Implementation notes: amd64, genji548, crypto_sign/picnicl5fs

Computer: genji548
Architecture: amd64
CPU ID: GenuineIntel-00050654-bfebfbff
SUPERCOP version: 20191017
Operation: crypto_sign
Primitive: picnicl5fs
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
34682084193180 2768 16311472 3648 1696optimizedct/avx2gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
38883704179960 2768 16295464 3648 1696optimizedct/avx2gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
39236708177234 2768 16292896 3648 1696optimizedct/avx2gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
40002062168765 2768 16283208 3640 1664optimizedct/avx2gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
64298998180075 2768 16223304 3640 1664optimizedct/sse2gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
65289550170001 2768 16210632 3640 1664optimizedct/sse2gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
66938850172716 2768 16213136 3640 1664optimizedct/sse2gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
68172796160164 2768 16199488 3632 1632optimizedct/sse2gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
74088706173783 2768 16216728 3640 1664optimizedct/cgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
83938994184928 1792 16230805 2712 1632optimizedct/cicc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer2019101920191017
83972430184912 1792 16230805 2712 1632optimizedct/cicc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer2019101920191017
84005352184912 1792 16230805 2712 1632optimizedct/cicc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer2019101920191017
84325750186248 1792 16232437 2712 1664optimizedct/cicc_-march=skylake-avx512_-mtune=skylake-avx512_-O2_-fomit-frame-pointer2019101920191017
84375736184928 1792 16230805 2712 1632optimizedct/cicc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer2019101920191017
84412696187720 1792 16233229 2712 1632optimizedct/cicc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer2019101920191017
84416902187720 1792 16233229 2712 1632optimizedct/cicc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer2019101920191017
84439602187720 1792 16233229 2712 1632optimizedct/cicc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer2019101920191017
84458768187720 1792 16233229 2712 1632optimizedct/cicc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer2019101920191017
84500604189184 1792 16235261 2712 1664optimizedct/cicc_-march=skylake-avx512_-mtune=skylake-avx512_-O3_-fomit-frame-pointer2019101920191017
92329680183168 1792 16227397 2712 1632optimizedct/cicc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer2019101920191017
93246216183312 1792 16228853 2712 1632optimizedct/cicc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer2019101920191017
93285654183312 1792 16228853 2712 1632optimizedct/cicc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer2019101920191017
93313454183312 1792 16228853 2712 1632optimizedct/cicc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer2019101920191017
93848388186064 1792 16231653 2712 1632optimizedct/cicc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer2019101920191017
93876134186064 1792 16231653 2712 1632optimizedct/cicc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer2019101920191017
93895900186064 1792 16231653 2712 1632optimizedct/cicc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer2019101920191017
93920676186064 1792 16231653 2712 1632optimizedct/cicc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer2019101920191017
94022262183312 1792 16228853 2712 1632optimizedct/cicc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer2019101920191017
94154614186032 1792 16230333 2712 1632optimizedct/cicc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer2019101920191017
102486888166016 2768 16206416 3640 1664optimizedct/cgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
113530752156739 2768 16195824 3632 1632optimizedct/cgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
129023964165436 2768 16205600 3640 1664optimizedct/cgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
12027758521097228 4 01142508 944 1600reficc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer2019101920191017
12042541781097228 4 01142508 944 1600reficc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer2019101920191017
12044175621097228 4 01142508 944 1600reficc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer2019101920191017
12048118721097228 4 01142508 944 1600reficc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer2019101920191017
12178702201093204 4 01137124 944 1600reficc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer2019101920191017
12337280321108600 4 01154180 944 1600reficc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer2019101920191017
12338256361108600 4 01154180 944 1600reficc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer2019101920191017
12360837681108600 4 01154180 944 1600reficc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer2019101920191017
12388811641108600 4 01154180 944 1600reficc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer2019101920191017
12548965121116512 4 01162356 944 1632reficc_-march=skylake-avx512_-mtune=skylake-avx512_-O2_-fomit-frame-pointer2019101920191017
13749148041064778 4 01107535 896 1632refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
13805756801099028 4 01144292 944 1600reficc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer2019101920191017
13815564261099028 4 01144292 944 1600reficc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer2019101920191017
13824929981099028 4 01144292 944 1600reficc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer2019101920191017
13828735721099028 4 01144292 944 1600reficc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer2019101920191017
13842842981093980 4 01137972 944 1600reficc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer2019101920191017
14338502961110008 4 01156092 944 1632reficc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer2019101920191017
14407945921110304 4 01155500 944 1600reficc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer2019101920191017
14410353161110304 4 01155500 944 1600reficc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer2019101920191017
14410618741110304 4 01155500 944 1600reficc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer2019101920191017
14438757661110304 4 01155500 944 1600reficc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer2019101920191017
14657293901046231 4 01086447 896 1632refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
14864498881116520 4 01162300 944 1632reficc_-march=skylake-avx512_-mtune=skylake-avx512_-O3_-fomit-frame-pointer2019101920191017
15704929001041223 4 01081207 896 1632refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017
16013555121109672 4 01156124 944 1632reficc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer2019101920191017
20155664161035912 4 01074919 888 1600refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019101920191017

Test failure

Implementation: crypto_sign/picnicl5fs/optimizedct/c
Compiler: icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer
error 111

Number of similar (compiler,implementation) pairs: 6, namely:
CompilerImplementations
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer optimizedct/c ref
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer optimizedct/c ref
icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer optimizedct/c
icc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer optimizedct/c

Compiler output

Implementation: crypto_sign/picnicl5fs/optimizedct/c
Compiler: icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer
io.c: In file included from io.h(16),
io.c: from io.c(11):
io.c: mzd_additional.h(39): warning #1292: unknown attribute "assume_aligned"
io.c: mzd_local_t* mzd_local_init_ex(uint32_t r, uint32_t c, bool clear) ATTR_ASSUME_ALIGNED(32);
io.c: ^
io.c:
lowmc.c: In file included from io.h(16),
lowmc.c: from lowmc.c(11):
lowmc.c: mzd_additional.h(39): warning #1292: unknown attribute "assume_aligned"
lowmc.c: mzd_local_t* mzd_local_init_ex(uint32_t r, uint32_t c, bool clear) ATTR_ASSUME_ALIGNED(32);
lowmc.c: ^
lowmc.c:
lowmc_256_256_38.c: In file included from lowmc_pars.h(15),
lowmc_256_256_38.c: from lowmc_256_256_38.h(4),
lowmc_256_256_38.c: from lowmc_256_256_38.c(4):
lowmc_256_256_38.c: mzd_additional.h(39): warning #1292: unknown attribute "assume_aligned"
lowmc_256_256_38.c: mzd_local_t* mzd_local_init_ex(uint32_t r, uint32_t c, bool clear) ATTR_ASSUME_ALIGNED(32);
lowmc_256_256_38.c: ^
lowmc_256_256_38.c:
mpc_lowmc.c: In file included from lowmc_pars.h(15),
mpc_lowmc.c: from lowmc.h(13),
mpc_lowmc.c: from mpc_lowmc.h(15),
mpc_lowmc.c: from mpc_lowmc.c(11):
mpc_lowmc.c: mzd_additional.h(39): warning #1292: unknown attribute "assume_aligned"
mpc_lowmc.c: mzd_local_t* mzd_local_init_ex(uint32_t r, uint32_t c, bool clear) ATTR_ASSUME_ALIGNED(32);
mpc_lowmc.c: ^
mpc_lowmc.c:
mzd_additional.c: In file included from mzd_additional.c(12):
mzd_additional.c: mzd_additional.h(39): warning #1292: unknown attribute "assume_aligned"
mzd_additional.c: mzd_local_t* mzd_local_init_ex(uint32_t r, uint32_t c, bool clear) ATTR_ASSUME_ALIGNED(32);
mzd_additional.c: ^
mzd_additional.c:
picnic.c: In file included from io.h(16),
picnic.c: from picnic.c(16):
picnic.c: mzd_additional.h(39): warning #1292: unknown attribute "assume_aligned"
picnic.c: mzd_local_t* mzd_local_init_ex(uint32_t r, uint32_t c, bool clear) ATTR_ASSUME_ALIGNED(32);
picnic.c: ^
picnic.c:
picnic_impl.c: In file included from io.h(16),
picnic_impl.c: from picnic_impl.c(13):
picnic_impl.c: mzd_additional.h(39): warning #1292: unknown attribute "assume_aligned"
picnic_impl.c: mzd_local_t* mzd_local_init_ex(uint32_t r, uint32_t c, bool clear) ATTR_ASSUME_ALIGNED(32);
picnic_impl.c: ^
picnic_impl.c:
picnic_instances.c: In file included from lowmc_pars.h(15),
picnic_instances.c: from lowmc.h(13),
picnic_instances.c: from picnic_instances.h(13),
picnic_instances.c: from picnic_instances.c(11):
picnic_instances.c: mzd_additional.h(39): warning #1292: unknown attribute "assume_aligned"
picnic_instances.c: mzd_local_t* mzd_local_init_ex(uint32_t r, uint32_t c, bool clear) ATTR_ASSUME_ALIGNED(32);
picnic_instances.c: ^
picnic_instances.c:

Number of similar (compiler,implementation) pairs: 24, namely:
CompilerImplementations
icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer optimizedct/c
icc -march=broadwell -mtune=broadwell -O3 -fomit-frame-pointer optimizedct/c
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer optimizedct/c
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer optimizedct/c
icc -march=core-avx-i -mtune=core-avx-i -O2 -fomit-frame-pointer optimizedct/c
icc -march=core-avx-i -mtune=core-avx-i -O3 -fomit-frame-pointer optimizedct/c
icc -march=core-avx2 -mtune=core-avx2 -O2 -fomit-frame-pointer optimizedct/c
icc -march=core-avx2 -mtune=core-avx2 -O3 -fomit-frame-pointer optimizedct/c
icc -march=corei7-avx -mtune=corei7-avx -O2 -fomit-frame-pointer optimizedct/c
icc -march=corei7-avx -mtune=corei7-avx -O3 -fomit-frame-pointer optimizedct/c
icc -march=corei7 -mtune=corei7 -O2 -fomit-frame-pointer optimizedct/c
icc -march=corei7 -mtune=corei7 -O3 -fomit-frame-pointer optimizedct/c
icc -march=haswell -mtune=haswell -O2 -fomit-frame-pointer optimizedct/c
icc -march=haswell -mtune=haswell -O3 -fomit-frame-pointer optimizedct/c
icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer optimizedct/c
icc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer optimizedct/c
icc -march=ivybridge -mtune=ivybridge -O2 -fomit-frame-pointer optimizedct/c
icc -march=ivybridge -mtune=ivybridge -O3 -fomit-frame-pointer optimizedct/c
icc -march=sandybridge -mtune=sandybridge -O2 -fomit-frame-pointer optimizedct/c
icc -march=sandybridge -mtune=sandybridge -O3 -fomit-frame-pointer optimizedct/c
icc -march=skylake-avx512 -mtune=skylake-avx512 -O2 -fomit-frame-pointer optimizedct/c
icc -march=skylake-avx512 -mtune=skylake-avx512 -O3 -fomit-frame-pointer optimizedct/c
icc -march=skylake -mtune=skylake -O2 -fomit-frame-pointer optimizedct/c
icc -march=skylake -mtune=skylake -O3 -fomit-frame-pointer optimizedct/c

Compiler output

Implementation: crypto_sign/picnicl5fs/optimizedct/sse2
Compiler: icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer
io.c: In file included from mzd_additional.h(24),
io.c: from io.h(16),
io.c: from io.c(11):
io.c: simd.h(105): warning #2423: target not recognized
io.c: apply_region(mm128_xor_region, word128, mm128_xor, FN_ATTRIBUTES_SSE2);
io.c: ^
io.c:
io.c: In file included from mzd_additional.h(24),
io.c: from io.h(16),
io.c: from io.c(11):
io.c: simd.h(106): warning #2423: target not recognized
io.c: apply_mask_region(mm128_xor_mask_region, word128, mm128_xor, mm128_and, FN_ATTRIBUTES_SSE2);
io.c: ^
io.c:
io.c: In file included from mzd_additional.h(24),
io.c: from io.h(16),
io.c: from io.c(11):
io.c: simd.h(107): warning #2423: target not recognized
io.c: apply_mask(mm128_xor_mask, word128, mm128_xor, mm128_and, FN_ATTRIBUTES_SSE2_CONST);
io.c: ^
io.c:
io.c: In file included from mzd_additional.h(24),
io.c: from io.h(16),
io.c: from io.c(11):
io.c: simd.h(108): warning #2423: target not recognized
io.c: ...

Number of similar (compiler,implementation) pairs: 24, namely:
CompilerImplementations
icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer optimizedct/sse2
icc -march=broadwell -mtune=broadwell -O3 -fomit-frame-pointer optimizedct/sse2
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer optimizedct/sse2
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer optimizedct/sse2
icc -march=core-avx-i -mtune=core-avx-i -O2 -fomit-frame-pointer optimizedct/sse2
icc -march=core-avx-i -mtune=core-avx-i -O3 -fomit-frame-pointer optimizedct/sse2
icc -march=core-avx2 -mtune=core-avx2 -O2 -fomit-frame-pointer optimizedct/sse2
icc -march=core-avx2 -mtune=core-avx2 -O3 -fomit-frame-pointer optimizedct/sse2
icc -march=corei7-avx -mtune=corei7-avx -O2 -fomit-frame-pointer optimizedct/sse2
icc -march=corei7-avx -mtune=corei7-avx -O3 -fomit-frame-pointer optimizedct/sse2
icc -march=corei7 -mtune=corei7 -O2 -fomit-frame-pointer optimizedct/sse2
icc -march=corei7 -mtune=corei7 -O3 -fomit-frame-pointer optimizedct/sse2
icc -march=haswell -mtune=haswell -O2 -fomit-frame-pointer optimizedct/sse2
icc -march=haswell -mtune=haswell -O3 -fomit-frame-pointer optimizedct/sse2
icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer optimizedct/sse2
icc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer optimizedct/sse2
icc -march=ivybridge -mtune=ivybridge -O2 -fomit-frame-pointer optimizedct/sse2
icc -march=ivybridge -mtune=ivybridge -O3 -fomit-frame-pointer optimizedct/sse2
icc -march=sandybridge -mtune=sandybridge -O2 -fomit-frame-pointer optimizedct/sse2
icc -march=sandybridge -mtune=sandybridge -O3 -fomit-frame-pointer optimizedct/sse2
icc -march=skylake-avx512 -mtune=skylake-avx512 -O2 -fomit-frame-pointer optimizedct/sse2
icc -march=skylake-avx512 -mtune=skylake-avx512 -O3 -fomit-frame-pointer optimizedct/sse2
icc -march=skylake -mtune=skylake -O2 -fomit-frame-pointer optimizedct/sse2
icc -march=skylake -mtune=skylake -O3 -fomit-frame-pointer optimizedct/sse2

Compiler output

Implementation: crypto_sign/picnicl5fs/optimizedct/avx2
Compiler: icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer
io.c: In file included from mzd_additional.h(24),
io.c: from io.h(16),
io.c: from io.c(11):
io.c: simd.h(96): warning #47: incompatible redefinition of macro "_mm256_set_m128i" (declared at line 1575 of "/opt/intel/compilers_and_libraries_2019.4.243/linux/compiler/include/icc/immintrin.h")
io.c: #define _mm256_set_m128i(v0, v1) _mm256_insertf128_si256(_mm256_castsi128_si256(v1), (v0), 1)
io.c: ^
io.c:
io.c: In file included from mzd_additional.h(24),
io.c: from io.h(16),
io.c: from io.c(11):
io.c: simd.h(97): warning #47: incompatible redefinition of macro "_mm256_setr_m128i" (declared at line 1601 of "/opt/intel/compilers_and_libraries_2019.4.243/linux/compiler/include/icc/immintrin.h")
io.c: #define _mm256_setr_m128i(v0, v1) _mm256_set_m128i((v1), (v0))
io.c: ^
io.c:
io.c: In file included from mzd_additional.h(24),
io.c: from io.h(16),
io.c: from io.c(11):
io.c: simd.h(106): warning #2423: target not recognized
io.c: apply_region(mm256_xor_region, word256, mm256_xor, FN_ATTRIBUTES_AVX2);
io.c: ^
io.c:
io.c: In file included from mzd_additional.h(24),
io.c: from io.h(16),
io.c: from io.c(11):
io.c: simd.h(107): warning #2423: target not recognized
io.c: ...

Number of similar (compiler,implementation) pairs: 24, namely:
CompilerImplementations
icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer optimizedct/avx2
icc -march=broadwell -mtune=broadwell -O3 -fomit-frame-pointer optimizedct/avx2
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer optimizedct/avx2
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer optimizedct/avx2
icc -march=core-avx-i -mtune=core-avx-i -O2 -fomit-frame-pointer optimizedct/avx2
icc -march=core-avx-i -mtune=core-avx-i -O3 -fomit-frame-pointer optimizedct/avx2
icc -march=core-avx2 -mtune=core-avx2 -O2 -fomit-frame-pointer optimizedct/avx2
icc -march=core-avx2 -mtune=core-avx2 -O3 -fomit-frame-pointer optimizedct/avx2
icc -march=corei7-avx -mtune=corei7-avx -O2 -fomit-frame-pointer optimizedct/avx2
icc -march=corei7-avx -mtune=corei7-avx -O3 -fomit-frame-pointer optimizedct/avx2
icc -march=corei7 -mtune=corei7 -O2 -fomit-frame-pointer optimizedct/avx2
icc -march=corei7 -mtune=corei7 -O3 -fomit-frame-pointer optimizedct/avx2
icc -march=haswell -mtune=haswell -O2 -fomit-frame-pointer optimizedct/avx2
icc -march=haswell -mtune=haswell -O3 -fomit-frame-pointer optimizedct/avx2
icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer optimizedct/avx2
icc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer optimizedct/avx2
icc -march=ivybridge -mtune=ivybridge -O2 -fomit-frame-pointer optimizedct/avx2
icc -march=ivybridge -mtune=ivybridge -O3 -fomit-frame-pointer optimizedct/avx2
icc -march=sandybridge -mtune=sandybridge -O2 -fomit-frame-pointer optimizedct/avx2
icc -march=sandybridge -mtune=sandybridge -O3 -fomit-frame-pointer optimizedct/avx2
icc -march=skylake-avx512 -mtune=skylake-avx512 -O2 -fomit-frame-pointer optimizedct/avx2
icc -march=skylake-avx512 -mtune=skylake-avx512 -O3 -fomit-frame-pointer optimizedct/avx2
icc -march=skylake -mtune=skylake -O2 -fomit-frame-pointer optimizedct/avx2
icc -march=skylake -mtune=skylake -O3 -fomit-frame-pointer optimizedct/avx2