Implementation notes: amd64, genji548, crypto_sign/falcon512tree

Computer: genji548
Architecture: amd64
CPU ID: GenuineIntel-00050654-bfebfbff
SUPERCOP version: 20191017
Operation: crypto_sign
Primitive: falcon512tree

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
552764	142881 0 0	174929 840 1632	`avx2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191019	20191017
566236	88074 0 0	117825 840 1632	`avx2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191019	20191017
576338	85097 0 0	114737 840 1632	`avx2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191019	20191017
682354	72226 0 0	100969 832 1600	`avx2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191019	20191017
820448	144143 0 0	176169 840 1632	`fpu`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191019	20191017
989562	82890 0 0	112561 840 1632	`fpu`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191019	20191017
1016834	85771 0 0	115545 840 1632	`fpu`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191019	20191017
1100498	70370 0 0	99145 832 1600	`fpu`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191019	20191017
7754322	133233 0 0	165625 840 1632	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191019	20191017
7975858	94292 0 0	124105 840 1632	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191019	20191017
8082082	77251 0 0	106209 832 1600	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191019	20191017
8171330	91127 0 0	120825 840 1632	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191019	20191017
8683582	292304 0 0	327374 888 1600	`ref`	`icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer`	20191019	20191017
8688236	292304 0 0	327374 888 1600	`ref`	`icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer`	20191019	20191017
8690382	292304 0 0	327374 888 1600	`ref`	`icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer`	20191019	20191017
8696684	292304 0 0	327374 888 1600	`ref`	`icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer`	20191019	20191017
8702930	243708 0 0	278758 888 1600	`ref`	`icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer`	20191019	20191017
8705294	246652 0 0	281734 888 1600	`ref`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer`	20191019	20191017
8706826	243708 0 0	278758 888 1600	`ref`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer`	20191019	20191017
8707790	246652 0 0	281734 888 1600	`ref`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer`	20191019	20191017
8707904	239460 0 0	273198 888 1600	`ref`	`icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer`	20191019	20191017
8708262	243716 0 0	277510 888 1600	`ref`	`icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer`	20191019	20191017
8713410	243708 0 0	278758 888 1600	`ref`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer`	20191019	20191017
8713786	320696 0 0	356814 888 1632	`ref`	`icc_-march=icelake-client_-mtune=icelake-client_-O3_-fomit-frame-pointer`	20191019	20191017
8716740	246652 0 0	281734 888 1600	`ref`	`icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer`	20191019	20191017
8721596	246652 0 0	281734 888 1600	`ref`	`icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer`	20191019	20191017
8739200	288064 0 0	323534 888 1600	`ref`	`icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer`	20191019	20191017
8745000	288064 0 0	323534 888 1600	`ref`	`icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer`	20191019	20191017
8754356	288064 0 0	323534 888 1600	`ref`	`icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer`	20191019	20191017
8754498	288064 0 0	323534 888 1600	`ref`	`icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer`	20191019	20191017
8762858	296448 0 0	332102 888 1632	`ref`	`icc_-march=skylake-avx512_-mtune=skylake-avx512_-O3_-fomit-frame-pointer`	20191019	20191017
8775538	311424 0 0	347894 888 1632	`ref`	`icc_-march=icelake-client_-mtune=icelake-client_-O2_-fomit-frame-pointer`	20191019	20191017
8822374	243708 0 0	278758 888 1600	`ref`	`icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer`	20191019	20191017
8833804	291120 0 0	326886 888 1632	`ref`	`icc_-march=skylake-avx512_-mtune=skylake-avx512_-O2_-fomit-frame-pointer`	20191019	20191017

Checksum failure

Implementation: avx2
Security model: unknown
Compiler: icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer

f2f344d1b8420bf3bf6d2affab29f4d047845c43c64e59cf745783aab2245178

Number of similar (compiler,implementation) pairs: 8, namely:

Compiler	Implementations
icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer	avx2
icc -march=broadwell -mtune=broadwell -O3 -fomit-frame-pointer	avx2
icc -march=core-avx2 -mtune=core-avx2 -O2 -fomit-frame-pointer	avx2
icc -march=core-avx2 -mtune=core-avx2 -O3 -fomit-frame-pointer	avx2
icc -march=haswell -mtune=haswell -O2 -fomit-frame-pointer	avx2
icc -march=haswell -mtune=haswell -O3 -fomit-frame-pointer	avx2
icc -march=skylake -mtune=skylake -O2 -fomit-frame-pointer	avx2
icc -march=skylake -mtune=skylake -O3 -fomit-frame-pointer	avx2

Checksum failure

Implementation: avx2
Security model: unknown
Compiler: icc -march=core-avx-i -mtune=core-avx-i -O2 -fomit-frame-pointer

40f836e56b78717dbd1d52a664b897e09239e3033049cec2e75a7b70347a0016

Number of similar (compiler,implementation) pairs: 16, namely:

Compiler	Implementations
icc -march=core-avx-i -mtune=core-avx-i -O2 -fomit-frame-pointer	avx2
icc -march=core-avx-i -mtune=core-avx-i -O3 -fomit-frame-pointer	avx2
icc -march=corei7-avx -mtune=corei7-avx -O2 -fomit-frame-pointer	avx2
icc -march=corei7-avx -mtune=corei7-avx -O3 -fomit-frame-pointer	avx2
icc -march=ivybridge -mtune=ivybridge -O2 -fomit-frame-pointer	avx2
icc -march=ivybridge -mtune=ivybridge -O3 -fomit-frame-pointer	avx2
icc -march=sandybridge -mtune=sandybridge -O2 -fomit-frame-pointer	avx2
icc -march=sandybridge -mtune=sandybridge -O3 -fomit-frame-pointer	avx2
icc -march=core-avx-i -mtune=core-avx-i -O2 -fomit-frame-pointer	fpu
icc -march=core-avx-i -mtune=core-avx-i -O3 -fomit-frame-pointer	fpu
icc -march=corei7-avx -mtune=corei7-avx -O2 -fomit-frame-pointer	fpu
icc -march=corei7-avx -mtune=corei7-avx -O3 -fomit-frame-pointer	fpu
icc -march=ivybridge -mtune=ivybridge -O2 -fomit-frame-pointer	fpu
icc -march=ivybridge -mtune=ivybridge -O3 -fomit-frame-pointer	fpu
icc -march=sandybridge -mtune=sandybridge -O2 -fomit-frame-pointer	fpu
icc -march=sandybridge -mtune=sandybridge -O3 -fomit-frame-pointer	fpu

Checksum failure

Implementation: avx2
Security model: unknown
Compiler: icc -march=corei7 -mtune=corei7 -O2 -fomit-frame-pointer

c5cffd904667acd135f289376a2b7708e15b8fa354d102a6259fde1806df406d

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
icc -march=corei7 -mtune=corei7 -O2 -fomit-frame-pointer	avx2
icc -march=corei7 -mtune=corei7 -O3 -fomit-frame-pointer	avx2
icc -march=corei7 -mtune=corei7 -O2 -fomit-frame-pointer	fpu
icc -march=corei7 -mtune=corei7 -O3 -fomit-frame-pointer	fpu

Checksum failure

Implementation: avx2
Security model: unknown
Compiler: icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer

91cbf56ad8942a73c073f737ec938fd31809101a485a55a36b54d07eeaa3a320

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer	avx2
icc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer	avx2
icc -march=skylake-avx512 -mtune=skylake-avx512 -O2 -fomit-frame-pointer	avx2
icc -march=skylake-avx512 -mtune=skylake-avx512 -O3 -fomit-frame-pointer	avx2

Checksum failure

Implementation: fpu
Security model: unknown
Compiler: icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer

2b2ad6bdc988c2932919ff9630e8e5dde00cf69ec2053a7f3c9930f9640c8a94

Number of similar (compiler,implementation) pairs: 8, namely:

Compiler	Implementations
icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer	fpu
icc -march=broadwell -mtune=broadwell -O3 -fomit-frame-pointer	fpu
icc -march=core-avx2 -mtune=core-avx2 -O2 -fomit-frame-pointer	fpu
icc -march=core-avx2 -mtune=core-avx2 -O3 -fomit-frame-pointer	fpu
icc -march=haswell -mtune=haswell -O2 -fomit-frame-pointer	fpu
icc -march=haswell -mtune=haswell -O3 -fomit-frame-pointer	fpu
icc -march=skylake -mtune=skylake -O2 -fomit-frame-pointer	fpu
icc -march=skylake -mtune=skylake -O3 -fomit-frame-pointer	fpu

Checksum failure

Implementation: fpu
Security model: unknown
Compiler: icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer

b08bf89e6e7047e17ec8273397079d1b4b359a7225467139ecab4b85efd5580a

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer	fpu
icc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer	fpu
icc -march=skylake-avx512 -mtune=skylake-avx512 -O2 -fomit-frame-pointer	fpu
icc -march=skylake-avx512 -mtune=skylake-avx512 -O3 -fomit-frame-pointer	fpu

Test failure

Implementation: avx2
Security model: unknown
Compiler: icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 6, namely:

Compiler	Implementations
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer	avx2
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer	avx2
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer	fpu
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer	fpu
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer	ref
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer	ref

Compiler output

Implementation: avx2
Security model: unknown
Compiler: icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer

api.c: In file included from api.c(10):
api.c: inner.h(297): warning #3438: unsupported option is ignored
api.c: #pragma GCC optimize ("fp-contract=off")
api.c: ^
api.c:
codec.c: In file included from codec.c(32):
codec.c: inner.h(297): warning #3438: unsupported option is ignored
codec.c: #pragma GCC optimize ("fp-contract=off")
codec.c: ^
codec.c:
common.c: In file included from common.c(32):
common.c: inner.h(297): warning #3438: unsupported option is ignored
common.c: #pragma GCC optimize ("fp-contract=off")
common.c: ^
common.c:
fft.c: In file included from fft.c(32):
fft.c: inner.h(297): warning #3438: unsupported option is ignored
fft.c: #pragma GCC optimize ("fp-contract=off")
fft.c: ^
fft.c:
fpr.c: In file included from fpr.c(35):
fpr.c: inner.h(297): warning #3438: unsupported option is ignored
fpr.c: #pragma GCC optimize ("fp-contract=off")
fpr.c: ^
fpr.c:
keygen.c: In file included from keygen.c(32):
keygen.c: inner.h(297): warning #3438: unsupported option is ignored
keygen.c: #pragma GCC optimize ("fp-contract=off")
keygen.c: ^
keygen.c:
rng.c: In file included from rng.c(34):
rng.c: inner.h(297): warning #3438: unsupported option is ignored
rng.c: #pragma GCC optimize ("fp-contract=off")
rng.c: ^
rng.c:
shake.c: In file included from shake.c(34):
shake.c: inner.h(297): warning #3438: unsupported option is ignored
shake.c: #pragma GCC optimize ("fp-contract=off")
shake.c: ^
shake.c:
sign.c: In file included from sign.c(32):
sign.c: inner.h(297): warning #3438: unsupported option is ignored
sign.c: #pragma GCC optimize ("fp-contract=off")
sign.c: ^
sign.c:
vrfy.c: In file included from vrfy.c(32):
vrfy.c: inner.h(297): warning #3438: unsupported option is ignored
vrfy.c: #pragma GCC optimize ("fp-contract=off")
vrfy.c: ^
vrfy.c:

Number of similar (compiler,implementation) pairs: 24, namely:

Compiler	Implementations
icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer	avx2
icc -march=broadwell -mtune=broadwell -O3 -fomit-frame-pointer	avx2
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer	avx2
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer	avx2
icc -march=core-avx-i -mtune=core-avx-i -O2 -fomit-frame-pointer	avx2
icc -march=core-avx-i -mtune=core-avx-i -O3 -fomit-frame-pointer	avx2
icc -march=core-avx2 -mtune=core-avx2 -O2 -fomit-frame-pointer	avx2
icc -march=core-avx2 -mtune=core-avx2 -O3 -fomit-frame-pointer	avx2
icc -march=corei7-avx -mtune=corei7-avx -O2 -fomit-frame-pointer	avx2
icc -march=corei7-avx -mtune=corei7-avx -O3 -fomit-frame-pointer	avx2
icc -march=corei7 -mtune=corei7 -O2 -fomit-frame-pointer	avx2
icc -march=corei7 -mtune=corei7 -O3 -fomit-frame-pointer	avx2
icc -march=haswell -mtune=haswell -O2 -fomit-frame-pointer	avx2
icc -march=haswell -mtune=haswell -O3 -fomit-frame-pointer	avx2
icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer	avx2
icc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer	avx2
icc -march=ivybridge -mtune=ivybridge -O2 -fomit-frame-pointer	avx2
icc -march=ivybridge -mtune=ivybridge -O3 -fomit-frame-pointer	avx2
icc -march=sandybridge -mtune=sandybridge -O2 -fomit-frame-pointer	avx2
icc -march=sandybridge -mtune=sandybridge -O3 -fomit-frame-pointer	avx2
icc -march=skylake-avx512 -mtune=skylake-avx512 -O2 -fomit-frame-pointer	avx2
icc -march=skylake-avx512 -mtune=skylake-avx512 -O3 -fomit-frame-pointer	avx2
icc -march=skylake -mtune=skylake -O2 -fomit-frame-pointer	avx2
icc -march=skylake -mtune=skylake -O3 -fomit-frame-pointer	avx2

Compiler output

Implementation: fpu
Security model: unknown
Compiler: icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer

api.c: In file included from api.c(10):
api.c: inner.h(270): warning #3438: unsupported option is ignored
api.c: #pragma GCC optimize ("fp-contract=off")
api.c: ^
api.c:
codec.c: In file included from codec.c(32):
codec.c: inner.h(270): warning #3438: unsupported option is ignored
codec.c: #pragma GCC optimize ("fp-contract=off")
codec.c: ^
codec.c:
common.c: In file included from common.c(32):
common.c: inner.h(270): warning #3438: unsupported option is ignored
common.c: #pragma GCC optimize ("fp-contract=off")
common.c: ^
common.c:
fft.c: In file included from fft.c(32):
fft.c: inner.h(270): warning #3438: unsupported option is ignored
fft.c: #pragma GCC optimize ("fp-contract=off")
fft.c: ^
fft.c:
fpr.c: In file included from fpr.c(35):
fpr.c: inner.h(270): warning #3438: unsupported option is ignored
fpr.c: #pragma GCC optimize ("fp-contract=off")
fpr.c: ^
fpr.c:
keygen.c: In file included from keygen.c(32):
keygen.c: inner.h(270): warning #3438: unsupported option is ignored
keygen.c: #pragma GCC optimize ("fp-contract=off")
keygen.c: ^
keygen.c:
rng.c: In file included from rng.c(34):
rng.c: inner.h(270): warning #3438: unsupported option is ignored
rng.c: #pragma GCC optimize ("fp-contract=off")
rng.c: ^
rng.c:
shake.c: In file included from shake.c(34):
shake.c: inner.h(270): warning #3438: unsupported option is ignored
shake.c: #pragma GCC optimize ("fp-contract=off")
shake.c: ^
shake.c:
sign.c: In file included from sign.c(32):
sign.c: inner.h(270): warning #3438: unsupported option is ignored
sign.c: #pragma GCC optimize ("fp-contract=off")
sign.c: ^
sign.c:
vrfy.c: In file included from vrfy.c(32):
vrfy.c: inner.h(270): warning #3438: unsupported option is ignored
vrfy.c: #pragma GCC optimize ("fp-contract=off")
vrfy.c: ^
vrfy.c:

Number of similar (compiler,implementation) pairs: 24, namely:

Compiler	Implementations
icc -march=broadwell -mtune=broadwell -O2 -fomit-frame-pointer	fpu
icc -march=broadwell -mtune=broadwell -O3 -fomit-frame-pointer	fpu
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer	fpu
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer	fpu
icc -march=core-avx-i -mtune=core-avx-i -O2 -fomit-frame-pointer	fpu
icc -march=core-avx-i -mtune=core-avx-i -O3 -fomit-frame-pointer	fpu
icc -march=core-avx2 -mtune=core-avx2 -O2 -fomit-frame-pointer	fpu
icc -march=core-avx2 -mtune=core-avx2 -O3 -fomit-frame-pointer	fpu
icc -march=corei7-avx -mtune=corei7-avx -O2 -fomit-frame-pointer	fpu
icc -march=corei7-avx -mtune=corei7-avx -O3 -fomit-frame-pointer	fpu
icc -march=corei7 -mtune=corei7 -O2 -fomit-frame-pointer	fpu
icc -march=corei7 -mtune=corei7 -O3 -fomit-frame-pointer	fpu
icc -march=haswell -mtune=haswell -O2 -fomit-frame-pointer	fpu
icc -march=haswell -mtune=haswell -O3 -fomit-frame-pointer	fpu
icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer	fpu
icc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer	fpu
icc -march=ivybridge -mtune=ivybridge -O2 -fomit-frame-pointer	fpu
icc -march=ivybridge -mtune=ivybridge -O3 -fomit-frame-pointer	fpu
icc -march=sandybridge -mtune=sandybridge -O2 -fomit-frame-pointer	fpu
icc -march=sandybridge -mtune=sandybridge -O3 -fomit-frame-pointer	fpu
icc -march=skylake-avx512 -mtune=skylake-avx512 -O2 -fomit-frame-pointer	fpu
icc -march=skylake-avx512 -mtune=skylake-avx512 -O3 -fomit-frame-pointer	fpu
icc -march=skylake -mtune=skylake -O2 -fomit-frame-pointer	fpu
icc -march=skylake -mtune=skylake -O3 -fomit-frame-pointer	fpu