mirror of
https://sourceware.org/git/glibc.git
synced 2024-12-26 12:41:05 +00:00
cfee7d9cf4
This patch removes the powerpc assembly implementation of fmax/fmin.
Based on benchtests, the assembly ones shows:
$ ./testrun.sh benchtests/bench-fmax
"fmax": {
"": {
"duration": 5.07586e+09,
"iterations": 2.01676e+09,
"max": 1350.39,
"min": 2.073,
"mean": 2.51684
},
"qNaN": {
"duration": 5.09315e+09,
"iterations": 8.4568e+08,
"max": 2788,
"min": 5.806,
"mean": 6.02255
},
"sNaN": {
"duration": 5.09073e+09,
"iterations": 8.42316e+08,
"max": 4215.84,
"min": 5.737,
"mean": 6.04373
}
And
$ ./testrun.sh benchtests/bench-fmin
"fmin": {
"": {
"duration": 5.07711e+09,
"iterations": 2.02982e+09,
"max": 497.094,
"min": 2.073,
"mean": 2.50126
},
"qNaN": {
"duration": 5.09134e+09,
"iterations": 8.46968e+08,
"max": 2255.14,
"min": 5.807,
"mean": 6.01125
},
"sNaN": {
"duration": 5.09122e+09,
"iterations": 8.4746e+08,
"max": 1969.38,
"min": 5.729,
"mean": 6.00763
}
}
The default implementation (math/s_f{max.min}_template.c) shows slight better
latency for all cases:
$ ./testrun.sh benchtests/bench-fmax
"fmax": {
"": {
"duration": 5.07044e+09,
"iterations": 2.38695e+09,
"max": 2048.58,
"min": 2.073,
"mean": 2.12423
},
"qNaN": {
"duration": 5.09004e+09,
"iterations": 9.45428e+08,
"max": 3306.93,
"min": 5.138,
"mean": 5.38385
},
"sNaN": {
"duration": 5.08458e+09,
"iterations": 1.15959e+09,
"max": 972.008,
"min": 3.321,
"mean": 4.3848
}
}
And:
$ ./testrun.sh benchtests/bench-fmin
"fmin": {
"": {
"duration": 5.06817e+09,
"iterations": 2.3913e+09,
"max": 1177.9,
"min": 2.073,
"mean": 2.11942
},
"qNaN": {
"duration": 5.08857e+09,
"iterations": 9.45656e+08,
"max": 2658.83,
"min": 5.09,
"mean": 5.38099
},
"sNaN": {
"duration": 5.08093e+09,
"iterations": 1.16725e+09,
"max": 1030.74,
"min": 3.323,
"mean": 4.3529
}
}
Both were run with GCC 5.4 (ubuntu 16 default installation) using default
compiler flags on POWER8E 3.4GHz (powerpc64le-linux-gnu).
|
||
|---|---|---|
| .. | ||
| 405 | ||
| 440 | ||
| 464 | ||
| 476 | ||
| 970 | ||
| a2 | ||
| bits | ||
| cell | ||
| e500/nofpu | ||
| fpu | ||
| power4 | ||
| power5 | ||
| power5+ | ||
| power6 | ||
| power6x | ||
| power7 | ||
| power8 | ||
| power9 | ||
| __longjmp-common.S | ||
| __longjmp.S | ||
| add_n.S | ||
| addmul_1.S | ||
| atomic-machine.h | ||
| backtrace.c | ||
| bsd-_setjmp.S | ||
| bsd-setjmp.S | ||
| bzero.S | ||
| compat-ppc-mcount.S | ||
| configure | ||
| configure.ac | ||
| crti.S | ||
| crtn.S | ||
| dl-dtprocnum.h | ||
| dl-irel.h | ||
| dl-machine.c | ||
| dl-machine.h | ||
| dl-start.S | ||
| dl-trampoline.S | ||
| gprrest0.S | ||
| gprrest1.S | ||
| gprsave0.S | ||
| gprsave1.S | ||
| Implies | ||
| libgcc-compat.S | ||
| lshift.S | ||
| Makefile | ||
| mcount.c | ||
| memset.S | ||
| mul_1.S | ||
| ppc-mcount.S | ||
| register-dump.h | ||
| rshift.S | ||
| rtld-memset.c | ||
| setjmp-common.S | ||
| setjmp.S | ||
| stackguard-macros.h | ||
| start.S | ||
| stpcpy.S | ||
| strchr.S | ||
| strcmp.S | ||
| strcpy.S | ||
| strlen.S | ||
| strncmp.S | ||
| sub_n.S | ||
| submul_1.S | ||
| sysdep.h | ||
| tls-macros.h | ||
| tst-audit.h | ||
| Versions | ||