Implementation notes: amd64, rumba5, crypto_dh/kumfp128g

Computer: rumba5
Architecture: amd64
CPU ID: AuthenticAMD-00800f11-178bfbff
SUPERCOP version: 20181216
Operation: crypto_dh
Primitive: kumfp128g

Compiler output

Implementation: crypto_dh/kumfp128g/v02/var
Compiler: cc

Number of similar (compiler,implementation) pairs: 107, namely:

Compiler	Implementations
cc	v02/var
gcc	v02/var
gcc -O2 -fomit-frame-pointer	v02/var
gcc -O3 -fomit-frame-pointer	v02/var
gcc -O -fomit-frame-pointer	v02/var
gcc -Os -fomit-frame-pointer	v02/var
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	v02/var
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	v02/var
gcc -fno-schedule-insns -O -fomit-frame-pointer	v02/var
gcc -fno-schedule-insns -Os -fomit-frame-pointer	v02/var
gcc -funroll-loops	v02/var
gcc -funroll-loops -O2 -fomit-frame-pointer	v02/var
gcc -funroll-loops -O3 -fomit-frame-pointer	v02/var
gcc -funroll-loops -O -fomit-frame-pointer	v02/var
gcc -funroll-loops -Os -fomit-frame-pointer	v02/var
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	v02/var
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	v02/var
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	v02/var
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	v02/var
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	v02/var
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	v02/var
gcc -funroll-loops -m64 -O -fomit-frame-pointer	v02/var
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	v02/var
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	v02/var
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	v02/var
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	v02/var
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	v02/var
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	v02/var
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	v02/var
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	v02/var
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	v02/var
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	v02/var
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	v02/var
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	v02/var
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	v02/var
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	v02/var
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	v02/var
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	v02/var
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	v02/var
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	v02/var
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	v02/var
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	v02/var
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	v02/var
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	v02/var
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	v02/var
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	v02/var
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	v02/var
gcc -m64 -O2 -fomit-frame-pointer	v02/var
gcc -m64 -O3 -fomit-frame-pointer	v02/var
gcc -m64 -O -fomit-frame-pointer	v02/var
gcc -m64 -Os -fomit-frame-pointer	v02/var
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer	v02/var
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer	v02/var
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer	v02/var
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer	v02/var
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer	v02/var
gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer	v02/var
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer	v02/var
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer	v02/var
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	v02/var
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	v02/var
gcc -m64 -march=core2 -O -fomit-frame-pointer	v02/var
gcc -m64 -march=core2 -Os -fomit-frame-pointer	v02/var
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	v02/var
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	v02/var
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	v02/var
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	v02/var
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	v02/var
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	v02/var
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	v02/var
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	v02/var
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer	v02/var
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer	v02/var
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer	v02/var
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer	v02/var
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	v02/var
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer	v02/var
gcc -m64 -march=corei7 -O -fomit-frame-pointer	v02/var
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	v02/var
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	v02/var
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	v02/var
gcc -m64 -march=k8 -O -fomit-frame-pointer	v02/var
gcc -m64 -march=k8 -Os -fomit-frame-pointer	v02/var
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	v02/var
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	v02/var
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	v02/var
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	v02/var
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	v02/var
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	v02/var
gcc -m64 -march=nocona -O -fomit-frame-pointer	v02/var
gcc -m64 -march=nocona -Os -fomit-frame-pointer	v02/var
gcc -march=barcelona -O2 -fomit-frame-pointer	v02/var
gcc -march=barcelona -O3 -fomit-frame-pointer	v02/var
gcc -march=barcelona -O -fomit-frame-pointer	v02/var
gcc -march=barcelona -Os -fomit-frame-pointer	v02/var
gcc -march=k8 -O2 -fomit-frame-pointer	v02/var
gcc -march=k8 -O3 -fomit-frame-pointer	v02/var
gcc -march=k8 -O -fomit-frame-pointer	v02/var
gcc -march=k8 -Os -fomit-frame-pointer	v02/var
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	v02/var
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	v02/var
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	v02/var
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	v02/var
gcc -march=nocona -O2 -fomit-frame-pointer	v02/var
gcc -march=nocona -O3 -fomit-frame-pointer	v02/var
gcc -march=nocona -O -fomit-frame-pointer	v02/var
gcc -march=nocona -Os -fomit-frame-pointer	v02/var

Compiler output

Implementation: crypto_dh/kumfp128g/v02/var
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

fp_2e128mc_x8664.c: In file included from fp_2e128mc_x8664.c:7:
fp_2e128mc_x8664.c: In file included from ./finite128.h:5:
fp_2e128mc_x8664.c: ./fpx.h:23:13: warning: inline function 'fp_cnt_bits' is not defined [-Wundefined-inline]
fp_2e128mc_x8664.c: inline void fp_cnt_bits(int *bc, const uni an, const uni_t al);
fp_2e128mc_x8664.c: ^
fp_2e128mc_x8664.c: fp_2e128mc_x8664.c:86:2: note: used here
fp_2e128mc_x8664.c: fp_cnt_bits(&i, n01, 1);
fp_2e128mc_x8664.c: ^
fp_2e128mc_x8664.c: 1 warning generated.
smul.c: In file included from smul.c:12:
smul.c: ./finite128.h:269:13: warning: inline function 'kum_fp_dbl_2e128mc_g_x8664_asm' is not defined [-Wundefined-inline]
smul.c: inline void kum_fp_dbl_2e128mc_g_x8664_asm(uni TMP, void *NOPARAM1, void *NOPARAM2, uni d1, void *NOPARAM3, uni CNS);
smul.c: ^
smul.c: smul.c:29:2: note: used here
smul.c: kum_fp_dbl_2e128mc_g_x8664_asm((uni)t, NULL, NULL, (uni)d1, NULL, (uni)cn);
smul.c: ^
smul.c: In file included from smul.c:12:
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:30:2: note: used here
smul.c: fp_cnt_bits(&i, kn, 2*FP_LEN); /*printf("%d ", i);*/
smul.c: ^
smul.c: In file included from smul.c:12:
smul.c: ./finite128.h:270:13: warning: inline function 'kum_fp_dbladd_2e128mc_g_x8664_asm' is not defined [-Wundefined-inline]
smul.c: inline void kum_fp_dbladd_2e128mc_g_x8664_asm(uni TMP, uni kn, uni_t i, uni d1, uni d2, uni CNS);
smul.c: ^
smul.c: smul.c:32:3: note: used here
smul.c: kum_fp_dbladd_2e128mc_g_x8664_asm((uni)t, kn, j, (uni)d1, (uni)d2, (uni)cn);
smul.c: ^
smul.c: 3 warnings generated.
try.c: crypto_dh_kumfp128g.a(fp_2e128mc_x8664.o): In function `fp_inv_2e128mc_x8664':
try.c: fp_2e128mc_x8664.c:(.text+0x...): undefined reference to `fp_cnt_bits'
try.c: crypto_dh_kumfp128g.a(smul.o): In function `kum_fp_smul_2e128mc_g':
try.c: smul.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: 10, namely:

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	v02/var
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	v02/var
clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	v02/var
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments	v02/var
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	v02/var
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	v02/var
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	v02/var
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	v02/var
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	v02/var
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	v02/var

Compiler output

Implementation: crypto_dh/kumfp128g/v02/var
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

fp_2e128mc_x8664.c: In file included from fp_2e128mc_x8664.c:7:0:
fp_2e128mc_x8664.c: finite128.h:797:13: warning: inline function 'kum_fp_dbladd_2e64mce2_g_x8664_asm' declared but never defined
fp_2e128mc_x8664.c: inline void kum_fp_dbladd_2e64mce2_g_x8664_asm(uni TMP, uni kn, uni_t i, uni d1, uni d2, uni CNS);
fp_2e128mc_x8664.c: ^
fp_2e128mc_x8664.c: finite128.h:796:13: warning: inline function 'kum_fp_dbl_2e64mce2_g_x8664_asm' declared but never defined
fp_2e128mc_x8664.c: inline void kum_fp_dbl_2e64mce2_g_x8664_asm(uni TMP, void *NOPARAM1, void *NOPARAM2, uni d1, void *NOPARAM3, uni CNS);
fp_2e128mc_x8664.c: ^
fp_2e128mc_x8664.c: finite128.h:773:13: warning: inline function 'hec_fp_aadd_2e64mce2_g2i_x8664_asm' declared but never defined
fp_2e128mc_x8664.c: inline void hec_fp_aadd_2e64mce2_g2i_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni d2);
fp_2e128mc_x8664.c: ^
fp_2e128mc_x8664.c: finite128.h:772:13: warning: inline function 'hec_fp_madd_2e64mce2_g2i_x8664_asm' declared but never defined
fp_2e128mc_x8664.c: inline void hec_fp_madd_2e64mce2_g2i_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni d2);
fp_2e128mc_x8664.c: ^
fp_2e128mc_x8664.c: finite128.h:771:13: warning: inline function 'hec_fp_add_2e64mce2_g2i_x8664_asm' declared but never defined
fp_2e128mc_x8664.c: inline void hec_fp_add_2e64mce2_g2i_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni d2);
fp_2e128mc_x8664.c: ^
fp_2e128mc_x8664.c: finite128.h:770:13: warning: inline function 'hec_fp_dbl_2e64mce2_g2i_a2is0_a3is0_x8664_asm' declared but never defined
fp_2e128mc_x8664.c: inline void hec_fp_dbl_2e64mce2_g2i_a2is0_a3is0_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni CNS);
fp_2e128mc_x8664.c: ^
fp_2e128mc_x8664.c: finite128.h:769:13: warning: inline function 'hec_fp_dbl_2e64mce2_g2i_x8664_asm' declared but never defined
fp_2e128mc_x8664.c: inline void hec_fp_dbl_2e64mce2_g2i_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni CNS);
fp_2e128mc_x8664.c: ^
fp_2e128mc_x8664.c: finite128.h:526:13: warning: inline function 'kum_fp_dbladd_2e61m1e2_g_x8664_asm' declared but never defined
fp_2e128mc_x8664.c: inline void kum_fp_dbladd_2e61m1e2_g_x8664_asm(uni TMP, uni kn, uni_t i, uni d1, uni d2, uni CNS);
fp_2e128mc_x8664.c: ^
fp_2e128mc_x8664.c: ...
fp_2e128mc_x8664.c: In file included from fp_2e128mc_x8664.c:7:0:
fp_2e128mc_x8664.c: finite128.h:797:13: warning: inline function 'kum_fp_dbladd_2e64mce2_g_x8664_asm' declared but never defined
fp_2e128mc_x8664.c: inline void kum_fp_dbladd_2e64mce2_g_x8664_asm(uni TMP, uni kn, uni_t i, uni d1, uni d2, uni CNS);
fp_2e128mc_x8664.c: ^
fp_2e128mc_x8664.c: finite128.h:796:13: warning: inline function 'kum_fp_dbl_2e64mce2_g_x8664_asm' declared but never defined
fp_2e128mc_x8664.c: inline void kum_fp_dbl_2e64mce2_g_x8664_asm(uni TMP, void *NOPARAM1, void *NOPARAM2, uni d1, void *NOPARAM3, uni CNS);
fp_2e128mc_x8664.c: ^
fp_2e128mc_x8664.c: finite128.h:773:13: warning: inline function 'hec_fp_aadd_2e64mce2_g2i_x8664_asm' declared but never defined
fp_2e128mc_x8664.c: inline void hec_fp_aadd_2e64mce2_g2i_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni d2);
fp_2e128mc_x8664.c: ^
fp_2e128mc_x8664.c: finite128.h:772:13: warning: inline function 'hec_fp_madd_2e64mce2_g2i_x8664_asm' declared but never defined
fp_2e128mc_x8664.c: inline void hec_fp_madd_2e64mce2_g2i_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni d2);
fp_2e128mc_x8664.c: ^
fp_2e128mc_x8664.c: finite128.h:771:13: warning: inline function 'hec_fp_add_2e64mce2_g2i_x8664_asm' declared but never defined
fp_2e128mc_x8664.c: inline void hec_fp_add_2e64mce2_g2i_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni d2);
fp_2e128mc_x8664.c: ^
fp_2e128mc_x8664.c: finite128.h:770:13: warning: inline function 'hec_fp_dbl_2e64mce2_g2i_a2is0_a3is0_x8664_asm' declared but never defined
fp_2e128mc_x8664.c: inline void hec_fp_dbl_2e64mce2_g2i_a2is0_a3is0_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni CNS);
fp_2e128mc_x8664.c: ^
fp_2e128mc_x8664.c: finite128.h:769:13: warning: inline function 'hec_fp_dbl_2e64mce2_g2i_x8664_asm' declared but never defined
fp_2e128mc_x8664.c: inline void hec_fp_dbl_2e64mce2_g2i_x8664_asm(uni TMP, uni_t prm, void *NOPARAM, uni D3, uni d1, uni CNS);
fp_2e128mc_x8664.c: ^
fp_2e128mc_x8664.c: finite128.h:526:13: warning: inline function 'kum_fp_dbladd_2e61m1e2_g_x8664_asm' declared but never defined
fp_2e128mc_x8664.c: inline void kum_fp_dbladd_2e61m1e2_g_x8664_asm(uni TMP, uni kn, uni_t i, uni d1, uni d2, uni CNS);
fp_2e128mc_x8664.c: ^
fp_2e128mc_x8664.c: ...

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

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	v02/var
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	v02/var
gcc -m64 -march=barcelona -O -fomit-frame-pointer	v02/var
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	v02/var