Implementation notes: amd64, avx512imath, crypto_hash/fugue256

Computer: avx512imath
Architecture: amd64
CPU ID: GenuineIntel-00050657-bfebfbff
SUPERCOP version: 20210125
Operation: crypto_hash
Primitive: fugue256

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
21931	32280 0 0	46919 812 952	`T:ccalik/aesni`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
22034	30376 0 0	42120 804 952	`T:ccalik/aesni`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
22752	28353 0 0	40056 804 952	`T:ccalik/aesni`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
24156	25150 0 0	35891 780 920	`T:ccalik/aesni`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
26078	51453 0 0	66134 820 952	`T:SSSE3`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
26408	49821 0 0	61573 812 952	`T:SSSE3`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
27290	41008 0 0	55647 812 952	`T:ccalik/vperm`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
27368	38672 0 0	50416 804 952	`T:ccalik/vperm`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
28471	36416 0 0	48120 804 952	`T:ccalik/vperm`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
29283	59210 0 0	70917 812 952	`T:SSSE3`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
29928	33106 0 0	43835 780 920	`T:ccalik/vperm`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
29946	48380 0 0	63062 820 952	`T:SSE4.1`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
30237	46687 0 0	58437 812 952	`T:SSE4.1`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
30637	46593 0 0	57449 796 920	`T:SSSE3`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
31047	53308 0 0	65013 812 952	`T:SSE4.1`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
32797	42169 0 0	53017 796 920	`T:SSE4.1`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
35085	71009 0 0	82646 804 952	`T:ANSI_opt64`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
35711	69531 0 0	81222 804 952	`T:ANSI_opt64`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
35908	71909 0 0	86471 812 952	`T:ANSI_opt64`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
37239	53107 0 0	64790 804 952	`T:ANSI_opt32`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
38155	66531 0 0	77298 788 920	`T:ANSI_opt64`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
38208	57499 0 0	72071 812 952	`T:ANSI_opt32`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
38208	57434 0 0	69078 804 952	`T:ANSI_opt32`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
39132	39787 0 0	51648 812 952	`T:sphlib`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
39134	36534 0 0	47524 796 920	`T:sphlib`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
39491	50375 0 0	61138 788 920	`T:ANSI_opt32`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
39721	40024 0 0	51928 812 952	`T:sphlib`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125
39829	41144 0 0	55929 820 952	`T:sphlib`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20210323	20210125

Compiler output

Implementation: T:ANSI_opt32
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

hash.c: In file included from aestab.h:4,
hash.c: from fugue_256_code.h:13,
hash.c: from hash.c:7:
hash.c: hash.c: In function 'crypto_hash_fugue256_ANSI_opt32_timingleaks':
hash.c: aestab_t.h:19:26: warning: result of '1718686559 << 24' requires 56 bits to represent, but 'int' only has 32 bits [-Wshift-overflow=]
hash.c: 19 | #define HO2BE_4(_x) ((_x<<24)|((_x<<8)&0xff0000)|((_x>>8)&0xff00)|(_x>>24))
hash.c: | ^~
hash.c: hash.c:32:27: note: in expansion of macro 'HO2BE_4'
hash.c: 32 | HO2BE_4(0xe952bdde),HO2BE_4(0x6671135f),HO2BE_4(0xe0d4f668),HO2BE_4(0xd2b0b594),
hash.c: | ^~~~~~~
hash.c: aestab_t.h:19:36: warning: result of '1718686559 << 8' requires 40 bits to represent, but 'int' only has 32 bits [-Wshift-overflow=]
hash.c: 19 | #define HO2BE_4(_x) ((_x<<24)|((_x<<8)&0xff0000)|((_x>>8)&0xff00)|(_x>>24))
hash.c: | ^~
hash.c: hash.c:32:27: note: in expansion of macro 'HO2BE_4'
hash.c: 32 | HO2BE_4(0xe952bdde),HO2BE_4(0x6671135f),HO2BE_4(0xe0d4f668),HO2BE_4(0xd2b0b594),
hash.c: | ^~~~~~~
hash.c: aestab_t.h:19:26: warning: result of '888717896 << 24' requires 55 bits to represent, but 'int' only has 32 bits [-Wshift-overflow=]
hash.c: 19 | #define HO2BE_4(_x) ((_x<<24)|((_x<<8)&0xff0000)|((_x>>8)&0xff00)|(_x>>24))
hash.c: | ^~
hash.c: hash.c:33:67: note: in expansion of macro 'HO2BE_4'
hash.c: 33 | HO2BE_4(0xf96c621d),HO2BE_4(0xfbf929de),HO2BE_4(0x9149e899),HO2BE_4(0x34f8c248)};
hash.c: | ^~~~~~~
hash.c: aestab_t.h:19:36: warning: result of '888717896 << 8' requires 39 bits to represent, but 'int' only has 32 bits [-Wshift-overflow=]
hash.c: 19 | #define HO2BE_4(_x) ((_x<<24)|((_x<<8)&0xff0000)|((_x>>8)&0xff00)|(_x>>24))
hash.c: | ^~
hash.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ANSI_opt32
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ANSI_opt32
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ANSI_opt32
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ANSI_opt32

Compiler output

Implementation: T:ANSI_opt64
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

hash.c: In file included from aestab.h:4,
hash.c: from fugue_256_code.h:13,
hash.c: from hash.c:7:
hash.c: hash.c: In function 'crypto_hash_fugue256_ANSI_opt64_timingleaks':
hash.c: aestab_t.h:19:26: warning: result of '1718686559 << 24' requires 56 bits to represent, but 'int' only has 32 bits [-Wshift-overflow=]
hash.c: 19 | #define HO2BE_4(_x) ((_x<<24)|((_x<<8)&0xff0000)|((_x>>8)&0xff00)|(_x>>24))
hash.c: | ^~
hash.c: hash.c:32:27: note: in expansion of macro 'HO2BE_4'
hash.c: 32 | HO2BE_4(0xe952bdde),HO2BE_4(0x6671135f),HO2BE_4(0xe0d4f668),HO2BE_4(0xd2b0b594),
hash.c: | ^~~~~~~
hash.c: aestab_t.h:19:36: warning: result of '1718686559 << 8' requires 40 bits to represent, but 'int' only has 32 bits [-Wshift-overflow=]
hash.c: 19 | #define HO2BE_4(_x) ((_x<<24)|((_x<<8)&0xff0000)|((_x>>8)&0xff00)|(_x>>24))
hash.c: | ^~
hash.c: hash.c:32:27: note: in expansion of macro 'HO2BE_4'
hash.c: 32 | HO2BE_4(0xe952bdde),HO2BE_4(0x6671135f),HO2BE_4(0xe0d4f668),HO2BE_4(0xd2b0b594),
hash.c: | ^~~~~~~
hash.c: aestab_t.h:19:26: warning: result of '888717896 << 24' requires 55 bits to represent, but 'int' only has 32 bits [-Wshift-overflow=]
hash.c: 19 | #define HO2BE_4(_x) ((_x<<24)|((_x<<8)&0xff0000)|((_x>>8)&0xff00)|(_x>>24))
hash.c: | ^~
hash.c: hash.c:33:67: note: in expansion of macro 'HO2BE_4'
hash.c: 33 | HO2BE_4(0xf96c621d),HO2BE_4(0xfbf929de),HO2BE_4(0x9149e899),HO2BE_4(0x34f8c248)};
hash.c: | ^~~~~~~
hash.c: aestab_t.h:19:36: warning: result of '888717896 << 8' requires 39 bits to represent, but 'int' only has 32 bits [-Wshift-overflow=]
hash.c: 19 | #define HO2BE_4(_x) ((_x<<24)|((_x<<8)&0xff0000)|((_x>>8)&0xff00)|(_x>>24))
hash.c: | ^~
hash.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ANSI_opt64
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ANSI_opt64
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ANSI_opt64
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ANSI_opt64

Compiler output

Implementation: T:SSE4.1
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

hash.c: In file included from fugue_256_sse4_code.h:15,
hash.c: from hash.c:24:
hash.c: aestab.h:53:92: warning: backslash and newline separated by space
hash.c: 53 | w(r,0x8c), w(r,0xa1), w(r,0x89), w(r,0x0d), w(r,0xbf), w(r,0xe6), w(r,0x42), w(r,0x68),\
hash.c: |
hash.c: In file included from aestab.h:4,
hash.c: from fugue_256_sse4_code.h:15,
hash.c: from hash.c:24:
hash.c: hash.c: In function 'crypto_hash_fugue256_SSE4_1_timingleaks':
hash.c: aestab_t.h:20:26: warning: result of '1718686559 << 24' requires 56 bits to represent, but 'int' only has 32 bits [-Wshift-overflow=]
hash.c: 20 | #define HO2BE_4(_x) ((_x<<24)|((_x<<8)&0xff0000)|((_x>>8)&0xff00)|(_x>>24))
hash.c: | ^~
hash.c: hash.c:69:27: note: in expansion of macro 'HO2BE_4'
hash.c: 69 | HO2BE_4(0xe952bdde),HO2BE_4(0x6671135f),HO2BE_4(0xe0d4f668),HO2BE_4(0xd2b0b594),
hash.c: | ^~~~~~~
hash.c: aestab_t.h:20:36: warning: result of '1718686559 << 8' requires 40 bits to represent, but 'int' only has 32 bits [-Wshift-overflow=]
hash.c: 20 | #define HO2BE_4(_x) ((_x<<24)|((_x<<8)&0xff0000)|((_x>>8)&0xff00)|(_x>>24))
hash.c: | ^~
hash.c: hash.c:69:27: note: in expansion of macro 'HO2BE_4'
hash.c: 69 | HO2BE_4(0xe952bdde),HO2BE_4(0x6671135f),HO2BE_4(0xe0d4f668),HO2BE_4(0xd2b0b594),
hash.c: | ^~~~~~~
hash.c: aestab_t.h:20:26: warning: result of '888717896 << 24' requires 55 bits to represent, but 'int' only has 32 bits [-Wshift-overflow=]
hash.c: 20 | #define HO2BE_4(_x) ((_x<<24)|((_x<<8)&0xff0000)|((_x>>8)&0xff00)|(_x>>24))
hash.c: | ^~
hash.c: hash.c:70:67: note: in expansion of macro 'HO2BE_4'
hash.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:SSE4.1
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:SSE4.1
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:SSE4.1
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:SSE4.1

Compiler output

Implementation: T:SSSE3
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

hash.c: In file included from fugue_256_ssse3_code.h:15,
hash.c: from hash.c:22:
hash.c: aestab.h:53:92: warning: backslash and newline separated by space
hash.c: 53 | w(r,0x8c), w(r,0xa1), w(r,0x89), w(r,0x0d), w(r,0xbf), w(r,0xe6), w(r,0x42), w(r,0x68),\
hash.c: |
hash.c: In file included from hash.c:22:
hash.c: fugue_256_ssse3_code.h:111:23: warning: backslash and newline separated by space
hash.c: 111 | t0 = xmm_out ; \
hash.c: |
hash.c: In file included from aestab.h:4,
hash.c: from fugue_256_ssse3_code.h:15,
hash.c: from hash.c:22:
hash.c: hash.c: In function 'crypto_hash_fugue256_SSSE3_timingleaks':
hash.c: aestab_t.h:20:26: warning: result of '1718686559 << 24' requires 56 bits to represent, but 'int' only has 32 bits [-Wshift-overflow=]
hash.c: 20 | #define HO2BE_4(_x) ((_x<<24)|((_x<<8)&0xff0000)|((_x>>8)&0xff00)|(_x>>24))
hash.c: | ^~
hash.c: hash.c:67:27: note: in expansion of macro 'HO2BE_4'
hash.c: 67 | HO2BE_4(0xe952bdde),HO2BE_4(0x6671135f),HO2BE_4(0xe0d4f668),HO2BE_4(0xd2b0b594),
hash.c: | ^~~~~~~
hash.c: aestab_t.h:20:36: warning: result of '1718686559 << 8' requires 40 bits to represent, but 'int' only has 32 bits [-Wshift-overflow=]
hash.c: 20 | #define HO2BE_4(_x) ((_x<<24)|((_x<<8)&0xff0000)|((_x>>8)&0xff00)|(_x>>24))
hash.c: | ^~
hash.c: hash.c:67:27: note: in expansion of macro 'HO2BE_4'
hash.c: 67 | HO2BE_4(0xe952bdde),HO2BE_4(0x6671135f),HO2BE_4(0xe0d4f668),HO2BE_4(0xd2b0b594),
hash.c: | ^~~~~~~
hash.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:SSSE3
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:SSSE3
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:SSSE3
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:SSSE3

Namespace violations

Implementation: T:SSE4.1
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

hash.o pretty_print_256 T
hash.o print_xmm T

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:SSE4.1
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:SSE4.1
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:SSE4.1
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:SSE4.1
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:SSSE3
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:SSSE3
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:SSSE3
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:SSSE3

Namespace violations

Implementation: T:ccalik/aesni
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

hash.o Compress256 T
hash.o Compress384 T
hash.o Compress512 T
hash.o Final T
hash.o Final256 T
hash.o Final384 T
hash.o Final512 T
hash.o Hash T
hash.o Init T
hash.o Update T
hash.o _IV256 R
hash.o _IV384 R
hash.o _IV512 R
hash.o _aes_shift_rows R
hash.o _inv_shift_rows R
hash.o _k_aesmix1 R
hash.o _k_aesmix2 R
hash.o _k_aesmix3 R
hash.o _k_aesmix4 R
hash.o _k_h0e R
hash.o _k_h15 R
hash.o _k_h4e R
hash.o _k_h5b R
hash.o _k_h63 R
hash.o _k_hc6 R
hash.o _k_inv R
hash.o _k_ipt R
hash.o _k_n R
hash.o _k_opt R
hash.o _k_s0F R
hash.o _k_sb1 R
hash.o _k_sb2 R
hash.o _k_sb3 R
hash.o _k_sb4 R
hash.o _k_sb5 R
hash.o _k_sb7 R
hash.o _k_sbo R
hash.o _lsbmask2 R
hash.o _maskd3n R
hash.o _mul2mask R
hash.o _mul4mask R
hash.o _shift_four_mask R
hash.o _shift_one_mask R
hash.o _shift_seven_mask R
hash.o _supermix1a R
hash.o _supermix1b R
hash.o _supermix1c R
hash.o _supermix1d R
hash.o _supermix2a R
hash.o _supermix4a R
hash.o _supermix4b R
hash.o _supermix4c R
hash.o _supermix7a R
hash.o _supermix7b R
hash.o _zero R

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ccalik/aesni
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ccalik/aesni
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ccalik/aesni
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ccalik/aesni
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ccalik/vperm
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ccalik/vperm
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ccalik/vperm
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ccalik/vperm

Namespace violations

Implementation: T:sphlib
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

fugue.o sph_fugue224 T
fugue.o sph_fugue224_addbits_and_close T
fugue.o sph_fugue224_close T
fugue.o sph_fugue224_init T
fugue.o sph_fugue256 T
fugue.o sph_fugue256_addbits_and_close T
fugue.o sph_fugue256_close T
fugue.o sph_fugue256_init T
fugue.o sph_fugue384 T
fugue.o sph_fugue384_addbits_and_close T
fugue.o sph_fugue384_close T
fugue.o sph_fugue384_init T
fugue.o sph_fugue512 T
fugue.o sph_fugue512_addbits_and_close T
fugue.o sph_fugue512_close T
fugue.o sph_fugue512_init T

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sphlib
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sphlib
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sphlib
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:sphlib