Implementation notes: amd64, ghf51, crypto_dh/hecfp64e2i

Computer: ghf51
Architecture: amd64
CPU ID: AuthenticAMD-00810f81-178bfbff
SUPERCOP version: 20200702
Operation: crypto_dh
Primitive: hecfp64e2i

Compiler output

Implementation: v01/var
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
divisor.c: In file included from divisor.c:12:
divisor.c: ./finite128.h:737:13: warning: inline function 'hec_fp_dbl_2e064mce2_g2i_x8664_asm' is not defined [-Wundefined-inline]
divisor.c: inline void hec_fp_dbl_2e064mce2_g2i_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni CNS);
divisor.c: ^
divisor.c: divisor.c:34:2: note: used here
divisor.c: hec_fp_dbl_2e064mce2_g2i_x8664_asm((uni)t, cn->prm, NULL, (uni)d3, (uni)d1, (uni)cn);
divisor.c: ^
divisor.c: In file included from divisor.c:12:
divisor.c: ./finite128.h:738:13: warning: inline function 'hec_fp_dbl_2e064mce2_g2i_a2is0_a3is0_x8664_asm' is not defined [-Wundefined-inline]
divisor.c: inline void hec_fp_dbl_2e064mce2_g2i_a2is0_a3is0_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni CNS);
divisor.c: ^
divisor.c: divisor.c:117:2: note: used here
divisor.c: hec_fp_dbl_2e064mce2_g2i_a2is0_a3is0_x8664_asm((uni)t, cn->prm, NULL, (uni)d3, (uni)d1, NULL);
divisor.c: ^
divisor.c: In file included from divisor.c:12:
divisor.c: ./finite128.h:739:13: warning: inline function 'hec_fp_add_2e064mce2_g2i_x8664_asm' is not defined [-Wundefined-inline]
divisor.c: inline void hec_fp_add_2e064mce2_g2i_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni d2);
divisor.c: ^
divisor.c: divisor.c:211:3: note: used here
divisor.c: hec_fp_add_2e064mce2_g2i_x8664_asm((uni)t, cn->prm, NULL, (uni)d3, (uni)d1, (uni)d2);
divisor.c: ^
divisor.c: In file included from divisor.c:12:
divisor.c: ./finite128.h:740:13: warning: inline function 'hec_fp_madd_2e064mce2_g2i_x8664_asm' is not defined [-Wundefined-inline]
divisor.c: inline void hec_fp_madd_2e064mce2_g2i_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni d2);
divisor.c: ^
divisor.c: ...
fp_2e064mc_x8664.c: In file included from fp_2e064mc_x8664.c:7:
fp_2e064mc_x8664.c: In file included from ./finite064.h:5:
fp_2e064mc_x8664.c: ./fpx.h:23:13: warning: inline function 'fp_cnt_bits' is not defined [-Wundefined-inline]
fp_2e064mc_x8664.c: inline void fp_cnt_bits(int *bc, const uni an, const uni_t al);
fp_2e064mc_x8664.c: ^
fp_2e064mc_x8664.c: fp_2e064mc_x8664.c:16:2: note: used here
fp_2e064mc_x8664.c: fp_cnt_bits(&i, n01, FP_LEN);
fp_2e064mc_x8664.c: ^
fp_2e064mc_x8664.c: 1 warning generated.
smul.c: In file included from smul.c:10:
smul.c: In file included from ./finite128.h:5:
smul.c: ./fpx.h:23:13: warning: inline function 'fp_cnt_bits' is not defined [-Wundefined-inline]
smul.c: inline void fp_cnt_bits(int *bc, const uni an, const uni_t al);
smul.c: ^
smul.c: smul.c:22:2: note: used here
smul.c: fp_cnt_bits(&i, kn, FP_LEN*2);
smul.c: ^
smul.c: In file included from smul.c:10:
smul.c: In file included from ./finite128.h:5:
smul.c: ./fpx.h:24:13: warning: inline function 'find_nextwindow' is not defined [-Wundefined-inline]
smul.c: inline void find_nextwindow(int *v, int *k, uni_t kl, int *wd, const uni en, const int i, uni_t WINDOW_SIZE_LTR, uni_t TABLE_SIZE_LTR);
smul.c: ^
smul.c: smul.c:52:3: note: used here
smul.c: find_nextwindow(&ni, &k, 2*FP_LEN, &wd, kn, i, WINDOW_SIZE_LTR, TABLE_SIZE_LTR);
smul.c: ^
smul.c: 2 warnings generated.
try.c: /usr/bin/ld: crypto_dh_hecfp64e2i.a(smul.o): in function `hec_fp_smul_2e064mce2_g2i':
try.c: smul.c:(.text+0x...): undefined reference to `fp_cnt_bits'
try.c: /usr/bin/ld: smul.c:(.text+0x...): undefined reference to `find_nextwindow'
try.c: /usr/bin/ld: smul.c:(.text+0x...): undefined reference to `find_nextwindow'
try.c: /usr/bin/ld: crypto_dh_hecfp64e2i.a(smul.o): in function `hec_fp_smul_2e064mce2_g2i_a2is0_a3is0':
try.c: smul.c:(.text+0x...): undefined reference to `fp_cnt_bits'
try.c: /usr/bin/ld: smul.c:(.text+0x...): undefined reference to `find_nextwindow'
try.c: /usr/bin/ld: smul.c:(.text+0x...): undefined reference to `find_nextwindow'
try.c: /usr/bin/ld: crypto_dh_hecfp64e2i.a(fp_2e064mc_x8664.o): in function `fp_inv_2e064mc_x8664':
try.c: fp_2e064mc_x8664.c:(.text+0x...): undefined reference to `fp_cnt_bits'
try.c: clang: error: linker command failed with exit code 1 (use -v to see invocation)

Number of similar (compiler,implementation) pairs: 5, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/var
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/var
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/var
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/var
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/var

Compiler output

Implementation: v01/var
Security model: unknown
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE
divisor.c: In file included from divisor.c:12:
divisor.c: finite128.h:763:13: warning: inline function ‘kum_fp_dbladd_2e064mce2_g_x8664_asm’ declared but never defined
divisor.c: 763 | inline void kum_fp_dbladd_2e064mce2_g_x8664_asm(uni TMP, uni kn, uni_t i, uni d1, uni d2, uni CNS);
divisor.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
divisor.c: finite128.h:762:13: warning: inline function ‘kum_fp_dbl_2e064mce2_g_x8664_asm’ declared but never defined
divisor.c: 762 | inline void kum_fp_dbl_2e064mce2_g_x8664_asm(uni TMP, void *NOPARAM1, void *NOPARAM2, uni d1, void *NOPARAM3, uni CNS);
divisor.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
divisor.c: finite128.h:741:13: warning: inline function ‘hec_fp_aadd_2e064mce2_g2i_x8664_asm’ declared but never defined
divisor.c: 741 | inline void hec_fp_aadd_2e064mce2_g2i_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni d2);
divisor.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
divisor.c: finite128.h:740:13: warning: inline function ‘hec_fp_madd_2e064mce2_g2i_x8664_asm’ declared but never defined
divisor.c: 740 | inline void hec_fp_madd_2e064mce2_g2i_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni d2);
divisor.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
divisor.c: finite128.h:739:13: warning: inline function ‘hec_fp_add_2e064mce2_g2i_x8664_asm’ declared but never defined
divisor.c: 739 | inline void hec_fp_add_2e064mce2_g2i_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni d2);
divisor.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
divisor.c: finite128.h:738:13: warning: inline function ‘hec_fp_dbl_2e064mce2_g2i_a2is0_a3is0_x8664_asm’ declared but never defined
divisor.c: 738 | inline void hec_fp_dbl_2e064mce2_g2i_a2is0_a3is0_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni CNS);
divisor.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
divisor.c: finite128.h:737:13: warning: inline function ‘hec_fp_dbl_2e064mce2_g2i_x8664_asm’ declared but never defined
divisor.c: 737 | inline void hec_fp_dbl_2e064mce2_g2i_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni CNS);
divisor.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
divisor.c: finite128.h:512:13: warning: inline function ‘kum_fp_dbladd_2e061m1e2_g_x8664_asm’ declared but never defined
divisor.c: 512 | inline void kum_fp_dbladd_2e061m1e2_g_x8664_asm(uni TMP, uni kn, uni_t i, uni d1, uni d2, uni CNS);
divisor.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
divisor.c: ...

Number of similar (compiler,implementation) pairs: 28, namely:
CompilerImplementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/var
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/var
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/var
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/var
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s01
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s01
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s01
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s01
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s02
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s02
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s02
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s02
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s04
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s04
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s04
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s04
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s08
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s08
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s08
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s08
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s16
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s16
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s16
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s16
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s32
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s32
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s32
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE v01/w8s32

Compiler output

Implementation: v01/w8s01
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
divisor.c: In file included from divisor.c:12:
divisor.c: ./finite128.h:737:13: warning: inline function 'hec_fp_dbl_2e064mce2_g2i_x8664_asm' is not defined [-Wundefined-inline]
divisor.c: inline void hec_fp_dbl_2e064mce2_g2i_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni CNS);
divisor.c: ^
divisor.c: divisor.c:34:2: note: used here
divisor.c: hec_fp_dbl_2e064mce2_g2i_x8664_asm((uni)t, cn->prm, NULL, (uni)d3, (uni)d1, (uni)cn);
divisor.c: ^
divisor.c: In file included from divisor.c:12:
divisor.c: ./finite128.h:738:13: warning: inline function 'hec_fp_dbl_2e064mce2_g2i_a2is0_a3is0_x8664_asm' is not defined [-Wundefined-inline]
divisor.c: inline void hec_fp_dbl_2e064mce2_g2i_a2is0_a3is0_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni CNS);
divisor.c: ^
divisor.c: divisor.c:117:2: note: used here
divisor.c: hec_fp_dbl_2e064mce2_g2i_a2is0_a3is0_x8664_asm((uni)t, cn->prm, NULL, (uni)d3, (uni)d1, NULL);
divisor.c: ^
divisor.c: In file included from divisor.c:12:
divisor.c: ./finite128.h:739:13: warning: inline function 'hec_fp_add_2e064mce2_g2i_x8664_asm' is not defined [-Wundefined-inline]
divisor.c: inline void hec_fp_add_2e064mce2_g2i_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni d2);
divisor.c: ^
divisor.c: divisor.c:211:3: note: used here
divisor.c: hec_fp_add_2e064mce2_g2i_x8664_asm((uni)t, cn->prm, NULL, (uni)d3, (uni)d1, (uni)d2);
divisor.c: ^
divisor.c: In file included from divisor.c:12:
divisor.c: ./finite128.h:740:13: warning: inline function 'hec_fp_madd_2e064mce2_g2i_x8664_asm' is not defined [-Wundefined-inline]
divisor.c: inline void hec_fp_madd_2e064mce2_g2i_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni d2);
divisor.c: ^
divisor.c: ...
fp_2e064mc_x8664.c: In file included from fp_2e064mc_x8664.c:7:
fp_2e064mc_x8664.c: In file included from ./finite064.h:5:
fp_2e064mc_x8664.c: ./fpx.h:23:13: warning: inline function 'fp_cnt_bits' is not defined [-Wundefined-inline]
fp_2e064mc_x8664.c: inline void fp_cnt_bits(int *bc, const uni an, const uni_t al);
fp_2e064mc_x8664.c: ^
fp_2e064mc_x8664.c: fp_2e064mc_x8664.c:16:2: note: used here
fp_2e064mc_x8664.c: fp_cnt_bits(&i, n01, FP_LEN);
fp_2e064mc_x8664.c: ^
fp_2e064mc_x8664.c: 1 warning generated.
io.c: io.c:352:14: warning: equality comparison with extraneous parentheses [-Wparentheses-equality]
io.c: if((buf[i] == -1)){
io.c: ~~~~~~~^~~~~
io.c: io.c:352:14: note: remove extraneous parentheses around the comparison to silence this warning
io.c: if((buf[i] == -1)){
io.c: ~ ^ ~
io.c: io.c:352:14: note: use '=' to turn this equality comparison into an assignment
io.c: if((buf[i] == -1)){
io.c: ^~
io.c: =
io.c: io.c:379:14: warning: equality comparison with extraneous parentheses [-Wparentheses-equality]
io.c: if((buf[i] == -1)){
io.c: ~~~~~~~^~~~~
io.c: io.c:379:14: note: remove extraneous parentheses around the comparison to silence this warning
io.c: if((buf[i] == -1)){
io.c: ~ ^ ~
io.c: io.c:379:14: note: use '=' to turn this equality comparison into an assignment
io.c: if((buf[i] == -1)){
io.c: ^~
io.c: =
io.c: 2 warnings generated.
smul.c: In file included from smul.c:10:
smul.c: In file included from ./finite128.h:5:
smul.c: ./fpx.h:23:13: warning: inline function 'fp_cnt_bits' is not defined [-Wundefined-inline]
smul.c: inline void fp_cnt_bits(int *bc, const uni an, const uni_t al);
smul.c: ^
smul.c: smul.c:22:2: note: used here
smul.c: fp_cnt_bits(&i, kn, FP_LEN*2);
smul.c: ^
smul.c: In file included from smul.c:10:
smul.c: In file included from ./finite128.h:5:
smul.c: ./fpx.h:24:13: warning: inline function 'find_nextwindow' is not defined [-Wundefined-inline]
smul.c: inline void find_nextwindow(int *v, int *k, uni_t kl, int *wd, const uni en, const int i, uni_t WINDOW_SIZE_LTR, uni_t TABLE_SIZE_LTR);
smul.c: ^
smul.c: smul.c:52:3: note: used here
smul.c: find_nextwindow(&ni, &k, 2*FP_LEN, &wd, kn, i, WINDOW_SIZE_LTR, TABLE_SIZE_LTR);
smul.c: ^
smul.c: 2 warnings generated.
try.c: /usr/bin/ld: crypto_dh_hecfp64e2i.a(smul.o): in function `hec_fp_smul_2e064mce2_g2i':
try.c: smul.c:(.text+0x...): undefined reference to `fp_cnt_bits'
try.c: /usr/bin/ld: smul.c:(.text+0x...): undefined reference to `find_nextwindow'
try.c: /usr/bin/ld: smul.c:(.text+0x...): undefined reference to `find_nextwindow'
try.c: /usr/bin/ld: crypto_dh_hecfp64e2i.a(smul.o): in function `hec_fp_smul_2e064mce2_g2i_a2is0_a3is0':
try.c: smul.c:(.text+0x...): undefined reference to `fp_cnt_bits'
try.c: /usr/bin/ld: smul.c:(.text+0x...): undefined reference to `find_nextwindow'
try.c: /usr/bin/ld: smul.c:(.text+0x...): undefined reference to `find_nextwindow'
try.c: /usr/bin/ld: crypto_dh_hecfp64e2i.a(fp_2e064mc_x8664.o): in function `fp_inv_2e064mc_x8664':
try.c: fp_2e064mc_x8664.c:(.text+0x...): undefined reference to `fp_cnt_bits'
try.c: clang: error: linker command failed with exit code 1 (use -v to see invocation)

Number of similar (compiler,implementation) pairs: 30, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s01
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s01
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s01
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s01
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s01
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s02
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s02
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s02
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s02
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s02
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s04
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s04
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s04
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s04
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s04
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s08
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s08
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s08
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s08
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s08
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s16
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s16
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s16
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s16
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s16
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s32
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s32
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s32
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s32
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE v01/w8s32