824	`avx2`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
264526	8765 0 0	30245 804 1792	`avx2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
264541	9083 0 0	35019 852 1792	`avx2`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
264887	9000 0 0	31669 812 1824	`avx2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
352597	9273 0 0	31451 852 1760	`avx`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
352984	9135 0 0	32101 844 1824	`avx`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
353791	? ? ?	? ? ?	`avx`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
354499	9451 0 0	30917 804 1792	`avx`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
354841	9620 0 0	33141 812 1824	`avx`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
355007	9577 0 0	33987 852 1760	`avx`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
355864	9769 0 0	35691 852 1792	`avx`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
822303	13746 0 0	39875 852 1824	`ref5u`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
854122	4291 0 0	27189 844 1824	`ref5u`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
855860	12215 0 0	38051 852 1792	`ref5u`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
865672	13943 0 0	38275 852 1760	`ref5`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
873559	13716 0 0	39811 852 1824	`ref5`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
889395	14185 0 0	38515 852 1760	`ref5u`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
897302	4552 0 0	27997 812 1824	`ref5`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
909378	12243 0 0	34299 852 1760	`ref5`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
911089	12045 0 0	37843 852 1792	`ref5`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
924030	4341 0 0	27245 844 1824	`ref5`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
931531	6470 0 0	32045 812 1824	`ref5`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
946886	4857 0 0	28317 812 1824	`ref5u`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
969260	6826 0 0	32429 812 1824	`ref5u`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
978181	12477 0 0	34539 852 1760	`ref5u`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231213	20231212
995584	4448 0 0	25845 804 1792	`ref5`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
1043167	4734 0 0	26141 804 1792	`ref5u`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
1044389	4757 0 0	27341 812 1824	`ref5`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
1099819	5076 0 0	27677 812 1824	`ref5u`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212

Compiler output

Implementation: avx
Security model: constbranchindex
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

try.c: /usr/bin/ld: can not read symbols: file truncated
try.c: /usr/bin/ld: .eh_frame/.stab edit: file truncated
try.c: /usr/bin/ld: try-small: warning: allocated section `.interp' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.note.gnu.property' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.note.gnu.build-id' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.note.ABI-tag' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.gnu.hash' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.dynsym' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.dynstr' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.gnu.version' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.gnu.version_r' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.rela.dyn' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.rela.plt' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.init' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.plt' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.plt.got' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.text' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.fini' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.rodata' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.eh_frame' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.init_array' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.fini_array' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.dynamic' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.got' not in segment
try.c: /usr/bin/ld: try-small: warning: allocated section `.got.plt' not in segment
try.c: ...

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx

Compiler output

Implementation: avx
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE

measure.c: /usr/bin/ld: failed to set dynamic section sizes: file truncated
measure.c: collect2: error: ld returned 1 exit status

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx

Compiler output

Implementation: avx
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE

try.c: /usr/bin/ld: /home/djb/benchmarking/supercop-20231212/supercop-data/samba/amd64/lib/libsupercop.a(crypto_rng_chacha20_ref_constbranchindex-rng.o) symbol number 2 references nonexistent SHT_SYMTAB_SHNDX section
try.c: /usr/bin/ld: failed to set dynamic section sizes: Success
try.c: collect2: error: ld returned 1 exit status

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	avx

Compiler output

Implementation: avx2int
Security model: constbranchindex
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

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 (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2int