Implementation notes: amd64, comet, crypto_dh/nistp256

Computer: comet
Microarchitecture: amd64; Comet Lake (806ec)
Architecture: amd64
CPU ID: GenuineIntel-000806ec-bfebfbff
SUPERCOP version: 20240625
Operation: crypto_dh
Primitive: nistp256

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
1714279	38458 32864 0	62025 33732 1792	`T:wbl`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
1717116	34867 32864 0	58113 33732 1760	`T:wbl`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
1769852	39494 32864 0	61361 33732 1728	`T:wbl`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
1894198	16183 32864 0	38532 33660 1792	`T:wbl`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2052862	32534 32864 0	52097 33732 1728	`T:wbl`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2097717	10611 32864 0	30999 33724 1792	`T:wbl`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2186513	13207 32864 0	33636 33660 1792	`T:wbl`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2311205	132 0 0	36084 31500 1760	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2311633	150 0 0	38052 31508 1792	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2312617	150 0 0	39988 31508 1792	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2327064	154 0 0	37244 31508 1792	`T:ref`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2331302	150 0 0	41201 31580 1792	`T:ref`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2331923	153 0 0	37209 31580 1728	`T:ref`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2331957	143 0 0	38015 31572 1792	`T:ref`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2332108	150 0 0	40889 31580 1760	`T:ref`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2332518	150 0 0	39569 31580 1728	`T:ref`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2819131	11360 32864 0	29788 33652 1760	`T:wbl`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625
2885005	11767 32864 0	31404 33660 1792	`T:wbl`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240630	20240625

Compiler output

curve.c: curve.c:256:7: warning: unused variable 'k' [-Wunused-variable]
curve.c:   int k;
curve.c:       ^
curve.c: 1 warning generated.
fep256.c: fep256.c:1076:14: warning: unused variable 'temp' [-Wunused-variable]
fep256.c:   smallfelem temp;
fep256.c:              ^
fep256.c: fep256.c:46:30: warning: unused variable 'nistp256_curve_params' [-Wunused-const-variable]
fep256.c: static const felem_bytearray nistp256_curve_params[5] = {
fep256.c:                              ^
fep256.c: fep256.c:98:19: warning: unused variable 'bottom32bits' [-Wunused-const-variable]
fep256.c: static const limb bottom32bits = 0xffffffff;
fep256.c:                   ^
fep256.c: fep256.c:133:13: warning: unused function 'smallfelem_assign' [-Wunused-function]
fep256.c: static void smallfelem_assign(smallfelem out, const smallfelem in)
fep256.c:             ^
fep256.c: fep256.c:159:13: warning: unused function 'felem_small_sum' [-Wunused-function]
fep256.c: static void felem_small_sum(felem out, const smallfelem in)
fep256.c:             ^
fep256.c: fep256.c:177:13: warning: unused function 'longfelem_scalar' [-Wunused-function]
fep256.c: static void longfelem_scalar(longfelem out, const u64 scalar)
fep256.c:             ^
fep256.c: fep256.c:200:13: warning: unused function 'smallfelem_neg' [-Wunused-function]
fep256.c: static void smallfelem_neg(felem out, const smallfelem small)
fep256.c:             ^
fep256.c: fep256.c:243:13: warning: unused function 'felem_diff_zero107' [-Wunused-function]
fep256.c: static void felem_diff_zero107(felem out, const felem in)
fep256.c:             ^
fep256.c: fep256.c:263:13: warning: unused function 'longfelem_diff' [-Wunused-function]
fep256.c: ...

Number of similar (implementation,compiler) pairs: 5, namely:

Implementation	Compiler
`T:wbl`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`T:wbl`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`T:wbl`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`T:wbl`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`
`T:wbl`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_14.0.6)`

Compiler output

curve.c: curve.c: In function 'p256dblmult_base':
curve.c: curve.c:256:7: warning: unused variable 'k' [-Wunused-variable]
curve.c:   256 |   int k;
curve.c:       |       ^
fep256.c: fep256.c:1064:32: warning: argument 1 of type 'unsigned char *' declared as a pointer [-Warray-parameter=]
fep256.c:  1064 | void fep256pack(unsigned char *out, fep256 *a){
fep256.c:       |                 ~~~~~~~~~~~~~~~^~~
fep256.c: In file included from fep256.c:30:
fep256.c: fep256.h:20:38: note: previously declared as an array 'unsigned char[32]'
fep256.c:    20 | extern void fep256pack(unsigned char c[32], fep256 *r);
fep256.c:       |                        ~~~~~~~~~~~~~~^~~~~
fep256.c: fep256.c:1075:51: warning: argument 2 of type 'const unsigned char *' declared as a pointer [-Warray-parameter=]
fep256.c:  1075 | void fep256unpack(fep256 *c, const unsigned char *in){
fep256.c:       |                              ~~~~~~~~~~~~~~~~~~~~~^~
fep256.c: fep256.h:21:57: note: previously declared as an array 'const unsigned char[32]'
fep256.c:    21 | extern void fep256unpack(fep256 *r, const unsigned char c[32]);
fep256.c:       |                                     ~~~~~~~~~~~~~~~~~~~~^~~~~
fep256.c: fep256.c: In function 'fep256unpack':
fep256.c: fep256.c:1076:14: warning: unused variable 'temp' [-Wunused-variable]
fep256.c:  1076 |   smallfelem temp;
fep256.c:       |              ^~~~
fep256.c: fep256.c: At top level:
fep256.c: fep256.c:967:1: warning: 'copy_small_conditional' defined but not used [-Wunused-function]
fep256.c:   967 | copy_small_conditional(felem out, const smallfelem in, limb mask)
fep256.c:       | ^~~~~~~~~~~~~~~~~~~~~~
fep256.c: fep256.c:955:1: warning: 'copy_conditional' defined but not used [-Wunused-function]
fep256.c:   955 | copy_conditional(felem out, const felem in, limb mask)
fep256.c:       | ^~~~~~~~~~~~~~~~
fep256.c: fep256.c:944:13: warning: 'smallfelem_inv_contract' defined but not used [-Wunused-function]
fep256.c: ...

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

Implementation	Compiler
`T:wbl`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`T:wbl`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`T:wbl`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`T:wbl`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`